Addressing issues such as the disconnect between theory and practice and low student engagement in control system education,this paper uses the course“The Working Process of Open-Loop Control Systems”as a case study...Addressing issues such as the disconnect between theory and practice and low student engagement in control system education,this paper uses the course“The Working Process of Open-Loop Control Systems”as a case study to explore the integration of AI technology with the“project-guided and task-driven”teaching model.By constructing a four-dimensional teaching framework of“situation-task-activity-evaluation,”AI tools are embedded in project practices such as the construction of a mechanical timed flower watering device and the optimization of a digital timed flower watering device,achieving precision,interactivity,and personalization in the teaching process.Teaching practice demonstrates that this model significantly enhances students’technical awareness,materialization capabilities,and engineering thinking,providing a reference for the teaching reform of technical courses in high school education.展开更多
Autonomous driving technology is constantly developing to a higher level of complex scenes,and there is a growing demand for the utilization of end-to-end data-driven control.However,the end-to-end path tracking proce...Autonomous driving technology is constantly developing to a higher level of complex scenes,and there is a growing demand for the utilization of end-to-end data-driven control.However,the end-to-end path tracking process often encounters challenges in learning efficiency and generalization.To address this issue,this paper designs a deep deterministic policy gradient(DDPG)-based reinforcement learning strategy that integrates imitation learning and feedforward exploration in the path following process.In imitation learning,the path tracking control data generated by the model predictive control(MPC)method is used to train an end-to-end steering control model of a deep neural network.Another feedforward exploration behavior is predicted by road curvature and vehicle speed,and adds it and imitation learning to the DDPG reinforcement learning to obtain decision-making experience and action prediction behavior of the path tracking process.In the reinforcement learning process,imitation learning is used to update the pre-training parameters of the actor network,and a feedforward steering technique with random noise is adopted for strategy exploration.In the reward function,a hierarchical progressive reward form and a constrained objective reward function referring to MPC are designed,and the actor-critic network architecture is determined.Finally,the path tracking performance of the designed method is verified by comparing various training results,simulations,and HIL tests.The results show that the designed method can effectively utilize pre-training and feedforward prior experience to obtain optimal path tracking performance of an autonomous vehicle,and has better generalization ability than other methods.This study provides an efficient control scheme for improving the end-to-end control performance of autonomous vehicles.展开更多
In this paper,a new study concerning the usage of artificial neural networks in the control application is given.It is shown,that the data gathered during proper operation of a given control plant can be used in the l...In this paper,a new study concerning the usage of artificial neural networks in the control application is given.It is shown,that the data gathered during proper operation of a given control plant can be used in the learning process to fully embrace the control pattern.Interestingly,the instances driven by neural networks have the ability to outperform the original analytically driven scenarios.Three different control schemes,namely perfect,linear-quadratic,and generalized predictive controllers were used in the theoretical study.In addition,the nonlinear recurrent neural network-based generalized predictive controller with the radial basis function-originated predictor was obtained to exemplify the main results of the paper regarding the real-world application.展开更多
The acquisition,tracking,and pointing(ATP)system is widely used in target tracking,counter-UAV operations,and other related fields.As UAV technology develops,there is a growing demand to enhance the tracking capabilit...The acquisition,tracking,and pointing(ATP)system is widely used in target tracking,counter-UAV operations,and other related fields.As UAV technology develops,there is a growing demand to enhance the tracking capabilities of ATP systems.However,in practical applications,ATP systems face various design constraints and functional limitations,making it infeasible to indefinitely improve hardware performance to meet tracking requirements.As a result,tracking algorithms are required to execute increasingly complex tasks.This study introduces a multi-rate feedforward predictive controller to address issues such as low image feedback frequency and significant delays in ATP systems,which lead to tracking jitter,poor tracking performance,low precision,and target loss.At the same time,the pro-posed approach aims to improve the tracking capabilities of ATP systems for high-speed and highly maneuverable targets under conditions of low sampling feedback rates and high feedback delays.The method suggested is also characterized by its low order,fast response,and robustness to model parameter variations.In this study,an actual ATP system is built for target tracking test,and the proposed algorithm is fully validated in terms of simulation and actual system application verification.Results from both simulations and experiments demonstrate that the method effectively compensates for delays and low sampling rates.For targets with relative angular velocities ranging from 0 to 90°/s and angular accelerations between 0 and 470°/s^(2),the system improved tracking accuracy by 70.0%-89.9%at a sampling frequency of 50 Hz and a delay of 30 m s.Moreover,the compensation algorithm demonstrated consistent performance across actuators with varying characteristics,further confirming its robustness to model insensitivity.In summary,the proposed algorithm considerably enhances the tracking accuracy and capability of ATP systems for high-speed and highly maneuverable targets,reducing the probability of target loss from high speed.This approach offers a practical solution for future multi-target tracking across diverse operational scenarios.展开更多
