Abstract
This research introduces a new technique to control constrained nonlinear systems, named Lyapunovbased neural network model predictive control using a metaheuristic optimization approach. This controller utilizes a feedforward neural network model as a prediction model and employs the driving training based optimization algorithm to resolve the related constrained optimization problem. The proposed controller relies on the simplicity and accuracy of the feedforward neural network model and the convergence speed of the driving training based optimization algorithm. The closedloop stability of the developed controller is ensured by including the Lyapunov function as a constraint in the cost function. The efficiency of the suggested controller is illustrated by controlling the angular speed of threephase squirrel cage induction motor. The reached results are contrasted to those of other methods, specifically the fuzzy logic controller optimized by teaching learningbased optimization algorithm, the optimized PID with particle swarm optimization algorithm, the neural network model predictive controller based on particle swarm optimization algorithm, and the neural network model predictive controller using driving training based optimization algorithm. This comparative study showcase that the suggested controller provides good accuracy, quickness and robustness due to the obtained values of the mean absolute error, mean square error root mean square error, enhancement percentage, and computing time in the different simulation cases, and it can be efficiently utilized to control constrained nonlinear systems with fast dynamics.
Similar content being viewed by others
Introduction
ModelBased Predictive Control, often known as MBPC or just MPC, does not specify a unique control approach but refers to a variety of control techniques^{1} that utilize a model to predict the system’s future outputs^{2}. The primary strategy of this type of controller is based on a good knowledge of the model representing the system to be controlled and the minimization of a performance criterion defined usually by the quadratic error between the predicted response and the desired reference trajectory along a finite horizon^{3,4}. The unifying principle across these varied techniques is the utilization of a predictive model to forecast future outputs of a system^{5,6}. This predictive ability is not inherent to a single type of model; instead, it relies on the precise and accurate representation of the system through the model utilized^{7,8}. The core methodology of MPC hinges on an intimate understanding of the system’s model^{9,10}. The effectiveness of MPC is predicated on the fidelity and accuracy of this model in representing the dynamics of the system under control^{11,12}. In practice, this means that the predictive model must be able to simulate future states of the system with high reliability, providing a foundation upon which control decisions can be made^{13,14}. Furthermore, MPC operates on the principle of optimizing a predefined performance criterion, which is often expressed in terms of minimizing the quadratic error^{15,16}. This error quantifies the difference between the system’s predicted output and the desired output, as defined by the reference trajectory^{17,18}. The optimization is performed over a finite horizon, meaning that the controller seeks to minimize this error not just for the immediate next step, but for a series of future steps within a specified timeframe^{19,20}. This approach allows for anticipatory adjustments in control actions, which are recalculated at each step based on updated predictions, thereby adapting to changes and disturbances affecting the system^{21,22}. Overall, MPC’s reliance on a robust model and its forwardlooking optimization strategy make it a powerful and flexible approach in the realm of control engineering, suitable for managing complex dynamic systems where future predictions and preemptive control actions are crucial for performance and stability^{23,24}.
MPC is a control approach that has been around since the work of J. Richalet in the late 70’s^{25}. This technique has been widely adopted by the academic and industrial world in various sectors, such as the chemical and petroleum industries, robotics, etc.^{26,27,28,29,30,31}. The popularity of this type of controller is due to its ability to control a different kinds of processes, like multivariable or monovariable, with long delay times, unstable or nonminimal phase, and those with simple or complex dynamics^{32,33}. Due to the use of various linear models to represent the different industrial processes, several MPC control algorithms have been approved, namely the Model Algorithmic Control (MAC) proposed by^{34}, the Dynamic Matrix Control (DMC) suggested by^{35}, the Extended Horizon Adaptive Control (EHAC) introduced by^{35} and in 1987 the work of Clarke proposed the Generalized Predictive Control (GPC)^{36,37,38} which has been very successful. Since then, several methods have been developed to improve the various MPC algorithms mentioned above^{26,39,40,41,42,43}. Even while linear MPC controllers have proven their efficiency in a variety of industrial applications, they remain insufficient to ensure effective control of highly nonlinear processes due to the difficulty of designing an accurate model representing the real system to be controlled^{18,44}. Despite the proven efficacy of linear MPCs in numerous industrial settings, they are often inadequate for controlling highly nonlinear processes^{20,45}. This limitation stems from the challenges associated with devising accurate models that can faithfully represent complex realworld systems^{22,46}. This insufficiency has given rise to a nonlinear control strategy known as Nonlinear Model Predictive Control (NMPC)^{47,48,49,50}. Various nonlinear modelling techniques have been used in NMPC, such as Volterra series^{51,52,53}, Fuzzy models^{54,55,56} and Neural Network models (NN)^{57,58,59,60,61}. Compared to conventional Nonlinear MPC techniques such as Volterra logic or fuzzy logic^{62,63}, Neural Network based MPC (NNMPC) employs less processing power, memory and can accurately model complex dynamic effects, even with scant training data, providing it more efficient for applications requiring nonlinear control.
Using the NMPC approach means solving a constrained, nonconvex, nonlinear optimization problem requiring long and tedious numerical calculation^{64,65,66}. In order to solve such problem, several suboptimal approaches have been proposed, such as stochastic optimization methods^{67,68,69}, which include metaheuristic algorithms^{70}. Due to the performances provided by this type of algorithm in terms of calculation time and finding the right solution, several works have been carried out to solve the nonconvex NMPC problem using different types of metaheuristics algorithms like, Particle Swarm Optimization (PSO)^{71,72,73}, Artificial Bee Colony (ABC)^{74,75}, Evolutionary Algorithm (EA)^{76}, Teaching Learning Based Optimization (TLBO)^{77,78} and Archimedes Optimization Algorithm (AOA)^{79}.
The Driving Training Based Optimization (DTBO) algorithm, proposed by Mohammad Dehghani, is one of the novel metaheuristic algorithms which appeared in 2022^{80}. This algorithm is founded on the principle of learning to drive, which unfolds in three phases: selecting an instructor from the learners, receiving instructions from the instructor on driving techniques, and practicing newly learned techniques from the learner to enhance one’s driving abilities^{81,82}. In this work, DTBO algorithm is used, due to its effectiveness, which was confirmed by a comparative study^{83} with other algorithms, including particle swarm optimization^{84}, Gravitational Search Algorithm (GSA)^{85}, teaching learningbased optimization, Gray Wolf Optimization (GWO)^{86}, Whale Optimization Algorithm (WOA)^{87}, and Reptile Search Algorithm (RSA)^{88}. The comparative study has been done using various kinds of benchmark functions, such as constrained, nonlinear and nonconvex functions.
Lyapunov based Model Predictive Control (LMPC) is a control approach integrating Lyapunov function as constraint in the optimization problem of MPC^{89,90}. This technique characterizes the region of the closedloop stability, which makes it possible to define the operating conditions that maintain the system stability^{91,92}. Since its appearance, the LMPC method has been utilized extensively for controlling a various nonlinear systems, such as robotic systems^{93}, electrical systems^{94}, chemical processes^{95}, and wind power generation systems^{90}. In contrast to the LMPC, both the regular MPC and the NMPC lack explicit stability restrictions and can’t combine stability guarantees with interpretability, even with their increased flexibility.
The proposed method, named Lyapunovbased neural network model predictive control using metaheuristic optimization approach (LNNMPCMOA), includes Lyapunov based constraint in the optimization problem of the neural network model predictive control (NNMPC), which is solved by the DTBO algorithm. The suggested controller consists of two parts: the first is responsible for calculating predictions using a neural network model of the feedforward type, and the second is responsible to resolve the constrained nonlinear optimization problem using the DTBO algorithm. This technique is suggested to solve the nonlinear and nonconvex optimization problem of the conventional NMPC, ensure online optimization in reasonable time thanks to their easy implementation and guaranty the stability using the Lyapunov functionbased constraint. The efficiency of the proposed controller regarding to the accuracy, quickness and robustness is assessed by taking into account the speed control of a threephase induction motor, and its stability is mathematically ensured using the Lyapunov functionbased constraint. The acquired results are compared to those of NNMPC based on DTBO algorithm (NNMPCDTBO), NNMPC using PSO algorithm (NNMPCPSO), Fuzzy Logic controller optimized by TLBO (FLCTLBO) and optimized PID controller using PSO algorithm (PIDPSO)^{95}.
This paper is structured like this: Sect. “Driving training based optimization algorithm” presents the DTBO algorithm. Section “Lyapunovbased neural network model predictive control using DTBO algorithm” describes the proposed LNNMPCMOA using the DTBO algorithm (LNNMPCDTBO); Section “Stability analysis” proves the stability of the suggested controller mathematically. Section “Simulation study” gives the system model’s under study, and several simulation results are presented and discussed. Finally, in Sect. “Conclusion and future research directions” the conclusion is given.
Driving training based optimization algorithm
Driving training based optimization is a recent metaheuristic algorithm, inspired by the human activities of driver training in driving schools. It is based on a population of learners and instructors that are considered as candidate solutions. They are updated throughout the optimization process until the best solution is obtained, which ensures the best value of the cost function.
This search process can be modelled into three phases: phase1, also known as the training by the driving instructor phase, is used to select the instructors who will teach the learnersdrivers how to drive. Phase 2 is referred to as learner driver modelling, during which the student drivers replicate the instructor’s gestures and manoeuvres. Phase3, which is the personal practice phase, is designed to enhance each learner driver’s progress and improve his driving skills through individual practice.
The DTBO algorithm with its three phases is given in the following steps:

