Prediction of Flank Wear of Inconel by using the Levenberg-Marquardt ANN Model

In metal turning processes, precise prediction of flank wear is critical for improving machining process efficiency and tool life. This research study describes a novel approach for estimating flank wear during Inconel turning that employs an Artificial Neural Network (ANN) technique. The proposed ANN model is trained using a large dataset that includes multiple cutting settings and tool wear measurements from experimental turning experiments. The study aims to create a prediction model that can estimate flank wear values based on input factors such cutting speed, feed rate, depth of cut, and tool material qualities. Experimenting with Carbide Inserts and cutting circumstances yielded diverse data points for model training and validation. The acquired data were used to train the ANN model with a backpropagation algorithm, and several performance indicators were employed to assess the model's prediction accuracy. The results show that the constructed ANN model forecasts flank wear accurately in Inconel Metal turning operations. To enable real-time flank wear prediction, the suggested ANN model can be linked into machining process monitoring and control systems. It is possible to improve machining parameters, reduce tool wear, and increase productivity and tool life in Inconel turning processes by precisely calculating these parameters.

I. INTRODUCTION

Inconel, a family of nickel-based superalloys, is widely used in various industries due to its exceptional high-temperature strength, corrosion resistance, and excellent mechanical properties. However, the machining of Inconel poses significant challenges due to its high hardness, low thermal conductivity, and tendency to work harden during cutting. The accurate prediction of flank wear and cutting force in Inconel turning operations is crucial for optimizing the machining process and extending tool life . [1] Flank wear, the gradual deterioration of the cutting tool's flank due to interaction with the workpiece material, is a critical parameter that directly affects tool life and machining performance. Monitoring and predicting flank wear in Inconel turning can enable timely tool replacement, reduce production downtime, and enhance productivity. Simultaneously, the measurement and prediction of cutting forces exerted during Inconel turning play a vital role in understanding the machining process dynamics. Cutting forces significantly impact tool wear, tool deflection, and surface quality. Accurate prediction of cutting forces facilitates the selection of appropriate cutting parameters, reducing the risk of tool failure and improving the overall machining efficiency [2].