Significant developments were seen in the last decade of cutting. Machine tool manufacturers in metal industry increased the level of integration of their products continously year by year, according to the demands of market. If a part required more, different type of machine tools in the past, now that can be machined even on a single machine. Beyond of new mechanical and mechatronic solutions, the abilities of machine tools were also broaden by information technology. The complete design and simulation of machining came into view as well as the supervision of cutting process using various sensors. As the expanding “knowledge” of machine tools, the cutting time decreased besides the improvement of quality.
After the operational elements were done on a single machine tool, there were no further considerable possibilities to decrease the non-productive time. That is why the optimization of productive cutting time came in the center of attention again. The most obvious method of doing this is the systematic modification of cutting parameters while increasing tool life and preserving machining quality and its thrift. The usage of optimal cutting parameters is not a new goal, practically coeval with cutting itself. During that time a lot of workarounds appeared along different approaches which were seemed to be applicable well or less under industrial circumstances.
In this thesis work, the implementation of a decision support system will be presented, which lays on new, different bases than previous ones and it also uses intelligent methods. The system tries to identify machining suboptimums through the measured sizes of workpieces in time, machined with indexable hard metal inserts. Depending on the function of recognized suboptimums, the system propose the modification of cutting parameters and makes prediction about momentary estimated tool life.