Article
Mathematics
Jiangming Jia, Chenan Zhang, Jianneng Chen, Zheng Zhu, Ming Mao
Summary: This article proposes a fault diagnosis method for an angle grinder based on an adaptive parameters and chaos theory of the dual-strategy differential evolution algorithm (ACD-DE) and SVM model hybrid algorithm. The effectiveness and robustness of the algorithm are proven by solving eight test functions, and experiments show that the hybrid algorithm has high diagnosis accuracy and robustness.
Article
Computer Science, Artificial Intelligence
Yunpeng Liu, Hongkai Jiang, Chaoqiang Liu, Wangfeng Yang, Wei Sun
Summary: This paper proposes a wavelet capsule generative adversarial network (WCGAN) for rolling bearing fault diagnosis with limited imbalance data. By introducing Harr wavelet and capsule networks, the method balances the dataset and improves the diagnosis accuracy.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Engineering, Multidisciplinary
Jing Yang, Guo Xie, Yanxi Yang
Summary: This paper proposes an intelligent diagnosis method based on a key-factor denoising strategy for quasi periodic non-stationary incipient faults. The method achieves signal denoising and handles the blindness of feature learning, and completes the health condition identification and fault severity level determination of machinery.
Article
Chemistry, Multidisciplinary
Zhijian Tu, Lifu Gao, Xiaoyan Wu, Yongming Liu, Zhuanzhe Zhao
Summary: This study proposes a fault diagnosis model based on EEMD-MPA-KELM, which can effectively judge the working state of rotating machinery.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Xinmiao Lu, Zihan Lu, Qiong Wu, Jiaxu Wang, Cunfang Yang, Shuai Sun, Dan Shao, Kaiyi Liu
Summary: This paper proposes a fault diagnosis method for analog circuits based on ensemble empirical pattern decomposition (EEMD) and improved multifractal detrended fluctuations analysis (MF-DFA) to solve the problems of nonlinearity and serious confusion of fault characteristics in analog circuits. The method includes three steps: preprocessing, feature extraction, and fault classification identification. The experimental results show that the proposed EEMD-improved MF-DFA method effectively extracts the features of soft faults in nonlinear analog circuits and achieves a high diagnosis rate.
Article
Automation & Control Systems
Zepeng Liu, Xiaoquan Tang, Xuefei Wang, Jose Errea Mugica, Long Zhang
Summary: This article diagnoses a naturally damaged wind turbine blade bearing and uses a novel signal denoising method, BAL algorithm, to reduce noise and improve diagnostic accuracy. The proposed framework is validated by experiments and case studies, demonstrating its superiority in comparison with popular diagnostic methods.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Engineering, Mechanical
Jesse Miettinen, Sampo Haikonen, Ivar Koene, Joni Keski-Rahkonen, Raine Viitala
Summary: Deep learning models can successfully recognize machine health conditions from vibration data. However, most studies have focused on lateral vibration data and ignored torsional vibration data, which could be advantageous for diagnosing gear faults. This study presents a large gear fault dataset and evaluates the performance of convolutional neural networks on both lateral and torsional vibration data.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Ruijun Liang, Yao Chen, Rupeng Zhu
Summary: This paper proposes a novel method based on WOA and KELM to solve the problem of difficult fault feature extraction and incomplete representation of state information by time-frequency features. Experimental results indicate that the proposed method can effectively extract fault features and achieve higher classification accuracy and faster convergence speed compared to existing fault diagnosis methods.
Article
Engineering, Industrial
Yunpeng Liu, Hongkai Jiang, Renhe Yao, Hongxuan Zhu
Summary: This paper proposes an interpretable data-augmented adversarial variational autoencoder with sequential attention (AVAE-SQA) for assisting imbalanced fault diagnosis. Experimental results demonstrate that this method performs well in fault diagnosis with imbalanced samples and has potential engineering applications.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Energy & Fuels
Zhenhao Tang, Mengjiao Wang, Tinghui Ouyang, Fei Che
Summary: Diagnosis of bearing faults is of significant importance in wind turbine maintenance. This paper proposes a feature extraction method for wind turbine bearing fault diagnosis, aiming to improve accuracy. The method involves three steps: time-domain feature extraction using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), deep frequency-domain features extraction using fast Fourier transform (FFT), and optimal feature subset selection using recursive feature elimination (RFE) combined with chi-square test. The proposed method is tested on industrial data from Case Western Reserve University (CWRU) and Jiangxi wind farm, and the results demonstrate its effectiveness and applicability in real wind turbine bearing fault diagnosis.
Article
Automation & Control Systems
Junhao Chen, Chunhui Zhao, Jinliang Ding
Summary: This article proposes a flexible probabilistic framework that can analyze both continuous and categorical variables for fault detection and diagnosis. It handles non-Gaussian and non-Bernoulli variables and captures their correlations under conditional independence assumption. Using variational inference for parameter estimation, the framework can adapt to different distributions of various classes and has the capability to distinguish unknown faults.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Materials Science, Multidisciplinary
Tingzhong Wang, Tingting Zhu, Lingli Zhu, Ping He
Summary: Fault diagnosis is crucial for the safe operation of machinery, and EMD-based methods are widely used for feature extraction. However, the scarcity of labeled samples hinders the application of intelligent classifiers in engineering.
