Related references
Note: Only part of the references are listed.
Article
Engineering, Multidisciplinary
Liang Meng et al.
Summary: To address the difficulty of fault feature extraction and low accuracy of pattern recognition in gearbox fault diagnosis, a differential continuous wavelet transform-parallel multi-block fusion residual network method is proposed. The method improves time-frequency feature resolution by applying continuous wavelet transform after the first-order difference. It utilizes parallel fusion residual blocks and an attentional feature fusion layer to enhance feature learning and achieve effective fault information fusion. Experimental results demonstrate superior diagnostic performance compared to other methods in bearing and gearbox gear faults.
Article
Automation & Control Systems
Xiaoli Tang et al.
Summary: Helical gearboxes are crucial for power transmission in industrial applications, but they are prone to various faults due to long-term and heavy-duty operations. Conventional measurements for gearbox fault diagnosis include lubricant analysis, vibration, airborne acoustics, thermal images, and electrical signals. However, relying on a single measurement domain may lead to unreliable diagnosis, especially in harsh environments. This article proposes a Compressive Sensing-based Dual-Channel Convolutional Neural Network method that utilizes non-contact measurements (thermal images and acoustic signals) to accurately diagnose gearbox faults.
Article
Engineering, Mechanical
Surinder Kumar et al.
Summary: In order to detect gear faults in a worm gearbox, a fault diagnosis scheme has been proposed. The scheme utilizes L-moment ratios as condition indicators and extracts information about the fault location from the frequency sidebands at higher harmonics of the gear meshing frequency in the vibration frequency spectrums. The results show that the proposed scheme can effectively classify different health conditions of the worm gearbox and achieve a higher fault classification accuracy compared to conventional indicators.
JOURNAL OF VIBRATION ENGINEERING & TECHNOLOGIES
(2023)
Article
Automation & Control Systems
Linshan Jia et al.
Summary: This paper proposes a Gramian-based noise reduction strategy and a denoising convolutional neural network model for bearing fault diagnosis. Experimental results show that this method can effectively reduce noise in vibrational signals and improve classification performance.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Mechanical
Zhenghong Wu et al.
Summary: This paper proposes a knowledge dynamic matching unit-guided multi-source domain adaptation network for bearing fault diagnosis, which can dynamically adapt its model parameters to input samples. The network consists of a feature extractor with the knowledge dynamic matching unit and two classifiers with attention mechanism. Experimental results demonstrate that KDMUMDAN achieves superior bearing fault diagnosis ability across multiple domains.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Mechanical
Josef Koutsoupakis et al.
Summary: This paper proposes a CM scheme for mechanical systems using a CNN trained with simulated data. The method shows potential for damage identification in real systems where experimental measurements are difficult to acquire.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Haoran Wen et al.
Summary: This paper presents a novel deep clustering network, c-GCN-MAL, for intelligent fault diagnosis of various bearings. The network utilizes autoencoder and graph convolutional network to extract multiple representations of data, and defines new loss functions to enhance its clustering and transfer ability. Experimental results show that the proposed network achieves higher accuracy and stable results for cross-domain fault diagnosis of bearings.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Review
Computer Science, Artificial Intelligence
Onur Surucu et al.
Summary: In modern industry, the quality of maintenance directly influences equipment's operational uptime and efficiency. Predictive maintenance, based on monitoring the condition of machinery, can minimize machine downtime and potential losses. However, the efficacy of predictive maintenance relies on selecting the appropriate data processing method and machine learning model. Existing surveys do not comprehensively inform users or evaluate the quality of proposed monitoring systems. This survey reviews the recent literature on machine learning-driven condition monitoring systems and provides insights into successful intelligent monitoring systems.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Engineering, Mechanical
Hongchuang Tan et al.
Summary: Due to the complexity of rolling bearing service conditions, vibration signals exhibit non-linear characteristics, making it challenging to extract fault features using single-scale feature extraction techniques. A new technique called multiscale symbolic dynamic entropy (MSDE) has been applied to fault diagnosis in machinery, but it has limitations such as poor stability, large errors, and even loss of information. To address these limitations, a novel sensible multiscale symbol dynamic entropy (SMSDE) method was proposed.
INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES
(2023)
Article
Thermodynamics
Mohamed Abdel-Basset et al.
Summary: The paper introduces a new metaheuristic algorithm, MIGTO, which utilizes EGAMM and GMS techniques to improve its performance. Experimental results demonstrate that MIGTO excels in extracting parameters of various PV models.
ENERGY CONVERSION AND MANAGEMENT
(2022)
Article
Automation & Control Systems
Shengnan Tang et al.
Summary: This article investigates the problem of fault diagnosis in hydraulic pumps, using a deep learning method for fault identification and introducing the Bayesian optimization algorithm for selecting hyperparameters. By comparing with traditional methods, the results show that CNN-BO can accurately achieve intelligent fault diagnosis of hydraulic pumps.
Article
Engineering, Multidisciplinary
Govind Vashishtha et al.
Summary: A deep learning-based defect identification scheme for the Pelton wheel was developed, achieving 100% accuracy using TVF-EMD optimization and CNN model. The proposed AGWO algorithm was tested on benchmark functions and Wilcoxon test, showing efficiency and superiority. The CNN classifier outperformed other learning models in the comparison.
