Prediction of surface roughness based on a hybrid feature selection method and long short-term memory network in grinding

Ground surface roughness is regarded as one of the most crucial indicators of machining quality and is hard to be predicted due to the random distribution of abrasive grits and sophisticated grinding mechanism. In order to estimate surface roughness accurately in grinding process and provide feasible monitoring scheme for practical manufacturing application, a novel prediction system of surface roughness is presented in this article, including the processing of grinding signals, selection of feature combination, and development of prediction model. Grinding force, vibration, and acoustic emission signals are collected during the grinding of C-250 maraging steel. Numerous features in time domain and frequency domain are extracted from original and decomposed signals. A hybrid feature selection approach is proposed to select features based on their relevance to surface roughness as well as hardware and time costs. A sequential deep learning framework, long short-term memory (LSTM) network, is employed to predict ground surface roughness. The results have shown that the LSTM model achieves excellent prediction performance with a feature combination of grinding force and acoustic emission. After considering the hardware and time costs, features in acceleration signal replace those in grinding force and acoustic emission signals with slight loss of prediction performance and significant reduction of costs, which proves the practicability and feasibility of proposed prediction system.

Automated summary

This article presents a novel prediction system for surface roughness by collecting signals during grinding process, extracting features, and utilizing long short-term memory network for accurate prediction. The proposed system shows excellent prediction performance and reduced costs, proving its practicality and feasibility.