Article
Automation & Control Systems
Yiming Wan, Yujia Ma, Maiying Zhong
Summary: The design of fault detection systems optimizes the trade-off between false alarm rate and fault detection rate under stochastic disturbances. To address the challenge of inexact stochastic disturbance distribution, a distributionally robust optimization approach is proposed, ensuring worst-case fault detection rate while accounting for distribution ambiguity.
INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL
(2021)
Article
Engineering, Marine
Ming Yang, Zhaowei Shen, Yanhui Wang, Jun Chen, Wei Han, Shaoqiong Yang
Summary: In this study, a remote anomaly detection method for underwater gliders (UGs) is proposed based on multi-feature fusion. By performing failure analysis and fusing characteristic parameters using principal component analysis, along with the adoption of the Density-Based Spatial Clustering of Applications with Noise Algorithm, the method achieves remote monitoring of UG anomalies while reducing false alarms. The feasibility of the proposed method is verified using historical data from multiple acoustic UGs, demonstrating its ability to detect all abnormal profiles with a decrease in false alarm rate after optimization, thereby reducing operational overhead and mission costs.
Article
Computer Science, Information Systems
Fei Li, Xiaoqiang Liu, Liangliang Shang, Guozhu Wang, Ziwei Pan, Yining Sun
Summary: This paper proposes a fault detection method based on entropy score contribution analysis, which can better determine the number of samples with a high contribution rate and achieve good fault detection results. The experimental results show that this method has more advantages than traditional methods and can be effectively applied to complex industrial processes.
Article
Automation & Control Systems
Wentao Mao, Ling Ding, Yamin Liu, Sajad Saraygord Afshari, Xihui Liang
Summary: This paper proposes a novel online early fault detection method based on deep transfer learning, which enhances the feature sensitivity to early faults and the robustness of the detection model by introducing priori degradation information and designing a deep domain adaptation neural network. Comparative experiments demonstrate the effectiveness of the proposed method in reducing false alarms and accurately detecting fault locations.
Article
Chemistry, Multidisciplinary
Eungyu Lee, Yongsoo Lee, Teajin Lee
Summary: This paper proposes a method based on explainable artificial intelligence (XAI) that provides interpretability through an interpretation of AI prediction results and a reliability analysis of predictions. Additionally, a high-quality data screening method is introduced to detect false predictions. The experiments demonstrate that this method can enhance the ability to respond to cyberattacks.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Kuiliang Chen, Zhiwei Wang, Xiaowei Gu, Zhanwei Wang
Summary: This study proposes a method based on global density-weighted support vector data description (GDW-SVDD) to detect chiller faults, which can effectively improve fault detection accuracy and reduce false alarm rate. Experimental results show that compared to conventional methods and other methods, this approach has significant advantages in fault detection accuracy.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Hardware & Architecture
Wenhao Jiang, Yuebin Bai
Summary: In this study, a data-driven propagation-based root cause analysis and fault detection approach called Alarm Propagation Graph Neural Network (APGNN) is proposed. This method associates alarms with root causes using Bayesian Network and constructs alarm propagation graphs (APG). Our approach not only detects true faults from a large volume of original alarms, but also analyzes root cause alarms.
Article
Computer Science, Information Systems
Minghe Zhang, Liyan Xie, Yao Xie
Summary: This paper proposes an online change detection algorithm called Spectral-CUSUM to detect unknown network structure changes using a generalized likelihood ratio statistic. The average run length (ARL) and the expected detection delay (EDD) of the Spectral-CUSUM procedure are characterized and its asymptotic optimality is proven. Finally, the good performance of the Spectral-CUSUM procedure is demonstrated and compared with several baseline methods on seismic event detection using sensor network data.
IEEE TRANSACTIONS ON INFORMATION THEORY
(2023)
Article
Construction & Building Technology
Dasheng Lee, Chih-Wei Lai, Kuo-Kai Liao, Jia-Wei Chang
Summary: The study proposed an innovative AI-assisted false alarm detection and diagnosis system, which can effectively reduce false alarms and improve the accuracy of fault detection. The system can meet high-reliability requirements and achieve significant maintenance cost savings.
JOURNAL OF BUILDING ENGINEERING
(2021)
Article
Green & Sustainable Science & Technology
Bojian Du, Yoshiaki Narusue, Yoko Furusawa, Nozomu Nishihara, Kentaro Indo, Hiroyuki Morikawa, Makoto Iida
Summary: Condition monitoring systems are commonly used for early fault detection in wind turbines to reduce downtime and increase availability. The use of data from SCADA systems has been proposed as a potential monitoring solution. However, variations in environmental conditions and manual control can lead to false alarms. To address these challenges, a clustering-based multi-turbine fault detection approach is proposed in this study, which consists of WT clustering, single-turbine modeling, and fault indicator calculation. The evaluation results using real large-scale SCADA data demonstrate that the proposed approach can reduce false alarms without compromising detection performance.
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY
(2023)
Article
Computer Science, Information Systems
Feifei Yin, Bingzhe He
Summary: The automatic fault detection system proposed in this paper, based on node association degree, includes hardware design and software design to accurately detect network cascade faults with high fault identification rate and small global error of fault detection.
COMPUTER COMMUNICATIONS
(2021)
Article
Engineering, Marine
Jian Wang, Haisen Li, Guanying Huo, Chao Li, Yuhang Wei
Summary: In the background of multi-background underwater surveying and mapping, detecting seafloor terrain is challenging due to environmental noise, sidelobe data, and tunnel emission. Constant false alarm detection, which can eliminate noise interference and provide accurate seabed topography information, is an important research field. This paper proposes an efficient weighted cell averaged constant false alarm detection method (WCA-CFAR) to increase detection probability, reduce missing probability, and improve detection speed. The method is validated through simulation data detection tests and actual lake test data, showing effective reduction in missing detection probability and improvement in detection probability.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Seung Hwan Park, Doo Hyun Kim, Sung Chul Kim
Summary: The use of IoT technology in fire-detection systems has increased in Korea due to communication technology convergence and the proliferation of IoT. However, there has been a lack of research based on actual operational data. This study investigates actual fire accidents over a 5-year period and develops a fuzzy logic system for recognizing fire signal patterns.
