检索结果-内蒙古大学图书馆

Anomaly-Resistant Decentralized State Estimation Under Minimum Error Entropy With Fiducial Points for Wide-Area Power Systems

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 74-87页

作者： Bogang Qu Zidong Wang Bo Shen Hongli Dong Hongjian Liu the College of Automation Engineering Shanghai University of Electric PowerShanghai 200090China IEEE the Department of Computer Science Brunel University LondonUxbridgeMiddiesex UB83PHUK the College of Information Science and Technology Donghua UniversityShanghai 200051 the Engineering Research Center of Digitalized Textile and Fashion Technology Ministry of EducationShanghai 201620China the Artificial Intelligence Energy Research Institute Northeast Petroleum UniversityDaqing 163318 the Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Northeast PetroleumDaqing 163318 the Sanya Offshore Oil&Gas Research Institute Northeast Petroleum UniversitySanya 572024China the Key Laboratory of Advanced Perception and Intelligent Control of High-End Equipment Ministry of EducationAnhui Polytechnic UniversityWuhu 2410000 the School of Mathematics and Physics Anhui Polytechnic UniversityWuhu 241000China

This paper investigates the anomaly-resistant decentralized state estimation(SE) problem for a class of wide-area power systems which are divided into several non-overlapping areas connected through transmission lines. Two classes of measurements(i.e., local measurements and edge measurements) are obtained, respectively, from the individual area and the transmission lines. A decentralized state estimator, whose performance is resistant against measurement with anomalies, is designed based on the minimum error entropy with fiducial points(MEEF) criterion. Specifically, 1) An augmented model, which incorporates the local prediction and local measurement, is developed by resorting to the unscented transformation approach and the statistical linearization approach;2) Using the augmented model, an MEEF-based cost function is designed that reflects the local prediction errors of the state and the measurement;and 3) The local estimate is first obtained by minimizing the MEEF-based cost function through a fixed-point iteration and then updated by using the edge measuring information. Finally, simulation experiments with three scenarios are carried out on the IEEE 14-bus system to illustrate the validity of the proposed anomaly-resistant decentralized SE scheme.

关键词： Decentralized state estimation(SE) measurements with anomalies minimum error entropy unscented Kalman filter wide-area power systems

Modeling Task Relationships in Multi-variate Soft Sensor with Balanced Mixture-of-Experts

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Huang, Yuxin Wang, Hao Liu, Zhaoran Pan, Licheng Li, Haozhe Liu, Xinggao The State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China

Accurate estimation of multiple quality variables is critical for building industrial soft sensor models, which have long been confronted with data efficiency and negative transfer issues. Methods sharing backbone parameters among tasks address the data efficiency issue;however, they still fail to mitigate the negative transfer problem. To address this issue, a balanced Mixture-of-Experts (BMoE) is proposed in this work, which consists of a multi-gate mixture of experts (MMoE) module and a task gradient balancing (TGB) module. The MoE module aims to portray task relationships, while the TGB module balances the gradients among tasks dynamically. Both of them cooperate to mitigate the negative transfer problem. Experiments on the typical sulfur recovery unit demonstrate that BMoE models task relationship and balances the training process effectively, and achieves better performance than baseline models significantly. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

A critical look at deep neural network for dynamic system modeling

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhou, Jinming Zhu, Yucai State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China

Neural network models become increasingly popular as dynamic modeling tools in the control community. They have many appealing features including nonlinear structures, being able to approximate any functions. While most researchers hold optimistic attitudes towards such models, this paper questions the capability of (deep) neural networks for the modeling of dynamic systems using input-output data. For the identification of linear time-invariant (LTI) dynamic systems, two representative neural network models, Long Short-Term Memory (LSTM) and Cascade Foward Neural Network (CFNN) are compared to the standard Prediction Error Method (PEM) of system identification. In the comparison, four essential aspects of system identification are considered, then several possible defects and neglected issues of neural network based modeling are pointed out. Detailed simulation studies are performed to verify these defects: for the LTI system, both LSTM and CFNN fail to deliver consistent models even in noise-free cases;and they give worse results than PEM in noisy cases. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep neural networks

IG2: Integrated Gradient on Iterative Gradient Path for Feature Attribution

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2023年

作者： Zhuo, Yue Ge, Zhiqiang The State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China