1. Initialization: Before starting the execution of the three DTBO phases, an initialization step is necessary to define the values of the subsequent parameters: the population size \((N)\), the number of problem variables for the optimization problem \((m)\), the bounds of the variables \(({L}_{b},{U}_{b})\) with dimension (m), the number of iterations \((T)\). The position of the population \(({X}_{i})\) is initialized randomly respecting their bounds using Eq. (1), the corresponding cost function \(({F}_{i})\) is assed and the best solution \(({{X}_{i}}^{best})\) is selected according to the best value of the cost function \(\left({{F}_{i}}^{best}\right)\).
$${X}_{i}={L}_{b}+r\left({U}_{b}{L}_{b}\right),$$(1)with \(i=\text{1,2}, ..., N\) and \(r\) is a random number from 0 to 1.

2. Phase1: Training by the driving instructor phase: During this phase, the driving instructors \({N}_{DI}\), represented by the \(DI\) matrix of dimension \([{N}_{DI},m]\), are calculated using Eq. (2).
$${N}_{DI}=0.1{\text{N}}\left(1\frac{{\text{z}}}{\text{T}}\right),$$(2)where \(\text{z}=1,..,\text{T}\) is the counter of iterations.
As shown in Eq. (2), \({N}_{DI}\) are selected among DTBO population depending on their cost function values, and the remaining members are classified as learner drivers. Then the new position for each candidate solution in phase1 \((P1)\) is calculated using Eq. (3) and updated using Eq. (4).
$$X_{i}^{{P1}} = \left\{ {\begin{array}{*{20}c} {X_{i} + r\left( {DI_{{ki}}  IX_{i} } \right),} & {F_{{DI_{{ki}} }} < F} \\ {X_{i} + r\left( {X_{i}  DI_{{ki}} } \right),} & {Otherwise} \\ \end{array} } \right.$$(3)$$X_{i} = \left\{ {\begin{array}{*{20}c} {X_{i}^{{P1}} ,~~} & {F_{i}^{{P1}} < F_{i} } \\ {X_{i} ,~} & {Otherwise} \\ \end{array} } \right.,$$(4)where the \({X}_{i}^{P1}\) is the new position with dimension \((m)\), for \(ith\) element of the population, \({F}_{i}^{P1}\) is its corresponding cost function value, \(I\) is a random number from 1 to 2, \(ki\) is a random number from 1 to \({N}_{DI}\), \({DI}_{ki}\) is the selected driving instructor and \({F}_{{DI}_{ki}}\) is its corresponding cost function value.
In this phase, the DTBO algorithm is in the exploration phase, moving its population into various regions of the search area to select the driving instructors and teach the learner drivers.

3. Phase2: learner driver modelling phase (exploration): During this phase, the learner driver imitates all the instructor’s movements and skills. This patterning is represented by the index P given by Eq. (5).
$$P=0.01+0.9\left(1\frac{z}{T}\right).$$(5)This process increases the DTBO’s capacity of exploration by moving its elements to different locations in the search area. To model this phase a new position \({X}_{i}^{P2}\) is calculated by the linear combination of each learner driver and instructor using Eq. (6).
$${X}_{i}^{P2}=P{X}_{i}+\left(1P\right){DI}_{ki}.$$(6)This new position takes the place of the old one if it enhances the value of the cost function using Eq. (7).
$$X_{i} = \left\{ {\begin{array}{*{20}c} {X_{i}^{{P2}} ,~} & {F_{i}^{{P2}} < F_{i} } \\ {X_{i} ,} & {Otherwise} \\ \end{array} } \right.$$(7) 
4. Phase 3: Personal practice phase: In this part, each learner driver progresses and improve his driving skills through individual practice. Throughout this period, each driver learner tries to get closer to his maximum capabilities. This enables each member to find a better position by performing a local search near their current position. This step illustrates how DTBO can benefit from local search exploitation. This phase is modelled in such a way that a random position is firstly generated near each learner driver using Eq. (8).
$${X}_{i}^{P3}={X}_{i}+\left(12r\right)R\left(1\frac{z}{T}\right){X}_{i},$$(8)with \(R=0.05\) is a constant.
The position of \({i}^{th}\) leaner driver is updated using the Eq. (9), as follows:
$$X_{i} = \left\{ {\begin{array}{*{20}c} {X_{i}^{{P3}} ,} & {F_{i}^{{P3}} < F} \\ {X_{i} ,} & {Otherwise} \\ \end{array} } \right..$$(9) 
5. Updated the best solution \(({{X}_{i}}^{best})\) according to the best value of the cost function.

