Article
Automation & Control Systems
Xiangning Lu, Zhenzhi He, Hector Gutierrez, Guanglan Liao, Tielin Shi
Summary: This paper investigates a wavelet-based resolution enhancement technique to reconstruct a high-quality image for scanning acoustic microscopy (SAM) test and improve the detection accuracy of micro-defects in flip chip packages.
Article
Computer Science, Information Systems
Jisha Anu Jose, C. Sathish Kumar, S. Sureshkumar
Summary: Tuna fish is commercially important and its classification plays a crucial role in the fishing industry. This study presents an automated tuna classification system using textural macro features, achieving high accuracy and performance.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Engineering, Multidisciplinary
Yongjun Yang, Jiankang Zhong, Aisong Qin, Hanling Mao, Hanying Mao, Zhengfeng Huang, Xinxin Li, Yongchuan Lin
Summary: This paper proposes a group sparse tunable Q-factor wavelet transform (GS-TQWT) model for defect detection of long weld using ultrasonic guided wave (UGW). The model is able to extract defect echo features in the presence of dispersion, multi-mode, background noise, and structural noise. Simulation and experimental results verify the effectiveness of the GS-TQWT model for UGW weld defect detection.
Article
Automation & Control Systems
Jinde Zheng, Shijun Cao, Haiyang Pan, Qing Ni
Summary: This paper proposes a novel spectral envelope-based adaptive empirical Fourier decomposition (SEAEFD) method to improve the performance of AEFD in rolling bearing vibration signal analysis. SEAEFD optimizes the spectrum segmentation boundary to achieve adaptive segmentation and minimize noise components, allowing nonstationary signals to be decomposed into single-component signals with physical significance.
Article
Engineering, Electrical & Electronic
Qianyu Chen, Gemma Nicholson, Clive Roberts, Jiaqi Ye, Yihong Zhao
Summary: An improved method utilizing feature extraction and neural network classification is proposed for fault diagnosis in railway switch systems, extracting features based on nonstationary signal characteristics and utilizing an energy-based thresholding wavelets approach for dimension reduction.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Engineering, Multidisciplinary
Yanlong Pan, Cai Yi, Xinwu Song, Du Xu, Qiuyang Zhou, Yanping Li, Jianhui Lin
Summary: In order to accurately locate the resonant zone caused by bearing failure, a compound fault resonant band detection method is proposed. Firstly, a multi-level frequency band segmentation method based on L2/L1 norm of envelope spectrum is designed. Secondly, based on the results of frequency band segmentations, a health index ICS2 is introduced to guide the detection of fault resonant band.
Article
Automation & Control Systems
Zhenjin Shi, Xu Yang, Yueyang Li, Gang Yu
Summary: This paper introduces a novel wavelet-based TF analysis approach called WSET, which enhances the concentration of TF representation by extracting the wavelet transform TF spectrum of signals. The effectiveness of WSET is demonstrated through processing bat signals and verifying its capability in extracting failure features for rotor and rolling bearing malfunction diagnosis.
CONTROL ENGINEERING PRACTICE
(2021)
Review
Acoustics
Mohamad Hazwan Mohd Ghazali, Wan Rahiman
Summary: Vibration analysis is an effective method for monitoring machine health and performance, providing important information about machine condition and severity of failure. Various methods are available for analyzing machine vibration data, each with its own advantages and disadvantages. With the emergence of various sensors and communication devices in smart machines, vibration monitoring and diagnosing will face new challenges.
SHOCK AND VIBRATION
(2021)
Article
Multidisciplinary Sciences
Xiyuan Su, Changqing Cao, Xiaodong Zeng, Zhejun Feng, Jingshi Shen, Xu Yan, Zengyan Wu
Summary: This study proposes a fault diagnosis method based on deep belief networks and restricted Boltzmann machines, combined with grey wolf optimization algorithm, to improve the accuracy and efficiency of analog circuit fault diagnosis.
SCIENTIFIC REPORTS
(2021)
Article
Engineering, Multidisciplinary
Kun Zhang, Chaoyong Ma, Yonggang Xu, Peng Chen, Jianxi Du
Summary: The paper proposes an adaptive and concise empirical wavelet transform method combined with weighted unbiased autocorrelation for fault diagnosis of rolling bearings. Simulation signals and experimental results verify the effectiveness of the proposed method.
Article
Acoustics
Jian-Da Wu, Jun-Yuan Ke, Fan-Yu Shih, Wen-Jye Shyr
Summary: This study presents a fault diagnosis system for vehicle HVAC acoustic signal using various feature extractions in a deep learning neural network. DWT and WPT are proposed for fault diagnosis and low-frequency decomposition is used to improve performance. The study attempts to use wavelet packet conversion for feature extraction and achieves good fault diagnosis capabilities with deep neural networks.