Article
Engineering, Mechanical
Jianbo Yu, Siyuan Wang, Lu Wang, Yuanhang Sun
Summary: This paper proposes a digital twin-based signal fusion model to accurately identify gearbox faults at the signal level. The model can identify minor faults occurring in planetary gearboxes by fusing actual and virtual signals.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Chemical
Lijun Wang, Xiangyang Li, Da Xu, Shijuan Ai, Changxin Chen, Donglai Xu, Chaoge Wang
Summary: This paper proposes a bearing fault feature extraction method based on the EEMD algorithm and improved sparse representation. By separating harmonic components, EEMD decomposition, and constructing a learning dictionary, the impact component in the signal can be effectively extracted.
Article
Engineering, Multidisciplinary
Hua Li, Tao Liu, Xing Wu, Shaobo Li
Summary: This paper introduces an improved Ensemble Empirical Mode Decomposition (EEMD) method based on Improved Adaptive Resonance Technology (IART), which enhances the denoising capability of EEMD by optimizing the selection of optimal IMF and parameter optimization. Experimental results demonstrate that the improved EEMD outperforms other commonly used methods.
Article
Materials Science, Multidisciplinary
Fernando Pereira Mascarenhas, Alexandre Luiz Amarante Mesquita, Sergio de Souza Custodio Filho, Andre Luiz Amarante Mesquita
MATERIA-RIO DE JANEIRO
(2017)
Article
Thermodynamics
Andre Luiz Amarante Mesquita, Alexandre Luiz Amarante Mesquita, Felipe Coutinho Palheta, Jerson Rogerio Pinheiro Vaz, Marcus Vinicius Girao de Morais, Carmo Goncalves
ENERGY CONVERSION AND MANAGEMENT
(2014)
Article
Thermodynamics
Jerson R. P. Vaz, Alexandre L. A. Mesquita, Andre L. Amarante Mesquita, Taygoara Felamingo de Oliveira, Antonio Cesar Pinho Brasil Junior
ENERGY CONVERSION AND MANAGEMENT
(2019)
Article
Engineering, Mechanical
Sergio de Souza Custodio Filho, Helder Monteiro Santana, Jerson Rogerio Pinheiro Vaz, Leonardo Dantas Rodrigues, Alexandre Luiz Amarante Mesquita
JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING
(2020)
Article
Green & Sustainable Science & Technology
Jouberson L. R. Moreira, Alexandre L. A. Mesquita, Leonam F. Araujo, Marcos A. B. Galhardo, Jerson R. P. Vaz, Joao T. Pinho
Article
Energy & Fuels
Fabio Antonio do Nascimento Setubal, Sergio de Souza Custodio Filho, Newton Sure Soeiro, Alexandre Luiz Amarante Mesquita, Marcus Vinicius Alves Nunes
Summary: This paper proposes a force identification method that uses the response surface methodology (RSM) based on central composite design (CCD) in conjunction with a random forest regression algorithm. The method accurately predicts the location, amplitude, and frequency of forces applied to a structure using vibration acquisition information.
Review
Agricultural Engineering
Francisco J. S. Bandeira, Jose A. S. Ribeiro Junior, Alexandre L. A. Mesquita, Andre L. A. Mesquita, Ednildo A. Torres
Summary: The lack of access to energy hinders regional development in the state of Para, Brazil. Palm oil and cocoa processing waste biomasses are potential alternative energy sources that can be used in biomass gasification plants. A literature review on the energy characteristics of these waste biomasses indicated their suitability for gasification plants, enabling the development of the region.
ENGENHARIA AGRICOLA
(2023)
Article
Materials Science, Multidisciplinary
Mauro Sergio Vieira Matos, Jessica Caroline Bezerra Vale, Alexandre Luiz Amarante Mesquita
Summary: Discrete Element Method (DEM) is a tool used to simulate the flow of granular material. In this study, a reduced number of DEM simulations using Design of Experiments (DOE) and Artificial Neural Network (ANN) were proposed to determine the contact parameters for predicting the angle of repose of a cohesive iron ore.
MATERIA-RIO DE JANEIRO
(2022)
Article
Engineering, Multidisciplinary
Roger R. Da Silva, Ednelson Da S. Costa, Roberto C. L. De Oliveira, Alexandre L. A. Mesquita
JOURNAL OF ENGINEERING SCIENCE AND TECHNOLOGY
(2017)
Article
Multidisciplinary Sciences
J. C. M. Lobato, F. P. Mascarenhas, A. L. A. Mesquita, A. L. A. Mesquita
Proceedings Paper
Energy & Fuels
Joao Jose Albernaz Lopes, Jerson Rogerio Pinheiro Vaz, Alexandre Luiz Amarante Mesquita, Andre Luiz Amarante Mesquita, Claudio Jose Cavalcante Blanco
CLEAN, EFFICIENT AND AFFORDABLE ENERGY FOR A SUSTAINABLE FUTURE
(2015)