The precise measurement of the antineutrino spectra produced by isotope fission in reactors is of great significance for studying neutrino oscillations,refining nuclear databases,and addressing the reactor antineutrin...The precise measurement of the antineutrino spectra produced by isotope fission in reactors is of great significance for studying neutrino oscillations,refining nuclear databases,and addressing the reactor antineutrino anomaly.In this paper,we report a method that utilizes a feedforward neural network(FNN)model to decompose the prompt energy spectrum observed in a short-baseline reactor neutrino experiment and extract the antineutrino spectra produced by the fission of major isotopes such as^(235)U,^(238)U,^(239)Pu,and^(241)Pu in the nuclear reactor.We present two training strategies for the model and compare them with the traditional X^(2) minimization method by applying them to the same set of pseudo-data corresponding to a total exposure of(2.9×5×1800)GW_(th)·tons·days.The results show that the FNN model not only converges faster and better during the fitting process but also achieves relative errors of less than 1%in the 2−8 MeV range in the extracted spectra,outperforming the X^(2) minimization method.The feasibility and superiority of this method were validated in the study.展开更多
This paper studies global stabilization via predictor-based sampled-data output feedback for a class of feedforward nonlinear time-delay systems.Note that the traditional sampled-data observer via zero-order holder ma...This paper studies global stabilization via predictor-based sampled-data output feedback for a class of feedforward nonlinear time-delay systems.Note that the traditional sampled-data observer via zero-order holder may result in the performance degradation of the observer.In this paper,an improved predictor-based observer is designed to compensate for the influence of the unmeasurable states,sampling errors and output delay.In addition,a sampled-data output-feedback controller is also constructed using the gain scaling technique.By the Lyapunov-Krasovskii functional method,the global exponential stability of the resulting closed-loop system can be guaranteed under some sufficient conditions.The simulation results are provided to demonstrate the main results.展开更多
Feedforward control is one of the most effective control techniques to increase the robot’s tracking accuracy.However,most of the dynamic models used in the feedforward controllers are linearly simplified such that t...Feedforward control is one of the most effective control techniques to increase the robot’s tracking accuracy.However,most of the dynamic models used in the feedforward controllers are linearly simplified such that the nonlinear and time-varying characteristics of dynamics in the workspace are ignored.In this paper,an iterative tuning method for feedforward control of parallel manipulators by taking nonlinear dynamics into account is proposed.Based on the robot rigid-body dynamic model,a feedforward controller considering the dynamic nonlinearity is presented.An iterative tuning method is given to iteratively update the feedforward controller by minimizing the root mean square(RMS)of the joint errors at each cycle.The effectiveness and extrapolation capability of the proposed method are validated through the experiments on a 2-DOF parallel manipulator.This research proposes an iterative tuning method for feedforward control of parallel manipulators considering nonlinear dynamics,which has better extrapolation capability in the whole workspace of manipulators.展开更多
Under the condition of large inertia load,the stability of the servo system is more sensitive to the response speed and more likely to produce overshoot oscillations.In order to realize the requirements of high-precis...Under the condition of large inertia load,the stability of the servo system is more sensitive to the response speed and more likely to produce overshoot oscillations.In order to realize the requirements of high-precision and fast-response control of permanent magnet synchronous motor(PMSM)under large inertia load,an improved feedforward control strategy based on position impulse compensation and PD iterative algorithm is proposed to improve the response speed of the PMSM servo system and reduce the overshoot oscillation.This paper analyzes the mathematical models of the speed servo system and position servo system of the PMSM,calculates position overshoot impulse of the PMSM servo system,and improves the traditional feedforward control strategy to reversely compensate when the position is about to overshoot.Moreover,in order to further reduce the position overshoot,the PD iterative control algorithm is superimposed without increasing the complexity of the algorithm.The input signal is continuously corrected through multiple runs to achieve a smoother response control.The effectiveness of the proposed feedforward control strategy is verified by simulation and experiment.展开更多
