Since the cumbersome collection process and high cost, the collected degradation of the product is basically small samples, which will affect the accuracy of reliability evaluation. It is necessary to expand the degra...
详细信息
ISBN:
(纸本)9798350321050
Since the cumbersome collection process and high cost, the collected degradation of the product is basically small samples, which will affect the accuracy of reliability evaluation. It is necessary to expand the degradation to improve the accuracy of later reliability assessment. Therefore, a degradation generation and prediction method is proposed combining the time series generator adversarial network (TimeGAN) and stochastic process. Firstly, the input degradation is expanded by the sliding window to improve the later training accuracy;Then, the construction of the generator in TimeGAN is linked with the stochastic process to make the generation data more realistic. Finally, the results of degradation prediction by the Gated Recurrent Unit (GRU) can be obtained. Two datasets and different generation methods are adopted to evaluate the effectiveness of the proposed method. The results shows that the Kullback-Leibler(KL) divergence is the smallest, and the prediction error is the smallest compared with the other methods. So, the proposed method is proved that it is valid in the degradation generation and prediction, and can be used for the further reliability assessment of the product in the industrial system.
This paper addresses the joint state estimation and online control problems of unknown linear time-invariant systems subject to process and measurement noises. The proposal is to design a finite-horizon linear quadrat...
详细信息
ISBN:
(纸本)9798350354416;9798350354409
This paper addresses the joint state estimation and online control problems of unknown linear time-invariant systems subject to process and measurement noises. The proposal is to design a finite-horizon linear quadratic Gaussian (LQG) controller from noisy data. To achieve this, relaxed data-based semi-definite programs (SDPs) are constructed, upon solving which, a robust finite-horizon linear quadratic regulator (LQR) and a robust Kalman filter are developed, and consequently, a robust data-driven finite-horizon LQG controller is designed. It is shown that the proposed data-driven finite-horizon LQG controller ensures robust global exponential stability (RGES) of the observer and the input-to-state stability (ISS) of the closed-loop system under standard conditions. Finally, a numerical example is provided to demonstrate its effectiveness.
Medium-voltage direct-current (MVDC) shipboard microgrids (SMGs) are the state-of-the-art architecture for onboard power distribution in navy. These systems are considered to be highly dynamic due to high penetration ...
详细信息
ISBN:
(纸本)9798350366235;9798350366242
Medium-voltage direct-current (MVDC) shipboard microgrids (SMGs) are the state-of-the-art architecture for onboard power distribution in navy. These systems are considered to be highly dynamic due to high penetration of power electronic converters and volatile load patterns such as pulsed-power load (PPL) and propulsion motors demand variation. Obtaining the dynamic model of an MVDC SMG is a challenging task due to the confidentiality of system components models and uncertainty in the dynamic models through time. In this paper, a dynamic identification framework based on a temporal convolutional neural network (TCN) is developed to learn the system dynamics from measurement data. Different kinds of testing scenarios are implemented, and the testing results show that this approach achieves an exceptional performance and high generalization ability, thus holding substantial promise for development of advanced data-drivencontrol strategies and stability prediction of the system.
The operation conditions of the satellite are always complex and variable, making it difficult to automatically and effectively capture the useful state features from a large volume of data. The paper designs a sensor...
详细信息
In this article, we develop data-driven optimal synchronization control architectures for leader-follower multiagent systems with additive disturbances and unknown system matrices. To minimize output synchronization e...
详细信息
In this article, we develop data-driven optimal synchronization control architectures for leader-follower multiagent systems with additive disturbances and unknown system matrices. To minimize output synchronization error, algebraic Riccati equations (AREs) are derived, and unique feedback gains are determined by policy iteration. On that basis, two data-driven optimal synchronization control algorithms are developed without relying on the dynamics of the system, which guarantee output synchronization while minimizing synchronization errors and rejecting disturbances. The first algorithm uses the output synchronization error data to perform online data-drivenlearning (DDL), while the second algorithm uses the input data to perform DDL, where both data sample requirements are transformed into rank conditions. We have presented rigorous theoretical analyses of our proposed algorithms, which demonstrate that if an initial control protocol can make the system achieve output synchronization under mild conditions, our proposed two algorithms can take advantage of the data from reaching synchronization to optimize the closed-loop performance. Finally, a numerical example is provided to emphasize the effectiveness of our methods.
