检索结果-南通市图书馆

A TWO-PCSN-STFF Algorithm for Steel Industry Yard Vehicle Action Recognition

第35届中国过程控制会议

作者： Yuelin yang chunjie yang Siwei Lou Xiongzhuo Zhu Weibin Wang College of Control Science and Engineering Zhejiang University

Blast furnace iron-making process is an essential component in the iron and steel industry. However, establishing an efficient process monitoring model remains a significant challenge due to dynamic and nonlinear qualities, coupled with substantial noise and outliers. This paper presents a flow-based deep variational canonical variate analysis(FDVCVA) method as a solution to overcome the aforementioned challenges. First, FDVCVA model is designed by incorporating the variational auto-encoder(VAE), flow-based model, and canonical variate analysis(CVA). Further, the statistic is founded on the results of FDVCVA and control limit is calculated using the kernel density estimation(KDE) technique. Finally, the utilization of practical blast furnace data serves to verify the efficiency of the proposed method.

关键词： Blast furnace iron-making process canonical variate analysis flow-based model process monitoring

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

A TWO-PCSN-STFF Algorithm for Steel Industry Yard Vehicle Ac...

A blast furnace fault monitoring algorithm with low false alarm rate:Ensemble of greedy dynamic principal component analysis-Gaussian mixture model

第35届中国过程控制会议

作者： Hang Xiao chunjie yang Xujie Zhang Zhe Liu Duojin Yan Yuchen Zhao College of Control Science and Engineering Zhejiang University

At present, iron and steel enterprises usually rely on manual observation to monitor the dust generated by largescale vehicle activities in the material store yard. However, this method is labor-intensive and cannot provide uninterrupted24-hour monitoring. Therefore, there is an urgent need for an intelligent monitoring system to identify the actions of vehicles on industrial sites, enabling uninterrupted unmanned monitoring and alert systems for dust in the yard. This paper proposes a novel two-stream vehicle action recognition model, incorporating a pruning-channel-separated convolution(PCSN) mechanism and a spatiotemporal feature fusion module(STFF), to process real-time video streams from steel yards. The proposed model consists of two specifically designed paths: the environment path, which extracts spatial features, and the action path, which extracts temporal features. The STFF is then employed to integrate the temporal characteristics of the action path into the environment path, thereby facilitating efficient fusion of spatiotemporal features. Additionally, the PCSN mechanism is designed to optimize the original Resnet 3D module during convolution operations. Ultimately, while maintaining the method's accuracy,the proposed approach is well-suited for deployment and real-time monitoring, providing valuable information for the subsequent dust suppression treatment.

关键词： Vehicle Action Recognition Spatiotemporal Feature Fusion Model Lightweight Attention Mechanism

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

Chinese Journal of Chemical Engineering 2023年第5期57卷 151-161页

作者： Xiongzhuo Zhu Dali Gao Chong yang chunjie yang State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China

The large blast furnace is essential equipment in the process of iron and steel manufacturing. Due to the complex operation process and frequent fluctuations of variables, conventional monitoring methods often bring false alarms. To address the above problem, an ensemble of greedy dynamic principal component analysis-Gaussian mixture model(EGDPCA-GMM) is proposed in this paper. First, PCA-GMM is introduced to deal with the collinearity and the non-Gaussian distribution of blast furnace ***, in order to explain the dynamics of data, the greedy algorithm is used to determine the extended variables and their corresponding time lags, so as to avoid introducing unnecessary noise. Then the bagging ensemble is adopted to cooperate with greedy extension to eliminate the randomness brought by the greedy algorithm and further reduce the false alarm rate(FAR) of monitoring results. Finally, the algorithm is applied to the blast furnace of a large iron and steel group in South China to verify *** with the basic algorithms, the proposed method achieves lowest FAR, while keeping missed alarm rate(MAR) remain stable.

