Predictive analytics to improve the quality of polymer component manufacturing

Abstract

In Today's Competitive Market, customers demand a quality product and a high response time is more important than its cost. These are the motivation points to develop a model that works on quality improvement parameters and recommends the respective team members in the Injection Molding (IM) process. This paper presents the predictive and prescriptive analysis of the parameters that decide the quality of the Car's molded polymer components like the bumper. When talking about product quality, first need to identify the affected parameters. These parameters might be mold design, thickness, temperature, molding process cycle time, material, etc. After finding these parameters, the respective team members should take care of/do modifications to improve the product quality. The developed model does the same things in this paper. This paper also discusses the molding process cycle and its time. The quality decision factor is the molding cycle, which has eight stages described in this paper and their importance. Here is also telling about the Teams and the Polypropylene material used in the IM process. It is naturally semi-crystalline and mainly used in the automotive industry, industrial applications, consumer goods, and furniture market.This paper has used a famous Machine Learning classified logistic regression algorithm during the Implementation of the predictive model. This developed model works on quality improvement parameters and recommends the respective team members in the Injection Molding (IM) process. As knows, Injection Molding can manufacture great precision/fine quality polymer products with high repeatability and speed. These advantages of IM make it possible to satisfy the customers and increase the demand & supply in the market. Hence, this predictive model automatically increases the return of investment and revenue of the manufacturing companies.