Recent advances in statistical physics highlight the significant potential of machine learning for phase transition recognition.This study introduces a deep learning framework based on graph neural network to investig...Recent advances in statistical physics highlight the significant potential of machine learning for phase transition recognition.This study introduces a deep learning framework based on graph neural network to investigate non-equilibrium phase transitions,specifically focusing on the directed percolation process.By converting lattices with varying dimensions and connectivity schemes into graph structures and embedding the temporal evolution of the percolation process into node features,our approach enables unified analysis across diverse systems.The framework utilizes a multi-layer graph attention mechanism combined with global pooling to autonomously extract critical features from local dynamics to global phase transition signatures.The model successfully predicts percolation thresholds without relying on lattice geometry,demonstrating its robustness and versatility.Our approach not only offers new insights into phase transition studies but also provides a powerful tool for analyzing complex dynamical systems across various domains.展开更多
Dear Editor,Aiming at the consensus tracking problem of a class of unknown heterogeneous nonlinear multiagent systems(MASs)with input constraints,a novel data-driven iterative learning consensus control(ILCC)protocol ...Dear Editor,Aiming at the consensus tracking problem of a class of unknown heterogeneous nonlinear multiagent systems(MASs)with input constraints,a novel data-driven iterative learning consensus control(ILCC)protocol based on zeroing neural networks(ZNNs)is proposed.First,a dynamic linearization data model(DLDM)is acquired via dynamic linearization technology(DLT).展开更多
In this paper we study the dynamic properties and stabilities of neural networks with delay-time (which includes the time-varying case) by differential inequalities and Lyapunov function approaches. The criteria of co...In this paper we study the dynamic properties and stabilities of neural networks with delay-time (which includes the time-varying case) by differential inequalities and Lyapunov function approaches. The criteria of connective stability, robust stability, Lyapunov stability, asymptotic atability, exponential stability and Lagrange stability of neural networks with delay-time are established, and the results obtained are very useful for the design, implementation and application of adaptive learning neural networks.展开更多
The nonlinear dynamical behaviors of artificial neural network (ANN) and their application to science and engineering were summarized. The mechanism of two kinds of dynamical processes, i.e. weight dynamics and activa...The nonlinear dynamical behaviors of artificial neural network (ANN) and their application to science and engineering were summarized. The mechanism of two kinds of dynamical processes, i.e. weight dynamics and activation dynamics in neural networks, and the stability of computing in structural analysis and design were stated briefly. It was successfully applied to nonlinear neural network to evaluate the stability of underground stope structure in a gold mine. With the application of BP network, it is proven that the neuro-com- puting is a practical and advanced tool for solving large-scale underground rock engineering problems.展开更多
This paper proposes an adaptive neural network control method for a class of perturbed strict-feedback nonlinear systems with unknown time delays. Radial basis function neural networks are used to approximate unknown ...This paper proposes an adaptive neural network control method for a class of perturbed strict-feedback nonlinear systems with unknown time delays. Radial basis function neural networks are used to approximate unknown intermediate control signals. By constructing appropriate Lyapunov-Krasovskii functionals, the unknown time delay terms have been compensated. Dynamic surface control technique is used to overcome the problem of ＂explosion of complexity＂ in backstepping design procedure. In addition, the semiglobal uniform ultimate boundedness of all the signals in the closed-loop system is proved. A main advantage of the proposed controller is that both problems of ＂curse of dimensionality＂ and ＂explosion of complexity＂ are avoided simultaneously. Finally, simulation results are presented to demonstrate the effectiveness of the approach.展开更多
This paper presents a solution to tracking control problem for a class of nonlinear systems with unknown parameters ana uncertain time-varying delays. A new adaptive neural network （NN） dynamic surface controller （...This paper presents a solution to tracking control problem for a class of nonlinear systems with unknown parameters ana uncertain time-varying delays. A new adaptive neural network （NN） dynamic surface controller （DSC） is developed. Some assumptions on uncertain time delays, which were required to be satisfied in previous works, are removed by introducing a novel indirect neural network algorithm into dynamic surface control framework. Also, the designed controller is independent of the time delays. Moreover, the dynamic compensation terms are introduced to facilitate the controller design. It is shown that the closed-loop tracking error converges to a small neighborhood of zero. Finally, a chaotic circuit system is initially bench tested to show the effectiveness of the proposed method.展开更多