Aeropropulsion System Test Facility (ASTF) is required to accurately control the pressure and temperature of the airflow to test the performance of the aero-engine. However, the control accuracy of ASTF is significant...Aeropropulsion System Test Facility (ASTF) is required to accurately control the pressure and temperature of the airflow to test the performance of the aero-engine. However, the control accuracy of ASTF is significantly affected by the flow disturbance caused by aero-engine acceleration and deceleration. This would reduce the credibility of ASTF’s test results for the aero-engine. Therefore, first, this paper proposes a feedforward compensation-based L1 adaptive control method for ASTF to address this problem. The baseline controller is first designed based on ideal uncoupled closed-loop dynamics to achieve dynamic decoupling. Then, L1 adaptive control is adopted to deal with various uncertainties and ensure good control performance. To further enhance the anti-disturbance performance, a feedforward strategy based on disturbance prediction is designed in the L1 adaptive control framework to compensate for the unmatched flow disturbance, which cannot be measured directly. In addition, this strategy takes into account the effects of actuator dynamics. With this method, the feedforward term can be determined from the nominal model parameters despite uncertainties. Finally, to demonstrate the effectiveness of the proposed method, various comparative experiments are performed on a hardware-in-the-loop system of ASTF. The experimental results show that the proposed method possesses excellent tracking performance, anti-disturbance performance and robustness.展开更多
Enhancing the accuracy of real-time ship roll prediction is crucial for maritime safety and operational efficiency.To address the challenge of accurately predicting the ship roll status with nonlinear time-varying dyn...Enhancing the accuracy of real-time ship roll prediction is crucial for maritime safety and operational efficiency.To address the challenge of accurately predicting the ship roll status with nonlinear time-varying dynamic characteristics,a real-time ship roll prediction scheme is proposed on the basis of a data preprocessing strategy and a novel stochastic trainer-based feedforward neural network.The sliding data window serves as a ship time-varying dynamic observer to enhance model prediction stability.The variational mode decomposition method extracts effective information on ship roll motion and reduces the non-stationary characteristics of the series.The energy entropy method reconstructs the mode components into high-frequency,medium-frequency,and low-frequency series to reduce model complexity.An improved black widow optimization algorithm trainer-based feedforward neural network with enhanced local optimal avoidance predicts the high-frequency component,enabling accurate tracking of abrupt signals.Additionally,the deterministic algorithm trainer-based neural network,characterized by rapid processing speed,predicts the remaining two mode components.Thus,real-time ship roll forecasting can be achieved through the reconstruction of mode component prediction results.The feasibility and effectiveness of the proposed hybrid prediction scheme for ship roll motion are demonstrated through the measured data of a full-scale ship trial.The proposed prediction scheme achieves real-time ship roll prediction with superior prediction accuracy.展开更多
The conventional feedforward hybrid active noise control(FFHANC)system combines the advantages of the feedforward narrowband active noise control(FFNANC)system and the feedforward broadband active noise control(FFBANC...The conventional feedforward hybrid active noise control(FFHANC)system combines the advantages of the feedforward narrowband active noise control(FFNANC)system and the feedforward broadband active noise control(FFBANC)system.To enhance its adaptive adjustment capability under frequency mismatch(FM)conditions,this paper introduces a narrowband frequency adaptive estimation module into the conventional FFHANC system.This module integrates an autoregressive(AR)model and a linear cascaded adaptive notch filter(LCANF),enabling accurate reference signal frequency estimation even under significant FM.Furthermore,in order to improve the coherence between narrowband and broadband components in the system’s error signal and its corresponding control filter for the conventional FFHANC system,this paper proposes an algorithm based on autoregressive bandpass filter bank(AR-BPFB)for error separation.Simulation results demonstrate that the proposed FFHANC system maintains robust performance under high FM conditions and effectively suppresses hybrid-band noise.The AR-BPFB algorithm significantly elevates the convergence speed of the FFHANC system.展开更多
Aim Aiming at the position tracking control for valve controlled motor electrohydraulic proportional servo systems mainly driving the static load torque, the tracking performance was studied in the presence of the v...Aim Aiming at the position tracking control for valve controlled motor electrohydraulic proportional servo systems mainly driving the static load torque, the tracking performance was studied in the presence of the variable gain and deadzone. Methods On the basis of conventional composite control with the deadzone compensation method, a comprehensive control approach with the deadzone and self adjusting feedforward compensation was proposed. Results Experimental results showed that the good tracking performance was achieved for the sinusoidal and constant velocity position tracking under a wide variations of load torque. Conclusion The position tracking accuracy for valve controlled motor electrohydraulic proportional servo systems has been solved by using the comprehensive control approach with the deadzone and self adjusting feedforward compensation.展开更多
在整体式车辆稳定性轨迹跟踪控制架构的基础之上,设计了一种引入预瞄曲率信息的自适应预测时域非线性模型预测控制(NMPC).基于预瞄的参考路径曲率点列指导控制维度变化,提升控制器对于路径曲率的动态响应能力;进一步地,引入状态协调优...在整体式车辆稳定性轨迹跟踪控制架构的基础之上,设计了一种引入预瞄曲率信息的自适应预测时域非线性模型预测控制(NMPC).基于预瞄的参考路径曲率点列指导控制维度变化,提升控制器对于路径曲率的动态响应能力;进一步地,引入状态协调优化机制,使控制器显示耦合至上一控制周期的车辆状态空间,有效避免预测时域变化造成的多步优化问题解耦效应,抑制因控制输入突变对轨迹跟踪控制任务的影响.结合两种优化方法,有效改善固定预测时域策略在高曲率轨迹跟踪中因累计误差造成的跟踪精度下降问题.最后,基于MATLAB/Simulink-CarSim联合仿真平台对算法进行了验证.经计算,高速单移线工况下,该方法在侧向偏差均值/峰值、纵向偏差均值/峰值、航向偏差均值/峰值指标中,相较于固定预测时域NMPC同比降低36.17%/15.25%、11.55%/38.58%、6.13%/25.27%;高速双移线工况下,同比降低30.28%/29.77%、25.07%/3.85%、11.02%/2.68%.此外,在高速低附着工况中,该方法仍能保证良好的控制精度及侧向稳定性,其峰值侧向偏差为0.2017 m、峰值纵向偏差为0.9744 km h^(-1)、峰值航向偏差为1.1936°、峰值质心侧偏角为1.9074°.展开更多
A learning algorithm based on a hard limiter for feedforward neural networks (NN) is presented,and is applied in solving classification problems on separable convex sets and disjoint sets.It has been proved that the a...A learning algorithm based on a hard limiter for feedforward neural networks (NN) is presented,and is applied in solving classification problems on separable convex sets and disjoint sets.It has been proved that the algorithm has stronger classification ability than that of the back propagation (BP) algorithm for the feedforward NN using sigmoid function by simulation.What is more,the models can be implemented with lower cost hardware than that of the BP NN.LEARNIN展开更多