6. This process is repeated until the number of iterations is reached.
The flow chart of the DTBO algorithm is given in Fig. 1.
Lyapunovbased neural network model predictive control using DTBO algorithm
Principle of neural network model predictive control using DTBO algorithm Consider the following system:
Consider the system described by the Eq. (10), as follows:
where \(x\), \(u\), and \(y\) are the state vectors, input and output, respectively, \(v\) is the disturbance\(, and f\) and \(g\) are nonlinear functions.
The NNMPC is an advanced control approach that requires two essential steps as follows:
First, a neural model representing the process to be controlled is established. This model predicts the system’s future behaviour along a prediction horizon defined by the interval \(\left[{N}_{1},{N}_{2}\right]\).
Second, a control sequence along the control horizon \(\left({N}_{u}\right)\) is determined and its initial element (\(u\left(k\right)\)) is employed to control the system under study. In this step, the NNMPC minimization problem given in Eq. (11) is solved using the DTBO algorithm.
Subject to:
where \(\Delta u\left(k\right)=u\left(k\right)u\left(k1\right)\) is the control increment, \(\widehat{y}\left(k+i/k\right)\) is the predicted output, \({y}_{r}\) is the desired reference trajectory, \(Q\) is a positive semidefinite matrix and \(R\) is a positive definite matrix.
Lyapunovbased neural network model predective control using DTBO algorithm
In order to ensure stable control and maintain the system within an acceptable operating range while respecting its safety conditions and physical limits, several constraints have been proposed. The constraints used in the proposed LNNMPCDTBO are the input, the output and the Lyapunov functionbased constraints, which are implemented in the constrained minimization problem defined in Eq. (12), as follows:
Subject to
where \(u(k)\) is the actual input control, \({\Gamma }_{y}\left(y\right)\) is the outputdependent weight function, and \(V\) represents the continuous differentiable Lyapunov function.
Constraints handling
The constraints used in the minimization problem of the LNNMPCDTBO are handled as follow:

The input constraints are defined in Eqs. (12.b), (12.c), and they are handled by limiting the search space of the DTBO algorithm.

The output constraints are handled using the penalty function \({\Gamma }_{y}\left(y\right)\) given by Eq. (13) below:
$${\Gamma }_{y}\left(y\right)=\left[\begin{array}{ccc}{\Gamma }_{{y}_{1}}{(y}_{1})& 0& \begin{array}{cc}\dots & 0\end{array}\\ 0& {\Gamma }_{{y}_{2}}{(y}_{2})& \begin{array}{cc}\dots & 0\end{array}\\ \begin{array}{c}\vdots \\ 0\end{array}& \begin{array}{c}\vdots \\ 0\end{array}& \begin{array}{c}\begin{array}{cc}\ddots & \vdots \end{array}\\ \begin{array}{cc}\cdots & {\Gamma }_{n}{(y}_{n})\end{array}\end{array}\end{array}\right]$$(13)
And:
with \({C}_{iy}\) is employed to define the penalization degree, \(i=\text{1,2},. . .,n\) where \(n\) is the number of system outputs and \({y\left(k\right)=\left[{y}_{1}\left(k\right), {y}_{2}\left(k\right), . . . ,{y}_{n}\left(k\right)\right]}^{T}\).

The Lyapunov functionbased constraint given in Eq. (12.e) is handled by adding a penalization of the Lyapunov function derivative to the cost function defined in Eq. (12). This technique ensures that the Lyapunov function derivative will be less than or equal to zero as long as the Lyapunov function derivative of the current control \((u)\) is less than that of the previous control.
Control algorithm
The suggested LNNMPCDTBO stapes’s are given as follows:
Step1: Initialization

Determine the MPC and DTBO parameters \({(N}_{1}, {N}_{2}, {N}_{u} , N,T,m,{U}_{b},{L}_{b})\).

Considering that \({X}_{i}\) with dimenssion \(m\) are the control inputs at sampling time \(k\) where \(m\) is the control inputs number.
Step2: Select the initial solution

Set a desired reference trajectory along \(k+{N}_{1}\) to \(k+{N}_{2}\).

Initialize the position of the population \({X}_{i}\) using Eq. (1).

Calculate the predicted outputs of the system for the initial position of the population, by utilizing the neural network model.

Evaluate the cost function \({F}_{i}\) using Eq. (12).

Select the best solution \({X}_{i}^{best}\) that corresponds to the best value of the cost function.
Step3: Optimization loop
For \(z=1:T\)
For \(i=1:N\)

Determine the driving instructor using Eq. (2) and calculate the new position \({X}_{i}^{p1}\) for the DTBO population using Eq. (3).

Calculate the predicted outputs of the system by utilizing the neural network model and \({X}_{i}^{p1}\).

Compute the new value of the cost function \({F}_{i}^{p1}\) using the new position \({X}_{i}^{p1}\).

Update \({X}_{i}^{p1}\) using Eq. (4).

Calculate the patterning index according to Eq. (5).

Compute the new position \({X}_{i}^{p2}\) using Eq. (6).

Calculate the predicted outputs of the system by utilizing the neural network model \({X}_{i}^{p2}\).

Compute the new value of the objective function \({F}_{i}^{p2}\) using the new position \({X}_{i}^{p2}\).

Update \({X}_{i}^{p2}\) using Eq. (7).

Compute the new position of the DTBO population \({X}_{i}^{p3}\) with Eq. (8).

Calculate the predicted outputs of the system by utilizing the neural network model and \({X}_{i}^{p3}\) .

Update \({X}_{i}^{p3}\) using Eq. (9).
End for (i).

\({X}_{i}^{best}\)
End for \((z)\).
Step4:

Apply the first element of the best solution \({X}_{i}^{best}\) to the system, which is the optimal control inputs.

