相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Engineering, Industrial
John Andrews et al.
Summary: Fault tree analysis is widely used in safety critical industries to predict system failures. However, existing commercial fault tree analysis codes have limitations in representing modern industrial systems. This paper proposes a new framework that overcomes these limitations.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Industrial
Junchao Guo et al.
Summary: This paper proposes a novel method for rotating machinery fault detection, which achieves multi-sensor data fusion using improved cyclic spectral covariance matrix (ICSCM) and motor current signal analysis. The proposed method adaptively acquires multi-sensor mode components and constructs ICSCM using sample entropy to preserve the interaction relationship between different sensors. The ICSCM is then incorporated into an extreme learning machine classifier for fault type identification. The proposed method has achieved satisfactory results and more reliable diagnosis accuracy than other state-of-the-art algorithms in rotating machinery fault detection.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Green & Sustainable Science & Technology
Ali Dibaj et al.
Summary: This study proposes a vibration-based fault detection method for offshore wind turbine drivetrain, which optimizes the selection of acceleration measurements to find the sensor positions that provide the most relevant fault-related information. The study examines different simulated shaft acceleration measurements to analyze the correlation between measurements under various faults and environmental conditions, and employs a combined PCA and CNN method for fault detection. The prediction results show that only two vibration sensors, one near the main shaft and another near the intermediate-speed shaft, are sufficient to fully detect the considered faulty bearings.
Article
Computer Science, Artificial Intelligence
Ana Rita Nogueira et al.
Summary: This article explores the complexity of causality and its significance in the field of artificial intelligence. Causality research aims at obtaining causal knowledge from observational data and estimating the impact of variable changes on outcomes. The article also provides a practical toolkit for researchers and practitioners, including software, datasets, and examples.
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY
(2022)
Article
Computer Science, Artificial Intelligence
Honghu Pan et al.
Summary: This paper proposes an adjacency-aware Graph Convolutional Network (AAGCN) to smooth intra-class features and reduce intra-class variance in person re-identification (ReID). The AAGCN establishes connections between intra-class features and applies low-pass filtering to smooth adjacent nodes. Two methods, Mahalanobis Neighborhood Adjacency (MNA) and Non-Linear Mapping (NLM), are proposed to learn adjacency relations for intra-class features. Experimental results demonstrate the effectiveness of the proposed method on visible and visual-infrared ReID datasets.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Engineering, Industrial
Haodong Yan et al.
Summary: This article proposes a virtual sensor-based imputed graph attention network for accurate anomaly detection in key parts of complex equipment. By using generative adversarial networks and graph attention networks, incomplete multi-source data can be processed and better performance can be achieved even without complete data. The research results demonstrate the strong ability of this method in missing data imputation.
JOURNAL OF MANUFACTURING SYSTEMS
(2022)
Article
Engineering, Industrial
Jie Liu et al.
Summary: This paper proposes three unsupervised feature extraction methods based on causal network, which extract principal components related to specific faults by discovering the causal network among monitoring variables in a rail transportation system. Compared with correlation-based methods, the effectiveness of these methods is verified on two public datasets and a real dataset considering high-speed train braking system.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Industrial
Zhe Yang et al.
Summary: This paper proposes a method for fault detection in evolving environments using a deep neural network and a novel procedure to reduce computational burden. The method achieves accurate fault detection in a synthetic case study and a bearing vibration dataset, outperforming other existing techniques.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Industrial
Fudong Li et al.
Summary: Anomaly detection in liquid rocket motors is a challenging task, and this paper conducts a study on intelligent fault detection of liquid rocket engines. The proposed method for engine state identification is verified to be feasible and effective through analysis of multiple sets of measured data.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Civil
Naoki Akai et al.
Summary: This study presents a method for detecting localization failures using Markov random fields with fully connected latent variables. The full connection allows for considering the entire relation among sensor measurements, contributing to accurate misalignment recognition. Additionally, localization failure probability calculation and efficient distance field representation methods are proposed. Experimental results demonstrate that the proposed method achieves precise and immediate failure detection on different datasets.
IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
(2022)
Article
Engineering, Industrial
Liqiao Xia et al.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2022)
Article
Engineering, Industrial
Umer Saeed et al.
Summary: Wireless Sensor Network (WSN) is susceptible to various types of failures due to its diversification, making precise detection and diagnosis challenging. This study proposes a supervised machine learning-based technique based on Extra-Trees to detect and diagnose faults in WSN efficiently and with low training time compared to other state-of-the-art approaches. Performance evaluation shows improved accuracy, precision, and Fl-score compared to other machine learning algorithms.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Engineering, Electrical & Electronic
Praveen Rai et al.
Summary: This paper presents a deep learning algorithm, Convolutional Neural Network (CNN), customized for fault classification in distributed networks integrated with DGs, achieving high accuracy through 10-fold cross-validation. Compared to conventional approaches, this method shows better performance in terms of accuracy and computation burden.
ELECTRIC POWER SYSTEMS RESEARCH
(2021)
Article
Engineering, Multidisciplinary
Yiyuan Gao et al.
Summary: The proposed intelligent fault diagnosis method based on semi-supervised graph convolutional network effectively extracts fault features from mechanical vibration data and maintains high accuracy even with a low label ratio.
Article
Computer Science, Artificial Intelligence
Marwa Tolba et al.
Summary: This research investigates various approaches combining diverse techniques in three dimensions: feature representation, imbalanced data handling, and supervised learning to efficiently handle online harassment detection. The study evaluates the potential of using hybrid approaches on highly-imbalanced Twitter data and determines the best combination for the intended purpose through extensive comparative study. Glove is identified as the best feature representation and certain combinations, such as LSTM and BLSTM with cost-sensitive learning and VL strategy, are found to be the best performing.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Automation & Control Systems
Teng Wang et al.
Summary: The article proposes a bearing fault detection and diagnosis technique based on temporal-spatio graph, which monitors the health condition of bearings by studying the correlation information in spatial configuration and temporal dynamic of frequencies. The method demonstrates superiority over existing techniques in experiments, providing a significant extension of existing spectrum analysis.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2021)
Article
Engineering, Industrial
Morteza Soleimani et al.
Summary: This paper presents a methodology for fault detection, prediction, and isolation in complex engineered systems, using HMM and BN to analyze data characteristics and capture causality for fault identification. The results show that the proposed methodology can identify faults faster and attribute them to the correct root cause.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Article
Engineering, Industrial
Tianfu Li et al.
Summary: This study proposes a sensor network model HAGCN for RUL prediction, which models spatial and temporal dependencies of sensors simultaneously using hierarchical graph representation layer and bi-directional long short-term memory network. Experimental results show the superiority of this method over existing approaches.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2021)
Review
Engineering, Multidisciplinary
Kun Kuang et al.
Review
Engineering, Industrial
Tosin Adedipe et al.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2020)
Article
Engineering, Multidisciplinary
Dingcheng Zhang et al.
Article
Engineering, Electrical & Electronic
Siyu Shao et al.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2020)
Article
Environmental Sciences
Jie Liu et al.
Article
Multidisciplinary Sciences
Jakob Runge et al.
Article
Health Care Sciences & Services
Ridho Rahmadi et al.
STATISTICAL METHODS IN MEDICAL RESEARCH
(2018)
Article
Engineering, Mechanical
Jie Liu et al.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2017)
Article
Engineering, Industrial
Kilian Zwirglmaier et al.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2017)
Article
Engineering, Industrial
Jing Li et al.
