Article
Engineering, Multidisciplinary
Jun Gu, Yuxing Peng, Hao Lu, Xiangdong Chang, Shuang Cao, Guoan Chen, Bobo Cao
Summary: The study proposes a feature extraction method based on VMD and PE, with SVM classifier for identifying bearing fault types. Genetic algorithm is used to optimize VMD parameters, and an evaluation indicator is constructed to compare signal decomposition methods. Experimental results show that the proposed method has better diagnostic accuracy than EMD, EEMD, and BP neural network under limited samples and unknown input samples.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2022)
Article
Physics, Multidisciplinary
Ruimin Shi, Bukang Wang, Zongyan Wang, Jiquan Liu, Xinyu Feng, Lei Dong
Summary: The paper proposes a method to optimize Variational Mode Decomposition (VMD) using the Niche Genetic Algorithm (NGA) for more efficient and accurate fault extraction of rolling bearings. By transferring the decomposition process of the fault signal to a variational frame, the NGA-VMD algorithm achieves better robustness and correct recognition rate.
Article
Engineering, Electrical & Electronic
Chuliang Liu, Jianping Tan, Zhonghe Huang
Summary: The vibration signals collected by sensors often contain complex frequency components, which pose challenges to bearing condition monitoring and fault diagnosis. This paper proposes an adaptive optimal mode extraction method based on the variational mode extraction (VME) method, which is capable of extracting weak fault features.
Article
Engineering, Multidisciplinary
Xiangyu Zhou, Yibing Li, Li Jiang, Li Zhou
Summary: A hybrid fault diagnosis method based on VMD and MOMEDA was proposed to extract fault features effectively. The method utilizes parameter-adaptive VMD, effective mode selection, and signal reconstruction to enhance fault characteristics, and retrieves periodic pulse signals via MOMEDA for fault frequency identification. The effectiveness of the proposed method was verified through experimental datasets and comparisons with other methods.
Article
Engineering, Multidisciplinary
Xiangyu Zhou, Yibing Li, Li Jiang, Li Zhou
Summary: A hybrid fault diagnosis method based on parameter-adaptive VMD and MOMEDA is proposed to effectively extract fault features, which is verified by experimental datasets and further demonstrated its superiority in fault feature extraction through comparisons with other methods.
Article
Engineering, Multidisciplinary
Xiangyu Zhou, Yibing Li, Li Jiang, Li Zhou
Summary: A hybrid fault diagnosis method based on parameter-adaptive VMD and MOMEDA is proposed for extracting fault features from vibration signals. The algorithm uses WOA to solve VMD parameter selection problem, selects effective modes for reconstruction to enhance fault characteristics, and extracts periodic pulse signals for fault frequency identification. The method is verified to be effective and superior to other latest methods in fault feature extraction.
Article
Engineering, Multidisciplinary
Xiangyu Zhou, Yibing Li, Li Jiang, Li Zhou
Summary: The study proposed a hybrid fault diagnosis method based on VMD and MOMEDA, which uses parameter-adaptive VMD to obtain effective modes and extracts fault characteristic frequencies through MOMEDA, proving its effectiveness on two different experimental datasets.
Article
Engineering, Multidisciplinary
Xiangyu Zhou, Yibing Li, Li Jiang, Li Zhou
Summary: The proposed hybrid fault diagnosis method based on parameter-adaptive variational mode decomposition and multi-point optimal minimum entropy deconvolution effectively extracts fault characteristic frequencies and has been validated on experimental datasets. Comparisons with other methods further highlight its superiority in fault feature extraction.
Article
Engineering, Multidisciplinary
Xiangyu Zhou, Yibing Li, Li Jiang, Li Zhou
Summary: A hybrid fault diagnosis method based on VMD and MOMEDA was proposed to effectively extract fault features, which were verified through experimental datasets and comparisons with other methods, demonstrating its superiority in fault feature extraction.
Article
Instruments & Instrumentation
Ruo Hu, Jinyang Feng, Zonglei Mou, Xunlong Yin, Zhenfei Li, Hongrong Ma
Summary: This paper proposes a novel method for incipient fault diagnosis of the cam-driven absolute gravimeter by integrating the parameter-optimized Variational Mode Decomposition (VMD) with Light Gradient Boosting Machine (LightGBM). The method effectively detects various incipient failures of the gravimeter and solves the problem of low measurement accuracy caused by these faults.
REVIEW OF SCIENTIFIC INSTRUMENTS
(2022)
Article
Engineering, Mechanical
Qing Ni, J. C. Ji, Ke Feng, Benjamin Halkon
Summary: This study proposes a fault information-guided VMD (FIVMD) method for extracting weak bearing repetitive transients. By using statistical models and defining the fault characteristic amplitude ratio, the optimal decomposition parameters can be determined to successfully diagnose bearing faults.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Computer Science, Information Systems
Mingzhu Lv, Shixun Liu, Changzheng Chen
Summary: Feature extraction technology plays an important role in bearing diagnosis, especially for early degradation detection. However, traditional methods often struggle with noise removal and the detection of weak periodic faults. In this study, a new feature extraction technique based on EHNR and AVMD is proposed to address these issues. Experimental results show that this method outperforms other detection methods in terms of early degradation point detection, false alarm rate, and computational complexity.