Go back to the step 2 for the next sampling time \((k=k+1)\).
Stability analysis
This section uses the stability analysis performed by^{90} in continuous time to prove the proposed controller’s closedloop stability.
Knowing that the optimization criterion of the proposed controller, defined in Eq. (12), can be written in continuous time with Eq. (14), as follows:
Subject to:
where \(h\) is the previous nonlinear feedback control, \(u({t}_{k})\) is the actual input control, \(N={N}_{2}\) is the prediction horizon, \(t\in \left[{t}_{k}, {t}_{k+1}\right]\) with \({t}_{k}=k{t}_{s}\) and \({t}_{s}\) is the sampling time.
Assumption 1:
Assuming that at the nominal operating point, the asymptotic stability of the closedloop system is assured, all state constraints are satisfied in the stability region with respect to the existing feedback control input \(u=h(x)\in U\) for all \(x \in {X}_{e}\), where \(U\) and \({X}_{e}\) are the space where the control \(u\) and the state is defined, respectively. Therefore, the inequalities bellow, given by Eqs. (15), (16), (17) are valid for the inverse Lyapunov theorembased nominal closedloop system^{96}.
where \({\alpha }_{i=\text{1,2},\text{3,4}}\) are the \(\mathcal{K}\) function.
In this study, let’s denote \(S\) as the region where the controlled system is stable under the input law \(u=h(x)\) and \({S}_{\delta }\) the Lyapunovbased stability zone given by
with \(\delta\) is a constant.
Lemma:
The inequalities bellow, given by Eqs. (18), (19) and (20) are hold if there exist positive constants \(C, {L}_{x},{L}_{\omega }, {\overline{L} }_{x}\) and \({\overline{L} }_{\omega }\), such that the constraints are satisfied for all \(x\) and \(u\).
where \(\overline{x }=x\left({t}_{k}\right)\) and \(\overline{v }=v\left({t}_{k}\right)\).
Proof:
The Eqs. (18)–(20) can be easily deduced by using the Lipschitz property of the function \(f\) and the continuous differentiability of the Lyapunov function \(V(x)\), that’s why the details are omitted, and the proof is considered complete.
Assumption 2
Assuming that the following scalar exists and is defined by the Eq. (21), as follows:
where \({\delta }_{s}\) is a constant and \({\delta }_{min}\) is the maximum value of \(V(x(t+{t}_{s}))\) at the next sampling time when \(V(x(t))\) is less than the constant \(\delta\).
Theorem
For the closedloop system given in Eq. (10) controlled by solving the criterion shown in Eq. (12), if it exists \(x\left({t}_{0}\right)\in {S}_{\delta }\), \(\varepsilon >0\) and \(\delta >{\delta }_{s}>0\) where \(\varepsilon\) is a constant, the inequality given by Eq. (22) can be hold assuming that the Eqs. (15)–(17) are satisfied.
where for all \(t\ge {t}_{0}\) there exists \(\left(\delta >{\delta }_{min}>0\right)\) guaranteeing the maintaining of states \(x(t)\) in the stability region and \(\varphi\) is the upper limit of disturbance variation over a sampling period.
Proof :
The timederivative of the Lyapunov function can be computed using Eq. (23), taking into account the closedloop system at time \(t \in \left[{t}_{k} , {t}_{k+1}\right]\):
The following inequality can be extended from Eq. (23) based on the constraint (14.e) as follow:
Using Eqs. (20), (24) can be written with this manner:
The formula below can be written according to Eq. (19) and during a sampling period where \(x(t)\) is continuous:
It is deduced from Eq. (16) that:
Replacing Eqs. (26) and \* MERGEFORMAT Eq. (27) in Eq. (25), the Eq. (28) bellow can be deduced:
If Eq. (22) is fulfilled, then there is a \(\varepsilon > 0\) for which the subsequent inequality given by the Eq. (29) bellow is applied.
The function \(V(x(t))\) continues to decrease at \(t\in [{t}_{k},{t}_{k+1}]\), as demonstrated by the previous inequality. By integrating it from \({t}_{k}\) to \({t}_{k+1}\), the Eq. (30) bellow is obtained:
Therefore, if \({x}_{{t}_{k}}\in {\text{S}}_{\delta }\), then at time \(t\ge {t}_{k}\), all states of \(x(t)\) remain in the stable area \({\text{S}}_{\delta }\). Furthermore, over a finite number of sampling times, the states \(x\left(t\right)\) will progressively converge to \({\text{S}}_{\delta min}\) and remain in this stable area for all of future periods.
This proof can be applied in discrete time to ensure that the controlled system is stable.
Simulation study
Several simulations are carried out to demonstrate the efficiency of the proposed LNNMPCDTBO controller, using as application a highly nonlinear system: the squirrel cage induction motor. A comparison study is conducted between the suggested controller and the NNMPCDTBO, NNMPCPSO, FLCTLBO and PIDPSO.
Squirrel cage induction motor model
The squirrel cage induction motor is one of the threephase induction motors currently used in industry in various applications, such as pumps, conveyors, turbines and so on^{97,98}. This kind of motor represents an excellent application for scientific research thanks to the number of nonlinearities it contains. The state model of this type of motor^{99,100} is given by Eq. (31), as follows:
where the state vector \(x={\left[{F}_{ds} {F}_{qs} {F}_{dr} {F}_{qr}\right]}^{T}\) are the stator and rotor flux linkages in the reference frame dq axis. The \(dq\) axis stator voltages are the control inputs vector \({{u= [U}_{ds} {U}_{qs}]}^{T}\) and \({U}_{dr}={U}_{qr}=0\) are the rotor \(dq\) axis voltages. \({w}_{b}=2\pi {f}_{b}\) Is the motor’s angular electrical base frequency, \({w}_{e}\) is the angular speed of the reference frame, and \({w}_{r}\) is the angular speed of the rotor. \({X}_{ml}\) ,\({X}_{is}\), \({X}_{ir}\), \({X}_{m}\) and \({\dot{w}}_{r}\) are given by Eqs. (32), (33), (34), (35), (36), respectively.
where \({T}_{e}\) is the electrical output torque, \({T}_{r}\) is the load torque, \({L}_{is}\) is the stator phase inductance , \({L}_{ir}\) is the rotor phase inductance and \({L}_{m}\) is the mutual inductance.
The electrical parameters of the considered squirrel cage induction motor are given in the table bellow:
System identification
In this work, four feed forward neural networks are used to identify the rotor and stator fluxes, which are utilized to compute the angular speed. The neural network models have the same following structure:

$$\left[{U}_{ds}\left(k1\right){, U}_{ds}\left(k\right){, U}_{qs}\left(k1\right), {U}_{qs}\left(k\right){, F}_{i}\left(k1\right), {F}_{i}(k)\right],$$
where \(i=\left\{ds,qs,dr,qr\right\}\).

One hidden layer containing fifteen neurons and using a sigmoid activation function.

