Automatic generation of glass insulator formulations based on time-scale uniformity

The glass insulator formulation is a major factor affecting the production yield of glass insulators. In actual production, there are multiple production stages, such as incoming, laboratory and manufacturing, and there are inconsistencies in the corresponding time scales of the raw materials in the formula at different production stages. During the production process, the inconsistency in the time scale of each production stage causes the ratio of raw materials in the formulation to change frequently, which has a significant impact on the quality of the product. To solve the current problem that the generation of glass insulator recipes can only be achieved manually, which is time-consuming and labourintensive, and is prone to errors due to the inconsistent time scales of each production stage. we propose a method for automatic generation of glass insulator recipes based on uniform time scales in combination with machine learning, and evaluate the results of the method using MAPE and RMSE metrics. It is concluded that the time-scale-uniform glass insulator recipe generation method is more effective than the method without time-scale uniformity.