In this paper, an adaptive dynamic control scheme based on a fuzzy neural network is presented, that presents utilizes both feed-forward and feedback controller elements. The former of the two elements comprises a neu...In this paper, an adaptive dynamic control scheme based on a fuzzy neural network is presented, that presents utilizes both feed-forward and feedback controller elements. The former of the two elements comprises a neural network with both identification and control role, and the latter is a fuzzy neural algorithm, which is introduced to provide additional control enhancement. The feedforward controller provides only coarse control, whereas the feedback controller can generate on-line conditional proposition rule automatically to improve the overall control action. These properties make the design very versatile and applicable to a range of industrial applications.展开更多
A new type controller, BP neural-networks-based sliding mode controller is developed for a class of large-scale nonlinear systems with unknown bounds of high-order interconnections in this paper. It is shown that dece...A new type controller, BP neural-networks-based sliding mode controller is developed for a class of large-scale nonlinear systems with unknown bounds of high-order interconnections in this paper. It is shown that decentralized BP neural networks are used to adaptively learn the uncertainty bounds of interconnected subsystems in the Lyapunov sense, and the outputs of the decentralized BP neural networks are then used as the parameters of the sliding mode controller to compensate for the effects of subsystems uncertainties. Using this scheme, not only strong robustness with respect to uncertainty dynamics and nonlinearities can be obtained, but also the output tracking error between the actual output of each subsystem and the corresponding desired reference output can asymptotically converge to zero. A simulation example is presented to support the validity of the proposed BP neural-networks-based sliding mode controller.展开更多
Based on high order dynamic neural network, this paper presents the tracking problem for uncertain nonlinear composite system, which contains external disturbance, whose nonlinearities are assumed to be unknown. A smo...Based on high order dynamic neural network, this paper presents the tracking problem for uncertain nonlinear composite system, which contains external disturbance, whose nonlinearities are assumed to be unknown. A smooth controller is designed to guarantee a uniform ultimate boundedness property for the tracking error and all other signals in the dosed loop. Certain measures are utilized to test its performance. No a priori knowledge of an upper bound on the “optimal” weight and modeling error is required; the weights of neural networks are updated on-line. Numerical simulations performed on a simple example illustrate and clarify the approach.展开更多
The goal of this paper is to introduce a new neural network architecture called Sigmoid Diagonal Recurrent Neural Network (SDRNN) to be used in the adaptive control of nonlinear dynamical systems. This is done by addi...The goal of this paper is to introduce a new neural network architecture called Sigmoid Diagonal Recurrent Neural Network (SDRNN) to be used in the adaptive control of nonlinear dynamical systems. This is done by adding a sigmoid weight victor in the hidden layer neurons to adapt of the shape of the sigmoid function making their outputs not restricted to the sigmoid function output. Also, we introduce a dynamic back propagation learning algorithm to train the new proposed network parameters. The simulation results showed that the (SDRNN) is more efficient and accurate than the DRNN in both the identification and adaptive control of nonlinear dynamical systems.展开更多
This paper develops a feedforward neural network based input output model for a general unknown nonlinear dynamic system identification when only the inputs and outputs are accessible observations. In the developed m...This paper develops a feedforward neural network based input output model for a general unknown nonlinear dynamic system identification when only the inputs and outputs are accessible observations. In the developed model, the size of the input space is directly related to the system order. By monitoring the identification error characteristic curve, we are able to determine the system order and subsequently an appropriate network structure for systems identification. Simulation results are promising and show that generic nonlinear systems can be identified, different cases of the same system can also be discriminated by our model.展开更多
A nonlinear feedback term is introduced into the evaluation equation of weights of the backpropagation algorithm for neural network, the network becomes a chaotic one. For the purpose of that we can investigate how th...A nonlinear feedback term is introduced into the evaluation equation of weights of the backpropagation algorithm for neural network, the network becomes a chaotic one. For the purpose of that we can investigate how the different feedback terms affect the process of learning and forecasting, we use the model to forecast the nonlinear time series which is produced by Makey-Glass equation. By selecting the suitable feedback term, the system can escape from the local minima and converge to the global minimum or its approximate solutions, and the forecasting results are better than those of backpropagation algorithm.展开更多
