A Mechanical Equipment Fault Diagnosis Model Based on TSK Fuzzy Broad Learning System

In an intelligent manufacturing context, the smooth operations of mechanical equipment in production process enterprises and timely fault diagnosis during have become increasingly important. However, effect traditional depends on feature extraction quality experts’ empirical knowledge, which is inefficient costly, cannot match needs manufacturing. The TSK fuzzy system has a strong approximation capability ability to interpret expert knowledge. broad learning (BLS) fast computation capabilities. this paper, we present new model—the (TSK-BLS). model integrates advantages BLS at same time, can be calculated quickly accurately by pseudo-inverse symmetry methods. On other hand, embedded model-building mechanism, extends application scope theory. was tested bearing data set, provided Case Western Reserve University, model’s accuracy as high 0.9967. results were compared with those convolutional neural network (CNN) models, whose accuracies are 0.6833 0.9133, respectively. Comparison showed that proposed model—TSK-BLS, achieved significant improvements.