Milling manufacturing system for mechanical manufacturing parts based on AFSA-GA

With the increasing demand for mechanical manufacturing parts in various fields, milling machining systems based on experience or traditional optimization algorithms are unable to satisfy the needs of multi-parameter collaborative optimization. To optimize the performance of milling manufacturing systems, a milling manufacturing system for mechanical manufacturing parts based on an artificial fish swarm algorithm and a genetic algorithm is proposed. The research integrates crossover and mutation operations from genetic algorithms into artificial fish swarm algorithms to enhance local search capabilities. A parameter library is constructed to store validated cutting parameters in the process database, and an embedded control system is developed to fine tune cutting parameters in real-time. The results showed that the processing power stabilized at 51 kW at the 80th iteration. In practical application testing, the system spindle power of the research method tended to stabilize at a feed rate of 225 mm/min. When the processing time was 20 min, the average material removal rate reached a peak of 212.5 cm³/min. The designed system has good machining performance, robustness, and the ability to suppress vibration energy accumulation, effectively solving the problem that traditional methods are difficult to satisfy the requirements of multi-parameter collaborative optimization and improving the machining efficiency of the system.