Taking advantage of the knowledge of top and bottom compositions of a distillation column, a dynamic neural network (DNN) is designed to identify the input-output relationship of the column. The weight-training algori...Taking advantage of the knowledge of top and bottom compositions of a distillation column, a dynamic neural network (DNN) is designed to identify the input-output relationship of the column. The weight-training algorithm is derived from a Lyapunov function. Based on this empirical model, a nonlinear H∞ controller is synthesized. The effectiveness of the control strategy is demonstrated using simulation results.展开更多
The paper develops a robust control approach for nonaffine nonlinear continuous systems with input constraints and unknown uncertainties. Firstly, this paper constructs an affine augmented system(AAS) within a pre-com...The paper develops a robust control approach for nonaffine nonlinear continuous systems with input constraints and unknown uncertainties. Firstly, this paper constructs an affine augmented system(AAS) within a pre-compensation technique for converting the original nonaffine dynamics into affine dynamics. Secondly, the paper derives a stability criterion linking the original nonaffine system and the auxiliary system, demonstrating that the obtained optimal policies from the auxiliary system can achieve the robust controller of the nonaffine system. Thirdly, an online adaptive dynamic programming(ADP) algorithm is designed for approximating the optimal solution of the Hamilton–Jacobi–Bellman(HJB) equation.Moreover, the gradient descent approach and projection approach are employed for updating the actor-critic neural network(NN) weights, with the algorithm's convergence being proven. Then, the uniformly ultimately bounded stability of state is guaranteed. Finally, in simulation, some examples are offered for validating the effectiveness of this presented approach.展开更多
Over 1.3 million people die annually in traffic accidents,and this tragic fact highlights the urgent need to enhance the intelligence of traffic safety and control systems.In modern industrial and technological applic...Over 1.3 million people die annually in traffic accidents,and this tragic fact highlights the urgent need to enhance the intelligence of traffic safety and control systems.In modern industrial and technological applications and collaborative edge intelligence,control systems are crucial for ensuring efficiency and safety.However,deficiencies in these systems can lead to significant operational risks.This paper uses edge intelligence to address the challenges of achieving target speeds and improving efficiency in vehicle control,particularly the limitations of traditional Proportional-Integral-Derivative(PID)controllers inmanaging nonlinear and time-varying dynamics,such as varying road conditions and vehicle behavior,which often result in substantial discrepancies between desired and actual speeds,as well as inefficiencies due to manual parameter adjustments.The paper uses edge intelligence to propose a novel PID control algorithm that integrates Backpropagation(BP)neural networks to enhance robustness and adaptability.The BP neural network is first trained to capture the nonlinear dynamic characteristics of the vehicle.Thetrained network is then combined with the PID controller to forma hybrid control strategy.The output layer of the neural network directly adjusts the PIDparameters(k_(p),k_(i),k_(d)),optimizing performance for specific driving scenarios through self-learning and weight adjustments.Simulation experiments demonstrate that our BP neural network-based PID design significantly outperforms traditional methods,with the response time for acceleration from 0 to 1 m/s improved from 0.25 s to just 0.065 s.Furthermore,real-world tests on an intelligent vehicle show its ability to make timely adjustments in response to complex road conditions,ensuring consistent speed maintenance and enhancing overall system performance.展开更多
The design and optimization of nonlinear fiber laser sources,such as soliton self-frequency shift(SSFS)tunable sources and supercontinuum(SC)sources,have traditionally relied on manual tuning and simulations,posing ch...The design and optimization of nonlinear fiber laser sources,such as soliton self-frequency shift(SSFS)tunable sources and supercontinuum(SC)sources,have traditionally relied on manual tuning and simulations,posing challenges for real-time applications.Machine learning has shown promise in fiber nonlinear propagation characterization,but the optimization and design of nonlinear systems remain relatively unexplored,especially under multitarget optimization conditions.In this paper,we propose a method that combines deep reinforcement learning(DRL)and deep neural network(DNN)to achieve fast synchronization optimization of ultrafast pulse nonlinear propagation in optical fibers under multitarget optimization tasks,with applications demonstrated in complex SSFS and SC generation systems in the mid-infrared band.The results indicate that a set of optimization parameters can be obtained in a few seconds,enabling rapid,automated tuning of pulse parameters in pursuit of diverse optimization objectives.This integration of DRL and DNN models holds transformative potential for the real-time optimization of not only fiber lasers but also a wide variety of complex photonic systems,paving the way for intelligent,adaptive optical system design and operation.展开更多
