The digital baseband predistorter is an effective technique to compensate for the nonlinearity of power amplifiers （PAs） with memory effects. However, most available adaptive predistorters based on direct learning a...The digital baseband predistorter is an effective technique to compensate for the nonlinearity of power amplifiers （PAs） with memory effects. However, most available adaptive predistorters based on direct learning architectures suffer from slow convergence speeds. In this paper, the recursive prediction error method is used to construct an adaptive Hammerstein predistorter based on the direct learning architecture, which is used to linearize the Wiener PA model. The effectiveness of the scheme is demonstrated on a digital video broadcasting-terrestrial system. Simulation results show that the predistorter outperforms previous predistorters based on direct learning architectures in terms of convergence speed and linearization. A similar algorithm can be applied to estimate the Wiener PA model, which will achieve high model accuracy.展开更多
The pneumatic artificial muscles are widely used in the fields of medicalrobots, etc. Neural networks are applied to modeling and controlling of artificial muscle system. Asingle-joint artificial muscle test system is...The pneumatic artificial muscles are widely used in the fields of medicalrobots, etc. Neural networks are applied to modeling and controlling of artificial muscle system. Asingle-joint artificial muscle test system is designed. The recursive prediction error (RPE)algorithm which yields faster convergence than back propagation (BP) algorithm is applied to trainthe neural networks. The realization of RPE algorithm is given. The difference of modeling ofartificial muscles using neural networks with different input nodes and different hidden layer nodesis discussed. On this basis the nonlinear control scheme using neural networks for artificialmuscle system has been introduced. The experimental results show that the nonlinear control schemeyields faster response and higher control accuracy than the traditional linear control scheme.展开更多
Reinforcement learning(RL)has emerged as a promising approach for building energy management(BEM).However,most existing research focuses on model-free reinforcement learning(MFRL)approaches,which can encounter the lea...Reinforcement learning(RL)has emerged as a promising approach for building energy management(BEM).However,most existing research focuses on model-free reinforcement learning(MFRL)approaches,which can encounter the learning challenge for heating,ventilation and air conditioning(HVAC)control due to extensive trial-and-error explorations and lengthy training times.To address this challenge,we propose a model-based reinforcement learning(MBRL)framework that incorporates a virtual environment to augment the agent’s exploration.By leveraging the branched rollout strategy to generate short rollout predictions branched from the experience trajectory,the MBRL method mitigates compounding errors introduced by the time-series prediction model,enabling robust and efficient policy updates.Evaluated in an EnergyPlus testbed with real-world data verification,the proposed method demonstrates significant advantages:(1)RL-based controllers outperform the rule-based control(RBC)baseline after one training episode,(2)MBRL reduces training time by over 50%compared to MFRL while maintaining comparable control performance,and(3)an equal mix of real and synthetic data for MBRL training achieves an optimal trade-off between efficiency and control outcomes.This study contributes an efficient model-based training method for RL development in HVAC control,offering insights into advanced control strategies for BEM applications.展开更多
The output feedback model predictive control(MPC),for a linear parameter varying(LPV) process system including unmeasurable model parameters and disturbance(all lying in known polytopes),is considered.Some previously ...The output feedback model predictive control(MPC),for a linear parameter varying(LPV) process system including unmeasurable model parameters and disturbance(all lying in known polytopes),is considered.Some previously developed tools,including the norm-bounding technique for relaxing the disturbance-related constraint handling,the dynamic output feedback law,the notion of quadratic boundedness for specifying the closed-loop stability,and the ellipsoidal state estimation error bound for guaranteeing the recursive feasibility,are merged in the control design.Some previous approaches are shown to be the special cases.An example of continuous stirred tank reactor(CSTR) is given to show the effectiveness of the proposed approaches.展开更多
文摘The digital baseband predistorter is an effective technique to compensate for the nonlinearity of power amplifiers （PAs） with memory effects. However, most available adaptive predistorters based on direct learning architectures suffer from slow convergence speeds. In this paper, the recursive prediction error method is used to construct an adaptive Hammerstein predistorter based on the direct learning architecture, which is used to linearize the Wiener PA model. The effectiveness of the scheme is demonstrated on a digital video broadcasting-terrestrial system. Simulation results show that the predistorter outperforms previous predistorters based on direct learning architectures in terms of convergence speed and linearization. A similar algorithm can be applied to estimate the Wiener PA model, which will achieve high model accuracy.
基金This project is supported by Foundation of Public Laboratory on Robotics of Chinese Academy of Sciences.
文摘The pneumatic artificial muscles are widely used in the fields of medicalrobots, etc. Neural networks are applied to modeling and controlling of artificial muscle system. Asingle-joint artificial muscle test system is designed. The recursive prediction error (RPE)algorithm which yields faster convergence than back propagation (BP) algorithm is applied to trainthe neural networks. The realization of RPE algorithm is given. The difference of modeling ofartificial muscles using neural networks with different input nodes and different hidden layer nodesis discussed. On this basis the nonlinear control scheme using neural networks for artificialmuscle system has been introduced. The experimental results show that the nonlinear control schemeyields faster response and higher control accuracy than the traditional linear control scheme.
基金supported by the China Scholarship Council(No.202306090264)granted to Kaichen Qu for his study at Politecnico di Milano.
文摘Reinforcement learning(RL)has emerged as a promising approach for building energy management(BEM).However,most existing research focuses on model-free reinforcement learning(MFRL)approaches,which can encounter the learning challenge for heating,ventilation and air conditioning(HVAC)control due to extensive trial-and-error explorations and lengthy training times.To address this challenge,we propose a model-based reinforcement learning(MBRL)framework that incorporates a virtual environment to augment the agent’s exploration.By leveraging the branched rollout strategy to generate short rollout predictions branched from the experience trajectory,the MBRL method mitigates compounding errors introduced by the time-series prediction model,enabling robust and efficient policy updates.Evaluated in an EnergyPlus testbed with real-world data verification,the proposed method demonstrates significant advantages:(1)RL-based controllers outperform the rule-based control(RBC)baseline after one training episode,(2)MBRL reduces training time by over 50%compared to MFRL while maintaining comparable control performance,and(3)an equal mix of real and synthetic data for MBRL training achieves an optimal trade-off between efficiency and control outcomes.This study contributes an efficient model-based training method for RL development in HVAC control,offering insights into advanced control strategies for BEM applications.
基金Supported by the National High Technology Research and Development Program of China(2014AA041802)the National Natural Science Foundation of China(61573269)
文摘The output feedback model predictive control(MPC),for a linear parameter varying(LPV) process system including unmeasurable model parameters and disturbance(all lying in known polytopes),is considered.Some previously developed tools,including the norm-bounding technique for relaxing the disturbance-related constraint handling,the dynamic output feedback law,the notion of quadratic boundedness for specifying the closed-loop stability,and the ellipsoidal state estimation error bound for guaranteeing the recursive feasibility,are merged in the control design.Some previous approaches are shown to be the special cases.An example of continuous stirred tank reactor(CSTR) is given to show the effectiveness of the proposed approaches.
