Article
Computer Science, Information Systems
Chengyuan Sun, Yizhen Yin, Haobo Kang, Hongjun Ma
Summary: This paper proposes a novel distributed kernel principal component regression (DKPCR) approach to address quality-related process monitoring in modern industrial processes. The approach reduces data scale and tackles robustness issues caused by large outliers, and involves Bayesian inference and weight diagnosis methods for data processing and fault variable isolation.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Bhabani Sankar Gouda, Meenakshi Panda, Trilochan Panigrahi, Sudhakar Das, Bhargav Appasani, Omprakash Acharya, Hossam M. Zawbaa, Salah Kamel
Summary: Sensor nodes deployed in hostile environments for military and commercial applications need fault diagnosis to inform other nodes of their status. However, diagnosing faults becomes difficult when nodes behave inconsistently. To address this, a one shot likelihood ratio test is proposed to determine the fault status of a sensor node by comparing statistics of received data with a threshold value. Simulation results show that this method provides better detection accuracy with lower false alarm rates compared to existing tests. The proposed method achieves a 100% detection accuracy, 0% false alarm rate, and 0% false positive rate for data from faulty nodes with a probability exceeding 25%.
Article
Engineering, Aerospace
Yujiang Zhong, Youmin Zhang, Shuzhi Sam Ge, Xiao He
Summary: This article investigates the fault detection and diagnosis problem in multiagent systems with sensor faults and disturbances. A distributed proportional integral derivative formation control protocol is constructed for practical formation. A distributed FDD scheme, consisting of a fault detection module, a fault isolation module, and a fault estimation module, is designed within the formation control. The effectiveness of the proposed FDD scheme is demonstrated through simulation results.
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS
(2023)
Article
Computer Science, Theory & Methods
Limei Lin, Yanze Huang, Yuhang Lin, Sun-Yuan Hsieh, Li Xu
Summary: In this paper, a novel indicator called m-FFNLFD is proposed to describe the diagnosability of a multiprocessor system at a local node, and its properties and applications are studied under different network models.
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS
(2022)
Article
Engineering, Chemical
Hongquan Ji
Summary: This study proposes a new data-driven process monitoring method for sensor fault detection and diagnosis in modern industrial processes. The SMD method is introduced for incipient fault detection, along with a discussion on parameter selection. Additionally, a hierarchical strategy for fault diagnosis is presented, demonstrating the effectiveness and merits of the method.
CHEMICAL ENGINEERING SCIENCE
(2021)
Article
Automation & Control Systems
Long Gao, Donghui Li, Lele Yao, Yanan Gao
Summary: This study proposes an innovative chiller sensor drift fault diagnosis method using deep recurrent canonical correlation analysis and KNN classifier. By developing a deep recurrent canonical correlation analysis model and designing a residual generator for feature extraction and classification of operation data, effective fault detection and diagnosis are achieved.
Article
Green & Sustainable Science & Technology
Saud Altaf, Shafiq Ahmad, Mazen Zaindin, Shamsul Huda, Sofia Iqbal, Muhammad Waseem Soomro
Summary: Induction motors in industrial powerline networks typically receive voltage supply from a shared power bus. The dynamic behavior of a single motor generates a signal that can travel across the powerline efficiently. A mathematical model is used to measure and determine the routing of different signals in the power network based on attenuation and the relationship between sensor signals and known fault patterns. A laboratory setup with Xbee devices and microcontrollers was developed to verify the propagation of faulty signals and identify the type of fault in induction motors.
Article
Chemistry, Analytical
Xue Li, Zhikang Fan, Shengfeng Wang, Aibing Qiu, Jingfeng Mao
Summary: This paper investigates a design framework for a class of distributed interconnected systems, where fault diagnosis and cooperative fault-tolerant control schemes are included. It proposes the use of fault detection observers and fault isolation observers to detect and locate faults in the subsystems. The paper also introduces a cooperative fault-tolerant control unit for system stability. The proposed design framework is demonstrated through simulation of an intelligent unmanned vehicle platooning scenario.
