This letter introduces an innovative data-driven integral reinforcement learning (IRL) algorithm for the control of a class of underactuated mechanical systems. We propose a novel value function that allows shaping an...
详细信息
This letter introduces an innovative data-driven integral reinforcement learning (IRL) algorithm for the control of a class of underactuated mechanical systems. We propose a novel value function that allows shaping and learning the potential energy of an underactuated system and to drive it to a desired closed-loop potential energy. Consequently, we derive an actor-control policy that ensures asymptotic stability. In addition, we propose to parameterize the value function with a multi-layered perceptron (with 0, 1, and 2 hidden layers), exploring various parameter configurations. Eventually, we assess the performance of the proposed IRL through simulations and experimental results, thus confirming the practical effectiveness of the control design approach.
This paper introduces a novel statistical learning method using adaptive regulated sparsity promotion for data-driven modeling and control of solar photovoltaic (PV) generation in smart grids. Unlike traditional data-...
详细信息
ISBN:
(纸本)9798350361612;9798350361629
This paper introduces a novel statistical learning method using adaptive regulated sparsity promotion for data-driven modeling and control of solar photovoltaic (PV) generation in smart grids. Unlike traditional data-driven modeling approaches that may encounter computational challenges with an expanding pool of candidate functions, we propose an innovative algorithm called adaptive regulated sparse regression (ARSR). The proposed ARSR dynamically adjusts the hyperparameter weights of candidate functions to effectively capture the dynamics of PV systems. Leveraging this algorithm, we derive open-loop and closed-loop models of single-stage PV systems from measurements, facilitating a data-drivencontrol design for PVs in smart grid.
Model Predictive control (MPC) has been widely used in the permanent magnet synchronous motor. However, in the finite control set MPC, only one voltage vector is applied, which leads to high current harmonics and torq...
详细信息
ISBN:
(纸本)9798350321050
Model Predictive control (MPC) has been widely used in the permanent magnet synchronous motor. However, in the finite control set MPC, only one voltage vector is applied, which leads to high current harmonics and torque fluctuations. Meanwhile, three-vector MPC inevitably increases the switching frequency of inverter. In this article, a multi-vector switching control approach is established. Based on the location information of the created reference voltage vector, the relevant control technique is implemented. The proposed control method with single-vector, two-vector and three-vector composite modes of action is designed to achieve low switching frequency with excellent steady-state performance. The proposed method's effectiveness is confirmed by the experimental results.
As the title suggests, in this work, a modern machine learning method called the Q-fractionalism reasoning is introduced. The proposed method is founded upon a synergy of the Q-learning and fractional fuzzy inference ...
详细信息
As the title suggests, in this work, a modern machine learning method called the Q-fractionalism reasoning is introduced. The proposed method is founded upon a synergy of the Q-learning and fractional fuzzy inference systems (FFISs). Unlike other approaches, the Q-fractionalism reasoning not only incorporates the knowledge base to understand how to perform but also explores a reasoning mechanism from the fractional order to justify what it has performed. This method suggests that the agent choose actions aimed at the characterization of reasoning. In fact, the agent deals with states termed as primary and secondary fuzzy states. The primary fuzzy states are unobservable and uncertain, for which the agent chooses actions. However, the projection of primary fuzzy states onto the knowledge base results in secondary fuzzy states, which are observable by the agent, allowing it to detect primary fuzzy states with degrees of detectability. With a practical experiment implemented on a linear switched reluctance motor (LSRM), the results demonstrate that the application of the Q-fractionalism reasoning in the real-time position control of the LSRM leads to a remarkable improvement of about 70% in the accuracy of the control objective compared with a typical fuzzy inference system (FIS) under the same setting.
It is a significant issue to achieve the fast maneuverability and the strong robustness of hypersonic aircraft. Based on the thoughts of finite-time control and active disturbance rejection control (ADRC), this paper ...
详细信息
ISBN:
(纸本)9798350321050
It is a significant issue to achieve the fast maneuverability and the strong robustness of hypersonic aircraft. Based on the thoughts of finite-time control and active disturbance rejection control (ADRC), this paper proposes a finite-time ADRC for controlling the longitudinal dynamics of hypersonic aircraft. The proposed design consists of three parts: finite-time feedback, finite-time estimation and estimating predictive modules. To avoid discontinuously changing of control input, the presented finite-time design is in a continuous form. Moreover, to overcome the delay phenomenon of estimation in the conventional ADRC, the predictive values of total disturbance and angular velocity are calculated based on Taylor expansion. The simulations for nonlinear uncertainties validate the effectiveness of the proposed method.
