Linguistics

Philosophy

Support vector machine

Embedded system

Vibration

Computer science

Acoustics

Fault (geology)

Seismology

Geology

Physics

Fusion

Pattern recognition (psychology)

Image (mathematics)

Feature (linguistics)

Bottleneck

Artificial intelligence

Programming language

Test data

Artificial neural network

Feature extraction

Convolutional neural network

Speech recognition

Computer vision

Computers in Industry

This paper proposed a novel fault recognition method for rotating machinery on the basis of multi-sensor data fusion and bottleneck layer optimized convolutional neural network (MB-CNN). A conversion method converting vibration signals from multiple sensors to images is proposed that can integrate information to get richer features than vibration signals from single sensor. By this method feature maps of different fault types can be obtained without tedious parameter adjustments. Based on the feature maps from multi-sensor data, a corresponding novel convolutional neural network is also constructed. The constructed network performs the bottleneck layers with an increased number of input features to avoid information lost. The data at the same time node can be fused by the convolutional kernels of which the size matches the number of sensors. Practical examples of diagnosis for the wind power test rig and the centrifugal pump test rig are given in order to verify the effectiveness of the proposed approaches, and prediction accuracy of 99.47% and 97.32% is obtained respectively. Otherwise, the performances of other conventional methods such as deep belief network (DBN), support vector machine (SVM) and artificial neural network (ANN) are evaluated for contrast with the proposed method. As shown in the results, the novel convolutional neural network obtains higher recognition accuracy and faster convergence speed.

A novel convolutional neural network based fault recognition method via image fusion of multi-vibration-signals