A5047138391- Machine Fault Diagnosis Techniques
- Reliability and Maintenance Optimization
- Advanced Manufacturing and Logistics Optimization
- Manufacturing Process and Optimization
- Scheduling and Optimization Algorithms
- Engineering Diagnostics and Reliability
- Assembly Line Balancing Optimization
- Fault Detection and Control Systems
- Gear and Bearing Dynamics Analysis
- Advanced Statistical Process Monitoring
- Business Process Modeling and Analysis
- Non-Destructive Testing Techniques
- Service-Oriented Architecture and Web Services
- Quality and Safety in Healthcare
- Industrial Vision Systems and Defect Detection
- Structural Health Monitoring Techniques
- Advanced machining processes and optimization
- Structural Integrity and Reliability Analysis
- Ultrasonics and Acoustic Wave Propagation
- Advanced Battery Technologies Research
- Product Development and Customization
- Energy Efficient Wireless Sensor Networks
- Probabilistic and Robust Engineering Design
- Petri Nets in System Modeling
- Mechanical Failure Analysis and Simulation
Huazhong University of Science and Technology
2016-2025
China University of Mining and Technology
2024
Guangdong Institute of Intelligent Manufacturing
2020
State Key Laboratory of Digital Manufacturing Equipment and Technology
2012
General Hospital of Guangzhou Military Command
2012
Wuhan University of Technology
2011
Wuhan University of Science and Technology
2010
Xi'an Jiaotong University
2004-2009
Jingdong (China)
2004
Machine health monitoring is of great importance in industrial informatics field. Recently, deep learning methods applied to machine have been proven effective. However, the existing face enormous difficulties extracting heterogeneous features indicating variation until failure and revealing inherent high-dimensional massive signals, which affect accuracy efficiency monitoring. In this paper, a novel data-driven method proposed using adaptive kernel spectral clustering (AKSC) long short-term...
Remaining useful life (RUL) prognosis is of great significance to improve the reliability, availability, and maintenance cost an industrial equipment. Traditional machine learning method not fit for dealing with time series signals has low generalization stability in prognostic. In this article, a novel ensemble long short-term memory neural network (ELSTMNN) model RUL prediction proposed enhance accuracy adaptive abilities under different prognostic scenarios. The ELSTMNN contains networks...
Remaining useful life (RUL) prediction is a key solution to improve the reliability, availability, and maintainability of engineering systems. Long short-term memory (LSTM) convolution neural networks (CNN) are current hotspots in field RUL prediction. However, LSTM-based prognostic approach has slow loop step process large-scale time-series data since dependence processing at each time on output previous limits parallelism, CNN-based not fit for although it can parallel. In this article,...
Remaining useful life (RUL) prediction of aircraft engine (AE) is great importance to improve its reliability and availability, reduce maintenance costs. This article proposes a novel deep bidirectional recurrent neural networks (DBRNNs) ensemble method for the RUL AEs. In this method, several kinds DBRNNs with different neuron structures are built extract hidden features from sensory data. A new customized loss function designed evaluate performance DBRNNs, series values obtained. Then,...
Accurate health evaluation is crucial to reliable operation of complex degradation systems. Although traditional machine learning methods such as artificial neural network (ANN) and support vector (SVM) have been used widely, state assessment schemes based on a single classification model still suffer from low multiclass efficiency, high variance, deviation. To solve these problems, this article proposes novel method stacking ensemble generalized (GMSVM) algorithm. The proposed framework...
Abstract Machine line is a type of manufacturing system in which machines are connected series or parallel. It significant to ensure the reliability as well reduce total cost maintenance and failure losses programs such systems. Cost‐based selective decision‐making, best method for selected group machine presented under limited durations. Fault costs single different actions i.e. minimal repair, preventive overhaul on fault rate calculated. An algorithm combining heuristic rules tabu search...
To solve the problems of serious backlog work-in-process (WIP) and high production cost in manufacturing workshop core components an aerospace engine, this paper proposes a two-stage simulation optimization method based on Allocated Clearing Function-Genetic Algorithm (ACF-GA), aiming to optimize processing process. Firstly, discrete event model is established according existing data factory, warmed up historical input data. In process, input-output loads each work center are collected unit...