Development of an Online Quality Control System for Injection Molding Process

Abstract

This research developed an adaptive control system for injection molding process. The purpose of this control system is to adaptively maintain the consistency of product quality by minimize the mass variation of injection molded parts. The adaptive control system works with the information collected through two sensors installed in the machine only—the injection nozzle pressure sensor and the temperature sensor. In this research, preliminary experiments are purposed to find master pressure curve that relates to product quality. Viscosity index, peak pressure, and timing of the peak pressure are used to characterize the pressure curve. The correlation between product quality and parameters such as switchover position and injection speed were used to produce a training data for back propagation neural network (BPNN) to compute weight and bias which are applied on the adaptive control system. By using this system, the variation of part weight is maintained to be as low as 0.14%.

Optimize Injection-Molding Process Parameters and Build an Adaptive Process Control System Based on Nozzle Pressure Profile and Clamping Force

“…Therefore, by installing a pressure sensor on the injection-molding machine or the mold, the pressure sensor can monitor the pressure history of the injection-molding process and visualize the product-forming process as much as possible. In recent years, some of the literature has mentioned that installing a pressure sensor at the nozzle end can inspect the product-forming process effectively, and the pressure history of the nozzle end has a significant relationship with the product weight [ 2 , 4 , 17 , 18 , 19 , 20 ].…”

“…Thus, the weight variation can be known through the viscosity index. Tsai et al [ 18 ] established a prediction model by a neural network to predict the quality of the injection-molded product. The prediction model by a neural network is incorporated into the adaptive process control system to stabilize the injection-molded product’s quality.…”

Injection Barrel/Nozzle/Mold-Cavity Scientific Real-Time Sensing and Molding Quality Monitoring for Different Polymer-Material Processes

“…It can be thus observed that when molding PS materials, the melt flow resistance requires a higher molding pressure to push the plastic materials, making the melt pressure-peak and viscosity index of the PS greater than that of PP materials. Through the literature [1,2], it can be found that by installing the sensor at the barrel position and by sensing the pressure trend change of the melt, the pressure trends obtained are the same as at the nozzle position. Moreover, by installing the sensor at the barrel position, it is also possible to grasp the changes in the plasticizing and injection conditions of the material.…”

“…Scientific injection molding technologies involve the integration and collaboration of cyber-physical systems and smart manufacturing. In order to achieve adaptive process control and production optimization, the injection molding system with real-time sensing has gradually become the development and application trend of smart injection molding in the rubber and plastics industries [1][2][3][4]. Injection molding is a highly non-linear process in which many factors affect the product quality during long-run fabrication processes.…”

“…The present study focused on PP and PS molding finished products with a thickness of 4 mm and investigated the melt-flow characteristics and its pressure-trend change. Additionally, the calculation formula (Equation ( 1), [1,2,5,[21][22][23]) of a viscosity index was introduced to compare the effects of PP and PS under the same and different MI parameters. During injection molding, properties of the material can vary considerably due to the difference between semi-crystalline (PP) and amorphous (PS) polymer materials; at the same time, a higher melting pressure is generally required in order to accurately obtain samples' weight/dimensional.…”