A5077747730- Fault Detection and Control Systems
- Electronic Packaging and Soldering Technologies
- Mineral Processing and Grinding
- 3D IC and TSV technologies
- Intermetallics and Advanced Alloy Properties
- Aluminum Alloy Microstructure Properties
- Machine Fault Diagnosis Techniques
- Advanced Welding Techniques Analysis
- Spectroscopy and Chemometric Analyses
- Aluminum Alloys Composites Properties
- Metal and Thin Film Mechanics
- Advanced Control Systems Optimization
- Advanced materials and composites
- Advanced Data Processing Techniques
- Advanced Statistical Process Monitoring
- Metallurgy and Material Forming
- Advanced Algorithms and Applications
- Advanced machining processes and optimization
- Advanced Sensor and Control Systems
- Machine Learning and ELM
- Industrial Technology and Control Systems
- Engineering Diagnostics and Reliability
- Gear and Bearing Dynamics Analysis
- Risk and Safety Analysis
- Neural Networks and Applications
Beijing University of Chemical Technology
2013-2025
Shanghai Sixth People's Hospital
2025
Shanghai Jiao Tong University
2025
Henan University of Technology
2024
Beijing Information Science & Technology University
2024
Shenyang Ligong University
2024
Huainan Mining Industry Group (China)
2023
Anhui University of Science and Technology
2023
Shenyang University of Technology
2023
Changchun Normal University
2021
Multivariate statistical process monitoring has been widely used in industry. However, traditional algorithms often ignore the dynamic characteristics of actual industry process. This study proposes a novel algorithm called multistep slow feature analysis (MS-DSFA), which completed full-condition system and divided structures more precisely. achieves an optimal detection rate according to multiple control limits. To enrich experiments, we select numerical example, Tennessee Eastman process,...
In this article, a novel fault detection and process monitoring method referred to as artificial neural correlation analysis (ANCA) is proposed. Because nonlinear characteristics are common in complex industrial processes, the classic canonical (CCA) always perform poorly. Many scholars have noticed problem of also proposed some improved schemes, such kernel method. However, selection suitable parameters extremely difficult, so most learning methods slightly unsatisfactory. Considering that...
Fault detection has long been a hot research issue for industry. Many common algorithms such as principal component analysis, recursive transformed statistical analysis and moments-based robust can deal with static processes only, whereas most industrial are dynamic. Therefore, dynamic have proposed to by expanding the dimensions. The computational complexity of these greatly increased, cannot divide data space accurately. In this paper, we propose novel algorithm called innovational...
With the increasing complexity of industrial systems, modeling and intelligent diagnosis high-dimensional data have become increasingly challenging. To address this issue, study proposes an optimal sparse principal component analysis (OSPCA) method with a varying regularization coefficient. The lower bound coefficient for achieving feature selection is given, theoretical proof provided. Subsequently, iterative optimization algorithm proposed model optimization. OSPCA are applied to...
The prognostic and health management (PHM) of rolling bearings has been a popular research area. Since bearing fault is inevitable during degradation, how to improve the PHM performance based on both degradation states types still an open problem. In this study, two multilabel learning algorithms are proposed for bearings, named personalized binary relevance (PBR) hierarchical K-nearest neighbor (HML-KNN), respectively. Degradation used as labels data so that each sample corresponding label...
Data-driven process monitoring is an effective approach to assure safe operation of modern manufacturing and energy systems, such as thermal power plants being studied in this work. Industrial processes are inherently dynamic need be monitored using algorithms. Mainstream algorithms rely on concatenating current measurement with past data. This work proposes a new, alternative algorithm, dot product feature analysis (DPFA). DPFA computes the consecutive samples, thus naturally capturing...
Multiview subspace clustering (MSC) maximizes the utilization of complementary description information provided by multiview data and achieves impressive performance. However, most them are inefficient or even invalid among large-scale scenarios due to expensive computational complexity. Recently, anchor strategy has been developed address this, which selects a few representative samples as points for representation learning graph construction. only explore single cross-view correlation,...
In modern industrial production, rotating machinery plays an important role. The gears in this adjust the speed and transmission of torque. Therefore, when gear fails, it is very to be able diagnose fault quickly accurately. Gear vibration signals are often used diagnosis, but signal overwhelmed by noises. To enable scientific efficient detection faults, study proposes a diagnosis method based on variational modal decomposition (VMD) wide+narrow visual field neural networks (WNVNNs), namely...
Accurate process monitoring plays a crucial role in thermal power plants since it constitutes large-scale industrial equipment and its production safety is of great significance. Therefore, accurate very important for plants. The vigorous nature the requires dynamic algorithms monitoring. Since common algorithm mainly based on data expansion, online computing complexity too high because redundancy. Accordingly, this article proposes an innovative, called autocorrelation feature analysis...
Significant progress has been made in the current fault diagnosis algorithms. However, they do not consider computational resources and require expensive equipment to complete training of models. To immediately model obtain higher accuracy rates using cheaper equipment, reduce cost industry, build a bridge for industrial with neural networks, this paper proposes convolutional network-based architecture that uses small number high accuracy. Simultaneously, loss function is proposed can...
Load fluctuations, unexpected disturbances, and switching of operating states typically make actual industrial processes exhibit nonstationary. In nonstationary processes, the statistical characteristics data will change. It is hard to distinguish process faults changes in hence leads false alarms. Cointegration analysis (CA) specializes solving difficulties caused by time-varying means variances finding long-term equilibrium relationships among multiple variables. However, components...