An evolutionary deep learning approach using flexible variable-length dynamic stochastic search for anomaly detection of robot joints

Abstract

Anomaly detection is crucial for condition monitoring of robot joints. An increasing number of anomaly detection methods based on deep learning have been investigated. However, since the deep learning architectures for anomaly detection are manually designed by trial and error, the design process is time-consuming, and the designed deep learning architectures may not be optimal for specific anomaly detection tasks. In this paper, a Flexible Variable-Length Dynamic Stochastic Search (FVLDSS) is proposed by designing and embedding the encoding and alignment strategies into the original Dynamic Stochastic Search (DSS). Subsequently, an Evolutionary Deep Learning Approach Using FVLDSS (EDLDSS) is proposed to automatically search for an optimal deep learning architecture for anomaly detection. In EDLDSS, Convolutional Neural Network (CNN) is used as the feature extractor, k-nearest neighbors trained only with normal samples is used as the anomaly detector, and FVLDSS is used to simultaneously optimize the network structure and hyperparameters of CNN. Furthermore, an anomaly detection method based on EDLDSS is developed to detect the anomalies in robot joints, in which S-transform spectrograms of vibration signals normalized by Z-score normalization are used as the input of CNN. To validate the performance of EDLDSS, a condition monitoring system using fiber Bragg grating sensors is first established for the industrial robot to acquire vibration signals from robot joints and conduct three experiments. The statistical results demonstrate the feasibility and satisfactory performance of EDLDSS in handling the anomaly detection problem of robot joints.