A5021724203- Manufacturing Process and Optimization
- Machine Fault Diagnosis Techniques
- Advanced machining processes and optimization
- Advanced Measurement and Metrology Techniques
- Non-Destructive Testing Techniques
- Industrial Vision Systems and Defect Detection
- Fault Detection and Control Systems
- Gear and Bearing Dynamics Analysis
- Advanced Surface Polishing Techniques
- Structural Integrity and Reliability Analysis
- Transportation and Mobility Innovations
- 3D Surveying and Cultural Heritage
- Reliability and Maintenance Optimization
- 3D Shape Modeling and Analysis
- Advanced Statistical Process Monitoring
- Injection Molding Process and Properties
- Mechanical stress and fatigue analysis
- Imbalanced Data Classification Techniques
- Advanced Battery Technologies Research
- Scientific Measurement and Uncertainty Evaluation
- Domain Adaptation and Few-Shot Learning
- Engineering Diagnostics and Reliability
- Electric Vehicles and Infrastructure
Shanghai Jiao Tong University
2018-2023
The effective remaining useful life (RUL) prediction of rolling bearings could guarantee mechanical equipment reliability and stability. hybrid physical data-driven prognosis model (HPDM) is recently receiving increasing attention. However, HPDM approaches suffer from two significant challenges that limit their applicability to complex scenarios: (1) the reality gap between simulation measurement data (2) limited generality accommodate different working conditions machines. From perspective...
Abstract In face milling process, the quality of surface texture is vital for mechanical performance workpieces. The texture, especially waviness, directly affected by tool marks, a commonly observed phenomenon in milling. However, appropriate approaches evaluation and modeling marks are absent to date. Limited resolution as well efficiency conventional measurement instruments, height data hard be entirely obtained, leading valuable information omission. Besides, most existing models...
Abstract Face milling is widely used in machining processes, aimed at providing workpieces with high surface quality. The chatter generated face could lead to tremendous damage machine tools, poor machined quality, and loss of processing efficiency. Most related researches have been focused on the modeling spindle dynamics discretization algorithms for prediction. However, few published articles taken geometric characteristics into consideration, especially discontinuous surfaces milling,...
Remaining Useful Life (RUL) prediction is significant in indicating the health status of sophisticated equipment, and it requires historical data because its complexity. The number complexity such environmental parameters as vibration temperature can cause non-linear states data, making tremendously difficult. Conventional machine learning models support vector (SVM), random forest, back propagation neural network (BPNN), however, have limited capacity to predict accurately. In this paper, a...
Geometric error represents the deviation of actual surface shape a machined part from its ideal shape, which directly affects quality 3D surface. Modeling and monitoring geometric can reveal information for evaluating stability production process. Advanced measurement technology allows large number points to express errors in close detail, but results problem spatial correlations. In this study, Gaussian correlation model is employed represent correlations A new statistic established monitor...
Abstract In face milling process, the cutting chatter induced by unsuitable processing parameters could lead to tremendous damage machine tools and loss of machined surface quality. Therefore, as one most effective efficient methods avoid chatter, stability lobe diagram (SLD) has received continuous concern from researchers. Since dynamic forces are definitely dependent on tool path stiffness distribution workpiece, exact interaction between cutter workpiece should be taken into...
The prognostic study of CNC machine component plays a key role in increasing the reliability and safety manufacturing systems. A systematic method based on multi-sensor information for is proposed this paper, where data characteristics system properties are all considered. includes pre-processing noise-assisted multivariate empirical mode decomposition method, two-stage feature selection strategy remaining useful life prediction trajectory similarity method. An experimental case given to...