An output layer corresponding to \(\left({F}_{ds},{F}_{qs}, {F}_{dr}\right)\) and \({F}_{qr}\), with a linear activation function.
A dataset is generated with random inputs using the state model given in Eq. (31).
The test results of the obtained neural network models for each predicted output are shown in Fig. 2, and the prediction errors are shown in Fig. 3. The values of the Root Mean Square Error (RMSE), Mean Square Error (MSE), Mean Absolute Error (MAE) and determination coefficient \({(R}^{2})\) for each model are gathered in Table 1. These values show that the obtained models are accurate.
Control implementation
Figure 4 illustrates the control diagram of the proposed LNNMPCDTBO. Two simulation cases are performed using the neural network models defined above and the parameters mentioned in Table 2.
In the initial case, no overshoot constraint is considered, and the multistep reference trajectory is used to evaluate the performances of the proposed controller. The parameters of the NNMPC, PSO, and DTBO are presented in Tables 3, 4, 5, respectively. The results are compared to those obtained from PIDPSO, FLCTLBO, NNMPCPSO, and NNMPCDTBO, as shown in Fig. 5. The values of the MAE, MSE, and RMSE are given in Table 6. These values demonstrate that the proposed controller (LNNMPCDTBO) gives the best tracking accuracy with the MAE enhancement percentage of \(1.57\%\), \(51.57\%\), \(89.16\%\) and \(88.23\%\) comparing to the NNMPCDTBO, NNMPC_PSO, FLCTLBO and PIDPSO, respectively.
In the second case, a 1% overshoot constraint is applied to the output of the predictive controllers (NNMPCDTBO, NNMPCPSO and LNNMPCDTBO) for the multistep and sinusoidal reference trajectories.
The obtained results for the second case, using multistep and sinusoidal reference trajectories, respectively, are presented in Figs. 6, 7, 8 and the control efforts signals are given in Figs. 7, 9. To evaluate the efficiency of the proposed controller, the values of the MAE, MSE, RMSE and computing time were calculated and are given in Table 7 for the multistep and sinusoidal reference trajectories. From these values and the enhancement percentages of the MAE for the multistep and sinusoidal reference trajectories, which are \(15.99\) and \(30.48\%\) compared to the NNMPCDTBO and NNMPCPSO, respectively, for the first reference, and 24.72 and 31.24% compared to the NNMPCDTBO and NNMPCPSO, respectively, for the second reference, it can be seen that the LNNMPC DTBO gives the best tracking accuracy with minimal computing time and without overshoot (respecting the limit of the overshoot constraint and sampling time) to the NNMPCPSO and NNMPCDTBO.
Effect of external disturbances and measurement noise
In order to show the LNNMPCDTBO controller’s proficiency to reject external disturbances and compensate for measurement noise, several simulation cases were proposed.
In the first case, a measurement noise of \(10\) (tr/min) amplitude, mean value of \(0.4955\) and variance of \(0.0854\) is applied to the system output throughout the simulation.
For the second case, two different disturbance types were used with the multistep and sinusoidal reference trajectories, respectively. A pulse of \(25\%\) of the input is added to the control input during the interval \([1.5 s,2.5 s]\). An output disturbance with an amplitude of \(+30\%\) of the output is added during the interval \([1.5 s,2.5 s]\).
In the third case, different perturbations are applied by changing the values of the load torque \({T}_{r}\) as follows:\({T}_{r}=0Nm\), \({T}_{r}=5Nm\), \({T}_{r}=10Nm\) and \({T}_{r}=25Nm\) illustrated in Table 8.The system’s response is illustrated in Figs. 16, 17 with multistep and sinusoidal reference trajectories, respectively, considering the last value of the load torque where the perturbation is significant.
After applying various disturbances to the induction motor with multistep and sinusoidal desired reference trajectories, as illustrated in the (Figs. 10, 11) for white noise measurement, in the (Figs. 12, 13) for the input disturbance, in the (Figs. 14, 15) for the output disturbance, in the (Figs. 16, 17) for the load torque variation, and based on the results gathered in Tables 9, 8, the proposed controller demonstrates its robustness with respect to disturbance rejection and less sensitivity to noise measurement.
Conclusion and future research directions
In this work, a new control method called Lyapunovbased neural network model predictive control using metaheuristic optimization approach was suggested. The efficiency of this approach is due to the use of neural network models on the one hand, known for their simplicity and ability to model complex and highly nonlinear systems, and the use of the DTBO optimization algorithm, known for its fast convergence, to optimize the cost function of predictive controller, on the other hand. The stability of the proposed technique was mathematically proved, and the carried out simulations demonstrated that the proposed controller can successfully manage the imposed constraints during the optimization process and offers better results in terms of robustness, accuracy and computation time than the others controller such as optimized PID by PSO algorithm, fuzzy logic using TLBO algorithm, NNMPC based on PSO and DTBO. Considering the obtained results, it can be concluded that the LNNMPCDTBO can be used to control highly nonlinear, multivariable, and constrained systems with fast dynamics.
The promising results obtained from the Lyapunovbased neural network model predictive control employing metaheuristic optimization suggest several avenues for future research. First, further investigation into alternative metaheuristic algorithms could provide insights into optimization efficiency and control accuracy, particularly under varying system dynamics and noise conditions. Additionally, expanding the application scope of LNNMPC to other complex and nonlinear systems such as aerospace or biological systems could demonstrate the versatility and robustness of this control strategy. Another critical area involves enhancing the model’s predictive capabilities through the integration of deep learning techniques, which could improve the handling of largescale data and complex variable interactions. Moreover, the development of realtime implementation strategies for LNNMPC that address computational constraints is crucial for its adoption in industrycritical applications. Lastly, exploring the theoretical aspects of stability and robustness within the framework of Lyapunov’s direct method could solidify the theoretical underpinnings of the control strategy and enhance its appeal in safety–critical applications. These efforts would not only extend the current capabilities of predictive control but also broaden the impact of LNNMPC in practical and industrial settings.
Data availability
The datasets used and/or analyzed during the current study available from the corresponding author on reasonable request.
References
Schwenzer, M., Ay, M., Bergs, T. & Abel, D. Review on model predictive control: An engineering perspective. Int. J. Adv. Manuf. Technol. 117, 1327–1349. https://doi.org/10.1007/s00170021076823 (2021).
Ahmed, A. A., Koh, B. K. & Il Lee, Y. A comparison of finite control set and continuous control set model predictive control schemes for speed control of induction motors. IEEE Trans. Ind. Inform. 14, 1334–1346. https://doi.org/10.1109/TII.2017.2758393 (2018).
