Separation Method of Knocking Sound from Engine Radiation Noise Using Deep Learning
深層学習を用いたエンジン放射音からのノッキング音分離手法
- Delivery
- Available on the other site
- Click here to order.
- Publication code
- 20224347
- Paper/Info type
- JSAE Transaction
Vol.53 No.4
- Pages
- 717-722(Total 6 p)
- Date of publication
- Jul 2022
- Publisher
- JSAE
- Language
- Japanese
Detailed Information
| Category(J) | 技術論文 Translation |
|---|---|
| Category(E) | TechnicalPaper |
| Author(J) | 1) 笠原 太郎, 2) 渡部 光, 3) 池田 太一, 4) 吉越 洋志 |
| Author(E) | 1) Taro Kasahara, 2) Hikaru Watabe, 3) Taichi Ikeda, 4) Hiroshi Yoshikoshi |
| Affiliation(J) | 1) 小野測器, 2) 小野測器, 3) 小野測器, 4) 小野測器 |
| Abstract(J) | 著者らはこれまでエンジン放射音からノッキング音を分離するDNN（Deep Neural Network）を提案し、回転速度ごとに特化したDNNを作成してきた．本稿では、限られたデータを用いて、より幅広い運転条件に適用可能なDNNを作成するため、学習データに含まれない回転速度におけるノッキング音を分離するDNNの訓練方法を提案する． Translation |
| Abstract(E) | The deep learning model (DNN, Deep Neural Net) we proposed separates knocking sound from engine radiation noise measured by a microphone. In this paper, we propose a method for training a DNN which can be used in a wide range of rotational speed conditions. The proposed method applies data augmentation to measurement data under several conditions. In addition, the proposed method trains a DNN (UNet) for sound source separation using the results of the previous method. The proposed method can reduce the time required for training data collection. In terms of practical application, reducing the burden of data collection is an important improvement. |
