[4M2] [General Session] 10. Vision / Speech

[4M2-05] Verification of CNN training from featuer images based on worker's experience knowledge.

〇Taishi Yamakawa¹, Masahiko Kuroki², Hiroshi Okabe² (1. Tokyo Electric Power Company Holdings, Inc., 2. TEPCO Fuel & Power, Incorporated)

Keywords:AI, CNN, abnormality detection, experience knowledge

For CNN training, abnormal images were drawn using original normal images based on skilled worker’s experience knowledge. CNN could learn features of abnormality from those drawn images. Even in the case of rare abnormality like machine trouble, if abnormal images are visualized with skilled worker’s know-how, CNN will be possible method to detect abnormality without real teacher data.