JOURNAL OF LOW FREQUENCY NOISE VIBRATION AND ACTIVE CONTROL
(2022)
Article
Multidisciplinary Sciences
Dastan Ismail, Samah Mustafa
Summary: This paper presents a new computer-aided microwave monitoring system using a bank of new wavelet-matched filters to detect and localize brain stroke. The system exposes the head to microwave radiation and analyzes the perturbation in the microwave signals from the brain. A novel technique is applied to estimate the target response by removing the strong reflection from the air-skull interface, and its performance is compared with other techniques from literature. The study results show promising candidate signatures for computer-aided detection and localization of a stroke based on wavelet energy and Shannon wavelet entropy in the filtered microwave signal.
ROYAL SOCIETY OPEN SCIENCE
(2023)
Article
Acoustics
Xing Yuan, Huijie Zhang, Hui Liu
Summary: This study proposes an adaptive sparse representation (ASR) method based on TQWT, which integrates SCS and parameter optimization for fault feature extraction. Due to weak fault symptoms and background noise interference, a fault diagnosis strategy based on CWT and ASR is also investigated. Simulated and experimental results verify the effectiveness of the proposed method in accurately extracting weak impulse features from the noise environment.
SHOCK AND VIBRATION
(2022)
Article
Acoustics
Gang Yang, Yuqian Wei, HengKui Li
Summary: This paper proposes an intelligent fault diagnosis method based on Cross Wavelet Transform (XWT) and GoogleNet model for acoustic diagnosis of motor bearing faults in Electric Multiple Units (EMU) trains. The fault features are enhanced using signal processing and filtering, and deep learning is used for fault classification. Experimental results show that the method achieves high accuracy.
SHOCK AND VIBRATION
(2022)
Article
Automation & Control Systems
Hua Li, Tao Liu, Xing Wu, Qing Chen
Summary: The study introduces an enhanced SVD method E-SVD to address the issues with SVD, achieving superior signal reconstruction and noise reduction effects through the combination of ISVD and IWPT. Additionally, an evaluation indicator is introduced to assess the performance of the results.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Materials Science, Composites
Yafei Xu, Guanghui Lian, Hongkuan Zhou, Yushan Hou, Hao Zhang, Liuyang Zhang, Ruqiang Yan, Xuefeng Chen
Summary: This paper proposes an intelligent THz 3D characterization system based on the deep adversarial domain adaptation (DADA) strategy, which can automatically locate and image hidden delamination defects in composites under different operating conditions. Through adversarial learning, an unsupervised CNN-DADA model is established to address the domain shift problem between different THz datasets. Experiments demonstrate the superior generalization performance of the CNN-DADA model on different THz datasets, enabling high accuracy and resolution automatic localization and imaging of delamination defects even with significant distribution discrepancies, facilitating the deployment of data-driven THz intelligent characterization in practical industrial scenarios.
COMPOSITES SCIENCE AND TECHNOLOGY
(2023)
Article
Automation & Control Systems
Chenye Hu, Jingyao Wu, Chuang Sun, Ruqiang Yan, Xuefeng Chen
Summary: Recent research has made significant progress in intelligent fault diagnosis algorithms. However, the lack of labeled data in practical scenarios poses challenges for data annotation and increases the risk of overfitting, hindering industrial applications. To address this, this article proposes a framework that combines self-supervised learning on unlabeled data with supervised learning on few labeled data to enhance the learnable data's capacity. The framework includes a time-amplitude signal augmentation technique, interinstance transform-consistency learning for domain-invariant features, intratemporal relation matching to improve temporal discriminability, and an uncertainty-based dynamic weighting mechanism for multitask optimization stability. Experimental results on both open-source and self-designed datasets demonstrate the superiority of the proposed framework over other supervised and semi-supervised methods.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Automation & Control Systems
