In recent developments in the field of manufacturing systems, there has been a growing emphasis on optimizing cutting conditions. These optimizations are primarily based on intricate parameters, such as the material removal rate (MRR), surface roughness, and position accuracy. Simultaneously, there’s an increasing focus on enhancing manufacturing efficiency through equipment maintenance strategies that consider parameters, such as corrosion, pressure, temperature, vibration, and other environmental factors. Wear is inevitable during processing, which affects productivity. It is generated in various forms, such as flank, crater, and edge wear, which reduce the tool lifespan and impact machining quality, especially by increasing the cutting forces. Various studies have been conducted to address this issue. Direct measurements using microscopes have high accuracy but require interruption during the process, which adversely affects efficiency and productivity. As a solution, the modern era has witnessed an increase in indirect methods. These methods are often sensor-based, capture data during the machining process, and employ various models, including emerging artificial intelligence techniques, for predicting tool wear. However, these methods have problems with environmental susceptibility, reduced reliability, limitations of application, and excessive costs. This paper suggests a tool wear integrated cutting load prediction model, tool wear detection, and fault diagnosis mechanism. The tool-wear-integrated cutting-load prediction model was constructed by combining the cutting-load prediction and tool-wear models. The coefficients of the model were derived from the actual cutting data extracted by the spindle load. Tool wear detection was implemented by dividing regions based on the tendency of the coefficient of the constructed tool wear integrated cutting load prediction model and the errors between the predicted and actual values. The proposed model demonstrated a performance comparable to that of the existing models in a single-cutting-condition path. However, it excelled in extracting the tool wear coefficients in paths with a mixture of various cutting conditions, which was not achievable with conventional models. Based on these coefficients, the cutting force was predicted with a maximum error of 3.3 %. Also, an accurate determination of the tool-wear regions was possible. Furthermore, the performance of the tool fault diagnosis method was validated using images of tools identified as being at risk of damage.
Read full abstract