Wang, Y., Sun, R., Cheng, Q. & Ochieng, W. Y. Measurement quality control aided multisensor system for improved vehicle navigation in urban areas. IEEE Trans. Ind. Electron. 71, 6407–6417. https://doi.org/10.1109/TIE.2023.3288188 (2024).
Djouadi, H. et al. Nonlinear multivariable permanent magnet synchronous machine control: A robust nonlinear generalized predictive controller approach. IET Control Theory Appl. 17, 1688–1702. https://doi.org/10.1049/cth2.12509 (2023).
Xu, B. & Guo, Y. A novel DVL calibration method based on Robust invariant extended Kalman filter. IEEE Trans. Veh. Technol. 71, 9422–9434. https://doi.org/10.1109/TVT.2022.3182017 (2022).
Belkhier, Y. et al. Experimental analysis of passivitybased control theory for permanent magnet synchronous motor drive fed by grid power. IET Control Theory Appl. 18, 495–510. https://doi.org/10.1049/cth2.12574 (2024).
Zhang, J., Chen, Y., Gao, Y., Wang, Z. & Peng, G. Cascade ADRC speed control base on FCSMPC for permanent magnet synchronous motor. J. Circuits Syst. Comput. https://doi.org/10.1142/S0218126621502029 (2021).
Kasri, A. et al. Realtime and hardware in the loop validation of electric vehicle performance: Robust nonlinear predictive speed and currents control based on space vector modulation for PMSM. Results Eng. 22, 102223. https://doi.org/10.1016/j.rineng.2024.102223 (2024).
Zhang, J. et al. Fractional order complementary nonsingular terminal sliding mode control of PMSM based on neural network. Int. J. Automot. Technol. 25, 213–224. https://doi.org/10.1007/s12239024000159 (2024).
Kasri, A., Ouari, K., Belkhier, Y., Bajaj, M. & Zaitsev, I. Optimizing electric vehicle powertrains peak performance with robust predictive direct torque control of induction motors: A practical approach and experimental validation. Sci. Rep. 14, 14977. https://doi.org/10.1038/s41598024659880 (2024).
Deng, Z. W., Zhao, Y. Q., Wang, B. H., Gao, W. & Kong, X. A preview driver model based on slidingmode and fuzzy control for articulated heavy vehicle. Meccanica 57, 1853–1878. https://doi.org/10.1007/s11012022015326 (2022).
Ouari, K. et al. Improved nonlinear generalized model predictive control for robustness and power enhancement of a DFIGbased wind energy converter. Front. Energy Res. https://doi.org/10.3389/fenrg.2022.996206 (2022).
Mohammadzadeh, A. et al. A nonlinear fractionalorder type3 fuzzy control for enhanced pathtracking performance of autonomous cars. IET Control Theory Appl. 18, 40–54. https://doi.org/10.1049/cth2.12538 (2024).
Kakouche, K. et al. Model predictive direct torque control and fuzzy logic energy management for multi power source electric vehicles. Sensors 22, 5669. https://doi.org/10.3390/s22155669 (2022).
Luo, R., Peng, Z., Hu, J. & Ghosh, B. K. Adaptive optimal control of affine nonlinear systems via identifier–critic neural network approximation with relaxed PE conditions. Neural Netw. 167, 588–600. https://doi.org/10.1016/j.neunet.2023.08.044 (2023).
Belkhier, Y. et al. Robust interconnection and damping assignment energybased control for a permanent magnet synchronous motor using high order sliding mode approach and nonlinear observer. Energy Rep. 8, 1731–1740. https://doi.org/10.1016/j.egyr.2021.12.075 (2022).
Guo, C., Hu, J., Wu, Y. & Čelikovský, S. Nonsingular fixedtime tracking control of uncertain nonlinear purefeedback systems with practical state constraints. IEEE Trans. Circuits Syst. I Regul. Pap. 70, 3746–3758. https://doi.org/10.1109/TCSI.2023.3291700 (2023).
Liu, X., Suo, Y., Zhang, Z., Song, X. & Zhou, J. A new model predictive current control strategy for hybrid energy storage system considering the SOC of the supercapacitor. IEEE J. Emerg. Sel. Top. Power Electron. 11, 325–338. https://doi.org/10.1109/JESTPE.2022.3159665 (2023).
Fang, L., Li, D. & Qu, R. Torque improvement of vernier permanent magnet machine with larger rotor pole pairs than stator teeth number. IEEE Trans. Ind. Electron. 70, 12648–12659. https://doi.org/10.1109/TIE.2022.3232651 (2023).
Dos Santos, T. B. et al. Robust finite control set model predictive current control for induction motor using deadbeat approach in stationary frame. IEEE Access 11, 13067–13078. https://doi.org/10.1109/ACCESS.2022.3223385 (2023).
Wang, Z., Wang, S., Wang, X. & Luo, X. Underwater moving object detection using superficial electromagnetic flow velometer arraybased artificial lateral line system. IEEE Sens. J. 24, 12104–12121. https://doi.org/10.1109/JSEN.2024.3370259 (2024).
Wu, W. et al. Datadriven finite controlset model predictive control for modular multilevel converter. IEEE J. Emerg. Sel. Top. Power Electron. 11, 523–531. https://doi.org/10.1109/JESTPE.2022.3207454 (2023).
Wang, Z., Wang, S., Wang, X. & Luo, X. Permanent magnetbased superficial flow velometer with ultralow output drift. IEEE Trans. Instrum. Meas. 72, 1–12. https://doi.org/10.1109/TIM.2023.3304692 (2023).
Zhang, H., Wu, H., Jin, H. & Li, H. Highdynamic and lowcost sensorless control method of highspeed brushless DC motor. IEEE Trans. Ind. Inform. 19, 5576–5584. https://doi.org/10.1109/TII.2022.3196358 (2023).
Richalet, J., Rault, A., Testud, J. L. & Papon, J. Model predictive heuristic control. Automatica 14, 413–428. https://doi.org/10.1016/00051098(78)900018 (1978).
Allgöwer, F., Badgwell, T. A., Qin, J. S., Rawlings, J. B. & Wright, S. J. Nonlinear predictive control and moving horizon estimation—an introductory overview. In Advances in Control (ed. Frank, Paul M.) 391–449 (Springer, London, 1999). https://doi.org/10.1007/9781447108535_19.
Kvasnica, M., Herceg, M., Čirka, Ľ & Fikar, M. Model predictive control of a CSTR: A hybrid modeling approach. Chem. Pap. https://doi.org/10.2478/s1169601000088 (2010).
Richalet, J. Industrial applications of model based predictive control. Automatica 29, 1251–1274. https://doi.org/10.1016/00051098(93)90049Y (1993).
K. Nejadkazemi, A. Fakharian, Pressure control in gas oil pipeline: A supervisory model predictive control approach, In: 2016 4th International Conference on Control, Instrumentation, and Automation, IEEE, 2016: pp. 396–400. https://doi.org/10.1109/ICCIAutom.2016.7483195.
Wang, Y., Geng, Y., Yan, Y., Wang, J. & Fang, Z. Robust model predictive control of a micro machine tool for tracking a periodic force signal. Optim. Control Appl. Methods 41, 2037–2047. https://doi.org/10.1002/oca.2642 (2020).
Durmuş, B., Temurtaş, H., Yumuşak, N. & Temurtaş, F. A study on industrial robotic manipulator model using model based predictive controls. J. Intell. Manuf. 20, 233–241. https://doi.org/10.1007/s1084500802212 (2009).
Holkar, K. S. & Waghmare, L. M. An overview of model predictive control. Int. J. Control Autom. 3, 47–63 (2010).
Morari, M., Garcia, C. E. & Prett, D. M. Model predictive control: Theory and practice. IFAC Proc. 21, 1–12. https://doi.org/10.1016/B9780080357355.500061 (1988).
C.R. cutler, dynamic matrix control: an optimal multivariable control algorithm with constraints, University of Houston ProQuest Dissertations & Theses, (1983).
Ydstie, B. E., Kemna, A. H. & Liu, L. K. Multivariable extendedhorizon adaptive control. Comput. Chem. Eng. 12, 733–743. https://doi.org/10.1016/00981354(88)800115 (1988).
Clarke, D. W., Mohtadi, C. & Tuffs, P. S. Generalized predictive control—part II extensions and interpretations. Automatica 23, 149–160. https://doi.org/10.1016/00051098(87)900884 (1987).
