Surface roughness prediction in turning processes using CEEMD-based vibration signal denoising and LSTM networks

Abstract

Surface roughness plays a pivotal role in assessing machining quality, and numerous research efforts have been devoted to predicting surface roughness in turning processes primarily based on cutting parameters. However, it's important to recognize that surface roughness isn’t solely governed by cutting parameters; it is also influenced by tool characteristics, workpiece properties, and the prevailing machining conditions. Therefore, the accurate prediction of surface roughness during turning operations is of utmost importance for facilitating timely corrective measures. However, the accuracy of prediction is affected by the intense background noise and usage of manual feature extraction. To address these issues, this article proposes a novel method combining the complete ensemble empirical mode decomposition (CEEMD) and sequence long short-term memory (LSTM) networks. The CEEMD decomposes the measured vibration signals, and noise-free intrinsic mode functions (IMFs) are chosen based on cross-correlation. The noise-free IMFs are then reconstructed to get the denoised signal. The denoised signals are fed straight into the Sequence LSTM network, a deep learning-based prediction algorithm for accurate prediction. The network parameters are optimized to minimize the error. An experimental study was conducted to assess the suggested method, and the results show that it effectively predicts surface roughness during turning using vibration signals. Further, the proposed approach has proven effective compared with other denoising methods. The proposed method has significant applications in the manufacturing industry, where it can contribute to better quality control and process optimization.