关键词： Chemical processes Principal component analysis Gaussian mixture model Process monitoring Ensemble Process control

Coordination Control for a Class of Multi-Agent Systems Under Asynchronous Switching

在线全文

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2019年第4期32卷 1019-1038页

作者： ZHAO Xiaodan LIU Wenhui yang chunjie College of Automation Hangzhou Dianzi UniversityHangzhou 310027China Big Date Decision Institute Jinan UniversityGuangzhou 510632China College of Control Science and Engineering Zhejiang UniversityHangzhou 310027China

This paper studies the coordination control of nonlinear multi-agent systems under asynchronous switching,including consensus,tracking control,and *** asynchronous switching considered here means that the switching of the controller lags behind the mode’s switching for each *** the matched controller is interrupted by the delayed *** the situation,the authors give some new results by applying the conventional distributed control *** authors show that all agents can achieve ***,the authors show that all followers can track the actual ***,the authors show that all followers will converge to the convex hull spanned by the dynamic leaders as time goes *** simulations are also provided and the results show highly consistent with the theoretical results.

关键词： Asynchronous switching consensus containment coordination control switched systems tracking control

Minimax entropy-based co-training for fault diagnosis of blast furnace

在线全文

学校读者我要写书评

暂无评论

中国化学工程学报:英文版 2023年第7期59卷 231-239页

作者： Dali Gao chunjie yang Bo yang Yu Chen Ruilong Deng The State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang UniversityHangzhou 310027China Jianwei Digital Sphere Co. LtdLianyungang 222113China Jiangsu Binxin Iron and Steel Group Co. LtdChongqing 401220China

Due to the problems of few fault samples and large data fluctuations in the blast furnace(BF)ironmaking process,some transfer learning-based fault diagnosis methods are *** vast majority of such methods perform distribution adaptation by reducing the distance between data distributions and applying a classifier to generate pseudo-labels for ***,since the training data is dominated by labeled source domain data,such classifiers tend to be weak classifiers in the target *** addition,the features generated after domain adaptation are likely to be at the decision boundary,resulting in a loss of classification ***,we propose a novel method called minimax entropy-based co-training(MMEC)that adversarially optimizes a transferable fault diagnosis model for the *** structure of MMEC includes a dual-view feature extractor,followed by two classifiers that compute the feature's cosine similarity to representative vector of each *** transfer is achieved by alternately increasing and decreasing the entropy of unlabeled target samples with the classifier and the feature extractor,*** BF fault diagnosis experiments show that our method improves accuracy by about 5%over state-of-the-art methods.

关键词： Co-training Fault diagnosis Blast furnace Minimax entropy Transfer learning

Intelligent Ironmaking Optimization Service on a Cloud Computing Platform by Digital Twin

在线全文

学校读者我要写书评

暂无评论

Engineering 2021年第9期7卷 1274-1281页

作者： Heng Zhou chunjie yang Youxian Sun The State Key Laboratory of Industrial Control Technology&College of Control Science and Engineering Zhejiang UniversityHangzhou 310027China

The shortage of computation methods and storage devices has largely limited the development of multiobjective optimization in industrial *** improve the operational levels of the process industries,we propose a multi-objective optimization framework based on cloud services and a cloud distribution ***-time data from manufacturing procedures are first temporarily stored in a local database,and then transferred to the relational database in the ***,a distribution system with elastic compute power is set up for the optimization ***,a multi-objective optimization model based on deep learning and an evolutionary algorithm is proposed to optimize several conflicting goals of the blast furnace ironmaking *** the application of this optimization service in a cloud factory,iron production was found to increase by 83.91 t∙d^(-1),the coke ratio decreased 13.50 kg∙t^(-1),and the silicon content decreased by an average of 0.047%.

关键词： Cloud factory Blast furnace Multi-objective optimization Distributed computation

Observer-Based Event-Triggered Tracking Control of Leader-Follower Systems with Time Delay

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2016年第4期29卷 865-880页

作者： LIU Wenhui yang chunjie SUN Youxian QIN Jiaxiang College of Control Science and Engineering Zhejiang University

This paper studies the tracking control of general linear multi-agent systems with out time delays. The observer-based event-triggered control schemes will be considered or with- For the conventional distributed tracking protocol, the authors will not update the relative state in continuous time, i.e., the relative state will be updated by some events which happened in discrete time. A completely decentralized event-trigger will be designed for leader-follower systems. It is shown that all followers can track the leader asymptotically by the proposed protocol, if the feedback gain matrices are designed appropriately. Numerical simulations are also provided and the results show highly consistent with the theoretical results.