Feature attribution explains Artificial Intelligence (AI) at the instance level by providing importance scores of input features’ contributions to model prediction. Integrated Gradients (IG) is the prevalent path attribution method for deep neural networks, involving the integration of gradients along a path from the explained input (explicand) to a counterfactual instance (baseline). Nonetheless, current IG variants exclusively consider the gradient of explicand’s output, but we have discovered that the gradient of the counterfactual output also exerts a substantial influence on feature attribution. To achieve this, we propose Iterative Gradient path Integrated Gradients (IG2), considering both two gradients. IG2 incorporates the counterfactual gradient iteratively into the integration path, consequently obtaining a novel path (GradPath) and a novel baseline (GradCF). These two novel IG components effectively address the issues of attribution noise and arbitrary baseline choice in earlier IG methods. IG2, as a path method, stratifies many desirable axioms, which are theoretically justified in the paper. Experimental results on XAI benchmark, ImageNet, MNIST, TREC questions answering, wafer-map failure patterns, and CelebA face attributes validate that IG2 delivers superior feature attributions compared to the state-of-the-art techniques. © 2023, CC BY.

关键词： Deep neural networks

Dyna-DepthFormer: Multi-frame Transformer for Self-Supervised Depth Estimation in Dynamic Scenes

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Songchun Zhao, Chunhui State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China

— Self-supervised methods have showed promising results on depth estimation task. However, previous methods estimate the target depth map and camera ego-motion simultaneously, underusing multi-frame correlation information and ignoring the motion of dynamic objects. In this paper, we propose a novel Dyna-Depthformer framework, which predicts scene depth and 3D motion field jointly and aggregates multi-frame information with transformer. Our contributions are twofold. First, we leverage multi-view correlation through a series of self- and cross-attention layers in order to obtain enhanced depth feature representation. Specifically, we use the perspective transformation to acquire the initial reference point, and use deformable attention to reduce the computational cost. Second, we propose a warping-based Motion Network to estimate the motion field of dynamic objects without using semantic prior. To improve the motion field predictions, we propose an iterative optimization strategy, together with a sparsity-regularized loss. The entire pipeline achieves end-to-end self-supervised training by constructing a minimum reprojection loss. Extensive experiments on the KITTI and Cityscapes benchmarks demonstrate the effectiveness of our method and show that our method outperforms state-of-the-art algorithms. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

Directed Acyclic Graphs With Tears

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Zhichao Ge, Zhiqiang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China

Bayesian network is a frequently-used method for fault detection and diagnosis in industrial processes. The basis of Bayesian network is structure learning which learns a directed acyclic graph from data. Since the search space in structure learning will scale super-exponentially with the increase of process variables, data-driven structure learning is a challenging problem. As a novel method for structure learning, DAGs with No Tears methods are being well studied in recent years due to their compatibility with deep learning framework. However, the DAGs with No Tears methods is far from application in industrial scenario due to problems in the gradient descent based solving stage and the post-processing stage. In this work, those problems are theoretically analyzed in detail by mathematical derivations. To solve these problems, the DAGs with Tears method is proposed by using mix-integer linear programming under the deep learning framework. In addition, prior knowledge is able to incorporate into the new proposed method, making structure learning more practical and useful in industrial processes. Finally, a numerical example and an industrial simulation example are adopted as case studies to demonstrate the superiority of the developed method. © 2023, CC BY.

关键词： Bayesian networks

TMoE-P: Towards the Pareto Optimum for Multivariate Soft Sensors

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Pan, Licheng Wang, Hao Chen, Zhichao Huang, Yuxing Liu, Xinggao The State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou310027 China

Multi-variate soft sensor seeks accurate estimation of multiple quality variables using measurable process variables, which have emerged as a key factor in improving the quality of industrial manufacturing. The current progress stays in some direct applications of multitask network architectures;however, there are two fundamental issues remain yet to be investigated with these approaches: (1) negative transfer, where sharing representations despite the difference of discriminate representations for different objectives degrades performance;(2) seesaw phenomenon, where the optimizer focuses on one dominant yet simple objective at the expense of others. In this study, we reformulate the multi-variate soft sensor to a multi-objective problem, to address both issues and advance state-of-the-art performance. To handle the negative transfer issue, we first propose an Objective-aware Mixture-of-Experts (OMoE) module, utilizing objective-specific and objective-shared experts for parameter sharing while maintaining the distinction between objectives. To address the seesaw phenomenon, we then propose a Pareto Objective Routing (POR) module, adjusting the weights of learning objectives dynamically to achieve the Pareto optimum, with solid theoretical supports. We further present a Task-aware Mixture-of-Experts framework for achieving the Pareto optimum (TMoE-P) in multi-variate soft sensor, which consists of a stacked OMoE module and a POR module. We illustrate the efficacy of TMoE-P with an open soft sensor benchmark, where TMoE-P effectively alleviates the negative transfer and seesaw issues and outperforms the baseline models. © 2023, CC BY.