Article
Acoustics
Yong Zhu et al.
Summary: Hydraulic piston pumps are critical components in fluid power systems and their health status is crucial for the safety and reliability of mechanical equipment. This research introduces the particle swarm optimization algorithm to automatically select the hyperparameters of a diagnosis model and constructs a convolutional neural network model optimized by PSO. The proposed PSO-LeNet model, based on acoustic signals, identifies five common states of a hydraulic piston pump with high accuracy and stability compared to other CNN models.
Article
Engineering, Multidisciplinary
Govind Vashishtha et al.
Summary: A novel bearing fault identification scheme using deep learning is proposed in this work. The raw vibration signal is processed through a time-varying filter-based empirical mode decomposition (TVF-EMD) to extract sensitive features representing different bearing conditions. These features are used to build fuzzy-based classification models. The results show that the developed method outperforms other classification models in terms of performance and computational time.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2022)
Article
Mathematics
Jayashree Piri et al.
Summary: This article introduces a novel discrete artificial gorilla troop optimization (DAGTO) technique for feature selection tasks in the healthcare sector. The presented method is proven to be superior in identifying relevant features and is demonstrated to be effective in real-world applications through a case study with COVID-19 samples.
Article
Automation & Control Systems
Yun Gao et al.
Summary: The study proposed a method using numerical simulation and generative adversarial network to augment gear fault samples, successfully detecting gear faults with practicality and effectiveness.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2022)
Article
Engineering, Mechanical
Govind Vashishtha et al.
Summary: This paper proposes a novel unsupervised learning method called general normalized sparse filtering (GNSF) based on Wasserstein distance with maximum mean discrepancy (MMD) for fault diagnosis. Experimental results demonstrate that the proposed method achieves high accuracy and efficiency in fault diagnosis of centrifugal pump and Pelton wheel vibration data.
JOURNAL OF VIBRATION ENGINEERING & TECHNOLOGIES
(2022)
Article
Computer Science, Artificial Intelligence
Yunyang Zhang et al.
Summary: This paper proposes an improved slime mold algorithm (DQOBLSMA) with a dynamic quantum rotation gate and opposition-based learning. Experimental results demonstrate the superiority of the proposed algorithm in convergence speed, convergence accuracy, and reliability.
Article
Acoustics
Yong Zhu et al.
Summary: The study successfully implemented intelligent fault diagnosis of hydraulic piston pump by constructing the PSO-Improve-CNN diagnostic model using an improved LeNet-5 model and particle swarm optimization. The improved model outperforms traditional models in terms of recognition accuracy and performance, exhibiting higher accuracy and robustness.
Article
Engineering, Multidisciplinary
Surinder Kumar et al.
Summary: A worm gearbox is a slow speed gear arrangement that can greatly reduce velocity. Signal processing techniques can be used to extract weak fault features and identify fault frequencies with high accuracy, up to 99.27%.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2021)
Article
Engineering, Multidisciplinary
Govind Vashishtha et al.
Summary: An artificial intelligence technique has been studied for automatic detection of bucket faults in the Pelton wheel. The Levy flight mutated genetic algorithm is implemented to optimize support vector machine parameters and tested against different optimization benchmark functions. The SVM model, trained with optimized parameters, achieves high recognition rates for identifying various defects.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2021)
Article
Automation & Control Systems
Qian Shi et al.
Summary: This article presents a research on steering actuator fault diagnosis for automated vehicles using model-based support vector machine classification, proposing an improved algorithm. Experimental results show the superiority of the proposed algorithm in classification over existing methods.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2021)
Article
Green & Sustainable Science & Technology
Ahmed Ginidi et al.
Summary: The article presents a novel approach to parameter extraction for solar photovoltaic systems using Gorilla Troops Optimization (GTO) technique, showing its effectiveness through numerical analysis of PV models. Comparison with other algorithms in 2020 demonstrates the superiority of GTO in terms of standard deviations of fitness values. Validation of GTO for diverse operating conditions of KC200GT module further confirms its efficacy.
Article
Engineering, Electrical & Electronic
Anil Kumar et al.
Summary: This study introduces a novel convolutional neural network (NCNN) for effectively identifying bearing defects. By modifying the cost function of the convolutional neural network to include additional sparsity cost, the network is able to effectively learn features from small samples. Experimental results validate the effectiveness of the proposed method.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Review
Engineering, Mechanical
Yaguo Lei et al.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2020)
Article
Automation & Control Systems
Yun Gao et al.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2020)
Article
Computer Science, Artificial Intelligence
Bo Zhao et al.
KNOWLEDGE-BASED SYSTEMS
(2020)
Review
Engineering, Multidisciplinary
Anil Kumar et al.
Article
Engineering, Multidisciplinary
Jingbo Gai et al.
Article
Computer Science, Artificial Intelligence
Jie Wu et al.
EXPERT SYSTEMS WITH APPLICATIONS
(2020)
Article
Computer Science, Artificial Intelligence
Zhiyu Zhu et al.
Review
Materials Science, Characterization & Testing
Anil Kumar et al.
JOURNAL OF NONDESTRUCTIVE EVALUATION
(2019)
Review
Energy & Fuels
Mohammadreza Tahan et al.
