no code implementations • 9 Nov 2023 • Xinkun Ai, Kun Liu, Wei Zheng, Yonggang Fan, Xinwu Wu, Peilong Zhang, Liye Wang, JanFeng Zhu, Yuan Pan
This paper presents an anomaly detection method based on Deep Convolutional Auto-encoding Neural Networks (DCAN) for addressing the issue of ball mill bearing fault detection.
no code implementations • 11 Sep 2023 • Chengshuo Shen, Wei Zheng, Bihao Guo, Yonghua Ding, Dalong Chen, Xinkun Ai, Fengming Xue, Yu Zhong, Nengchao Wang, Biao Shen, Binjia Xiao, Zhongyong Chen, Yuan Pan, J-TEXT team
The second step is to align a few data from the future tokamak (target domain) and a large amount of data from existing tokamak (source domain) based on a domain adaptation algorithm called CORrelation ALignment (CORAL).
no code implementations • 27 Mar 2023 • Xinkun Ai, Wei Zheng, Ming Zhang, Dalong Chen, Chengshuo Shen, Bihao Guo, Bingjia Xiao, Yu Zhong, Nengchao Wang, Zhoujun Yang, Zhipeng Chen, Zhongyong Chen, Yonghua Ding, Yuan Pan, J-TEXT team
Finally, we optimize precursor labeling using the onset times inferred by the anomaly detection predictor and test the optimized labels on supervised learning disruption predictors.
Semi-supervised Anomaly Detection Supervised Anomaly Detection
no code implementations • 28 Aug 2022 • Chengshuo Shen, Wei Zheng, Yonghua Ding, Xinkun Ai, Fengming Xue, Yu Zhong, Nengchao Wang, Li Gao, Zhipeng Chen, Zhoujun Yang, Zhongyong Chen, Yuan Pan, J-TEXT team
Understanding why a predictor makes a certain prediction can be as crucial as the prediction's accuracy for future tokamak disruption predictors.
no code implementations • 20 Aug 2022 • Wei Zheng, Fengming Xue, Ming Zhang, Zhongyong Chen, Chengshuo Shen, Xinkun Ai, Nengchao Wang, Dalong Chen, Bihao Guo, Yonghua Ding, Zhipeng Chen, Zhoujun Yang, Biao Shen, Bingjia Xiao, Yuan Pan
Based on the feature extractor trained on J-TEXT, the disruption prediction model was transferred to EAST data with mere 20 discharges from EAST experiment.