Li, Z. & Wang, G. Generalized predictive control of linear timevarying systems. J. Frankl. Inst. 354, 1819–1832. https://doi.org/10.1016/j.jfranklin.2016.10.021 (2017).
Clarke, D. W., Mohtadi, C. & Tuffs, P. S. Generalized predictive control—Part I The basic algorithm. Automatica 23, 137–148. https://doi.org/10.1016/00051098(87)900872 (1987).
Anis, K. & Tarek, G. An improved robust predictive control approach based on generalized 3rd order SPARAFAC volterra model applied to a 2DoF helicopter system. Int. J. Control Autom. Syst. 19, 1618–1632. https://doi.org/10.1007/s1255501909361 (2021).
Kansha, Y. & Chiu, M.S. Adaptive generalized predictive control based on JITL technique. J. Process Control 19, 1067–1072. https://doi.org/10.1016/j.jprocont.2009.04.002 (2009).
Zhou, X., Lu, F., Zhou, W. & Huang, J. An improved multivariable generalized predictive control algorithm for direct performance control of gas turbine engine. Aerosp. Sci. Technol. 99, 105576. https://doi.org/10.1016/j.ast.2019.105576 (2020).
Lee, J. B. et al. Enhanced model predictive control (eMPC) strategy for automated glucose control. Ind. Eng. Chem. Res. 55, 11857–11868. https://doi.org/10.1021/acs.iecr.6b02718 (2016).
Aufderheide, B. & Bequette, B. W. Extension of dynamic matrix control to multiple models. Comput. Chem. Eng. 27, 1079–1096. https://doi.org/10.1016/S00981354(03)000383 (2003).
Qin, C. et al. RCLSTMNet: A residualconvolutionalLSTM neural network for forecasting cutterhead torque in shield machine. Int. J. Control Autom. Syst. 22, 705–721. https://doi.org/10.1007/s125550220104x (2024).
Bai, X., Xu, M., Li, Q. & Yu, L. Trajectorybattery integrated design and its application to orbital maneuvers with electric pumpfed engines. Adv. Space Res. 70, 825–841. https://doi.org/10.1016/j.asr.2022.05.014 (2022).
Yin, L. et al. AFBNet: A lightweight adaptive feature fusion module for superresolution algorithms. Comput. Model Eng. Sci. https://doi.org/10.32604/cmes.2024.050853 (2024).
Conceição, A. S., Moreira, A. P. & Costa, P. J. A nonlinear model predictive control strategy for trajectory tracking of a fourwheeled omnidirectional mobile robot. Optim. Control Appl. Methods 29, 335–352. https://doi.org/10.1002/oca.827 (2008).
Käpernick, B. & Graichen, K. Nonlinear model predictive control based on constraint transformation. Optim. Control Appl. Methods 37, 807–828. https://doi.org/10.1002/oca.2215 (2016).
Grüne, L. & Pannek, J. Nonlinear Model Predictive Control (Springer London, 2011). https://doi.org/10.1007/9780857295019.
Karak, T., Basak, S., Joseph, P. A. & Sengupta, S. Nonlinear model predictive control based trajectory tracking of hand and wrist motion using functional electrical stimulation. Control Eng. Pract. 146, 105895. https://doi.org/10.1016/j.conengprac.2024.105895 (2024).
Doyle, F. J., Ogunnaike, B. A. & Pearson, R. K. Nonlinear modelbased control using secondorder Volterra models. Automatica 31, 697–714. https://doi.org/10.1016/00051098(94)00150H (1995).
J.K. Gruber, D.R. Ramirez, T. Alamo, C. Bordons, Nonlinear MinMax Model Predictive Control based on Volterra models. Application to a pilot plant, In: 2009 European Control Conference, IEEE, 2009: pp. 1112–1117. https://doi.org/10.23919/ECC.2009.7074554.
B.R. Maner, F.J. Doyle, B.A. Ogunnaike, R.K. Pearson, A nonlinear model predictive control scheme using second order Volterra models, In: Proceedings of 1994 American Control Conference  ACC ’94, IEEE, n.d.: pp. 3253–3257. https://doi.org/10.1109/ACC.1994.735176.
Hu, J., Liu, K. & Xia, Y. Output feedback fuzzy model predictive control with multiple objectives. J. Frankl. Inst. 361, 32–45. https://doi.org/10.1016/j.jfranklin.2023.11.026 (2024).
Lu, Q., Shi, P., Lam, H.K. & Zhao, Y. Interval type2 fuzzy model predictive control of nonlinear networked control systems. IEEE Trans. Fuzzy Syst. 23, 2317–2328. https://doi.org/10.1109/TFUZZ.2015.2417975 (2015).
Howlett, P. J. P. P. G. Advances in Industrial Control (Springer International Publishing, 2006). https://doi.org/10.1007/9783319210216.
Botto, M. A., Van Den Boom, T. J. J., Krijgsman, A. & Da Costa, J. S. Predictive control based on neural network models with I/O feedback linearization. Int. J. Control 72, 1538–1554. https://doi.org/10.1080/002071799220038 (1999).
Draeger, H. R. A. & Engell, S. Model predictive control using neural networks [25 years ago]. IEEE Control Syst. 40, 11–12. https://doi.org/10.1109/MCS.2020.3005008 (2020).
Lupu, D. & Necoara, I. Exact representation and efficient approximations of linear model predictive control laws via HardTanh type deep neural networks. Syst. Control Lett. 186, 105742. https://doi.org/10.1016/j.sysconle.2024.105742 (2024).
Mazinan, A. H. & Sheikhan, M. On the practice of artificial intelligence based predictive control scheme: A case study. Appl. Intell. 36, 178–189. https://doi.org/10.1007/s1048901002530 (2012).
Patan, K. Two stage neural network modelling for robust model predictive control. ISA Trans. 72, 56–65. https://doi.org/10.1016/j.isatra.2017.10.011 (2018).
Zhao, D., Cui, L. & Liu, D. Bearing weak fault feature extraction under timevarying speed conditions based on frequency matching demodulation transform. IEEE/ASME Trans. Mechatron. 28, 1627–1637. https://doi.org/10.1109/TMECH.2022.3215545 (2023).
Wang, R. et al. FINPI: Exploring optimal control in parallel platform systems. Electronics 13, 1168. https://doi.org/10.3390/electronics13071168 (2024).
Allgöwer, Z. K. N. F. & Findeisen, R. Nonlinear model predictive control: From theory to application. J. Chin. Inst. Chem. Eng. 35, 299–315 (2004).
Silva, N. F., Dórea, C. E. T. & Maitelli, A. L. An iterative model predictive control algorithm for constrained nonlinear systems. Asian J. Control 21, 2193–2207. https://doi.org/10.1002/asjc.1815 (2019).
Mayne, D. Nonlinear model predictive control: challenges and opportunities. In Nonlinear Model Predictive Control (ed. Mayne, D.) 23–44 (Birkhäuser Basel, 2000).
Farina, M., Giulioni, L. & Scattolini, R. Stochastic linear model predictive control with chance constraints—a review. J. Process Control 44, 53–67. https://doi.org/10.1016/j.jprocont.2016.03.005 (2016).
Kouvaritakis, B. & Cannon, M. Stochastic model predictive control. In Encyclopedia of Systems and Control (eds Kouvaritakis, B. & Cannon, M.) 1–9 (Springer London, 2014). https://doi.org/10.1007/9781447151029_71.
Ma, Y., Matusko, J. & Borrelli, F. Stochastic model predictive control for building HVAC systems: Complexity and conservatism. IEEE Trans. Control Syst. Technol. 23, 101–116. https://doi.org/10.1109/TCST.2014.2313736 (2015).
De Mendonca Mesquita, E., Sampaio, R. C., Ayala, H. V. H. & Llanos, C. H. Recent metaheuristics improved by selfadaptation applied to nonlinear modelbased predictive control. IEEE Access 8, 118841–118852. https://doi.org/10.1109/ACCESS.2020.3005318 (2020).
M.S. and Y.L. Q. Zou, J. Ji, S. Zhang, Model predictive control based on particle swarm optimization of greenhouse climate for saving energy consumption, in: 2010 World Automation Congress Kobe, Japan, 2010: pp. 123–128.
C. Stiti, K. Kara, M. Benrabah, A. Aouaichia, Neural Network Model Predictive Control Based on PSO Approach: Applied to DC Motor, In: 2023 2nd International Conference on Electronics, Energy and Measurement, IEEE, 2023: pp. 1–6. https://doi.org/10.1109/IC2EM59347.2023.10419476.