Article
Thermodynamics
Zahra Soltani, Kresten Kjaer Sorensen, John Leth, Jan Dimon Bendtsen
Summary: This study tested different machine learning classifiers to find the best solution for diagnosing twenty faults possibly encountered in industrial refrigeration systems. The results showed that the fault detection reliability of the algorithms highly depends on how well the training data covers the operation regime, and a well-trained SVM can classify twenty types of fault with 95% accuracy.
INTERNATIONAL JOURNAL OF REFRIGERATION
(2022)
Article
Automation & Control Systems
Adam Glowacz
Summary: In this paper, the author proposes a fault diagnosis technique for thermal images analysis of commutator motors (CMs) and single-phase induction motors (SIMs). Original feature extraction methods, including DAMOM, DAM20HP, DAMMH, and IB, were used, and the feature vectors were classified using the Nearest Neighbor classifier and Long short-term memory (LSTM). The proposed analysis was successful, achieving high recognition efficiency for both CMs and SIMs. The study presents an innovative perspective on the development of thermal imaging diagnostics and provides valuable insights into thermographic diagnostics of electrical motors.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Automation & Control Systems
Chao Cheng, Qiang Wang, Yury Nikitin, Chun Liu, Yang Zhou, Hongtian Chen
Summary: This article aims to develop a data-driven design of distributed fault detection for dynamic systems using the measurement in a complex sensor network, utilizing the subspace technique and the average consensus algorithm. The design process includes distributed off-line learning and distributed online fault detection, and the former involves the average consensus algorithm and parameter identification by subspace technique. The proposed distributed approach achieves the same performance as the centralized fault detection approach and avoids complex information exchange, as demonstrated by numerical simulation and case studies.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2023)
Article
Automation & Control Systems
Zhennan Li, Linlin Li, Steven X. Ding
Summary: This paper explores data-driven distributed fault diagnosis for large-scale systems using sensor networks. It introduces a distributed fault detection scheme based on correlation analysis to enhance fault detection performance by reducing the impact of noise-induced uncertainty. The method focuses on implementing the correlation of coupled nodes to minimize the covariance of the residual signal in a distributed manner. Additionally, a fault localization approach is developed to identify faults by measuring and comparing the degree of abnormality.
IET CONTROL THEORY AND APPLICATIONS
(2023)
Article
Automation & Control Systems
Jiarui Zhang, Steven X. Ding, Deyu Zhang, Linlin Li
Summary: This paper develops a distributed fault detection approach for large-scale interconnected systems using sensor networks. The one-step prediction based on measured data is implemented in a distributed fashion, allowing each node to receive corresponding estimations and innovation sequences in real-time. The innovation sequences are then used to improve the estimation result through filtering and smoothing, and to detect faults. A case study demonstrates the efficient performance of the distributed approach in fault detection.
IET CONTROL THEORY AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Jinxin Wang, Xiuquan Sun, Chi Zhang, Xiuzhen Ma
Summary: This paper proposes a system-level fault diagnosis methodology based on fault behavior analysis, optimal sensor placement, and intelligent data analytics for multiple fault detection and isolation. By constructing a dynamical model and using set partitioning theory, a condition monitoring system with optimal sensor placement can be designed, and multivariate statistic measures are used to detect potential faults.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Energy & Fuels
Shuqing Wen, Weirong Zhang, Yifu Sun, Zhenxi Li, Boju Huang, Shouguo Bian, Lin Zhao, Yan Wang
Summary: This study proposes an enhanced principal component analysis (PCA) method using the Savitzky-Golay (SG) filter and density-based spatial clustering of applications with noise (DBSCAN) algorithm to detect and identify sensor faults quickly. The proposed strategy divides the dataset into sub-datasets with different working conditions using the DBSCAN algorithm, and smooths each sub-dataset using the SG algorithm. The validation results show significant improvements in fault detection accuracy and fault identification sensitivity compared to the conventional PCA method.
