In this paper, the multi-objective Hybrid Taguchi-genetic Algorithm is used to search for the best processing parameters with specified processing accuracy. The experimental cutting parameters used for the L9 orthogonal table process are cutting depth, cutting velocity and feed rate. The surface roughness of the machined workpiece surface was measured according to the standard of centerline average roughness. The Material Removal Rate (MRR) will be calculated by measuring the diameter of the processed workpiece from the formula to give the MRR. A linear regression model is constructed from the processed quality and the processing parameters of the orthogonal table and the reliability of the model is confirmed by analysis of variance (ANOVA). A Hybrid Taguchi Genetic Algorithm (HTGA) was used to calculate the optimal cutting parameters for multi-objective processing. The results of the experiments indicate that HTGA gave better convergence and robustness than the conventional Genetic Algorithm (GA) using the same number of iterations. This process produces multiple combinations of optimal cutting parameters for material removal rate and surface roughness. As the enhancement of material removal rate improved efficiency on the production line, the optimal cutting parameters were based on the tolerance range of Ra 1.6μm ~ 3.2μm according to the international standard of surface roughness. After actual processing with the selected optimum cutting parameters, the quality of processing is even better than the experimental design of the L9 Orthogonal table.

During the production process of the components of precision machines, a stable quality is the key consideration of the vendors. During the production process of metal parts, a thermal expansion error of the spindle will occur due to long time operations, which causes machining errors during the production process. The chatter phenomenon that occurs during the production of components causes knife marks on the processing surface. Thus, chatter is also a major factor that affects the stability of quality. The occurrence of chatter phenomenon not only affects the quality of metal components, it also causes severe wear of the blade surface and shortens the life of the knife tool, and makes the cutting quality more difficult to control. Therefore, this paper uses the lathe machine to simulate the production process in the factory, to collect signals of the thermal expansion error of the spindle phenomenon and the coexistence of chatter, for timely compensation of the thermal expansion error and the development of the chatter suppression system, while spending extra efforts to implement real-time dynamic detection with the Lorenz chaotic system and applying spindle speed selection to control the chatter phenomenon, thus enhancing the processing quality and lengthening the longevity of the knife tool. As for the compensation of temperature, the system applies multi-regression analysis to detect the front and rear bearings of the spindle and room temperature and to compensate the error of the spindle in real time. The system takes real-time control of the chatter phenomenon and compensation of long-time thermal expansion error as its core architecture, while the secondary architecture combines the Internet of Things with Skymars to enable the machine to stabilize communication and to combine with heterogeneous machines such as robotic arm, milling machine, and grinding machine. It is a framework with horizontal development and establishes a database to record the critical value of the occurrence of chatter and implement two-time quality detection, achieving management of the production line, improvement of quality, and cloud information storage.