Abstract
Today, tool life, catastrophe modes, and wear machinery occur due to increasing component forces produced under diverse machining conditions. The performance of the cemented carbide cutting tool is required to solve the most challenging problems with machining materials, like machining titanium alloys. Titanium alloy has excellent mechanical properties, such as being lightweight and corrosion-resistant. Thus, it is used in a variety of industrial and engineering applications. An artificial neural network (ANN) is used in this study to predict and evaluate the performance of a nano-lubricant on tool wear during titanium alloy machining. To maintain the surface quality of the product, a modern machining system must detect tool wear while machining. Nano-lubricant is a viable, long-term alternative to conventional flood cooling, providing excellent cooling and lubrication when cutting difficult-to-cut materials. A homogenised mixture is obtained by oscillating the solution for 5 hours in a Branson 2800 ultrasonic bath. A computer numerical milling machine was used to machine the titanium alloy. The study used a portable digital microscope (DINO-LITE Premier) to measure the tool wear after each machining process. The study considered the cutting speed, feed rate, and depth of cut as the input parameters to predict the tool wear under the TiO2 nano-lubricant and mineral oil. A feed-forward neural network is employed via the MATLAB toolbox, where the neural network model was trained and tested. The result from the prediction shows that the regression coefficient for training data was R = 0.9081, R = 0.84045 for testing data, R = 0.92746 for confirmation data, and R = 0.89816 for all data. As a result, there is a close connection between the investigational and developed models. The TiO2 nano-ointment cutting condition has the ideal boundaries for the best instrument life for machining TI-6AL-4V-ELI.