Industrial noise can be successfully mitigated with the combined use of passive and Active Noise Control (ANC) strategies. In a noisy area, a practical solution for noise attenuation may include both the use of baffle...Industrial noise can be successfully mitigated with the combined use of passive and Active Noise Control (ANC) strategies. In a noisy area, a practical solution for noise attenuation may include both the use of baffles and ANC. When the operator is required to stay in movement in a delimited spatial area, conventional ANC is usually not able to adequately cancel the noise over the whole area. New control strategies need to be devised to achieve acceptable spatial coverage. A three-dimensional actuator model is proposed in this paper. Active Noise Control (ANC) usually requires a feedback noise measurement for the proper response of the loop controller. In some situations, especially where the real-time tridimensional positioning of a feedback transducer is unfeasible, the availability of a 3D precise noise level estimator is indispensable. In our previous works [1,2], using a vibrating signal of the primary source of noise as an input reference for spatial noise level prediction proved to be a very good choice. Another interesting aspect observed in those previous works was the need for a variable-structure linear model, which is equivalent to a sort of a nonlinear model, with unknown analytical equivalence until now. To overcome this in this paper we propose a model structure based on an Artificial Neural Network (ANN) as a nonlinear black-box model to capture the dynamic nonlinear behaveior of the investigated process. This can be used in a future closed loop noise cancelling strategy. We devise an ANN architecture and a corresponding training methodology to cope with the problem, and a MISO (Multi-Input Single-Output) model structure is used in the identification of the system dynamics. A metric is established to compare the obtained results with other works elsewhere. The results show that the obtained model is consistent and it adequately describes the main dynamics of the studied phenomenon, showing that the MISO approach using an ANN is appropriate for the simulation of the investigated process. A clear conclusion is reached highlighting the promising results obtained using this kind of modeling for ANC.展开更多
A new method is presented in this paper for fitting VFC*ss (voltage to frequency converter) output functions by using high order neural networks. The nonlinear estimation is implemented when the VFC110 is used at a...A new method is presented in this paper for fitting VFC*ss (voltage to frequency converter) output functions by using high order neural networks. The nonlinear estimation is implemented when the VFC110 is used at a full scale output frequency of 4 MHz. Two kinds of on line dynamic calibrating circuits are designed to improve the sampling precision. This method can also be applied to different industrial applications.展开更多
Aiming at solving the initial value problem of nonlinear dynamic system,a neural network method based on Lie symmetry theory of differential equation is proposed.Because the Lie series representation of the solution o...Aiming at solving the initial value problem of nonlinear dynamic system,a neural network method based on Lie symmetry theory of differential equation is proposed.Because the Lie series representation of the solution of the problem to be solved provides the prior knowledge of the solution for the network training,the structure of the neural network is simple,and the network solution is more effective to approximate the true solution.Theoretical analysis and numerical examples demonstrate the reliability and effectiveness of the proposed algorithm.展开更多
Kerr resonator is one of the most popular platforms to produce optical frequency comb and temporal cavity soliton.As an essential method for investigating the nonlinear dynamics of Kerr resonators,traditional numerica...Kerr resonator is one of the most popular platforms to produce optical frequency comb and temporal cavity soliton.As an essential method for investigating the nonlinear dynamics of Kerr resonators,traditional numerical simulations rely on solving the Lugiato-Lefever equation(LLE)using the split-step Fourier method(SSFM),which is computationally intensive and time-consuming.To address this challenge,this study proposes a recurrent neural network model with prior information feedback,enabling efficient and accurate prediction of soliton dynamics in Kerr resonator.With the acceleration of graphics processing unit(GPU),the computational efficiency improved by 20 times.We compared various recurrent neural networks and found that the gated recurrent unit(GRU)network demonstrated superior performance in this task.This work highlights the potential of artificial intelligence(AI)for modeling nonlinear optical dynamics in Kerr resonator,paving the way for designing optical frequency comb and generating ultrafast pulse.展开更多
基金supported by the Fund from the Science and Technology Department of Henan Province,China(Grant Nos.222102210233 and 232102210064)the National Natural Science Foundation of China(Grant Nos.62373169 and 72474086)+5 种基金the Young and Midcareer Academic Leader of Jiangsu Province,China(Grant No.Qinglan Project in 2024)the National Statistical Science Research Project(Grant No.2022LZ03)Shaanxi Provincial Soft Science Project(Grant No.2022KRM111)Shaanxi Provincial Social Science Foundation(Grant No.2022R016)the Special Project for Philosophical and Social Sciences Research in Shaanxi Province,China(Grant No.2024QN018)the Fund from the Henan Office of Philosophy and Social Science(Grant No.2023CJJ112).