This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that th...This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.展开更多
As it is well known,it is difficult to identify a nonlinear time varying system using traditional identification approaches,especially under unknown nonlinear function.Neural networks have recently emerged as a succes...As it is well known,it is difficult to identify a nonlinear time varying system using traditional identification approaches,especially under unknown nonlinear function.Neural networks have recently emerged as a successful tool in the area of identification and control of time invariant nonlinear systems.However,it is still difficult to apply them to complicated time varying system identification.In this paper we present a learning algorithm for identification of the nonlinear time varying system using feedforward neural networks.The main idea of this approach is that we regard the weights of the network as a state of a time varying system,then use a Kalman filter to estimate the state.Thus the network implements nonlinear and time varying mapping.We derived both the global and local learning algorithms.Simulation results demonstrate the effectiveness of this approach.展开更多
Freezing of gait is a significant and debilitating motor symptom often observed in individuals with Parkinson's disease.Resting-state functional magnetic resonance imaging,along with its multi-level feature indice...Freezing of gait is a significant and debilitating motor symptom often observed in individuals with Parkinson's disease.Resting-state functional magnetic resonance imaging,along with its multi-level feature indices,has provided a fresh perspective and valuable insight into the study of freezing of gait in Parkinson's disease.It has been revealed that Parkinson's disease is accompanied by widespread irregularities in inherent brain network activity.However,the effective integration of the multi-level indices of resting-state functional magnetic resonance imaging into clinical settings for the diagnosis of freezing of gait in Parkinson's disease remains a challenge.Although previous studies have demonstrated that radiomics can extract optimal features as biomarkers to identify or predict diseases,a knowledge gap still exists in the field of freezing of gait in Parkinson's disease.This cross-sectional study aimed to evaluate the ability of radiomics features based on multi-level indices of resting-state functional magnetic resonance imaging,along with clinical features,to distinguish between Parkinson's disease patients with and without freezing of gait.We recruited 28 patients with Parkinson's disease who had freezing of gait(15 men and 13 women,average age 63 years)and 30 patients with Parkinson's disease who had no freezing of gait(16 men and 14 women,average age 64 years).Magnetic resonance imaging scans were obtained using a 3.0T scanner to extract the mean amplitude of low-frequency fluctuations,mean regional homogeneity,and degree centrality.Neurological and clinical characteristics were also evaluated.We used the least absolute shrinkage and selection operator algorithm to extract features and established feedforward neural network models based solely on resting-state functional magnetic resonance imaging indicators.We then performed predictive analysis of three distinct groups based on resting-state functional magnetic resonance imaging indicators indicators combined with clinical features.Subsequently,we conducted 100 additional five-fold cross-validations to determine the most effective model for each classification task and evaluated the performance of the model using the area under the receiver operating characteristic curve.The results showed that when differentiating patients with Parkinson's disease who had freezing of gait from those who did not have freezing of gait,or from healthy controls,the models using only the mean regional homogeneity values achieved the highest area under the receiver operating characteristic curve values of 0.750(with an accuracy of 70.9%)and 0.759(with an accuracy of 65.3%),respectively.When classifying patients with Parkinson's disease who had freezing of gait from those who had no freezing of gait,the model using the mean amplitude of low-frequency fluctuation values combined with two clinical features achieved the highest area under the receiver operating characteristic curve of 0.847(with an accuracy of 74.3%).The most significant features for patients with Parkinson's disease who had freezing of gait were amplitude of low-frequency fluctuation alterations in the left parahippocampal gyrus and two clinical characteristics:Montreal Cognitive Assessment and Hamilton Depression Scale scores.Our findings suggest that radiomics features derived from resting-state functional magnetic resonance imaging indices and clinical information can serve as valuable indices for the identification of freezing of gait in Parkinson's disease.展开更多
文摘Addressing issues such as the disconnect between theory and practice and low student engagement in control system education,this paper uses the course“The Working Process of Open-Loop Control Systems”as a case study to explore the integration of AI technology with the“project-guided and task-driven”teaching model.By constructing a four-dimensional teaching framework of“situation-task-activity-evaluation,”AI tools are embedded in project practices such as the construction of a mechanical timed flower watering device and the optimization of a digital timed flower watering device,achieving precision,interactivity,and personalization in the teaching process.Teaching practice demonstrates that this model significantly enhances students’technical awareness,materialization capabilities,and engineering thinking,providing a reference for the teaching reform of technical courses in high school education.