Article
Telecommunications
Shao Sujie, Guo Shaoyong, Qiu Xuesong, Meng Luoming, Lei Min
CHINA COMMUNICATIONS
(2015)
Article
Energy & Fuels
Sujie Shao, Shaoyong Guo, Xuesong Qiu
Article
Energy & Fuels
Sujie Shao, Qingtao Zeng, Shaoyong Guo, Xuesong Qiu
Article
Computer Science, Information Systems
Tianhong Su, Sujie Shao, Shaoyong Guo, Min Lei
WIRELESS COMMUNICATIONS & MOBILE COMPUTING
(2020)
Article
Computer Science, Information Systems
Sujie Shao, Qinghang Zhang, Shaoyong Guo, Feng Qi
Summary: This article proposes a task allocation mechanism for cable real-time online monitoring business based on edge computing, aiming to solve the problem of limited resources in edge nodes through dynamic task allocation and resource optimization. The research results show that the mechanism can effectively reduce the delay of monitoring business and improve the security and reliability of the smart grid.
IEEE SYSTEMS JOURNAL
(2021)
Article
Computer Science, Information Systems
Sujie Shao, Weichao Gong, Shaoyong Guo, Xuesong Qiu
Summary: This paper focuses on the trade between edge computing providers (ECP) and nodes in the context of public blockchain networks. A computational resource market model based on auction is established, with two strategies proposed to achieve higher system profit through offloading methods. The proposed strategies are proven to be individually rational and authentic under resource constraints, providing significance for administrators to improve computing resource allocation efficiency in public blockchain networks.
WIRELESS COMMUNICATIONS & MOBILE COMPUTING
(2021)
Article
Computer Science, Information Systems
Ao Xiong, Yuanzheng Tong, Shaoyong Guo, Yanru Wang, Sujie Shao, Lin Mei
Summary: The optimization of power multimodal network resources is crucial for the stable operation of power business. This paper proposes an optimal allocation method based on NSGA-II, which successfully solves the coding and convergence problems of using genetic algorithm in network resource allocation optimization by establishing a power multimodal network-resource model and applying preprocessing technology and indirect coding technology. Simulation results show that this method further optimizes various indicators of power multimodal network resource allocation, improving performance by more than 6% compared to the control algorithm.
WIRELESS COMMUNICATIONS & MOBILE COMPUTING
(2021)
Article
Computer Science, Information Systems
Sujie Shao, Qinghang Zhang, Shaoyong Guo, Lin Sun, Xuesong Qiu, Luoming Meng
Summary: The article introduces an energy-efficient solar insecticidal lamp management architecture based on edge computing, and proposes a management mechanism that considers real-time information. Simulation results demonstrate that the proposed mechanism can improve energy utilization and alleviate battery discharge issues compared to traditional methods.
IEEE SYSTEMS JOURNAL
(2022)
Article
Computer Science, Information Systems
Sujie Shao, Weichao Gong, Huifeng Yang, Shaoyong Guo, Liandong Chen, Ao Xiong
Summary: The 6G wireless network aims to connect trillions of devices in the future by establishing a new spectrum, high technical standards, and 100% geographic coverage. However, ensuring privacy and security becomes challenging as connectivity and novel applications increase. Blockchain is seen as a promising technology to improve efficiency, reduce costs, and establish a trusted data-sharing environment. This article presents a trusted framework based on blockchain technology for building a trusted software-defined content delivery network, enhancing security and trust relationships between entities in different domains.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Qianjun Wang, Sujie Shao, Shaoyong Guo, Xuesong Qiu, Zhili Wang
Article
Computer Science, Information Systems
Yunzhao Li, Feng Qi, Zhili Wang, Xiuming Yu, Sujie Shao
Article
Computer Science, Information Systems
Xiao Cheng, Jinma Sheng, Xiuting Rong, Hui Zhang, Lei Feng, Sujie Shao
Article
Computer Science, Information Systems
Xudong Niu, Sujie Shao, Chen Xin, Jun Zhou, Shaoyong Guo, Xingyu Chen, Feng Qi
Article
Computer Science, Information Systems
Zitong Ma, Sujie Shao, Shaoyong Guo, Zhili Wang, Feng Qi, Ao Xiong