Interpretable Fault Diagnosis of Rolling Element Bearings with Temporal Logic Neural Network

Abstract

Machine learning-based methods have achieved successful applications in machinery fault diagnosis. However, the main limitation that exists for these methods is that they operate as a black box and are generally not interpretable. This paper proposes a novel neural network structure, called temporal logic neural network (TLNN), in which the neurons of the network are logic propositions. More importantly, the network can be described and interpreted as a weighted signal temporal logic. TLNN not only keeps the nice properties of traditional neuron networks but also provides a formal interpretation of itself with formal language. Experiments with real datasets show the proposed neural network can obtain highly accurate fault diagnosis results with good computation efficiency. Additionally, the embedded formal language of the neuron network can provide explanations about the decision process, thus achieve interpretable fault diagnosis.

Learning Signal Temporal Logic through Neural Network for Interpretable Classification

“…Efforts have been made to incorporate temporal logic tools as a way to improve the interpretability of the classification models. Existing work includes combining the neural network with weighted signal temporal logic [10]- [13], extending SVMs to Support-Vector Machine-Signal Temporal Logic (SVM-STL) [14], building a decision tree that can be represented as signal temporal logic formulae [15]. These methods, however, focus only on binary classification based on the signs of the quantitative satisfaction of the signal temporal logic formulae.…”