A5033308608- Machine Fault Diagnosis Techniques
- Gear and Bearing Dynamics Analysis
- Structural Health Monitoring Techniques
- Fault Detection and Control Systems
- Optical measurement and interference techniques
- Engineering Diagnostics and Reliability
- Ultrasonics and Acoustic Wave Propagation
- Adhesion, Friction, and Surface Interactions
- Metal and Thin Film Mechanics
- Mechanical stress and fatigue analysis
- Advanced Measurement and Detection Methods
- Force Microscopy Techniques and Applications
- Anomaly Detection Techniques and Applications
- Mechanical Behavior of Composites
- Thermography and Photoacoustic Techniques
- Advanced Battery Technologies Research
- Image and Signal Denoising Methods
- Advanced Measurement and Metrology Techniques
- Advanced machining processes and optimization
- Integrated Circuits and Semiconductor Failure Analysis
- Vibration and Dynamic Analysis
- Blind Source Separation Techniques
- Industrial Vision Systems and Defect Detection
- Bladed Disk Vibration Dynamics
- Advanced Surface Polishing Techniques
Xi'an Jiaotong University
2016-2025
Minzu University of China
2024-2025
State Grid Corporation of China (China)
2022-2025
Guangdong Academy of Medical Sciences
2018-2024
Southern Medical University
2023-2024
Guangdong Provincial People's Hospital
2022-2024
Tianjin University
2015-2024
Henan Normal University
2013-2024
Beijing Academy of Artificial Intelligence
2024
Zhuhai Institute of Advanced Technology
2024
Recent progress on intelligent fault diagnosis (IFD) has greatly depended deep representation learning and plenty of labeled data. However, machines often operate with various working conditions or the target task different distributions collected data used for training (the domain shift problem). Besides, newly test in are usually unlabeled, leading to unsupervised transfer based (UDTL-based) IFD problem. Although it achieved huge development, a standard open source code framework as well...
The authors introduce an iterative algorithm, called matching demodulation transform (MDT), to generate a time-frequency (TF) representation with satisfactory energy concentration. As opposed conventional TF analysis methods, this algorithm does not have devise ad-hoc parametric dictionary. Assuming the FM law of signal can be well characterized by determined mathematical model reasonable accuracy, MDT adopt partial and stepwise refinement strategy for investigating properties signal....
Vibration monitoring is one of the most effective ways for bearing fault diagnosis, and a challenge how to accurately estimate signals from noisy vibration signals. In this paper, nonconvex sparse regularization method diagnosis proposed based on generalized minimax-concave (GMC) penalty, which maintains convexity sparsity-regularized least squares cost function, thus global minimum can be solved by convex optimization algorithms. Furthermore, we introduce k-sparsity strategy adaptive...
Bearing faults are one of the most common inducements for machine failures. Therefore, it is very important to perform bearing fault diagnosis reliably and rapidly. However, fundamental but difficult extract impulses buried in heavy background noise diagnosis. In this paper, a novel adaptive enhanced sparse period-group lasso (AdaESPGL) algorithm proposed. The based on proposed group penalty, which promotes sparsity within across groups impulsive feature faults. Moreover, periodic prior...
This paper presents a new time-frequency (TF) analysis method called matching synchrosqueezing wavelet transform (MSWT) to signals with fast varying instantaneous frequency (IF). The original (SWT) can effectively improve the readability of TF representation (TFR) slowly IF. However, SWT still suffers from blurs for Moreover, variable operating conditions aeroengine always make vibration signal IF, especially when it comes significant speed changes, which results in obscure TFR monitoring....
Machinery fault diagnosis has progressed over the past decades with evolution of machineries in terms complexity and scale. High-value require condition monitoring to guarantee their designed functions performance throughout lifetime. Research on machinery Fault diagnostics grown rapidly recent years. This paper attempts summarize review R&D trends basic research field four main aspects: mechanism, sensor technique signal acquisition, processing, intelligent diagnostics. The discusses...
Artificial neural network (ANN) has achieved great success in mechanical fault diagnosis and been widely used. However, traditional ANN is still opaque terms of interpretability, making it difficult for users to understand trust the results. This paper proposes an interpretable provide high-performance credible The proposed mainly generated by unrolling nested iterative soft thresholding algorithm (NISTA) a sparse coding model named NISTA-Net. Therefore, architecture NISTA-Net clear...
Abstract Soil salinization is a global problem that limits agricultural productivity and sustainable development. As waste‐derived soil amendments, biochar organic fertilizer have garnered considerable attention for their ability to improve physicochemical properties contribution waste resource recovery. However, comparable data on the effects of fertilizers saline‐alkali soils are lacking. Therefore, we applied (B1: 5 t ha −1 year ; B2: 10 B3: 20 ) (OF1: 7.5 OF2: in Yellow River Delta...
In mechanical anomaly detection, algorithms with higher accuracy, such as those based on artificial neural networks, are frequently constructed black boxes, resulting in opaque interpretability architecture and low credibility results. This article proposes an adversarial algorithm unrolling network (AAU-Net) for interpretable detection. AAU-Net is a generative (GAN). Its generator, composed of encoder decoder, mainly produced by sparse coding model, which specially designed feature encoding...
Conventional time-frequency analysis (TFA) methods have played an important role in characterizing the TF pattern of nonstationary signals. In this paper, a new TFA algorithm, called matching demodulation transform (MDT), is introduced to extract highly oscillatory frequency modulation (FM) feature rotor rub-impact fault. When fault occurs system, vibration signals will present FM because periodic between stator and rotor. Through partial stepwise refinement procedure, represented with...
Blade tip timing (BTT) methods have been increasingly implemented for blade health monitoring (BHM). However, there are two drawbacks of current signal analysis preventing them from applying to online monitoring: first, requires the manual judgment resonance region, which is time-consuming. Second, existing BTT not suitable monitoring. The spectral-analysis-based method presents spectral aliasing, while computational complexity sparse-based usually high. In this article, we propose an...