检索结果-内蒙古大学图书馆

Recurrent Stochastic Configuration Networks with Incremental Blocks

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dang, Gang Wang, Dianhui State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Research Center for Stochastic Configuration Machines China University of Mining and Technology Xuzhou221116 China

Recurrent stochastic configuration networks (RSCNs) have shown promise in modelling nonlinear dynamic systems with order uncertainty due to their advantages of easy implementation, less human intervention, and strong approximation capability. This paper develops the original RSCNs with block increments, termed block RSCNs (BRSCNs), to further enhance the learning capacity and efficiency of the network. BRSCNs can simultaneously add multiple reservoir nodes (subreservoirs) during the construction. Each subreservoir is configured with a unique structure in the light of a supervisory mechanism, ensuring the universal approximation property. The reservoir feedback matrix is appropriately scaled to guarantee the echo state property of the network. Furthermore, the output weights are updated online using a projection algorithm, and the persistent excitation conditions that facilitate parameter convergence are also established. Numerical results over a time series prediction, a nonlinear system identification task, and two industrial data predictive analyses demonstrate that the proposed BRSCN performs favourably in terms of modelling efficiency, learning, and generalization performance, highlighting their significant potential for coping with complex dynamics. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

Self-Organizing Recurrent Stochastic Configuration Networks for Nonstationary Data Modelling

学校读者我要写书评

暂无评论

arXiv 2024年

Recurrent stochastic configuration networks (RSCNs) are a class of randomized learner models that have shown promise in modelling nonlinear dynamics. In many fields, however, the data generated by industry systems often exhibits nonstationary characteristics, leading to the built model performing well on the training data but struggling with the newly arriving data. This paper aims at developing a self-organizing version of RSCNs, termed as SORSCNs, to enhance the continuous learning ability of the network for modelling nonstationary data. SORSCNs can autonomously adjust the network parameters and reservoir structure according to the data streams acquired in real-time. The output weights are updated online using the projection algorithm, while the network structure is dynamically adjusted in the light of the recurrent stochastic configuration algorithm and an improved sensitivity analysis. Comprehensive comparisons among the echo state network (ESN), online self-learning stochastic configuration network (OSL-SCN), self-organizing modular ESN (SOMESN), RSCN, and SORSCN are carried out. Experimental results clearly demonstrate that the proposed SORSCNs outperform other models with sound generalization, indicating great potential in modelling nonlinear systems with nonstationary dynamics. Copyright © 2024, The Authors. All rights reserved.

关键词： Sensitivity analysis

Deep Recurrent Stochastic Configuration Networks for Modelling Nonlinear Dynamic Systems

学校读者我要写书评

暂无评论

arXiv 2024年

Deep learning techniques have shown promise in many domain applications. This paper proposes a novel deep reservoir computing framework, termed deep recurrent stochastic configuration network (DeepRSCN) for modelling nonlinear dynamic systems. DeepRSCNs are incrementally constructed, with all reservoir nodes directly linked to the final output. The random parameters are assigned in the light of a supervisory mechanism, ensuring the universal approximation property of the built model. The output weights are updated online using the projection algorithm to handle the unknown dynamics. Given a set of training samples, DeepRSCNs can quickly generate learning representations, which consist of random basis functions with cascaded input and readout weights. Experimental results over a time series prediction, a nonlinear system identification problem, and two industrial data predictive analyses demonstrate that the proposed DeepRSCN outperforms the single-layer network in terms of modelling efficiency, learning capability, and generalization performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

Recurrent Stochastic Configuration Networks with Hybrid Regularization for Nonlinear Dynamics Modelling