Subspace predictive control (SPC) is a widely utilized data-drivencontrol technique in various industrial applications. However, its static nature restricts its ability to effectively track nonlinear dynamic systems,...
详细信息
Subspace predictive control (SPC) is a widely utilized data-drivencontrol technique in various industrial applications. However, its static nature restricts its ability to effectively track nonlinear dynamic systems, resulting in diminished performance. To address this problem, an adaptive subspace predictive control approach is proposed, incorporating an adaptive mechanism to continuously update the subspace predictor. The designed adaptive mechanism mitigates the negative impact of historical data by sliding the data window. It simultaneously employs the addition and deletion of data vectors in the data matrix through recursive matrix transformation, simplifying computational complexity while maintaining accuracy. In addition, the developed subspace predictor enables online learning and effectively handles the dynamic nature of industrial processes, requiring little prior knowledge. The theoretical analysis of the proposed control approach includes recursive feasibility and stability, along with a discussion on determining relevant parameters. The effectiveness of the proposed control approach is demonstrated through its application to a continuous stirred tank heater benchmark. The results exhibit significant improvements in tracking control performance, leading to enhanced efficiency and cost reduction. Overall, this research presents a promising solution for addressing the challenges of predictive control in industrial processes.
This paper investigates the learning-based control of robotic systemsdriven by string-type artificial muscles. Due to the highly nonlinear dynamics of the actuators and the complicated mechanical structure, it is typ...
ISBN:
(纸本)9798350382662;9798350382655
This paper investigates the learning-based control of robotic systemsdriven by string-type artificial muscles. Due to the highly nonlinear dynamics of the actuators and the complicated mechanical structure, it is typically very challenging to design traditional model-based controllers that exhibit desired control performances. With the rapid development of machine learning techniques, deep reinforcement learning (DRL) algorithms have been utilized to control a variety of complex robotic systems. However, these DRL algorithms usually require a huge amount of training data and iterations to converge, which is generally unacceptable for the robotic systems of interest. Therefore, this paper designs an efficient learning-based control algorithm, aiming to improve the training efficiency for robotic systemsdriven by string-type artificial muscle actuators. Specially, two training improvements are proposed including imitation learning and data augmentation. This paper applies the proposed learning methods to three popular DRL algorithms and tests the control performances in three case studies using three string-type artificial muscle-driven robots, including a parallel robotic wrist, a two degrees-of-freedom (DOF) robotic eye and a robotic finger. Simulation results show that the proposed learning-based control methods significantly accelerate the convergence speed and improve the data efficiency in all the three case studies.
control of linear dynamics with multiplicative noise naturally introduces robustness against dynamical uncertainty. Moreover, many physical systems are subject to multiplicative disturbances. In this work, we show how...
详细信息
control of linear dynamics with multiplicative noise naturally introduces robustness against dynamical uncertainty. Moreover, many physical systems are subject to multiplicative disturbances. In this work, we show how these dynamics can be identified from state trajectories. The least-squares scheme enables the exploitation of prior information and comes with practical data-driven confidence bounds and sample complexity guarantees. We complement this scheme with an associated control synthesis procedure for linear quadratic regulator (LQR) that robustifies against distributional uncertainty, guarantees stability with high probability, and converges to the true optimum at a rate inversely proportional to the sample count. Throughout, we exploit the underlying multilinear problem structure through tensor algebra and completely positive operators. The scheme is validated through numerical experiments.
We present a learning Model Predictive controller (LMPC) for systems with multi-modal dynamics performing iterative control tasks. Our goal is to use historical data from previous task iterations to design a data-driv...
详细信息
To achieve more stable and rapid control of ship motion, we proposed the Compensation Function Observer (CFO)-based control algorithm and used the Particle Swarm Optimization (PSO) to adjust its parameters. The perfor...
详细信息
暂无评论