Article
Automation & Control Systems
Ali Dibaj, Reza Hassannejad, Mir Mohammad Ettefagh, Mir Biuok Ehghaghi
Summary: Most proposed fault diagnosis methods focus on detecting localized and incipient bearing faults, but it is unclear to what extent of fault severity they are capable of detecting. This study aims to address the crucial issue of defining criteria for incipient defects and provides a measure for assessing a decomposed-based fault diagnosis method using a parameter-optimized VMD approach and a new fault-sensitive index called WKI. Validation is done by investigating simulated vibration signals of a defective bearing at different fault severity and comparing with available methods in the literature.
Article
Physics, Multidisciplinary
Carole Lebreton, Fabrice Kbidi, Alexandre Graillet, Tifenn Jegado, Frederic Alicalapa, Michel Benne, Cedric Damour
Summary: This paper presents an online diagnosis method using the electrical output of PV plants, combining variational mode decomposition (VMD) and multiscale dispersion entropy (MDE) to detect and isolate faults. The method aims for a low-cost design, ease of implementation, and low computation cost.
Article
Engineering, Electrical & Electronic
Jianqiang Zhang, Kai Qian, Da Qiu, Guoping Zhang, Yang Long, Li Zhu, Song Liu
Summary: This paper proposes a denoising method based on parameter-optimized variational mode decomposition (VMD) to solve the problem of difficulty in filtering noise components in the monitoring of strain on wind turbine blades using fiber bragg grating. Experimental results show that the proposed method effectively removes noise and has better denoising performance.
OPTICAL FIBER TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Pradeep Kundu, Makarand S.Kulkarni, Ashish K.Darpe
Summary: This study proposes a hybrid prognosis approach for estimating the growth of pitting on gear teeth by utilizing both empirical models and measured pitting area. The model takes into account the gear material properties, oil properties, gear geometrical parameters, and operating conditions to predict the growth rate of pitting. The model parameters are updated using Bayesian inference to improve the accuracy of life prediction.
JOURNAL OF INTELLIGENT MANUFACTURING
(2023)
Article
Acoustics
Yuqing Zhou, Anil Kumar, Chander Parkash, Govind Vashishtha, Hesheng Tang, Adam Glowacz, An Dong, Jiawei Xiang
Summary: This paper proposes a novel method based on tangent hyperbolic fuzzy entropy measure to determine the sensitive frequency band for identifying defective components in an axial piston pump. The method decomposes the vibration signal into frequency bands and computes the energy of the WPT band. The proposed measure is used to identify the band with the most information, and envelope demodulation is performed on the sensitive band to identify defects.
Article
Engineering, Electrical & Electronic
Sumika Chauhan, Govind Vashishtha, Anil Kumar, Laith Abualigah
Summary: A combination of reptile search algorithms with differential evolution (CRSADE) has been developed to solve the problems of sluggish convergence at local minima. The developed algorithm improves exploration capability and accelerates convergence by enhancing population diversity. It has been demonstrated that CRSADE is superior to other optimization algorithms in designing finite impulse response filters.
CIRCUITS SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Mechanical
Yuqing Zhou, Anil Kumar, C. P. Gandhi, Govind Vashishtha, Hesheng Tang, Pradeep Kundu, Manpreet Singh, Jiawei Xiang
Summary: This study aims to develop a new discrete probabilistic entropy-based health indicator (HI) and a long short-term memory (LSTM)-based method for forecasting bearing health. The proposed indicator is robust and unaffected by load and speed. It is utilized to create an LSTM model that can accurately predict bearing health. The proposed method outperforms other time-series prediction models.
JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING
(2023)
Article
Engineering, Industrial
Hui Wang, Junkang Zheng, Jiawei Xiang
Summary: Digital twin is the embodiment of the most advanced achievements of the current simulation technology theory development and the direction of intelligent development in the future. However, it is a great challenge to really integrate it into practical project application. Motivated by DT, an application method combining numerical simulation model and machine learning classification is proposed to show the advantages of digital twin.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Engineering, Industrial
Yi Liu, Hang Xiang, Zhansi Jiang, Jiawei Xiang
Summary: Intelligent fault diagnosis methods are effective in ensuring the safety and reliability of key parts of rotating machinery. However, the lack of data during equipment acceptance period and the assumption of high data quality affect the reliability of results. To address these issues, a time-frequency-based method is introduced to analyze impulse components based on fault features. An accurate time-frequency analysis method named the second-order transient-extracting S-transform is proposed to overcome the influence of uncertain parameters. It produces a highly concentrated time-frequency representation and demonstrates higher accuracy in feature detection compared to other methods.
