A5022475126- Advanced machining processes and optimization
- Advanced Machining and Optimization Techniques
- Industrial Vision Systems and Defect Detection
- ECG Monitoring and Analysis
- Machine Fault Diagnosis Techniques
- Advanced Measurement and Metrology Techniques
- Fault Detection and Control Systems
- Image and Object Detection Techniques
- Surface Roughness and Optical Measurements
- Advanced Surface Polishing Techniques
- EEG and Brain-Computer Interfaces
- Manufacturing Process and Optimization
- Advanced Vision and Imaging
- Gear and Bearing Dynamics Analysis
- Robotics and Sensor-Based Localization
- Metal Alloys Wear and Properties
- Advanced Numerical Analysis Techniques
- Reliability and Maintenance Optimization
- Engineering Diagnostics and Reliability
- Phonocardiography and Auscultation Techniques
- Advanced Neural Network Applications
- Geophysics and Sensor Technology
- Multilevel Inverters and Converters
- Advanced Chemical Sensor Technologies
- Statistical Distribution Estimation and Applications
Shanghai University
2019-2023
Huazhong University of Science and Technology
2016-2019
Xi'an Jiaotong University
1995
Accurate identification of the tool wear states in machining titanium alloys continues to be a thorny problem. Rapid construction accurate and effective predictive models with regard various is indispensable for promoting development intelligent manufacturing. This article presents novel WOA-SVM model that integrates support vector machine (SVM) whale optimization algorithm (WOA), which utilized estimation end milling alloy Ti-6Al-4V under variable cutting conditions. The signal features...
Ti-6Al-4V has a wide range of applications, especially in the aerospace field; however, it is difficult-to-cut material. In order to achieve sustainable machining Ti-6Al-4V, multiple objectives considering not only economic and technical requirements but also environmental requirement need be optimized simultaneously. this work, optimization design process parameters such as type inserts, feed rate, depth cut for turning under dry condition was investigated experimentally. The major...
Abstract Learning-based visual odometry (VO), that estimates frame-to-frame (F2F) translation and rotation in end-to-end network, has attracted much attention recent years. However, existing methods perform poorly complex environments, especially when there are moving objects the scene. To solve above issues, a novel monocular is proposed based on motion segmentation mechanism under dynamic environments. Firstly, semantic information optical flow residuals adopted for through iterative...
Monitoring tool wear has drawn much attention recently since failure will make it hard to guarantee the surface integrity of workpieces and stability manufacturing process. In this paper, integrated approach that combines wavelet package decomposition, least square support vector machine, gravitational search algorithm is proposed for monitoring in turning Firstly, decomposition utilized decompose original cutting force signals into multiple sub-bands. Root mean packet coefficients each...
(1) Background and objective: Cardiovascular disease is one of the most common causes death in today's world. ECG crucial early detection prevention cardiovascular disease. In this study, an improved deep learning method proposed to diagnose abnormal normal accurately. (2) Methods: This paper proposes a CNN-FWS that combines three convolutional neural networks (CNN) recursive feature elimination based on weights (FW-RFE), which diagnoses ECG. F1 score Recall are used evaluate performance....
Fault diagnosis of rotating machinery plays an important role in modern industrial machines. In this paper, a modified sparse Bayesian classification model (i.e., Standard_SBC) is utilized to construct the fault system machinery. The features are extracted and adopted as input SBC-based system, kernel neighborhood preserving embedding (KNPE) proposed fuse features. effectiveness based on KNPE Standard_SBC validated by utilizing two case studies: rolling bearing shaft diagnosis. Experimental...
The 12-lead resting electrocardiogram (ECG) is commonly used in hospitals to assess heart health. ECG can reflect a variety of cardiac abnormalities, requiring multi-label classification. However, the diagnosis results previous studies have been imprecise. For example, some studies, abnormalities that cannot coexist often appeared diagnostic results. In this work, we explore how realize effective signals and prevent prediction arrhythmias coexist. classification method based on convolutional...