A5101826214- Machine Fault Diagnosis Techniques
- Fault Detection and Control Systems
- Gear and Bearing Dynamics Analysis
- Engineering Diagnostics and Reliability
- Advanced Algorithms and Applications
- Industrial Technology and Control Systems
- Chaos control and synchronization
- Advanced Measurement and Detection Methods
- Advanced Battery Technologies Research
- Advanced Graph Neural Networks
- Advanced Sensor and Control Systems
- Advanced Decision-Making Techniques
- Traffic Prediction and Management Techniques
- Tribology and Lubrication Engineering
- Magnetic Bearings and Levitation Dynamics
- Oil and Gas Production Techniques
- Anomaly Detection Techniques and Applications
- Machine Learning in Bioinformatics
- Mass Spectrometry Techniques and Applications
- Financial Risk and Volatility Modeling
- Complex Systems and Time Series Analysis
- Advanced machining processes and optimization
- Human Mobility and Location-Based Analysis
- Color perception and design
- Iterative Methods for Nonlinear Equations
Zhengzhou University of Light Industry
2016-2025
Beijing University of Technology
2024
Peking University Sixth Hospital
2024
Peking University
2024
Emory University
2024
National Institute of Metrology
2022
The University of Sydney
2022
Shandong University of Science and Technology
2020
Zhengzhou University
2011-2012
Fudan University
2007
Convolutional neural network has been widely used in fault diagnosis of mechanical devices. In particular, a 2-D convolutional requires manual selection multiscale transformation to transform vibration signal into the structure. Although 1-D convolution can directly use for processing, it cannot make full nonlinear information space. order advantages and networks, this article, we develop one-dimension tandem with joint (1D–2D JCNN) rotating machinery diagnosis. More specifically, is...
Through systematic first-principles calculations, we found extraordinarily high piezoresistance coefficients in a pristine Si(111) nanowire. This stems from interplay between the presence of two surface states with different localizations and unusual relaxation. Lattice compression along axis causes switch light heavy and, subsequently, alters effective masses carriers. Fascinatingly, model calculations produced main features experimental data [R. R. He P. D. Yang, Nat. Nanotechnol. 1, 42...
Abstract: In the era of big data, there has been a surge in availability data containing rich spatial and temporal information, offering valuable insights into dynamic systems processes for applications such as weather forecasting, natural disaster management, intelligent transport systems, precision agriculture. Graph neural networks (GNNs) have emerged powerful tool modeling understanding with dependencies to each other dependencies. There is large amount existing work that focuses on...
Carbohydrate antigen 199 (CA199) is a serum biomarker which has certain value and significance in the diagnosis, prognosis, treatment, postoperative monitoring of cancer. In this study, lateral flow immunoassay based on europium (III) polystyrene time-resolved fluorescence microspheres (TRFM-based LFIA), integrated with portable reader, been successfully establish for rapid quantitative analysis CA199 human serum. Briefly, (TRFMs) were conjugated antibody I (Ab1) against as detection probes,...
As vital renewable energy devices, wind turbines suffer from gearbox failures due to harsh speed increasing operations. Therefore, the fault diagnosis is crucial for turbine maintenance with reducing economic costs. However, obtaining faulty data rather challenging, especially at early stage. For this reason, a sparse isolation encoding forest (SIEF) proposed aiming both anomaly detection and novel discrimination gearboxes. In present SIEF method, autoencoder first trained only normal obtain...
The battery system is one of the core technologies new energy electric vehicle, so frequent occurrence safety accidents seriously limits large-scale promotion and application. An innovative extreme learning machine optimized by genetic algorithm (GA-ELM)-based method proposed to estimate current status, which improves accuracy timeliness fault identification. It feasible in application vehicles. To ensure effectiveness signal, adopted using simple mean filter clean data with eliminate wrong...
Vibration signals are used to monitor the running state of mechanical equipment, but always suffer from a lot noise in acquisition process. In order eliminate interference as much possible, multilevel residual convolution autoencoder network based learning method (LN-MRSCAE) is proposed this paper. The LN-MRSCAE consists deep convolutional and residual, which module encodes decodes components, combining with obtain denoised signal. structure designed address gradient disappearance improve...
Bearing and reducer are the key transmission components of rotating machinery, timely accurate fault diagnosis is an important guarantee for safe operation machinery system. The collected signals bearing have typical non-stationary nonlinear characteristics. In order to make full use spatial temporal features contained in running signals, combining with bidirectional Long short-term memory network, this paper proposes a one-dimensional convolutional neural network model SAM-1DCNN-BiLSTM...
Induction motors, the key equipment for rotating machinery, are prone to compound faults, such as a broken rotor bars and bearing defects. It is difficult extract fault features identify faults from single signal because multiple overlap interfere with each other in fault. Since current signals vibration have different sensitivities multi-channel deep convolutional neural network (MC-DCNN) diagnosis model based on multi-source proposed this paper, which integrates original of motor. Dynamic...
Abstract Due to harsh and variable working conditions, the wind turbine gearbox may be damaged during operation, resulting in an extended downtime with reduced productivity economic loss. This calls for efficient fault diagnostics gearboxes. Commonly-used based on classical deep learning networks cannot guarantee good performance time series signals due weakness of feature extraction. For this reason, channel attention residual approach is proposed enhance extraction diagnosis gearboxes,...
In practical engineering applications, rotating machinery is often in a healthy state, with more samples and fewer multi-faults samples, which leads to be misdiagnosed. A finite element simulation model (FEM) proposed expand imbalanced sample data. However, there significant difference vibration response between the FEM data measured collected on machinery. Therefore, method based eigenvalue correction has been adopted, aiming narrow gap order solve problem of low accuracy imbalance fault...
When a gear fault is presented, the ensemble empirical decomposition (EEMD) method has been widely used in detection of and given good results. However, under signals from two vibration transducers which are installed different directions, data every sensor becomes necessary to obtain much more precise This paper suggests new feature frequency extraction approach for malfunctions diagnosis using full vector spectrum (FCS) EEMD method. The embodies model building multi-sensor fusion main...
As the plunger pump always works in a complicated environment and hydraulic cycle has an intrinsic fluid-structure interaction character, fault information is submerged noise disturbance impact signals. For diagnosis of bearings pump, optimum mode functions (IMFs) selection based envelope analysis was proposed. Firstly, Wigner-Ville distribution calculated for acquired vibration signals, resonance frequency brought on by obtained. Secondly, empirical decomposition (EMD) employed signal, IMFs...
A novel multifractal detrended fluctuation analysis based on improved empirical mode decomposition for the non-linear and non-stationary vibration signal of machinery is proposed. As intrinsic functions selection Kolmogorov–Smirnov test are utilized in detrending procedure, present approach quite available contaminated data sets. The employed to deal with undesired named pseudocomponents, two-sample works each function Gaussian noise detect noise-like functions. proposed method adaptive...
Autism spectrum disorder (ASD) is a neurodevelopmental condition characterized by increasing prevalence, diverse impairments, and unclear origins mechanisms. To gain better grasp of the ASD, it essential to identify most distinctive structural brain abnormalities in individuals with ASD.