Application of machine learning for acoustic emissions waveform to classify galling wear on sheet metal stamping tools

Galling wear in sheet metal stamping processes can degrade the product quality and adversely affect mass production. Studies have shown that acoustic emission (AE) sensors can be used to measure galling. In the literature, attempts have been made to correlate the AE features and galling wear in the sheet metal stamping process. However, there is very little attempt made to implement machine learning (ML) techniques to detect AE features that can classify non-galling and galling wear as well as provide additional wear-state information in the form of strong visualisations. In the first part of the paper, time domain and frequency domain analysis is used to determine the AE features that can be used for unsupervised classification. Due to galling wear progression on the stamping tools, the behaviour of AE waveform changes from stationary to a non-stationary state. The initial change in AE waveform behaviour due to galling wear initiation is very difficult to observe due to the ratio of change against the large data size of the waveform. Therefore, a time-frequency technique "Hilbert Huang transform" is applied to the AE waveform as that is sensitive to change of wear state and is used for the classification of "non-galling" and the "transition of galling." Also, the unsupervised learning algorithm fuzzy clustering is used as comparison against the supervised learning techniques. Despite not knowing a priori the wear-state labels, fuzzy clustering is able to define three relatively accurate distinct classes: "unworn", "transition to galling" and "severe galling". In the second part of the paper, the AE features are used as an input to the supervised ML algorithms to classify AE features related to non-galling and galling wear. An accuracy of 96% was observed for the prediction of non-galling and galling wear using classification, regression tree (CART) and neural network techniques. In the last part, a reduced short time Fourier transform of top 10 absolute maximum component AE feature sets that correlates to wear measurement data "profile depth" is used to train and test supervised neural network and CART algorithms. The algorithms predicted the profile depth of 530 unseen parts (530 unseen cases), which did not have any associated labelled depth data. This shows the power of using ML techniques that can use a small data training set to provide additional predicted wear state on a much larger data set. Furthermore, the ML techniques presented in this paper can be used further to develop a real-time measurement system to detect the transition of galling wear from measured AE features.