A5100774955- Machine Fault Diagnosis Techniques
- Fault Detection and Control Systems
- Gear and Bearing Dynamics Analysis
- Engineering Diagnostics and Reliability
- Reliability and Maintenance Optimization
- Structural Health Monitoring Techniques
- Advanced Computational Techniques and Applications
- Fatigue and fracture mechanics
- Advanced machining processes and optimization
- Advanced Algorithms and Applications
- Adaptive Control of Nonlinear Systems
- Graphite, nuclear technology, radiation studies
- Aerospace Engineering and Energy Systems
- Geological Modeling and Analysis
- Simulation and Modeling Applications
- Electrohydrodynamics and Fluid Dynamics
- Vehicle Noise and Vibration Control
- Power Systems and Technologies
- Mobile Agent-Based Network Management
- Power Line Inspection Robots
- Adaptive optics and wavefront sensing
- IoT and Edge/Fog Computing
- Tribology and Lubrication Engineering
- Advanced Measurement and Metrology Techniques
- Fluid Dynamics and Vibration Analysis
Zhejiang Sci-Tech University
2014-2024
Xi'an Jiaotong University
2012-2021
Imperial College London
2021
Aviation Industry Corporation of China (China)
2021
Nanjing Institute of Mechatronic Technology
2021
Zhejiang University
2019
China Electronics Technology Group Corporation
2016
Baoding University
2014
Northeast Petroleum University
2012-2013
University of Petroleum
2013
The key challenge of intelligent fault diagnosis is to develop features that can distinguish different categories. Because the unique properties mechanical data, predetermined based on prior knowledge are usually used as inputs for classification. However, proper selection often requires expertise and becomes more difficult time consuming when volume data increases. In this paper, a novel deep learning network (LiftingNet) proposed learn adaptively from raw without knowledge. Inspired by...
Intelligent fault detection has been widely used for feature extraction and classification. However, various complex signal processing methods are adopted in many researches. This article presents a novel deep learning network via shunt-wound restricted Boltzmann machines (RBMs) with layerwise to learn the features from big raw vibration signals directly. The consists of split layer, predict update dephasing softmax layer. RBMs both layer improve ability ensure effective training network....
Abstract The fracture toughness of ductile cast iron for large-scale spent nuclear fuel transportation containments was investigated and statistically analyzed by the methodology Weibull distribution. data specimens at different locations (top nesting parts) were obtained conducting tests. two-parameter distribution utilized statistical analysis to verify applicability method specific domestic material, also determine satisfaction requirement vessels with a large cross-section in ultimate...
Machine learning approaches work well with large labeled data sets. In the field of fault diagnosis, need to analyze amounts provides a foundation for machine be applied. However, due changes rotation speed, load, and other factors, sets will different distributions. Therefore, under conditions features feature distributions, it is great importance improve generalization ability model. this paper, deep convolutional neural network principle parameter transfer are used extract parameters...
The generation of homogeneous dielectric barrier discharge (DBD) in a 8-mm large-gap Ar at atmospheric pressure by employing microsecond pulsed power supply excitation is presented. electrical and optical characteristics the DBD are experimentally studied, comparison with its sinusoidal counterpart improvement stability using water electrodes also investigated. Results show that, as compared filamentary-mode discharges excitation, stable higher energy efficiency shown to be generated over...
Abstract Sharp corners usually are used on glass contours to meet the highly increasing demand for personalized products, but they result in a broken wheel center toolpath edge grinding. To ensure that whole is of G1 continuity and grinding depth controllable at corners, transition generation method based velocity-blending algorithm proposed. Taking into consideration, sharp-corner process planned, introduced. With constraints, such as traverse displacement depth, generated with three-phase...
The Internet of Things has been regarded as an extension the and can bring significant changes to our world. A large variety IoT applications have greatly facilitated daily lives, such sharing bicycles, power banks, for example. These optimize resource allocation thus enhance efficiency society. This article presents a novel application which aims protect everyday direct-drinking water in schools, via blockchain. system, developed by team from Zhejiang University CMCC (China Mobile...
This paper describes the simulated annealing algorithm and TSP problems, analyze applicability of to solve problem, takes China urban travel questions as an examples vertified validity model, results showed that when number iterations reached at 4000,it will obtain optimal solution.
Ensemble local mean decomposition has been gradually introduced into mechanical vibration signal processing due to its excellent performance in electroencephalogram analysis. However, an unsatisfactory problem is that ensemble cannot effectively process signals of complex system the constraints moving average. The average time-consuming and inaccurate Therefore, improved method called C-ELMD with modified envelope algorithm based on cubic trigonometric cardinal spline interpolation proposed...
This paper puts forward a kind of evolutionary algorithm and the neural network combining with new method optimization hidden layer nodes number particle swarm network. The BP technology is more mature method, but there are easy to fall into local minimum value, unable accurately determine network, disadvantages such as slow convergence speed. node (HPSO network) (PSO) an important goal, each weights closed value together, common goal.