基金Supported by National Natural Science Foundation of China(Grant No.52405104)Jiangxi Provincial Natural Science Foundation(Grant Nos.20242BAB20249 and 20232BAB204041)Science and Technology Project of Department of Transportation of Jiangxi Province(Grant No.2025QN003).
文摘Autonomous driving technology is constantly developing to a higher level of complex scenes,and there is a growing demand for the utilization of end-to-end data-driven control.However,the end-to-end path tracking process often encounters challenges in learning efficiency and generalization.To address this issue,this paper designs a deep deterministic policy gradient(DDPG)-based reinforcement learning strategy that integrates imitation learning and feedforward exploration in the path following process.In imitation learning,the path tracking control data generated by the model predictive control(MPC)method is used to train an end-to-end steering control model of a deep neural network.Another feedforward exploration behavior is predicted by road curvature and vehicle speed,and adds it and imitation learning to the DDPG reinforcement learning to obtain decision-making experience and action prediction behavior of the path tracking process.In the reinforcement learning process,imitation learning is used to update the pre-training parameters of the actor network,and a feedforward steering technique with random noise is adopted for strategy exploration.In the reward function,a hierarchical progressive reward form and a constrained objective reward function referring to MPC are designed,and the actor-critic network architecture is determined.Finally,the path tracking performance of the designed method is verified by comparing various training results,simulations,and HIL tests.The results show that the designed method can effectively utilize pre-training and feedforward prior experience to obtain optimal path tracking performance of an autonomous vehicle,and has better generalization ability than other methods.This study provides an efficient control scheme for improving the end-to-end control performance of autonomous vehicles.
文摘In this paper,a new study concerning the usage of artificial neural networks in the control application is given.It is shown,that the data gathered during proper operation of a given control plant can be used in the learning process to fully embrace the control pattern.Interestingly,the instances driven by neural networks have the ability to outperform the original analytically driven scenarios.Three different control schemes,namely perfect,linear-quadratic,and generalized predictive controllers were used in the theoretical study.In addition,the nonlinear recurrent neural network-based generalized predictive controller with the radial basis function-originated predictor was obtained to exemplify the main results of the paper regarding the real-world application.
基金supported by the National Natural Science Foun-dation of China(Grant No.52275099).
文摘The acquisition,tracking,and pointing(ATP)system is widely used in target tracking,counter-UAV operations,and other related fields.As UAV technology develops,there is a growing demand to enhance the tracking capabilities of ATP systems.However,in practical applications,ATP systems face various design constraints and functional limitations,making it infeasible to indefinitely improve hardware performance to meet tracking requirements.As a result,tracking algorithms are required to execute increasingly complex tasks.This study introduces a multi-rate feedforward predictive controller to address issues such as low image feedback frequency and significant delays in ATP systems,which lead to tracking jitter,poor tracking performance,low precision,and target loss.At the same time,the pro-posed approach aims to improve the tracking capabilities of ATP systems for high-speed and highly maneuverable targets under conditions of low sampling feedback rates and high feedback delays.The method suggested is also characterized by its low order,fast response,and robustness to model parameter variations.In this study,an actual ATP system is built for target tracking test,and the proposed algorithm is fully validated in terms of simulation and actual system application verification.Results from both simulations and experiments demonstrate that the method effectively compensates for delays and low sampling rates.For targets with relative angular velocities ranging from 0 to 90°/s and angular accelerations between 0 and 470°/s^(2),the system improved tracking accuracy by 70.0%-89.9%at a sampling frequency of 50 Hz and a delay of 30 m s.Moreover,the compensation algorithm demonstrated consistent performance across actuators with varying characteristics,further confirming its robustness to model insensitivity.In summary,the proposed algorithm considerably enhances the tracking accuracy and capability of ATP systems for high-speed and highly maneuverable targets,reducing the probability of target loss from high speed.This approach offers a practical solution for future multi-target tracking across diverse operational scenarios.
