Article
Engineering, Electrical & Electronic
Bo Xu, Zhuofan Wen, Guoqing Zhang, Peng Li
Summary: In this article, an extended RIMU system is proposed to achieve fault location in a four axis system. By adding three additional accelerometers and a four-axis RIMU to the original system, specific force information is used to obtain reference angular velocity information, and a fault detection procedure is designed to isolate faulty gyroscopes and reconfigure the system. Simulation results show that the extended system can effectively isolate gyroscope failures in a four-axis RIMU system. Compared to the non-redundant three-axis system, the extended system is 1.75x more reliable and has 37% better average navigation accuracy.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Automation & Control Systems
Zhen Shi, Xuan Liu, Jinglong Chen, Yanyang Zi, Zitong Zhou
Summary: Intelligent fault diagnosis with small training samples is crucial for ensuring the safety of mechanical equipment. However, the weak fault features due to sharp speed variation and the mutual coupling of multi-component fault features pose challenges for fault diagnosis. In this study, a multi-branch redundant adversarial net (RedundancyNet) is proposed, which utilizes the redundant second generation wavelet transform for non-stationary feature extraction. The network consists of a discriminator, a generator for redundant reconstruction, and a classifier for redundant decomposition. Through adversarial training and multi-resolution feature enhancement, the RedundancyNet achieves high classification accuracy in fault diagnosis, outperforming other existing methods. The effectiveness of the net is demonstrated in two cases with drastically variable speeds and small faulty training samples. The proposed classifier is also easy to interpret, providing insights into the feature learning process under varying speeds.
Article
Engineering, Mechanical
Ruqiang Yan, Zuogang Shang, Hong Xu, Jingcheng Wen, Zhibin Zhao, Xuefeng Chen, Robert X. Gao
Summary: This paper provides a comprehensive overview of the advancement in wavelet transform-based fault diagnosis research over the last decade. It highlights the applications of wavelet transform in traditional fault diagnosis and intelligent fault diagnosis as well as discusses future research trends.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Yong Hyeon Cho, Woo Jung Park, Chan Gook Park
Summary: This paper proposes two novel methods to mitigate lever arm effect in RIMUs, increasing the accuracy of compensating for the effect. These methods use lever arm vectors and nonlinear least squares method in different ways, providing higher computational efficiency and overall navigation performance compared to previous methods.
IEEE SENSORS JOURNAL
(2021)
Article
Engineering, Multidisciplinary
Zhenwei Li, Yongmei Cheng, Xuhua Wu, Yachong Zhang, Huaxia Wang
Summary: This paper proposes a novel fault detection method for small faults in redundant IMUs, which introduces an adaptive low-pass filter to reduce sensor noise interference. Theoretical derivation and simulation results validate the effectiveness of the proposed method in reducing the probability of missing detection for small faults.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2021)
Article
Engineering, Aerospace
Shizhuang Wang, Xingqun Zhan, Yawei Zhai, Lingxiao Zheng, Baoyu Liu
Summary: Urban Air Mobility (UAM) relies on highly automated air vehicles to provide safe and efficient low-altitude urban transportation services. Ensuring navigation safety is crucial for UAM operations. This research proposes a new approach to enhance navigation integrity by integrating multiple IMUs with GNSS, using a centralized Kalman filter.
AEROSPACE SCIENCE AND TECHNOLOGY
(2022)
Article
Engineering, Multidisciplinary
Subhamita Roy, Sudipta Debnath
Summary: The study proposes an algorithm for HIF detection and classification in distribution systems based on power spectral density calculation. By utilizing discrete wavelet transform to separate time and frequency information, this technique offers fast and accurate fault detection and classification with high practical value.