This paper proposes a partially model-free optimal control strategy for a class of continuous-time systems in a datadriven way. Although a series of optimal control have achieving superior performance, the following c...
详细信息
ISBN:
(纸本)9798350321050
This paper proposes a partially model-free optimal control strategy for a class of continuous-time systems in a datadriven way. Although a series of optimal control have achieving superior performance, the following challenges still exist: (i) The controller designed based on the nominal system is difficult to cope with sudden disturbances. (ii) Feedback control is highly dependent on system dynamics and generally requires full state information. A novel composite control method combining output feedback reinforcement learning and input-output disturbance observer for these two challenges is concluded in this paper. Firstly, an output feedback policy iteration (PI) algorithm is given to acquire the feedback gain iteratively. Simultaneously, the observer continuously provides estimates of the disturbance. System dynamic information and states information are not needed to be known in advance in our approach, thus offering a higher degree of robustness and practical implementation prospects. Finally, an example is given to show the effectiveness of the proposed controller.
This paper presents a novel distributed data-drivencontrol scheme for the longitudinal formation control of a connected heterogeneous vehicle (CHV) platoon. Initially, an event-triggered mechanism is devised to allev...
详细信息
A large number of electric vehicles (EVs), distributed solar and/or wind turbine generators (WTGs) connected to distribution systems lead to frequent and sharp voltages fluctuations. The action rates of conventional a...
详细信息
A large number of electric vehicles (EVs), distributed solar and/or wind turbine generators (WTGs) connected to distribution systems lead to frequent and sharp voltages fluctuations. The action rates of conventional adjustable devices and smart inverters are very different. In this context, a novel dual-timescale voltage control scheme is proposed by organically combining data-driven with physics-based optimization. On fast timescale, a quadratic programming (QP) for balanced and unbalanced distribution systems is developed based on branch flow equations. The optimal reactive power of renewable distributed generators (DGs) and static VAR compensators (SVCs) is configured on several minutes or seconds. Whereas, on slow timescale, a data-driven Markovian decision process (MDP) is developed, in which the charge/discharge power of energy storage systems (ESSs), statuses/ratios of switchable capacitors reactors (SCRs), and voltage regulators (VRs) are configured hourly to minimize long-term discounted squared voltages magnitudes deviations using an adapted deep deterministic policy gradient (DDPG) deep reinforcement learning (DRL) algorithm. The capabilities of the proposed method are validated with ieee 33-bus balanced and 123-bus unbalanced distribution systems.
This paper proposes an adaptive sliding mode controller (ASMC) for trajectory tracking of high-speed trains (HST) with uncertainties. The ASMC incorporates a radial basis function neural network (RBFNN) to approximate...
详细信息
ISBN:
(纸本)9798350321050
This paper proposes an adaptive sliding mode controller (ASMC) for trajectory tracking of high-speed trains (HST) with uncertainties. The ASMC incorporates a radial basis function neural network (RBFNN) to approximate the model uncertainties and uses a sigmoid function to reduce chattering. The Lyapunov function is employed to prove the stability of the controller. Numerical simulations using the data of China Railway High-Speed (CRH) 380 train demonstrate the effectiveness of the controller in ensuring the train follows the tracking target under different prior knowledge conditions.
This paper studies the distributed model free adaptive iterative learningcontrol (MFAILC) of multiple high-speed trains (MHSTs) under malicious denial-of-service (DoS) attacks. By using the equivalent linearization t...
详细信息
ISBN:
(纸本)9798350321050
This paper studies the distributed model free adaptive iterative learningcontrol (MFAILC) of multiple high-speed trains (MHSTs) under malicious denial-of-service (DoS) attacks. By using the equivalent linearization technique, the discrete-time dynamic model of MHSTs is firstly converted into a linear data-based one. Then, the strategy of DoS attacker is introduced, which is represented by a Bernoulli variable with unknown mathematical expectation. Next, the distributed MFAILC scheme is conducted, which belongs to the scope of data-driven approach. Finally, the stability of MHSTs is studied and the validity of the MFAILC is confirmed by a numerical test.
暂无评论