基金supported by the China Postdoctoral Science Foundation(No.2024M753715)Fundamental Research Funds for the Central Universities,Sun Yat-sen University(Nos.24qnpy125 and 22lglj11)Guangdong Basic and Applied Basic Research Foundation(No.2023B1515120030).
文摘The precise measurement of the antineutrino spectra produced by isotope fission in reactors is of great significance for studying neutrino oscillations,refining nuclear databases,and addressing the reactor antineutrino anomaly.In this paper,we report a method that utilizes a feedforward neural network(FNN)model to decompose the prompt energy spectrum observed in a short-baseline reactor neutrino experiment and extract the antineutrino spectra produced by the fission of major isotopes such as^(235)U,^(238)U,^(239)Pu,and^(241)Pu in the nuclear reactor.We present two training strategies for the model and compare them with the traditional X^(2) minimization method by applying them to the same set of pseudo-data corresponding to a total exposure of(2.9×5×1800)GW_(th)·tons·days.The results show that the FNN model not only converges faster and better during the fitting process but also achieves relative errors of less than 1%in the 2−8 MeV range in the extracted spectra,outperforming the X^(2) minimization method.The feasibility and superiority of this method were validated in the study.
基金supported by the Autonomous Innovation Team Foundation for“20 Items of the New University”of Jinan City(202228087)the National Natural Science Foundation of China(62073190).
文摘This paper studies global stabilization via predictor-based sampled-data output feedback for a class of feedforward nonlinear time-delay systems.Note that the traditional sampled-data observer via zero-order holder may result in the performance degradation of the observer.In this paper,an improved predictor-based observer is designed to compensate for the influence of the unmeasurable states,sampling errors and output delay.In addition,a sampled-data output-feedback controller is also constructed using the gain scaling technique.By the Lyapunov-Krasovskii functional method,the global exponential stability of the resulting closed-loop system can be guaranteed under some sufficient conditions.The simulation results are provided to demonstrate the main results.
基金Supported by National Natural Science Foundation of China(Grant No.52375502)EU H2020 MSCA R&I Programme(Grant No.101022696).
文摘Feedforward control is one of the most effective control techniques to increase the robot’s tracking accuracy.However,most of the dynamic models used in the feedforward controllers are linearly simplified such that the nonlinear and time-varying characteristics of dynamics in the workspace are ignored.In this paper,an iterative tuning method for feedforward control of parallel manipulators by taking nonlinear dynamics into account is proposed.Based on the robot rigid-body dynamic model,a feedforward controller considering the dynamic nonlinearity is presented.An iterative tuning method is given to iteratively update the feedforward controller by minimizing the root mean square(RMS)of the joint errors at each cycle.The effectiveness and extrapolation capability of the proposed method are validated through the experiments on a 2-DOF parallel manipulator.This research proposes an iterative tuning method for feedforward control of parallel manipulators considering nonlinear dynamics,which has better extrapolation capability in the whole workspace of manipulators.
基金supported in part by the National Natural Science Foundation of China under Project No.52207043。
文摘Under the condition of large inertia load,the stability of the servo system is more sensitive to the response speed and more likely to produce overshoot oscillations.In order to realize the requirements of high-precision and fast-response control of permanent magnet synchronous motor(PMSM)under large inertia load,an improved feedforward control strategy based on position impulse compensation and PD iterative algorithm is proposed to improve the response speed of the PMSM servo system and reduce the overshoot oscillation.This paper analyzes the mathematical models of the speed servo system and position servo system of the PMSM,calculates position overshoot impulse of the PMSM servo system,and improves the traditional feedforward control strategy to reversely compensate when the position is about to overshoot.Moreover,in order to further reduce the position overshoot,the PD iterative control algorithm is superimposed without increasing the complexity of the algorithm.The input signal is continuously corrected through multiple runs to achieve a smoother response control.The effectiveness of the proposed feedforward control strategy is verified by simulation and experiment.
基金supported by the“Shuimu Tsinghua Scholar”Project,China(No.2024SM223)the National Science and Technology Major Project,China(No.Y2022-V-0002-0028).
文摘Aeropropulsion System Test Facility (ASTF) is required to accurately control the pressure and temperature of the airflow to test the performance of the aero-engine. However, the control accuracy of ASTF is significantly affected by the flow disturbance caused by aero-engine acceleration and deceleration. This would reduce the credibility of ASTF’s test results for the aero-engine. Therefore, first, this paper proposes a feedforward compensation-based L1 adaptive control method for ASTF to address this problem. The baseline controller is first designed based on ideal uncoupled closed-loop dynamics to achieve dynamic decoupling. Then, L1 adaptive control is adopted to deal with various uncertainties and ensure good control performance. To further enhance the anti-disturbance performance, a feedforward strategy based on disturbance prediction is designed in the L1 adaptive control framework to compensate for the unmatched flow disturbance, which cannot be measured directly. In addition, this strategy takes into account the effects of actuator dynamics. With this method, the feedforward term can be determined from the nominal model parameters despite uncertainties. Finally, to demonstrate the effectiveness of the proposed method, various comparative experiments are performed on a hardware-in-the-loop system of ASTF. The experimental results show that the proposed method possesses excellent tracking performance, anti-disturbance performance and robustness.