学校读者我要写书评

暂无评论

arXiv 2024年

Recurrent stochastic configuration networks (RSCNs) have shown great potential in modelling nonlinear dynamic systems with uncertainties. This paper presents an RSCN with hybrid regularization to enhance both the learning capacity and generalization performance of the network. Given a set of temporal data, the well-known least absolute shrinkage and selection operator (LASSO) is employed to identify the significant order variables. Subsequently, an improved RSCN with L2 regularization is introduced to approximate the residuals between the output of the target plant and the LASSO model. The output weights are updated in real-time through a projection algorithm, facilitating a rapid response to dynamic changes within the system. A theoretical analysis of the universal approximation property is provided, contributing to the understanding of the network’s effectiveness in representing various complex nonlinear functions. Experimental results from a nonlinear system identification problem and two industrial predictive tasks demonstrate that the proposed method outperforms other models across all testing datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

Fuzzy Recurrent Stochastic Configuration Networks for Industrial Data Analytics

学校读者我要写书评

暂无评论

arXiv 2024年

This paper presents a novel neuro-fuzzy model, termed fuzzy recurrent stochastic configuration networks (F-RSCNs), for industrial data analytics. Unlike the original recurrent stochastic configuration network (RSCN), the proposed F-RSCN is constructed by multiple sub-reservoirs, and each sub-reservoir is associated with a Takagi–Sugeno–Kang (TSK) fuzzy rule. Through this hybrid framework, first, the interpretability of the model is enhanced by incorporating fuzzy reasoning to embed the prior knowledge into the network. Then, the parameters of the neuro-fuzzy model are determined by the recurrent stochastic configuration (RSC) algorithm. This scheme not only ensures the universal approximation property and fast learning speed of the built model but also overcomes uncertain problems, such as unknown dynamic orders, arbitrary structure determination, and the sensitivity of learning parameters in modelling nonlinear dynamics. Finally, an online update of the output weights is performed using the projection algorithm, and the convergence analysis of the learning parameters is given. By integrating TSK fuzzy inference systems into RSCNs, F-RSCNs have strong fuzzy inference capability and can achieve sound performance for both learning and generalization. Comprehensive experiments show that the proposed F-RSCNs outperform other classical neuro-fuzzy and non-fuzzy models, demonstrating great potential for modelling complex industrial systems. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

Collaboration Energy Efficiency with Mobile Edge Computing for Target Tracking in IoT 7th

学校读者我要写书评

暂无评论

Collaboration Energy Efficiency with Mobile Edge Computing f...

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Zou, Guobin Yu, Gang Zhang, Jian Tang, Jian Zhou, Junwu College of Information Science and Engineering Northeastern University Shenyang110819 China State Key Laboratory of Process Automation in Mining and Metallurgy Beijing102600 China School of Computer and Software Nanjing University of Information Science and Technology Nanjing210044 China Faculty of Information Technology Beijing University of Technology Beijing100024 China Beijing Key Laboratory of Process Automation in Mining and Metallurgy Beijing102600 China BGRIMM Technology Group Co. Ltd. Beijing102600 China

ISBN: (纸本)9783030786205

In this paper, the target tracking problem is investigated with mobile edge computing (MEC) mechanism in internet of things (IoT), where the challenge of energy efficiency is a significant issue when the target tracking event is driven. In order to prolong the lifetime of IoT, we adopt dynamic clustering methods to improve energy efficiency while guaranteeing target tracking effects. We deign the sensor selection scheme for carrying out the tracking tasks according to energy distribution of the sensor node. Concretely, by considering the reality of random deployment and introducing the definition of node density for IoT, we develop a Pareto optimality for sensor nodes selection in terms of energy efficiency without reducing the accuracy of target tracking. Furthermore, we recruit voluntary mobile devices as mobile edge computing servers to offload the data from selected sensor nodes in the cluster and process them to the estimate the target state. Simulations demonstrate the efficiency for tracking performance on energy balance in terms of efficiently prolonging the IoT lifetime. © 2021, Springer Nature Switzerland AG.

关键词： Target tracking

Collaboration Energy Efficiency with Mobile Edge Computing for Data Collection in IoT 7th

学校读者我要写书评

暂无评论

Collaboration Energy Efficiency with Mobile Edge Computing f...

