Modelling the plastic extrusion process with artifical intelligence

The history and evolution of the plastic extrusion process will be examined. The historical background of extruder machines used in the plastic extrusion process, machine selection, machine motor power, heating and cooling system PID control, transmission selection and gear ratio, number of holes and hole diameters in the die head, pool water temperature, and cutting methods, which directly affect the process, will be investigated. In addition to machine parameters in the plastic extrusion production process, the impact of polymers, fillers, and various process improvement additives (such as wax, PIB, UV, etc.) on the production process and quality results will be analyzed and interpreted through real test machines and test methods in a laboratory environment. A data analysis will be conducted based on the information provided by plastic extruder machine manufacturers and raw material producers regarding the production process, along with test results. Through this data analysis, a filtering process will be applied to identify the most critical variables directly impacting the process. These identified variables and data groups will be transferred to the artificial intelligence model developed within the scope of the thesis using deep learning methods. As a result of these inputs, the data and outputs presented by the artificial intelligence method will simulate the production process, allowing observation of how specific inputs lead to certain outputs before actual production. The artificial intelligence model developed will ensure that manufacturers conduct minimal trials and experiments before production, based on the information it provides about the production process. Through the outputs of the simulated production process generated by the artificial intelligence model, companies will be able to obtain information about production results and quality outcomes. By utilizing the data and outputs provided by the artificial intelligence model, companies can minimize negative results directly impacting production costs such as production losses, extra energy costs, energy losses in heating and cooling systems, and labor costs, leading to cost reduction. Consequently, the contributions of the developed model to both quality outcomes and cost optimization in the production process will be examined alongside the productions made according to the results provided by this artificial intelligence model.