关键词： Multiobjective optimization

Research on Optimization Method of Injection Molding Machine Temperature control System Based on IK-SS

学校读者我要写书评

暂无评论

Research on Optimization Method of Injection Molding Machine...

Chinese Automation Congress (CAC)

作者： Haipeng Zou Quanxiang Ye Xiaoyu Li Xiangsong Kong Dan Zhao Zhijiang Shao School of Electrical Engineering and Automation Xiamen University of Technology Xiamen China State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China Zhangzhou Hongxingtai Electronics Co. Ltd China College of Control Science and Engineering and State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

Injection molding, as a plastic processing technology, is widely used in the mass production of plastic products with high precision and automation. However, the performance optimization process of this system currently faces some prominent issues, such as time consumption, reliance on experience, and difficulty in achieving optimality. Traditional optimization methods typically rely on manual experience and rules, which are inefficient and time-consuming. To enhance the performance of the control system, this paper focuses on utilizing an improved simplex search method based on the data-driven optimization concept to optimize the parameters of the temperature control system of the injection molding machine. The method introduced in this paper is termed the Knowledge-Informed Simplex Search Method Based on Adjacent Historical Centroid Points Information (IK-SS). The IK-SS algorithm is a variant of the simplex search method that utilizes information from the centroids of neighboring simplices to evaluate the current state of the optimization process and dynamically adjust the iteration step size. This approach aims to improve optimization efficiency while reducing computational complexity and time costs. Simulation and experimental validation demonstrate that the IK-SS algorithm significantly enhances the temperature control performance of the injection molding machine (IMM). This demonstrates the potential of the IK-SS algorithm as a tool for optimizing the temperature control system of injection molding machines.

关键词： Systematics Automation Search methods Heuristic algorithms System performance Optimization methods Injection molding Temperature control Plastics Tuning

Generalized-Extended-State-Observer and Equivalent-Input-Disturbance Methods for Active Disturbance Rejection: Deep Observation and Comparison

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2023年第4期10卷 957-968页

作者： Jinhua She Kou Miyamoto Qing-Long Han Min Wu Hiroshi Hashimoto Qing-Guo Wang School of Engineering Tokyo University of TechnologyHachiojiTokyo 192-0982Japan K.Miyamoto is with the Institute of Technology Shimizu CorporationKotoTokyo 135-0044Japan School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia School of Automation China University of GeosciencesWuhan 430074 Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of EducationWuhan 430074China School of Industrial Technology Advanced Institute of Industrial TechnologyTokyo 140-0011Japan Institute of Artificial Intelligence and Future Networks Beijing Normal UniversityZhuhai 519087 Guangdong Key Lab of AI and Multi-Modal Data Processing Guangdong Provincial Key Laboratory of Interdisciplinary Research and Application for Data Science BNUHKBU United International College Zhuhai 519087China

Active disturbance-rejection methods are effective in estimating and rejecting disturbances in both transient and steady-state *** paper presents a deep observation on and a comparison between two of those methods:the generalized extended-state observer(GESO)and the equivalent input disturbance(EID)from assumptions,system configurations,stability conditions,system design,disturbance-rejection performance,and extensibility.A time-domain index is introduced to assess the disturbance-rejection performance.A detailed observation of disturbance-suppression mechanisms reveals the superiority of the EID approach over the GESO method.A comparison between these two methods shows that assumptions on disturbances are more practical and the adjustment of disturbance-rejection performance is easier for the EID approach than for the GESO method.

关键词： Active disturbance-rejection control(ADRC) disturbance observer(DOB) equivalent input disturbance(EID) extendedstate observer(ESO) generalized extended-state observer(GESO)