RELIABILITY ENGINEERING & SYSTEM SAFETY
(2023)
Article
Chemistry, Analytical
Qizhe Lin, Xiaoqi Li, Bicheng Tu, Junwei Cao, Ming Zhang, Jiawei Xiang
Summary: This study proposes a two-stage method for estimating the SOC of a lithium-ion battery by combining a second-order resistor-capacitor (RC) equivalent circuit model and an eXogenous Kalman filter (XKF). The SOC estimation values obtained by a stable observer are fed into XKF to enhance accuracy and stability. Experimental results show that the proposed method outperforms the commonly used EKF method in SOC estimation.
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
Engineering, Electrical & Electronic
Guilherme Beraldi Lucas, Bruno Albuquerque De Castro, Jorge Alfredo Ardila-Rey, Adam Glowacz, Jose Vital Ferraz Leao, Andre Luiz Andreoli
Summary: In this article, a novel approach using piezoelectric transducers was proposed for the detection of transient interturn short circuits in three-phase induction motors. The proposed algorithm successfully performed the detection, phase identification, and evolution classification of the short circuits. The experimental results demonstrated the effectiveness of this approach and its improvement over traditional acoustic emission systems.
IEEE SENSORS JOURNAL
(2023)
Article
Nanoscience & Nanotechnology
Chander Parkash, William C. Parke, Parvinder Singh
Summary: This study proposes a new method to obtain the explicit/closed representation of the two linearly independent solutions of a large class of second order ordinary linear differential equation with special polynomial coefficients. The method is applied to obtain the closed forms of regular and irregular solutions of the Coulombic Schrödinger equation for an electron experiencing the Coulomb force. The obtained solutions have important implications for studying bound state poles and Regge trajectories.
NANOSYSTEMS-PHYSICS CHEMISTRY MATHEMATICS
(2023)
Article
Materials Science, Multidisciplinary
Chuan Sun, Yuancheng Geng, Adam Glowacz, Maciej Sulowicz, Zhenjun Ma, Patrick Siarry, Munish Kumar Gupta, Z. Li
Summary: This study investigated the impact of a magnetic field on the heat transfer of Fe3O4 ferrofluid swirl flow. The results showed that applying the magnetic field at different locations improved the convective heat transfer coefficient and reduced the absorber tube temperature, but increased the pressure drop over the tube.
JOURNAL OF MAGNETISM AND MAGNETIC MATERIALS
(2023)
Article
Chemistry, Analytical
Ruozhu Liu, Xingbing Wang, Anil Kumar, Bintao Sun, Yuqing Zhou
Summary: This paper proposes a fault diagnosis technique for rolling bearings based on graph node-level fault information extracted from 1D vibration signals. Experimental results demonstrate that this method outperforms contrastive learning-based fault diagnosis methods, enabling rapid fault diagnosis, thus ensuring the normal operation of mechanical systems.
Article
Engineering, Electrical & Electronic
Yuqing Zhou, Hongche Wang, Gonghai Wang, Anil Kumar, Weifang Sun, Jiawei Xiang
Summary: In recent years, deep learning-based methods have made remarkable achievements in the intelligent fault diagnosis of rotating machinery. However, the lack of labeled and large unlabeled samples in actual industrial scenes affects the performance of supervised learning methods. This paper proposes a novel semi-supervised fault diagnosis method based on multiscale permutation entropy (MPE) enhanced contrastive learning (CL). Experimental results in gearbox and milling tool fault diagnosis experiments show that the proposed MPE-CL method outperforms other benchmark methods with classification accuracy above 95.4% and 96.0% when the labeled training dataset size is 50/class, respectively.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Engineering, Electrical & Electronic
Yi Liu, Hang Xiang, Zhansi Jiang, Jiawei Xiang
Summary: An improved general linear chirplet transform method is developed to overcome the limitations of traditional short-time Fourier transform (STFT)-based methods in processing non-stationary signals. By iteratively upgrading the instantaneous frequency (IF) and introducing a synchrosqueezing operator, the method improves the estimation accuracy of IF curves and enhances the concentration of time-frequency representation under variable operating conditions. Experiments with simulated data confirm the effectiveness of the enhanced time-frequency analysis (TFA) method, showing superior sharpness of IF curves and enhanced time-frequency readability compared to other advanced TFA methods, as well as superior feature extraction ability.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Artificial Intelligence
Adam Glowacz
Summary: This paper presents a technique for analyzing thermal images of minigrinders. Different states of minigrinders were analyzed and two methods for computing essential areas of thermal images were proposed. The analysis was verified and found to be effective for fault diagnosis with 100% recognition efficiency.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)