A5050342030- Fault Detection and Control Systems
- Machine Fault Diagnosis Techniques
- Advanced Sensor and Control Systems
- Social Robot Interaction and HRI
- Infant Health and Development
- Emotion and Mood Recognition
- Gear and Bearing Dynamics Analysis
- Risk and Safety Analysis
- Engineering and Test Systems
University of Toronto
2020
Tongji University
2018-2020
For social robots to effectively engage in human-robot interaction (HRI), they need be able interpret human affective cues and respond appropriately via display of their own emotional behavior. In this article, we present a novel multimodal HRI architecture promote natural engaging bidirectional communications between robot user. User affect is detected using unique combination body language vocal intonation, classification performed Bayesian Network. The Emotionally Expressive Robot...
In recent years, machine learning and deep based fault diagnosis methods have been studied, however, most of them remain at the experimental stage mainly because two obstacles, briefly, a) inadequate faulty examples b) various working conditions industrial data. this literature, a practical algorithm named Data Simulation by Resampling (DSR) is proposed for data augmentation to alleviate problems in diagnosis. essence, as form Vicinal Risk Minimization (VRM), DSR utilizes two-stage...
In recent years, deep learning-based fault diagnosis methods have drawn lots of attention. However, for most cases, the success machine models relies on circumstance that training data and testing are under same working condition, which is too strict real implementation cases. Combined with features robustness convolutional neural network vibration signal characteristics, information fusion technology introduced in this study to enhance feature representation capability as well...
Bearings are critical parts of rotating machines, making bearing fault diagnosis based on signals a research hotspot through the ages. In real application scenarios, normally non-linear and unstable, thus difficult to analyze in time or frequency domain only. Meanwhile, feature vectors extracted conventionally with fixed dimensions may cause insufficiency redundancy diagnostic information result poor performance. this paper, Self-adaptive Spectrum Analysis (SSA) SSA-based framework proposed...