変化する環境への適応を目指したモジュール構造ネットワークによる音響診断

抄録

The detection of gas leakage sound from pipes is important in petroleum refining plants and chemical plants, as often the gas used in these plants are flammable or poisonous. In order to establish the acoustic diagnosis technique for the leakage sound, we examined the application of modular neural networks to the stable detection. The modular neural network has the ability to adapt its structure according to the environment. Experiments were performed for an artificial gas leakage device with various experimental conditions to imitate the change of environment for a long term. The discrimination accuracy with the proposed network was observed to be about 93%. From the results, we confirmed the effectiveness for the application of the modular neural network to the detection of the leakage sound for the practical use.