文摘Recent advances in statistical physics highlight the significant potential of machine learning for phase transition recognition.This study introduces a deep learning framework based on graph neural network to investigate non-equilibrium phase transitions,specifically focusing on the directed percolation process.By converting lattices with varying dimensions and connectivity schemes into graph structures and embedding the temporal evolution of the percolation process into node features,our approach enables unified analysis across diverse systems.The framework utilizes a multi-layer graph attention mechanism combined with global pooling to autonomously extract critical features from local dynamics to global phase transition signatures.The model successfully predicts percolation thresholds without relying on lattice geometry,demonstrating its robustness and versatility.Our approach not only offers new insights into phase transition studies but also provides a powerful tool for analyzing complex dynamical systems across various domains.
基金supported by the National Nature Science Foundation of China(U21A20166)the Science and Technology Development Foundation of Jilin Province(20230508095RC)+2 种基金the Major Science and Technology Projects of Jilin Province and Changchun City(20220301033GX)the Development and Reform Commission Foundation of Jilin Province(2023C034-3)the Interdisciplinary Integration and Innovation Project of JLU(JLUXKJC2020202).
文摘Dear Editor,Aiming at the consensus tracking problem of a class of unknown heterogeneous nonlinear multiagent systems(MASs)with input constraints,a novel data-driven iterative learning consensus control(ILCC)protocol based on zeroing neural networks(ZNNs)is proposed.First,a dynamic linearization data model(DLDM)is acquired via dynamic linearization technology(DLT).
文摘In this paper we study the dynamic properties and stabilities of neural networks with delay-time (which includes the time-varying case) by differential inequalities and Lyapunov function approaches. The criteria of connective stability, robust stability, Lyapunov stability, asymptotic atability, exponential stability and Lagrange stability of neural networks with delay-time are established, and the results obtained are very useful for the design, implementation and application of adaptive learning neural networks.
基金This work was financially supported by the Key Project for National Science of "9.5" (Reward Ⅱ for National Science and Technol
文摘The nonlinear dynamical behaviors of artificial neural network (ANN) and their application to science and engineering were summarized. The mechanism of two kinds of dynamical processes, i.e. weight dynamics and activation dynamics in neural networks, and the stability of computing in structural analysis and design were stated briefly. It was successfully applied to nonlinear neural network to evaluate the stability of underground stope structure in a gold mine. With the application of BP network, it is proven that the neuro-com- puting is a practical and advanced tool for solving large-scale underground rock engineering problems.
文摘This paper proposes an adaptive neural network control method for a class of perturbed strict-feedback nonlinear systems with unknown time delays. Radial basis function neural networks are used to approximate unknown intermediate control signals. By constructing appropriate Lyapunov-Krasovskii functionals, the unknown time delay terms have been compensated. Dynamic surface control technique is used to overcome the problem of ＂explosion of complexity＂ in backstepping design procedure. In addition, the semiglobal uniform ultimate boundedness of all the signals in the closed-loop system is proved. A main advantage of the proposed controller is that both problems of ＂curse of dimensionality＂ and ＂explosion of complexity＂ are avoided simultaneously. Finally, simulation results are presented to demonstrate the effectiveness of the approach.