Article
Multidisciplinary Sciences
Majid Valizadeh, Sadegh Rahimi, Mohamad Yousefinezhad, Milad Alirezaiean
Summary: Power swings can cause issues, but usually the power system stabilizes after a power swing. This article focuses on detecting single-phase faults during power swings, particularly asymmetric power swings. The suggested approach uses wavelet transform on the zero-sequence current signal to identify the faults. Simulation and analysis results confirm the effectiveness of the proposed method.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Lijie Zhang, Bin Wang, Pengfei Liang, Xiaoming Yuan, Na Li
Summary: This paper proposes a semi-supervised fault diagnosis approach based on feature pre-extraction and improved generative adversarial network (IGAN) to address the issues of requiring a large amount of labeled data and noise interference in traditional methods. Experimental results demonstrate that the proposed approach achieves better diagnosis accuracy and anti-noise robustness in limited labeled samples and noise environment.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Engineering, Electrical & Electronic
Ting Wang, Antonello Monti
Summary: This article introduces an FDI method for dc microgrids using SDOC information and a singularity detection method based on SWT. The method not only achieves fault isolation but also allows for fault-type classification, with advantages in robustness against nonfault disturbances.
IEEE JOURNAL OF EMERGING AND SELECTED TOPICS IN POWER ELECTRONICS
(2021)
Article
Engineering, Electrical & Electronic
Yuming Zhang, Davide A. A. Cucci, Roberto Molinari, Stephane Guerrier
Summary: The increased use of low-cost gyroscopes in navigation systems has led to extensive research on improving their measurement precision. A recent approach is to combine the measurements from arrays of gyroscopes to reduce individual sensor noise. However, combining these measurements is difficult due to the complex nature of the errors. In this study, a non-parametric method using wavelet cross-covariance is proposed to construct an optimal measurement signal with weak assumptions on individual errors.
IEEE TRANSACTIONS ON SIGNAL PROCESSING
(2022)
Article
Computer Science, Information Systems
Ahmadreza Sezavar, Randa Atta, Mohammad Ghanbari
Summary: In this paper, a person identification framework based on smartphone-acquired gait signals is proposed, which combines convolutional neural network (CNN) and dual-tree complex wavelet transform (DTCWT) to achieve higher recognition accuracy. Experimental results demonstrate the superiority of the proposed method over the state-of-the-art models.
MULTIMEDIA SYSTEMS
(2022)
Article
Engineering, Mechanical
Rismaya Kumar Mishra, Anurag Choudhary, A. R. Mohanty, S. Fatima
Summary: This paper proposes an intelligent vibration signal-based fault diagnosis approach for early identification of bearing faults, regardless of speed conditions. The approach combines frequency shift-based hybrid signal processing technique, sliding window-based feature extraction, and Henry Gas Solubility Optimization algorithm for feature selection, followed by Artificial Neural Network model training for fault classification. Experimental validation under constant and varying speed conditions demonstrates the tremendous potential of this approach in eliminating unplanned failures caused by bearing in rotating machinery.
PROCEEDINGS OF THE INSTITUTION OF MECHANICAL ENGINEERS PART C-JOURNAL OF MECHANICAL ENGINEERING SCIENCE
(2022)
Article
Engineering, Electrical & Electronic
Hongwen Liu, Qing Yang, Lijun Tang, Tao Yuan, Tong Zhou
Summary: Different types of faults have different levels of threat to the distribution network. Accurate identification of fault types is crucial for maintenance and prevention of hazards in the distribution network.
ELECTRIC POWER SYSTEMS RESEARCH
(2023)
Article
Construction & Building Technology
Yongkang Zeng, Jingjing Chen, Ning Jin, Xiaoping Jin, Yang Du
Summary: Air quality measurement and forecasting is a popular research topic in the field of sustainable intelligent environmental design, urban area development, and pollution control, especially for developing countries in Asia like China. This study proposes a novel forecasting model that integrates the extended stationary wavelet transform and nested long short-term memory neural network for PM2.5 air quality forecasting. The results show that the proposed method outperforms state-of-the-art forecasting methods in terms of different error metrics.
BUILDING AND ENVIRONMENT
(2022)