Zhang, Y., Zhao, D., He, L., Zhang, Y. & Huang, J. Research on prediction model of electric vehicle thermal management system based on particle swarm optimization back propagation neural network. Therm. Sci. Eng. Prog. 47, 102281. https://doi.org/10.1016/j.tsep.2023.102281 (2024).
Ait Sahed, O., Kara, K., Benyoucef, A. & Hadjili, M. L. An efficient artificial bee colony algorithm with application to nonlinear predictive control. Int. J. Gen. Syst. 45, 393–417. https://doi.org/10.1080/03081079.2015.1086344 (2016).
Sahed, O. A., Kara, K. & Benyoucef, A. Artificial bee colonybased predictive control for nonlinear systems. Trans. Inst. Meas. Control 37, 780–792. https://doi.org/10.1177/0142331214546796 (2015).
Zimmer, A., Schmidt, A., Ostfeld, A. & Minsker, B. Evolutionary algorithm enhancement for model predictive control and realtime decision support. Environ. Model. Softw. 69, 330–341. https://doi.org/10.1016/j.envsoft.2015.03.005 (2015).
Rao, R. V., Savsani, V. J. & Vakharia, D. P. Teaching–learningbased optimization: A novel method for constrained mechanical design optimization problems. Comput. Des. 43, 303–315. https://doi.org/10.1016/j.cad.2010.12.015 (2011).
Benrabah, M., Kara, K., AitSahed, O. & Hadjili, M. L. Constrained nonlinear predictive control using neural networks and teaching–learningbased optimization. J. Control Autom. Electr. Syst. 32, 1228–1243. https://doi.org/10.1007/s40313021007554 (2021).
Aouaichia, A., Kara, K., Benrabah, M. & Hadjili, M. L. Constrained neural network model predictive controller based on Archimedes optimization algorithm with application to robot manipulators. J. Control Autom. Electr. Syst. 34, 1159–1178. https://doi.org/10.1007/s40313023010331 (2023).
and P.T. M. Dehghani, E. Trojovská, Driving TrainingBased Optimization: A New HumanBased Metaheuristic Algorithm for Solving Optimization Problems, 2022.
Sun, Q., Lyu, G., Liu, X., Niu, F. & Gan, C. Virtual current compensationbased quasisinusoidalwave excitation scheme for switched reluctance motor drives. IEEE Trans. Ind. Electron. 71, 10162–10172. https://doi.org/10.1109/TIE.2023.3333056 (2024).
Bai, X., He, Y. & Xu, M. Lowthrust reconfiguration strategy and optimization for formation flying using Jordan normal form. IEEE Trans. Aerosp. Electron. Syst. 57, 3279–3295. https://doi.org/10.1109/TAES.2021.3074204 (2021).
Dehghani, M., Trojovská, E. & Trojovský, P. A new humanbased metaheuristic algorithm for solving optimization problems on the base of simulation of driving training process. Sci. Rep. 12, 9924. https://doi.org/10.1038/s41598022142257 (2022).
Freitas, D., Lopes, L. G. & MorgadoDias, F. Particle swarm optimisation: A historical review up to the current developments. Entropy 22, 362. https://doi.org/10.3390/e22030362 (2020).
N.M. Sabri, M. Puteh, M.R. Mahmood, An overview of Gravitational Search Algorithm utilization in optimization problems, In: 2013 IEEE 3rd International Conference System Engineering Technology, IEEE, 2013: pp. 61–66. https://doi.org/10.1109/ICSEngT.2013.6650144.
Faris, H., Aljarah, I., AlBetar, M. A. & Mirjalili, S. Grey wolf optimizer: A review of recent variants and applications. Neural Comput. Appl. 30, 413–435. https://doi.org/10.1007/s0052101732725 (2018).
Mirjalili, S. & Lewis, A. The whale optimization algorithm. Adv. Eng. Softw. 95, 51–67. https://doi.org/10.1016/j.advengsoft.2016.01.008 (2016).
Abualigah, L., Elaziz, M. A., Sumari, P., Geem, Z. W. & Gandomi, A. H. Reptile search algorithm (RSA): A natureinspired metaheuristic optimizer. Expert Syst. Appl. 191, 116158. https://doi.org/10.1016/j.eswa.2021.116158 (2022).
Mhaskar, P., ElFarra, N. H. & Christofides, P. D. Stabilization of nonlinear systems with state and control constraints using Lyapunovbased predictive control. Syst. Control Lett. 55, 650–659. https://doi.org/10.1016/j.sysconle.2005.09.014 (2006).
Luo, J. et al. Lyapunov based nonlinear model predictive control of wind power generation system with external disturbances. IEEE Access 12, 5103–5116. https://doi.org/10.1109/ACCESS.2024.3350204 (2024).
Gao, S. et al. Extremely compact and lightweight triboelectric nanogenerator for spacecraft flywheel system health monitoring. Nano Energy 122, 109330. https://doi.org/10.1016/j.nanoen.2024.109330 (2024).
Wang, S. et al. Tooth backlash inspired combshaped singleelectrode triboelectric nanogenerator for selfpowered condition monitoring of gear transmission. Nano Energy 123, 109429. https://doi.org/10.1016/j.nanoen.2024.109429 (2024).
Ouabi, O.L. et al. Learning the propagation properties of rectangular metal plates for Lamb wavebased mapping. Ultrasonics 123, 106705. https://doi.org/10.1016/j.ultras.2022.106705 (2022).
Babaghorbani, B., Beheshti, M. T. & Talebi, H. A. A Lyapunovbased model predictive control strategy in a permanent magnet synchronous generator wind turbine. Int. J. Electr. Power Energy Syst. 130, 106972. https://doi.org/10.1016/j.ijepes.2021.106972 (2021).
Wang, R. & Bao, J. A differential Lyapunovbased tube MPC approach for continuoustime nonlinear processes. J. Process Control 83, 155–163. https://doi.org/10.1016/j.jprocont.2018.11.006 (2019).
B. Mohamed, K. Kamel, Optimal Fuzzy Logic Controller Using Teaching Learning Based Optimization for asynchronous motor, In: 2022 19th International MultiConference Systems, Signals and Devices, IEEE, 2022: pp. 1478–1483. https://doi.org/10.1109/SSD54932.2022.9955752.
Wang, H., Sun, W., Jiang, D. & Qu, R. A MTPA and fluxweakening curve identification method based on physicsinformed network without calibration. IEEE Trans. Power Electron. 38, 12370–12375. https://doi.org/10.1109/TPEL.2023.3295913 (2023).
Li, J., Wu, X. & Wu, L. A computationallyefficient analytical model for SPM machines considering PM shaping and property distribution. IEEE Trans. Energy Convers. 39, 1034–1046. https://doi.org/10.1109/TEC.2024.3352577 (2024).
Dorji, P. & Subba, B. DQ mathematical modelling and simulation of threephase induction motor for electrical fault analysis. IARJSET 7, 38–46. https://doi.org/10.17148/IARJSET.2020.7909 (2020).
Bhagyashree, M. S. & Adappa, M. R. Modelling and simulation of an induction machine. IJIREEICE 4, 119–123. https://doi.org/10.17148/IJIREEICE/NCAEE.2016.24 (2016).
Author information
Authors and Affiliations
Contributions
Chafea Stiti, Mohamed Benrabah: Conceptualization, Methodology, Software, Visualization, Investigation, Writing—Original draft preparation. Abdelhadi Aouaichia, Adel Oubelaid: Data curation, Validation, Supervision, Resources, Writing—Review & Editing. Mohit Bajaj, Milkias Berhanu Tuka, Kamel Kara: Project administration, Supervision, Resources, Writing—Review & Editing.
Corresponding authors
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons AttributionNonCommercialNoDerivatives 4.0 International License, which permits any noncommercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/byncnd/4.0/.
About this article
Cite this article
Stiti, C., Benrabah, M., Aouaichia, A. et al. Lyapunovbased neural network model predictive control using metaheuristic optimization approach. Sci Rep 14, 18760 (2024). https://doi.org/10.1038/s41598024693659
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598024693659
Keywords
Comments
By submitting a comment you agree to abide by our Terms and Community Guidelines. If you find something abusive or that does not comply with our terms or guidelines please flag it as inappropriate.