基金supported by the National Natural Science Foundation of China(Grant Nos.52231014 and 52271361)the Natural Science Foundation of Guangdong Province of China(Grant No.2023A1515010684).
文摘Enhancing the accuracy of real-time ship roll prediction is crucial for maritime safety and operational efficiency.To address the challenge of accurately predicting the ship roll status with nonlinear time-varying dynamic characteristics,a real-time ship roll prediction scheme is proposed on the basis of a data preprocessing strategy and a novel stochastic trainer-based feedforward neural network.The sliding data window serves as a ship time-varying dynamic observer to enhance model prediction stability.The variational mode decomposition method extracts effective information on ship roll motion and reduces the non-stationary characteristics of the series.The energy entropy method reconstructs the mode components into high-frequency,medium-frequency,and low-frequency series to reduce model complexity.An improved black widow optimization algorithm trainer-based feedforward neural network with enhanced local optimal avoidance predicts the high-frequency component,enabling accurate tracking of abrupt signals.Additionally,the deterministic algorithm trainer-based neural network,characterized by rapid processing speed,predicts the remaining two mode components.Thus,real-time ship roll forecasting can be achieved through the reconstruction of mode component prediction results.The feasibility and effectiveness of the proposed hybrid prediction scheme for ship roll motion are demonstrated through the measured data of a full-scale ship trial.The proposed prediction scheme achieves real-time ship roll prediction with superior prediction accuracy.
基金supported in part by the Postgraduate Research&Practice Innovation Program of Nanjing University of Aeronautics and Astronautics(No.xcxjh20240326).
文摘The conventional feedforward hybrid active noise control(FFHANC)system combines the advantages of the feedforward narrowband active noise control(FFNANC)system and the feedforward broadband active noise control(FFBANC)system.To enhance its adaptive adjustment capability under frequency mismatch(FM)conditions,this paper introduces a narrowband frequency adaptive estimation module into the conventional FFHANC system.This module integrates an autoregressive(AR)model and a linear cascaded adaptive notch filter(LCANF),enabling accurate reference signal frequency estimation even under significant FM.Furthermore,in order to improve the coherence between narrowband and broadband components in the system’s error signal and its corresponding control filter for the conventional FFHANC system,this paper proposes an algorithm based on autoregressive bandpass filter bank(AR-BPFB)for error separation.Simulation results demonstrate that the proposed FFHANC system maintains robust performance under high FM conditions and effectively suppresses hybrid-band noise.The AR-BPFB algorithm significantly elevates the convergence speed of the FFHANC system.
文摘Aim Aiming at the position tracking control for valve controlled motor electrohydraulic proportional servo systems mainly driving the static load torque, the tracking performance was studied in the presence of the variable gain and deadzone. Methods On the basis of conventional composite control with the deadzone compensation method, a comprehensive control approach with the deadzone and self adjusting feedforward compensation was proposed. Results Experimental results showed that the good tracking performance was achieved for the sinusoidal and constant velocity position tracking under a wide variations of load torque. Conclusion The position tracking accuracy for valve controlled motor electrohydraulic proportional servo systems has been solved by using the comprehensive control approach with the deadzone and self adjusting feedforward compensation.
文摘在整体式车辆稳定性轨迹跟踪控制架构的基础之上,设计了一种引入预瞄曲率信息的自适应预测时域非线性模型预测控制(NMPC).基于预瞄的参考路径曲率点列指导控制维度变化,提升控制器对于路径曲率的动态响应能力;进一步地,引入状态协调优化机制,使控制器显示耦合至上一控制周期的车辆状态空间,有效避免预测时域变化造成的多步优化问题解耦效应,抑制因控制输入突变对轨迹跟踪控制任务的影响.结合两种优化方法,有效改善固定预测时域策略在高曲率轨迹跟踪中因累计误差造成的跟踪精度下降问题.最后,基于MATLAB/Simulink-CarSim联合仿真平台对算法进行了验证.经计算,高速单移线工况下,该方法在侧向偏差均值/峰值、纵向偏差均值/峰值、航向偏差均值/峰值指标中,相较于固定预测时域NMPC同比降低36.17%/15.25%、11.55%/38.58%、6.13%/25.27%;高速双移线工况下,同比降低30.28%/29.77%、25.07%/3.85%、11.02%/2.68%.此外,在高速低附着工况中,该方法仍能保证良好的控制精度及侧向稳定性,其峰值侧向偏差为0.2017 m、峰值纵向偏差为0.9744 km h^(-1)、峰值航向偏差为1.1936°、峰值质心侧偏角为1.9074°.
