Degradation assessment for the ball screw with variational autoencoder and kernel density estimation

The ball screw is an important component of machine tools, and its degradation assessment is therefore critical for the health management of the entire machine tool. Generally, the degradation assessment includes health indicator construction and degradation modeling. However, the health indicator is often constructed manually with prior knowledge, and its sensitivity can be affected by various factors. In addition, most existing degradation models rely on a large amount of failure data, which is not practical for the ball screw due to its high reliability. To solve these problems, this article presents a novel ball screw performance evaluation method. First, the raw data collected in the normal status are used to train the variational autoencoder, and then, the online raw signals are input into the learned variational autoencoder to construct health indicators. After that, the kernel density estimation is utilized to estimate the probability distribution of health indicator points in a dynamic sliding window, and then, the deterioration can be evaluated by summarizing the probability distribution that exceeds a predefined threshold. Experimental results show that the presented methodology can establish the health indicator automatically and adaptively. Also, it can evaluate the ball screw performance effectively and quantitatively when only data in healthy state are available.