Toshiba AI Technology Catalog

  • Anomaly detection
  • Sensor data recognition

Deep learning denoising

Detect faint signals buried in noise.

  • Takes into account loss function specially designed to detect week signals.
  • Picks up on signs of degradation from faint partial discharges arising in power sources and other facilities.


  • Degradation diagnosis for equipments and facilities

Benchmarks, strengths, and track record

  • Estimate partial discharge type with 80% accuracy, even in the case of sensor signals that contain noise with amplitude of 10x the partial discharge pulse. (Institute of Electrical Engineers of Japan National Conference 2019)


Please include the title “Toshiba AI Technology Catalog: Deep learning denoising” or the URL in the inquiry text.
Please note that because this technology is currently the subject of R&D activities, immediate responses to inquiries may not be possible.