关键词： Consensus distributed control event-triggered control multi-agent systems time delay tracking control.

Dust Distribution Study at the Blast Furnace Top Based on k-Sε-u_(p)Model

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2021年第1期8卷 121-135页

作者： Zhipeng Chen Zhaohui Jiang chunjie yang Weihua Gui Youxian Sun the School of Automation Central South UniversityChangsha 410083China the School of Control Science and Engineering Zhejiang UniversityHangzhou 310027China

The dust distribution law acting at the top of a blast fumace(BF)is of great significance for understanding gas flow distribution and mitigating the negative influence of dust particles on the accuracy and service life of detection *** harsh environment inside a BF makes it difficult to describe the dust *** paper adresses this problem by proposing a dust distribution k-Sε-u_(p)model based on interphase(gas-powder)*** proposed model is coupled with a k-Sεmodel(which describes gas flow movement)and a u_(p)model(which depicts dust movement).First,the kinetic energy equation and turbulent dissipation rate equation in the k-Sεmodel are established based on the modeling theory and single Green-function two scale direct interaction approximation(SGF-TSDIA)***,a dust particle mnovement u_(p)model is built based on a force analysis of the dust and Newton's laws of ***,a coupling factor that descibes the interphase interaction is proposed,and the k-Sε-u_(p)model,with clear physical *** mathematical logic,and adequate generality,is *** results and o-site verification show that the k-Sε-u_(p)model not only has high precision,but also reveals the aggregate distribution features of the dust,which are helpful in optimizing the installation position of the detection equipment and imnproving its accuracy and service life.

关键词： Blast furnace(BF) dust movement interphase interaction modeling theory turbulent flow two-scale direct interaction approximation(TSDIA)

Stochastic process-based degradation modeling and RUL prediction: from Brownian motion to fractional Brownian motion

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2021年第7期64卷 5-24页

作者： Hanwen ZHANG Maoyin CHEN Jun SHANG chunjie yang Youxian SUN School of Automation and Electrical Engineering University of Science and Technology Beijing State Key Laboratory of Industrial Control Technology College of Control Science and EngineeringZhejiang University Department of Automation Tsinghua University School of Automation and Electrical Engineering Linyi University Department of Electrical and Computer Engineering University of Alberta

Brownian motion(BM) has been widely used for degradation modeling and remaining useful life(RUL) prediction, but it is essentially Markovian. This implies that the future state in a BM-based degradation process relies only on its current state, independent of the past states. However, some practical industrial devices such as Li-ion batteries, ball bearings, turbofans, and blast furnace walls show degradations with long-range dependence(LRD), where the future degradation states depend on both the current and past degradation states. This type of degradation naturally brings two interesting problems, that is, how to model the degradations and how to predict their RULs. Recently, in contrast to the work that uses only BM, fractional Brownian motion(FBM) is introduced to model practical degradations. The most important feature of the FBM-based degradation models is the ability to characterize the non-Markovian degradations with LRD. Although FBM is an extension of BM, it is neither a Markovian process nor a semimartingale. Therefore, how to obtain the first passage time of an FBM-based degradation process has become a challenging task. In this paper, a review of the transition of RUL prediction from BM to FBM is provided. The peculiarities of FBM when addressing the LRD inherent in some practical degradations are discussed. We first review the BM-based degradation models of the past few decades and then give details regarding the evolution of FBM-based research. Interestingly, the existing BM-based models scarcely consider the effect of LRD on the prediction of RULs. Two practical cases illustrate that the newly developed FBMbased models are more generalized and suitable for predicting RULs than the BM-based models, especially for degradations with LRD. Along with the direction of FBM-based RUL prediction, we also introduce some important and interesting problems that require further study.

关键词： remaining useful life degradation model Brownian motion fractional Brownian motion long-range dependence