SIGNAL (programming language)

Linguistics

Engineering

Philosophy

Support vector machine

Computer science

Acoustics

Fault (geology)

Seismology

Cepstrum

Geology

Mel-frequency cepstrum

Mechanical engineering

Physics

Pattern recognition (psychology)

Belt conveyor

Feature (linguistics)

Automotive engineering

Artificial intelligence

Decision tree

Programming language

Feature extraction

Conveyor belt

Speech recognition

Advanced Powder Technology

Belt conveyor systems are widely utilized in transportation applications. This research aims to achieve fault detection on belt conveyor idlers with an acoustic signal based method. The presented novel method uses Mel Frequency Cepstrum Coefficients and Gradient Boost Decision Tree for feature extraction and classification. Thirteen Mel Frequency Cepstrum Coefficients are extracted from acquired sound signal as features. A Gradient Boost Decision Tree model is developed and trained. After training, the model is applied to a testing dataset. Results show that the trained model can achieve diagnosis accuracy of 94.53%, as well as recall rate up to 99.7%. This study verifies the proposed method for acoustic signal based fault detection of belt conveyor idlers.

Acoustic signal based fault detection on belt conveyor idlers using machine learning