Zengkun Wang, Zhibo Yang, Guangrong Teng, Ruqiang Yan, Shaohua Tian, Haoqi Li, Jiahui Cao, Xuefeng Chen
Summary: MUSIC is widely used for frequency estimation but cannot estimate the amplitude. This article rederives MUSIC based on real signals and proposes an amplitude-identifiable MUSIC (Aid-MUSIC) approach to recover the amplitude information. Simulations and experiments demonstrate that Aid-MUSIC can simultaneously and stably extract the amplitude and frequency of asynchronous frequency components.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Mechanical
Zuogang Shang, Zhibin Zhao, Ruqiang Yan, Xuefeng Chen
Summary: Machine anomaly detection is the task of detecting abnormal machine conditions using collected monitoring data. Autoencoder (AE) based unsupervised anomaly detection (UAD) has gained increasing attention for mechanical equipment. However, the raw monitoring data may be polluted by abnormal data, and without effective regularization, AE-based methods would overfit these polluted data. To address this issue, the core loss is designed to perform AE-based UAD in a model-agnostic and end-to-end manner under data pollution.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Mechanical
Wengang Xu, Zhiying Wang, Zheng Zhou, Chuang Sun, Junhui Zhang, Ruqiang Yan, Xuefeng Chen
Summary: This paper proposes a new pressure pulsation model for external gear pumps by considering lateral clearance and manufacturing error. The lateral clearance model is established by measuring the maximum roughness peak of the lateral bushing surface, and the manufacturing error model is constructed based on the errors of the master-slave gear. The robustness of the new model is verified under different working conditions, and the influence of the lateral clearance model and manufacturing error model on pressure pulsation is revealed.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Mechanical
Nan Shao, Zhuo Chen, Xian Wang, Chengxin Zhang, Jiawen Xu, Xiaosu Xu, Ruqiang Yan
Summary: In this article, a dual-beam piezoelectric energy harvester with an annular potential energy function is proposed to harvest vibration energy over a wide spectrum. The harvester consists of two orthogonal conventional piezoelectric cantilevers coupled by repulsive magnetic force. Analytical and numerical analysis shows that a new annular potential energy function can be built with proper configuration. The proposed annular stable harvester demonstrates a bandwidth of 3.9 Hz and a voltage output performance 3.01 times better than that of a conventional bistable harvester under 3 m/s(2) excitations. The nonlinear dynamics of the proposed harvester are analyzed in detail.
NONLINEAR DYNAMICS
(2023)
Article
Automation & Control Systems
Yongyi Chen, Dan Zhang, Kunpeng Zhu, Ruqiang Yan
Summary: In this article, a new activation function called Parameter-free Adaptively Swish (PASwish) is developed to improve the flexibility and generalization ability of deep learning frameworks in industrial scenarios with changing operating conditions. Additionally, deep parameter-free cosine networks with PASwish are proposed to adjust network weights based on domain-specific and domain-invariant features. The proposed method achieves better performance in cross-domain fault diagnosis compared to current studies, with an average accuracy of 95.16% (+/- 1.76%) on 72 transfer tasks.
IEEE-ASME TRANSACTIONS ON MECHATRONICS
(2023)
Article
Engineering, Industrial
Sinan Li, Tianfu Li, Chuang Sun, Ruqiang Yan, Xuefeng Chen
Summary: This article proposes a novel Multilayer Grad-CAM (MLG-CAM) as a tool to explain deep neural networks, improving network explainability. Three indicators are defined to quantify the explainability of deep neural networks. Experimental results demonstrate that MLG-CAM not only highlights cyclostationary impulses in the time domain but also emphasizes fault characteristic frequencies in the frequency domain. These results indicate that MLG-CAM is an effective way to explain deep neural networks and build trust in networks.