基金supported by Natural Science Foundation of Hebe Province(No.F2014208119)Doctoral Foundation of Hebei University of Science and Technology(No.010075)
文摘This paper presents a solution to tracking control problem for a class of nonlinear systems with unknown parameters ana uncertain time-varying delays. A new adaptive neural network （NN） dynamic surface controller （DSC） is developed. Some assumptions on uncertain time delays, which were required to be satisfied in previous works, are removed by introducing a novel indirect neural network algorithm into dynamic surface control framework. Also, the designed controller is independent of the time delays. Moreover, the dynamic compensation terms are introduced to facilitate the controller design. It is shown that the closed-loop tracking error converges to a small neighborhood of zero. Finally, a chaotic circuit system is initially bench tested to show the effectiveness of the proposed method.
基金China Postdoctoral Science Foundation and Natural Science of Heibei Province!698004
文摘In this paper, an adaptive dynamic control scheme based on a fuzzy neural network is presented, that presents utilizes both feed-forward and feedback controller elements. The former of the two elements comprises a neural network with both identification and control role, and the latter is a fuzzy neural algorithm, which is introduced to provide additional control enhancement. The feedforward controller provides only coarse control, whereas the feedback controller can generate on-line conditional proposition rule automatically to improve the overall control action. These properties make the design very versatile and applicable to a range of industrial applications.
基金The National Natural Science Foundations of China(50505029)
文摘A new type controller, BP neural-networks-based sliding mode controller is developed for a class of large-scale nonlinear systems with unknown bounds of high-order interconnections in this paper. It is shown that decentralized BP neural networks are used to adaptively learn the uncertainty bounds of interconnected subsystems in the Lyapunov sense, and the outputs of the decentralized BP neural networks are then used as the parameters of the sliding mode controller to compensate for the effects of subsystems uncertainties. Using this scheme, not only strong robustness with respect to uncertainty dynamics and nonlinearities can be obtained, but also the output tracking error between the actual output of each subsystem and the corresponding desired reference output can asymptotically converge to zero. A simulation example is presented to support the validity of the proposed BP neural-networks-based sliding mode controller.
基金This work was supported by the National Natural Science Foundation of China(No.60274009)and Specialized Research Fundfor the Doctoral Program of Higher Education(No.20020145007).
文摘Based on high order dynamic neural network, this paper presents the tracking problem for uncertain nonlinear composite system, which contains external disturbance, whose nonlinearities are assumed to be unknown. A smooth controller is designed to guarantee a uniform ultimate boundedness property for the tracking error and all other signals in the dosed loop. Certain measures are utilized to test its performance. No a priori knowledge of an upper bound on the “optimal” weight and modeling error is required; the weights of neural networks are updated on-line. Numerical simulations performed on a simple example illustrate and clarify the approach.
文摘The goal of this paper is to introduce a new neural network architecture called Sigmoid Diagonal Recurrent Neural Network (SDRNN) to be used in the adaptive control of nonlinear dynamical systems. This is done by adding a sigmoid weight victor in the hidden layer neurons to adapt of the shape of the sigmoid function making their outputs not restricted to the sigmoid function output. Also, we introduce a dynamic back propagation learning algorithm to train the new proposed network parameters. The simulation results showed that the (SDRNN) is more efficient and accurate than the DRNN in both the identification and adaptive control of nonlinear dynamical systems.
文摘This paper develops a feedforward neural network based input output model for a general unknown nonlinear dynamic system identification when only the inputs and outputs are accessible observations. In the developed model, the size of the input space is directly related to the system order. By monitoring the identification error characteristic curve, we are able to determine the system order and subsequently an appropriate network structure for systems identification. Simulation results are promising and show that generic nonlinear systems can be identified, different cases of the same system can also be discriminated by our model.
文摘A nonlinear feedback term is introduced into the evaluation equation of weights of the backpropagation algorithm for neural network, the network becomes a chaotic one. For the purpose of that we can investigate how the different feedback terms affect the process of learning and forecasting, we use the model to forecast the nonlinear time series which is produced by Makey-Glass equation. By selecting the suitable feedback term, the system can escape from the local minima and converge to the global minimum or its approximate solutions, and the forecasting results are better than those of backpropagation algorithm.
文摘Taking advantage of the knowledge of top and bottom compositions of a distillation column, a dynamic neural network (DNN) is designed to identify the input-output relationship of the column. The weight-training algorithm is derived from a Lyapunov function. Based on this empirical model, a nonlinear H∞ controller is synthesized. The effectiveness of the control strategy is demonstrated using simulation results.
