In the (bio)chemical processes, traditional hardware sensors are difficult to directly measure the quality of critical products due to their time-varying, non-linear, and dynamic characteristics. This makes process so...
详细信息
ISBN:
(纸本)9781665402460
In the (bio)chemical processes, traditional hardware sensors are difficult to directly measure the quality of critical products due to their time-varying, non-linear, and dynamic characteristics. This makes process soft sensor modeling methods important. Since the process variables can be regarded as natural graph data, this work introduces graphs in the soft sensor modeling area. A soft sensor model based on the graph neural network (GNN) is proposed. The model can learn the topological structure of graph data between each unit variable. Moreover, it characterizes variable relationships from the spatial and temporal dimensions to the output prediction by introducing the spatial-temporal convolutional layer. The effectiveness and advantages of the GNN-based soft sensor model are verified using a simulated fermentation process.
Development of reliable soft sensors using limited labeled samples is not an easy task in industrial processes. A selective generative adversarial network (SGAN)-based support vector regression (SGAN-SVR) soft sensor ...
详细信息
ISBN:
(纸本)9781665402460
Development of reliable soft sensors using limited labeled samples is not an easy task in industrial processes. A selective generative adversarial network (SGAN)-based support vector regression (SGAN-SVR) soft sensor is proposed for quality prediction using limited labeled training data. Specifically, SVR is considered as a base prediction model. The Wasserstein GAN (WGAN) is adopted to capture the distribution of available labeled data and generate virtual candidates. Subsequently, using a proposed similarity measurement strategy, those synthetic data with more information are selected and introduced into the training set. Using the designed data augmentation approach, the SGAN-SVR model can achieve better prediction performance compared with the SVR soft sensor. The quality prediction results on an industrial polyethylene process demonstrate the effectiveness and advantages of the proposed method.
Electroluminescence imaging is a crucial diagnostic tool for assessing the quality and performance of photovoltaic (PV) modules. However, current research often focuses on defect detection in PV modules, neglecting th...
详细信息
Electroluminescence imaging is a crucial diagnostic tool for assessing the quality and performance of photovoltaic (PV) modules. However, current research often focuses on defect detection in PV modules, neglecting the need for detailed segmentation at the individual cell level. To address the limitations of existing methods in recognizing complex defects and suppressing background noise, this paper proposes a novel semantic segmentation algorithm (CAAK-Net), capable of identifying anomalies at the cell level of photovoltaic panels. To enhance network performance, CAAK-Net uses K-Net as a baseline and incorporates the Convolutional Block Attention Module (CBAM), Attention Refinement Module (ARM), and Atrous Spatial Pyramid Pooling (ASPP) modules. Experimental results comparing CAAK-Net with mainstream segmentation networks demonstrate its superior segmentation performance, particularly in recognizing defect edges and small-area attached defects. Additionally, we establish a quantitative correlation model between detection errors and PV system efficiency losses, pioneering the translation of pixel-level segmentation accuracy into measurable operational costs, thereby providing an economic assessment framework for industrial PV inspection. Furthermore, the network exhibits a certain degree of robustness in noisy environments, showcasing its segmentation advantages in diverse defect scenarios.
This paper investigates the problem of H ∞ asynchronous control for discrete-time semi-Markov jump systems. In practice, it is difficult to ensure that controller modes and system modes are updated synchronously. The...
详细信息
This paper investigates the problem of H ∞ asynchronous control for discrete-time semi-Markov jump systems. In practice, it is difficult to ensure that controller modes and system modes are updated synchronously. Therefore, a hidden semi-Markov model is introduced to characterize such an asynchronous phenomenon between system modes and controller modes. Meanwhile, the switching signal of the controller is generated by a given conditional probability related to the system mode. Based on the mode-dependent and elapsed-time-dependent Lyapunov function, together with the semi-Markov kernel (SMK) method, sufficient conditions constructed by linear matrix inequalities (LMIs) are derived to ensure the existence of an asynchronous controller such that the resulting system is σ-error mean square stable and satisfies an H ∞ performance index. Finally, a numerical example is given to illustrate the effectiveness and feasibility of the method proposed.
This article discusses the adaptive identifier–critic–actor neural optimal control for stochastic nonstrict-feedback nonlinear systems with elastic state constraints. Reinforcement learning is used to achieve optima...
This article discusses the adaptive identifier–critic–actor neural optimal control for stochastic nonstrict-feedback nonlinear systems with elastic state constraints. Reinforcement learning is used to achieve optimal control, which is designed based on the identifier–critic–actor structure of neural network approximation. In this framework, the identifier, critic and actor are used to estimate unknown dynamics, evaluate system performance and execute control actions, respectively. This control scheme designs the actual control from all virtual controls and dynamic surface controls as the optimal solution to the corresponding subsystems. The update law is derived through the negative gradient of a simple positive function, which is generated by the partial derivative of the Hamilton–Jacobi-Bellman (HJB) equation. At the same time, this design can also alleviate the requirement for continuous excitation conditions in current optimal control methods. A key innovation lies in formulating an elastic constraint function with flexible capabilities, thus providing a unified framework capable of flexibly addressing custom time constraints without changing the control structure. Stability analysis shows that all signals are semi-globally uniformly ultimately bounded in probability.
In this paper, a method of distributionally robust fault detection (FD) is proposed for stochastic linear discrete-time systems by using the kernel density estimation (KDE) technique. For this purpose, an H 2 optimiza...
详细信息
In this paper, a method of distributionally robust fault detection (FD) is proposed for stochastic linear discrete-time systems by using the kernel density estimation (KDE) technique. For this purpose, an H 2 optimization-based fault detection filter is constructed for residual generation. Towards maximizing the fault detection rate (FDR) for a prescribed false alarm rate (FAR), the residual evaluation issue regarding the design of residual evaluation function and threshold is formulated as a distributionally robust optimization problem, wherein the so-called confidence sets are constituted to model the ambiguity of distribution knowledge of residuals in fault-free and faulty cases. A KDE based solution, robust to the estimation errors in probability distribution of residual caused by the finite number of samples, is further developed to address the targeting problem such that the residual evaluation function, threshold as well as the lower bound of FDR can be achieved simultaneously. A case study on a vehicle lateral control system demonstrates the applicability of the proposed FD method.
Since the earliest conceptualizations by Lee and Markus, and Propoi in the 1960s, Model Predictive control (MPC) has become a major success story of systems and control with respect to industrial impact and with respe...
详细信息
This paper considers distributed nonconvex optimization with the cost functions being distributed over agents. Noting that information compression is a key tool to reduce the heavy communication load for distributed a...
详细信息
This article investigates the distributed control problem for nonlinear multiagent systems (MASs) with unknown system models. A novel distributed model-free adaptive learning algorithm is developed to learn a controll...
详细信息
This article investigates the distributed control problem for nonlinear multiagent systems (MASs) with unknown system models. A novel distributed model-free adaptive learning algorithm is developed to learn a controller from the online system data. Notably, a significant advancement over conventional methods is that the proposed algorithm requires only local interaction data from neighboring agents, eliminating dependencies on both a priori system structural knowledge and global topology information. Comprehensive simulations validate the theoretical results and demonstrate the superior efficacy of the devised algorithm.
Dexterous manipulation, which refers to the ability of a robotic hand or multi-fingered end-effector to skillfully control, reorient, and manipulate objects through precise, coordinated finger movements and adaptive f...
详细信息
暂无评论