JOURNAL OF MANUFACTURING SYSTEMS
(2023)
Article
Engineering, Mechanical
Zihao Lei, Ping Zhang, Yuejian Chen, Ke Feng, Guangrui Wen, Zheng Liu, Ruqiang Yan, Xuefeng Chen, Chunsheng Yang
Summary: In recent years, intelligent fault diagnosis based on deep learning has made significant progress in feature representation. However, the lack of high-quality data, especially under severe fault states, and variable operating conditions have limited its industrial application. To address this issue, a novel prior knowledge-embedded meta-transfer learning (PKEMTL) method is proposed for few-shot fault diagnosis. The method focuses on improving adaptability in few-shot fault diagnosis under variable operating conditions by employing a metric-based meta-learning framework and embedding prior knowledge. Experimental results on two case studies demonstrate the effectiveness and superiority of the proposed method.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Mechanical
Qisheng Wang, Xin Lin, Xianyin Duan, Ruqiang Yan, Jerry Ying Hsi Fuh, Kunpeng Zhu
Summary: Laser powder bed fusion (L-PBF) is a metal additive manufacturing process with potential for high-performance metal components. However, stability and repeatability issues limit its industrial application. To ensure product quality, process monitoring and control are crucial. A new motion feature is extracted and a classification model is constructed to identify the changing melt pool states during the L-PBF process. The Gaussian process classification (GPC) model achieves better recognition results compared to other models, with an overall recognition rate of 87.1%.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Yongyi Chen, Dan Zhang, Ruqiang Yan
Summary: Rolling bearings are important components of rotating machinery and typically operate under variable speed and load conditions. Vibration signals in the same health state exhibit significant differences due to changes in operating conditions. To address fixed non-linear transformations in existing deep learning methods for cross-domain fault diagnosis, a new activation function called parameter-free adaptively rectified linear units (PfAReLU) is proposed. PfAReLU performs adaptive non-linear transformations based on input data and effectively captures fault features of vibration signals under different operating conditions. Furthermore, a deep parameter-free reconstruction-classification network with PfAReLU (DPRCN-PfAReLU) is constructed, which outperforms other methods for cross-domain fault diagnosis in real experiment studies under nine different operating conditions.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Sinan Li, Tianfu Li, Chuang Sun, Xuefeng Chen, Ruqiang Yan
Summary: Proposed an interpretable wavelet packet kernel-constrained convolutional network (WPConvNet) for noise-robust fault diagnosis, which combines the feature extraction ability of wavelet bases and the learning ability of convolutional kernels. The proposed architecture outperforms other diagnosis models in terms of interpretability and noise robustness.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Xi Chen, Hui Wang, Siliang Lu, Ruqiang Yan
Summary: This article proposes a new method for bearing remaining useful life (RUL) prediction, called RUL-FLTNP, based on federated learning (FL) and Taylor-expansion network pruning. Through collaborative training between a central server and multiple clients, trimmed models are aggregated using the federated averaging (FedAvg) algorithm, offering a promising solution for prognostic problems in data privacy-preserving scenarios.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Automation & Control Systems
Tianfu Li, Chuang Sun, Olga Fink, Yuangui Yang, Xuefeng Chen, Ruqiang Yan
Summary: This article proposes a filter-informed spectral graph wavelet network (SGWN) for intelligent fault diagnosis. SGWN utilizes the spectral graph wavelet convolutional (SGWConv) layer to simultaneously extract low-pass and band-pass features, thereby preventing the over-smoothing problem caused by long-range low-pass filtering. Experimental results on collected solenoid valve dataset and aero-engine intershaft bearing dataset demonstrate that SGWN outperforms comparative methods in terms of diagnostic accuracy and prevention of over-smoothing, and its extracted features are interpretable with domain knowledge.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Engineering, Mechanical
Busra Duran, Jerome Cavoret, David Philippon, Fabrice Ville, Arnaud Ruellan, Frank Berens
Summary: This study analyzes the changes in the physicochemical properties and tribological performances of gear transmission oils during field operation, finding differences from traditional engine oils.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Baocheng Liu, Hongsheng Chen, Jun Zhou, Jing Wang, Wenxian Wang, Xiaochun Chen, Sanxiao Xi
Summary: This study used fast hot pressing sintering to fabricate WC/AlCoCrFeNi2.1 metal matrix composites (MMCs). It was found that the addition of reinforced particles increased the microhardness, nanoindentation and wear resistance of the MMCs. During frictional processes, an oxide film formed, providing material protection, enhancing stability and reducing friction-induced losses.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Pradip Kumar Verma, Alok Singh
Summary: This study investigates the mechanical properties and wear resistance of CoMoMnNiV high entropy alloy reinforced aluminium matrix composite processed through stir-squeeze casting assisted with an ultrasonic transducer. The results show significant improvements in mechanical properties and wear resistance, with the composite containing 8 wt% HEA demonstrating the highest resistance to wear. Optical microscopy, SEM, and an optical profilometer were used for a thorough examination of the microstructure and worn surface.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Zhenghai Yang, Yingjian Song, Jinlong Jiao, Wenbo Li, Bao Shangguan, Yongzhen Zhang
Summary: This study investigated the friction, wear properties, and current-carrying properties of copper-graphite composites paired with brass C28000. The results showed that the current-carrying properties of the composite materials were excellent, but their wear rate was the main limiting factor. Furthermore, an increase in the thickness of the graphite layer led to an improvement in the uniformity of damage.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Moustafa Mahmoud Yousry Zaghloul, Karen Steel, Martin Veidt, Michael T. Heitzmann
