Enhancement of tool life using magneto-rheological fluid damping and tool wear prediction through deep learning model in milling

Undesirable vibrations generated during milling significantly intensify milling tool wear and reduces tool life. Hence it is imperative to employ the effective vibration control strategy during milling to optimize the overall effectiveness of the process. Thus, the present study incorporates the magneto-rheological fluid damping for vibration mitigation during the milling to enhance the life of a cutting tool under different operating conditions. Simultaneously, the data-driven modelling are employed to predict the tool wear using real-time multi-sensor machining data under different operating conditions. Accordingly, the real-time multi-sensor data was acquired at different operating conditions during normal and vibration-damped milling. Later, the extracted tine-domain features were selected using the sequential feature selection with Random Forest Regressor to obtain the most relevant time-domain features from multi-sensor data for improving the model performance. These selected features are then fed to the different deep-learning algorithms for tool wear prediction. Thus, Magneto-rheological fluid damping significantly reduces the vibrations and cutting forces in vibration-damped milling between 65 and 80% and improves the tool life by 18–21 % compared to normal milling under different operating conditions. Moreover, among the different deep learning algorithms, hybrid Encoder-Decoder Long short-term Memory is considered the optimal choice for tool wear prediction due to highest accuracy with coefficient of determinations (R2) ranging from 0.980 to 0.995 with the lowest mean squared error between 22 and 50 μm under varying operating conditions during normal and vibration-damped milling. Thus, it facilitates the significant enhancement in the tool life under different operating conditions, and robust data-driven model for the effective implementation of predictive maintenance approach. © 2024 Elsevier B.V., All rights reserved.