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Zou, Guobin Zhang, Jian Tang, Jian Zhou, Junwu College of Information Science and Engineering Northeastern University Shenyang110819 China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing102600 China School of Computer and Software Nanjing University of Information Science & Technology Nanjing210044 China Faculty of Information Technology Beijing University of Technology Beijing100024 China Beijing Key Laboratory of Process Automation in Mining & Metallurgy Beijing102600 China BGRIMM Technology Group Co. Ltd. Beijing102600 China

ISBN: (纸本)9783030786144

In this paper, we investigated collaboration energy efficiency with mobile edge computing (MEC) mechanism in internet of things (IoT), which is a challenge issue. In order to prolong the lifetime of IoT, we adopt dynamic clustering methods to improve energy efficiency while guaranteeing energy balance. We deign the sensor selection scheme for collecting data according to Pareto optimality. Concretely, by considering the reality of random deployment and introducing the definition of node density for IoT, we develop a Pareto optimality for sensor nodes selection in terms of energy efficiency. Furthermore, we recruit voluntary mobile devices as mobile edge computing servers to offload the data from selected sensor nodes in the cluster and process them to the estimate the data state. Simulations demonstrate the efficiency for the performance on energy balance in terms of efficiently prolonging the IoT lifetime. © 2021, Springer Nature Switzerland AG.

关键词： Internet of things

Grade Monitoring using Semantic Features of Flotation Froth Image

学校读者我要写书评

暂无评论

Grade Monitoring using Semantic Features of Flotation Froth ...

Chinese Control and Decision Conference, CCDC

作者： Xu Wang Jingmin Lian Daoxi Liu Yutian Lei School of Information Science and Engineering Northeastern University Shenyang China BGRIMM Technology Group Beijing China State Key Laboratory of Process Automation in Mining & Metallurgy Beijing China

ISBN: (纸本)9781665478977

In the industrial flotation circuits, grades are the key performance indicators for flotation condition recognition and operations. Modeling based on machine vision is an effective tool for grade monitoring, and froth image feature extraction as a model input plays a crucial role. Given the low efficiency of hand-crafted features and the poor interpretability of high-dimensional features extracted by convolutional neural networks, a grade monitoring method with human-understandable semantic features as input is proposed in this paper. First, based on the combination of generative adversarial networks and encoder, we design a new network structure that maps the froth images data space to the latent semantic space. Then the semantic features of froth images can be automatically extracted by decomposing the constructed matrix with rich latent semantics. Finally, as demonstrated in the industrial experiment, the extracted semantic features can not only be visually interpreted but also can be effectively used in grade monitoring.

关键词： Machine vision Semantics key performance indicator process control Predictive models Feature extraction Generative adversarial networks

Adaptive Dynamic Programming and Decentralized Optimal Output Regulation of Two-Time-Scale Interconnected Systems

学校读者我要写书评

暂无评论

Adaptive Dynamic Programming and Decentralized Optimal Outpu...

International Conference on Control, automation and Information Sciences (ICCAIS)

作者： Jianguo Zhao Chunyu Yang Linna Zhou Weinan Gao School of Information and Control Engineering China University of Mining and Technology Xuzhou China State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang China

In this paper, we address the decentralized optimal output regulation problem for two-time-scale (TTS) interconnected systems with unknown slow dynamics through adaptive dynamic programming (ADP). Firstly, singular perturbation theory is leveraged to decompose the TTS interconnected system into a slow subsystem and several interconnected fast time-scale subsystems. Secondly, we develop a decentralized optimal control scheme for the fast time-scale subsystems with interconnections. Also, we devise an off-policy ADP algorithm to learn the optimal control strategy for the slow time-scale subsystem with unknown dynamics. Moreover, we combine the slow and fast control strategies to design the composite decentralized optimal output regulator. Both optimality and stability of the closed-loop system are rigorously analyzed. Finally, simulation results are provided to validate the effectiveness of the proposed methodology.

关键词：