Summary: This research evaluates and compares the impact of different material types on the tribological characteristics of Polyamide 6 composites, and finds that glass fiber-reinforced Polyamide 6 exhibits better friction and wear performance under high-pressure velocity factors.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Shaoqing Qin, Lida Zhu
Summary: In this paper, the surface and subsurface damage of laser assisted grinding CrCoNi medium entropy alloys were investigated using molecular dynamics simulations. The results showed that the application of laser energy can reduce cutting forces and minimize subsurface damage.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Kaikui Zheng, Youxi Lin, Tingzheng Lai, Chenghui Gao, Ming Liu, Zhiying Ren
Summary: The study investigated the use of waste foundry resin-bonded sand as a substitute for copper in resin-based brake material. It found that the waste sand was more favorable for improving the overall friction and wear properties of the material compared to copper. Waste sand benefited the material by forming a friction layer, leading to increased friction coefficient and stability. Brake material with 10-15% waste sand showed excellent heat-fade resistance.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Dayang Li, Fanhao Zhou, Yutong Gao, Kun Yang, Huimin Gao
Summary: This article introduces a continuous prediction model based on deep learning for predicting the power output of steam turbines. The model uses long short term memory (LSTM) method to develop a trend prediction model and optimizes the prediction model through feature selection method. Experimental results show that the model outperforms other models in terms of prediction performance.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Tomohiro Toyoda, Ryo Yasuike, Toshihiro Noda
Summary: In this study, a elasto-plastic constitutive model of friction incorporating the concept of superloading surface was developed based on the subloading friction model. The proposed model achieves a smooth transition of friction by describing the evolution rule of structure, treating the state with static friction coefficient larger than kinetic friction coefficient as the bulkiness of structure. The positive definiteness of the plastic multiplier, loading condition, and material parameters were derived, and the validity of the proposed model in accordance with the subloading-friction model was confirmed through a stick-slip simulation of a mass-spring system.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
P. Balaji, B. Surya Rajan, K. Sathickbasha, P. Baskara Sethupathi, Deviga Magadevan
Summary: This study emphasizes the importance of using a variety of solid lubricants with different oxidation temperature regimes to enhance the tribological performance of brake pads.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Jian Ma, Yancong Liu, Javad Mostaghimi, Na Zhang
Summary: This paper investigates the influence of preparation strategies on the lubrication properties of surface textures. Three laser scanning strategies are proposed to achieve a sinusoidal textured surface, and the evolution of surface structure and chemical composition is discussed. The findings show that ridge structures enhance anti-wear properties but also increase the friction coefficient. However, the oil cover preparation method prevents the formation of ridges and improves wettability.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Mohammad Roostaei, Arvin Taghizadeh Tabrizi, Hossein Aghajani
Summary: In this research, the Al2O3/MoS2 nanocomposite coating layer was successfully applied on the surface of Ti-6Al-4 V alloy. The relation between the surface characteristics and wear resistance of the coating was studied using atomic force microscopy analysis and pin-on-disk wear test method. The results showed that the nanocomposite coating significantly reduced the wear rate and provided an equation to calculate the Lancaster coefficient.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Musa Bilgin, Sener Karabulut, Halil Karakoc, Yunus Kayir, Murat Sarikaya
Summary: This study investigates various methods to improve the machinability efficiency of Inconel 718 alloy while considering their effect on microstructural properties. The results show that hot+PMQL, hot+SiCNMQL, and hot+Al2O3-NMQL contribute significantly to the improvement of machinability characteristics. The EBSD analysis also reveals that a limited area is affected by heat in the hot machining environment and that the removal of the heated layer during milling process helps preserve the microstructure.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Q. Gao, Y. Fan, Y. G. Wu, J. L. Liu, J. Wang, L. Li
Summary: Fretting wear significantly affects the hysteresis behavior of the contact surface and leads to joint degradation. This study investigates the influence of harmonic normal force on the evolution of interface morphology and contact parameters with fretting wear. The results show that the harmonic normal force can significantly influence the hysteresis loop and the energy dissipation distribution on the contact surface.
TRIBOLOGY INTERNATIONAL
(2024)
Article
Engineering, Mechanical
Benjamin Weiland, Floriane Leclinche, Anis Kaci, Brigitte Camillieri, Betty Lemaire-Semail, Marie -Ange Bueno
Summary: This study presents a systematic approach to generating control signals for a tactile simulator that simulate the touch of textile fabrics. By using a friction modulation tactile surface and acquiring forces from real surfaces with artificial finger mimicking fingerprints, control signals are generated and processed in the frequency domain before sending them to the tactile stimulator. The study focuses on the potential benefits of incorporating fingerprint information in fabric simulations to achieve a more realistic tactile perception. A sensory analysis with 36 participants using the generated control signals showed better discrimination without fingerprint information.
TRIBOLOGY INTERNATIONAL
(2024)
