Replacing precipitately is related directly to the higher cost of a new cutting tool and additional changeover time. Optimal costs can be achieved only if the cutting tool is changed at the right time-just before the quality of the machined surface does not meet the requirements due to the worn cutting tool. The financial aspect is also needs to be taken into account. However, not only the quality of the product is affected by the wear of the cutting tool. The condition of the cutting tool is one of the main factors affecting the quality of the final product therefore the tool wear prediction is critical for product quality control.
Several advantages can be obtained by monitoring the wear of a cutting tool. By introducing a reliable smart system that makes decisions instead of humans, it is possible to eliminate any error in judgement that may occur due to the human factor (e.g., inexperience).
Researchers are often confronted with the question of how to determine tool wear with the TCM System (Tool Condition Monitoring System). One also monitors the sound of the process (vibrations), the roughness of the workpiece surface, the colour (temperature) of the chips, the dimensional accuracy of the workpiece, etc. One needs to rely on experience and visual inspection of the cutting edge of the cutting tool at the end of the cut. There is no easy way for a machine operator to determine tool wear. One example is the assessment of tool wear and the decision to change the cutting tool, which is usually left to the machine operator.
Despite all the technological innovations, many decisions in individual or small series production are still made by humans. One of the keystones of this transition is the digitalisation of manufacturing, which is called Industry 4.0-the fourth industrial revolution. The evolution of the machining industry is based on automation, modern smart systems, unmanned machining, dynamic autonomous control of processes, etc. While existing temperature based TCM systems focus on measuring a cutting tool absolute temperature, the proposed system analyses a temperature distribution (relative temperatures) on the whole image based on image features.
The most appropriate time of image acquisition is 6–12 s after the cut is finished. The proposed model, combining Infrared Thermography, Computer Vision, and Deep Learning, proved to be a suitable method with results of more than 96% accuracy. Based on classification result, one gets information about the cutting capability of the tool for further machining. The Convolutional Neural Network Inception V3 was used to analyse and classify the thermographic images, which were divided into different groups depending on the time of acquisition. A cutting tool was monitored with infrared (IR) camera immediately after the cut and in the following 60 s. In this paper, a Tool Condition Monitoring (TCM) system is presented that automatically classifies tool wear of turning tools into four classes (no, low, medium, high wear).
Bad decisions can often lead to greater costs, production downtime, and scrap. In small series and individual production, the machine operator is the one who determines when to change a cutting tool, based upon their experience. In turning, the wear control of a cutting tool benefits product quality enhancement, tool-related costs‘ optimisation, and assists in avoiding undesired events.