基金Project supported by the National Natural Science Foundation of China (Grant No. 62103408)Beijing Nova Program (Grant No. 20240484516)the Fundamental Research Funds for the Central Universities (Grant No. KG16314701)。
文摘The paper develops a robust control approach for nonaffine nonlinear continuous systems with input constraints and unknown uncertainties. Firstly, this paper constructs an affine augmented system(AAS) within a pre-compensation technique for converting the original nonaffine dynamics into affine dynamics. Secondly, the paper derives a stability criterion linking the original nonaffine system and the auxiliary system, demonstrating that the obtained optimal policies from the auxiliary system can achieve the robust controller of the nonaffine system. Thirdly, an online adaptive dynamic programming(ADP) algorithm is designed for approximating the optimal solution of the Hamilton–Jacobi–Bellman(HJB) equation.Moreover, the gradient descent approach and projection approach are employed for updating the actor-critic neural network(NN) weights, with the algorithm's convergence being proven. Then, the uniformly ultimately bounded stability of state is guaranteed. Finally, in simulation, some examples are offered for validating the effectiveness of this presented approach.
基金supported by the National Key Research and Development Program of China(No.2023YFF0715103)-financial supportNational Natural Science Foundation of China(Grant Nos.62306237 and 62006191)-financial support+1 种基金Key Research and Development Program of Shaanxi(Nos.2024GX-YBXM-149 and 2021ZDLGY15-04)-financial support,NorthwestUniversity Graduate Innovation Project(No.CX2023194)-financial supportNatural Science Foundation of Shaanxi(No.2023-JC-QN-0750)-financial support.
文摘Over 1.3 million people die annually in traffic accidents,and this tragic fact highlights the urgent need to enhance the intelligence of traffic safety and control systems.In modern industrial and technological applications and collaborative edge intelligence,control systems are crucial for ensuring efficiency and safety.However,deficiencies in these systems can lead to significant operational risks.This paper uses edge intelligence to address the challenges of achieving target speeds and improving efficiency in vehicle control,particularly the limitations of traditional Proportional-Integral-Derivative(PID)controllers inmanaging nonlinear and time-varying dynamics,such as varying road conditions and vehicle behavior,which often result in substantial discrepancies between desired and actual speeds,as well as inefficiencies due to manual parameter adjustments.The paper uses edge intelligence to propose a novel PID control algorithm that integrates Backpropagation(BP)neural networks to enhance robustness and adaptability.The BP neural network is first trained to capture the nonlinear dynamic characteristics of the vehicle.Thetrained network is then combined with the PID controller to forma hybrid control strategy.The output layer of the neural network directly adjusts the PIDparameters(k_(p),k_(i),k_(d)),optimizing performance for specific driving scenarios through self-learning and weight adjustments.Simulation experiments demonstrate that our BP neural network-based PID design significantly outperforms traditional methods,with the response time for acceleration from 0 to 1 m/s improved from 0.25 s to just 0.065 s.Furthermore,real-world tests on an intelligent vehicle show its ability to make timely adjustments in response to complex road conditions,ensuring consistent speed maintenance and enhancing overall system performance.
基金supported by the National Natural Science Foundation of China(Grant No.62575051)the Aeronautical Science Foundation of China(Grant No.2023M038080001)+1 种基金the Equipment Pre-research Joint Fund of the Ministry of Education(Grant No.8091B042228)the Science and Technology Project of Sichuan Province(Grant Nos.2023NSFSC1964 and 203NSFSC0033).
文摘The design and optimization of nonlinear fiber laser sources,such as soliton self-frequency shift(SSFS)tunable sources and supercontinuum(SC)sources,have traditionally relied on manual tuning and simulations,posing challenges for real-time applications.Machine learning has shown promise in fiber nonlinear propagation characterization,but the optimization and design of nonlinear systems remain relatively unexplored,especially under multitarget optimization conditions.In this paper,we propose a method that combines deep reinforcement learning(DRL)and deep neural network(DNN)to achieve fast synchronization optimization of ultrafast pulse nonlinear propagation in optical fibers under multitarget optimization tasks,with applications demonstrated in complex SSFS and SC generation systems in the mid-infrared band.The results indicate that a set of optimization parameters can be obtained in a few seconds,enabling rapid,automated tuning of pulse parameters in pursuit of diverse optimization objectives.This integration of DRL and DNN models holds transformative potential for the real-time optimization of not only fiber lasers but also a wide variety of complex photonic systems,paving the way for intelligent,adaptive optical system design and operation.
