| dc.description.abstract | In today's competitive market, customers demand a quality product and a quick response time is more important than its cost. These are the motivational points and objectives of the research. The presented research work is focused on quality improvement parameters and recommends the respective team members in the Injection Molding (IM) process. The product quality dominates the supply chain market in the country. If product quality is degraded or low, the customer is not going to accept the product, and as a result, demand and the company's revenue also decrease.
The current research presents a comprehensive overview of the development of the Predictive Injection Molding (PIM) Model with the use of data mining and predictive analytics to perform the prediction of the molded items based on their parameter value. Data is being collected from the organization a massive set of data to find a pattern and establish relationships among the variables to perform the prediction. It is not easy to complete the prediction process without data mining.
Further, it is understood that a lot of data from a database or machine is generated that was unknown earlier, but with the help of intelligent techniques, it is possible to recognize the pattern for prediction. The logistic regression, AI ML algorithm has been used to develop this PIM model for injection molding.
In the AI ML system, a developed model automatically takes decision without external support and sends the alarm or notification to the respective teams. Predictive Analytics (PA) is an integral part of ML. The PA works based on a pattern they find from a machine or database, and after further analysis, they return the outcome, which can be a prediction. The predictive analysis is used to predict the molded items' product quality and presented in this thesis. Product quality is essential because the success of the company and its reputation in customer markets depend on it. That is why companies have more focus and spend a lot of time and money to maintain and improve the quality.
The presented here research has used the CRISP-DM framework. | en_US |