Article
Engineering, Electrical & Electronic
Huan Wu, Chao Shang, Kun Zhu, Chao Lu
Summary: This study proposes a model to quantify the relationship between signal-to-noise ratio (SNR) and detection performance, providing a method for setting the decision threshold. Experimental validation shows that the autocorrelation-energy-based method achieves high detection probability and low false alarm probability in a DAS system.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2021)
Article
Geochemistry & Geophysics
Yunrong Zhu, Yang Li, Qiming Zhang
Summary: Compared with CFAR detector, NN-based detector has better detection performance for weak targets in a nonhomogeneous environment. However, it is difficult to control PFA using the CE loss function. NP criterion is used to find the optimal detector under the constraint of PFA, but cannot be directly used for NN. This paper introduces differentiable-NP loss functions for NNs under the ESIS and achieves false-alarm-controllable detection using a lightweight U-Net segmentation network.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Engineering, Chemical
Xinrui Gao, Fan Yang, Enbo Feng
CANADIAN JOURNAL OF CHEMICAL ENGINEERING
(2020)
Article
Engineering, Chemical
Cen Guo, Wenkai Hu, Fan Yang, Dexian Huang
CHINESE JOURNAL OF CHEMICAL ENGINEERING
(2020)
Article
Mathematics
Vladimir Klimchenko, Andrei Torgashov, Yuri A. W. Shardt, Fan Yang
Summary: This paper discusses the development of a multi-output soft sensor for industrial reactive distillation of methyl tert-butyl ether production, proposing a unique approach using filters to predict model errors and correct final predictions. By decomposing the optimal estimation of time delays for each input of the soft sensor, significant improvements were achieved in predicting key compounds in the output product.
Article
Physics, Multidisciplinary
Xiangxiang Zhang, Wenkai Hu, Fan Yang
Summary: This study proposes an improved method for causality inference based on transfer entropy and information granulation, which significantly reduces computational complexity while maintaining accurate causality detection. It combines information granulation as a critical preceding step in the calculation of transfer entropy and introduces a window-length determination method based on delay estimation for appropriate data compression.
Article
Automation & Control Systems
Jiandong Wang, Zhen Wang, Xuan Zhou, Fan Yang
Summary: This paper proposes a method to design delay timers based on probability mass functions (PMFs) of alarm durations, which can be used to remove nuisance alarms. The method does not rely on the assumption of IID and is equally applicable to both analog and digital process variables.
JOURNAL OF PROCESS CONTROL
(2022)
Article
Computer Science, Interdisciplinary Applications
Wenkai Hu, Jiandong Wang, Fan Yang, Banglei Han, Zhen Wang
Summary: This paper proposes a new cause-effect detection method to analyze time-varying cause-effect relations in complex process industries. The method utilizes piecewise linear representation of the key variable's time series, extracts qualitative trends of involved variables, and calculates the contribution factors of influence variables to the changes of the key variable.
COMPUTERS & CHEMICAL ENGINEERING
(2022)
Article
Automation & Control Systems
Feng Yu, Qiluo Xiong, Liang Cao, Fan Yang
Summary: Data-driven soft sensors are crucial for monitoring the stable and safe operation of industrial processes. However, traditional machine-learning methods face challenges when handling test data from unknown operating modes. This paper proposes stable soft sensor frameworks based on causality analysis and stable learning to address this issue.
CONTROL ENGINEERING PRACTICE
(2022)
Article
Automation & Control Systems
Xiangxiang Zhang, Wenkai Hu, Fan Yang, Weihua Cao, Min Wu
Summary: This paper proposes a new transfer entropy approach based on information granulation and clustering to identify the root causes of faults in complex industrial facilities. The approach includes information granulation based transfer entropy and information granulation based direct transfer entropy, as well as a PDF estimator based on OPTICS clustering. The effectiveness of the proposed approach is demonstrated through two case studies.
CONTROL ENGINEERING PRACTICE
(2023)
Article
Engineering, Environmental
Poku Gyasi, Jiandong Wang, Fan Yang, Iman Izadi
Summary: This paper proposes an adaptive method to update alarm deadbands for nonstationary process variables in order to eliminate false alarms. The method detects statistically significant changes in process variables and determines when to update the alarm deadband width based on a confidence interval.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2023)
Proceedings Paper
Automation & Control Systems
Chao Wang, Chao Shang, Fan Yang, Dexian Huang, Bin Yu
Proceedings Paper
Automation & Control Systems
Feng Yu, Liang Cao, Weiyang Li, Fan Yang, Chao Shang
Article
Automation & Control Systems
Liang Cao, Feng Yu, Fan Yang, Yankai Cao, R. Bhushan Gopaluni
CONTROL ENGINEERING PRACTICE
(2020)
Article
Automation & Control Systems
Yun Li, Fan Yang
IEEE-CAA JOURNAL OF AUTOMATICA SINICA
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Chao Shang, Xiaolin Huang, Fan Yang, Dexian Huang
2019 1ST INTERNATIONAL CONFERENCE ON INDUSTRIAL ARTIFICIAL INTELLIGENCE (IAI 2019)
(2019)
Proceedings Paper
Automation & Control Systems
Andrei Torgashov, Anton Goncharov, Fan Yang