基金CAPES and CNPq(Brazilian federal research agencies)for their financial support.
文摘Industrial noise can be successfully mitigated with the combined use of passive and Active Noise Control (ANC) strategies. In a noisy area, a practical solution for noise attenuation may include both the use of baffles and ANC. When the operator is required to stay in movement in a delimited spatial area, conventional ANC is usually not able to adequately cancel the noise over the whole area. New control strategies need to be devised to achieve acceptable spatial coverage. A three-dimensional actuator model is proposed in this paper. Active Noise Control (ANC) usually requires a feedback noise measurement for the proper response of the loop controller. In some situations, especially where the real-time tridimensional positioning of a feedback transducer is unfeasible, the availability of a 3D precise noise level estimator is indispensable. In our previous works [1,2], using a vibrating signal of the primary source of noise as an input reference for spatial noise level prediction proved to be a very good choice. Another interesting aspect observed in those previous works was the need for a variable-structure linear model, which is equivalent to a sort of a nonlinear model, with unknown analytical equivalence until now. To overcome this in this paper we propose a model structure based on an Artificial Neural Network (ANN) as a nonlinear black-box model to capture the dynamic nonlinear behaveior of the investigated process. This can be used in a future closed loop noise cancelling strategy. We devise an ANN architecture and a corresponding training methodology to cope with the problem, and a MISO (Multi-Input Single-Output) model structure is used in the identification of the system dynamics. A metric is established to compare the obtained results with other works elsewhere. The results show that the obtained model is consistent and it adequately describes the main dynamics of the studied phenomenon, showing that the MISO approach using an ANN is appropriate for the simulation of the investigated process. A clear conclusion is reached highlighting the promising results obtained using this kind of modeling for ANC.
文摘A new method is presented in this paper for fitting VFC*ss (voltage to frequency converter) output functions by using high order neural networks. The nonlinear estimation is implemented when the VFC110 is used at a full scale output frequency of 4 MHz. Two kinds of on line dynamic calibrating circuits are designed to improve the sampling precision. This method can also be applied to different industrial applications.
基金supported by the National Natural Science Foundation of China under Grant No.11571008。
文摘Aiming at solving the initial value problem of nonlinear dynamic system,a neural network method based on Lie symmetry theory of differential equation is proposed.Because the Lie series representation of the solution of the problem to be solved provides the prior knowledge of the solution for the network training,the structure of the neural network is simple,and the network solution is more effective to approximate the true solution.Theoretical analysis and numerical examples demonstrate the reliability and effectiveness of the proposed algorithm.
基金supported by the National Natural Science Foundation of China(Grant No.42327803)the Open Project Program of Wuhan National Laboratory for Optoelectronics(2023WNLOKF007)+4 种基金the Open Fund of the State Laboratory of Photonics and Communications(2025QZKF021)Technology Innovation Project of Hubei Province(2022BEC003)Key R&D Program of Hubei Province(2023BAB062)Major Science and Technology Projects of Wuhan(2023010302020030)Guangdong Basic and Applied Basic Research Foundation(2023A1515010965,2024A1515010017).
文摘Kerr resonator is one of the most popular platforms to produce optical frequency comb and temporal cavity soliton.As an essential method for investigating the nonlinear dynamics of Kerr resonators,traditional numerical simulations rely on solving the Lugiato-Lefever equation(LLE)using the split-step Fourier method(SSFM),which is computationally intensive and time-consuming.To address this challenge,this study proposes a recurrent neural network model with prior information feedback,enabling efficient and accurate prediction of soliton dynamics in Kerr resonator.With the acceleration of graphics processing unit(GPU),the computational efficiency improved by 20 times.We compared various recurrent neural networks and found that the gated recurrent unit(GRU)network demonstrated superior performance in this task.This work highlights the potential of artificial intelligence(AI)for modeling nonlinear optical dynamics in Kerr resonator,paving the way for designing optical frequency comb and generating ultrafast pulse.