文摘A learning algorithm based on a hard limiter for feedforward neural networks (NN) is presented,and is applied in solving classification problems on separable convex sets and disjoint sets.It has been proved that the algorithm has stronger classification ability than that of the back propagation (BP) algorithm for the feedforward NN using sigmoid function by simulation.What is more,the models can be implemented with lower cost hardware than that of the BP NN.LEARNIN
文摘This paper studies the generalization capability of feedforward neural networks (FNN).The mechanism of FNNs for classification is investigated from the geometric and probabilistic viewpoints. It is pointed out that the outputs of the output layer in the FNNs for classification correspond to the estimates of posteriori probability of the input pattern samples with desired outputs 1 or 0. The theorem for the generalized kernel function in the radial basis function networks (RBFN) is given. For an 2-layer perceptron network (2-LPN). an idea of using extended samples to improve generalization capability is proposed. Finally. the experimental results of radar target classification are given to verify the generaliztion capability of the RBFNs.
基金National Natural Science Foundation of China!(No.6 97740 33)
文摘As it is well known,it is difficult to identify a nonlinear time varying system using traditional identification approaches,especially under unknown nonlinear function.Neural networks have recently emerged as a successful tool in the area of identification and control of time invariant nonlinear systems.However,it is still difficult to apply them to complicated time varying system identification.In this paper we present a learning algorithm for identification of the nonlinear time varying system using feedforward neural networks.The main idea of this approach is that we regard the weights of the network as a state of a time varying system,then use a Kalman filter to estimate the state.Thus the network implements nonlinear and time varying mapping.We derived both the global and local learning algorithms.Simulation results demonstrate the effectiveness of this approach.
基金supported by the National Natural Science Foundation of China,No.82071909(to GF)the Natural Science Foundation of Liaoning Province,No.2023-MS-07(to HL)。
文摘Freezing of gait is a significant and debilitating motor symptom often observed in individuals with Parkinson's disease.Resting-state functional magnetic resonance imaging,along with its multi-level feature indices,has provided a fresh perspective and valuable insight into the study of freezing of gait in Parkinson's disease.It has been revealed that Parkinson's disease is accompanied by widespread irregularities in inherent brain network activity.However,the effective integration of the multi-level indices of resting-state functional magnetic resonance imaging into clinical settings for the diagnosis of freezing of gait in Parkinson's disease remains a challenge.Although previous studies have demonstrated that radiomics can extract optimal features as biomarkers to identify or predict diseases,a knowledge gap still exists in the field of freezing of gait in Parkinson's disease.This cross-sectional study aimed to evaluate the ability of radiomics features based on multi-level indices of resting-state functional magnetic resonance imaging,along with clinical features,to distinguish between Parkinson's disease patients with and without freezing of gait.We recruited 28 patients with Parkinson's disease who had freezing of gait(15 men and 13 women,average age 63 years)and 30 patients with Parkinson's disease who had no freezing of gait(16 men and 14 women,average age 64 years).Magnetic resonance imaging scans were obtained using a 3.0T scanner to extract the mean amplitude of low-frequency fluctuations,mean regional homogeneity,and degree centrality.Neurological and clinical characteristics were also evaluated.We used the least absolute shrinkage and selection operator algorithm to extract features and established feedforward neural network models based solely on resting-state functional magnetic resonance imaging indicators.We then performed predictive analysis of three distinct groups based on resting-state functional magnetic resonance imaging indicators indicators combined with clinical features.Subsequently,we conducted 100 additional five-fold cross-validations to determine the most effective model for each classification task and evaluated the performance of the model using the area under the receiver operating characteristic curve.The results showed that when differentiating patients with Parkinson's disease who had freezing of gait from those who did not have freezing of gait,or from healthy controls,the models using only the mean regional homogeneity values achieved the highest area under the receiver operating characteristic curve values of 0.750(with an accuracy of 70.9%)and 0.759(with an accuracy of 65.3%),respectively.When classifying patients with Parkinson's disease who had freezing of gait from those who had no freezing of gait,the model using the mean amplitude of low-frequency fluctuation values combined with two clinical features achieved the highest area under the receiver operating characteristic curve of 0.847(with an accuracy of 74.3%).The most significant features for patients with Parkinson's disease who had freezing of gait were amplitude of low-frequency fluctuation alterations in the left parahippocampal gyrus and two clinical characteristics:Montreal Cognitive Assessment and Hamilton Depression Scale scores.Our findings suggest that radiomics features derived from resting-state functional magnetic resonance imaging indices and clinical information can serve as valuable indices for the identification of freezing of gait in Parkinson's disease.
