TY - BOOK

T1 - Advancing Industry 4.0

T2 - AI-Enhanced In-Line MIMO Quality Control for Piano-Black Curved Plastic Injection Molded Parts with OPC UA Integration

AU - Saeidi Aminabadi, Saeid

N1 - embargoed until 03-10-2026

PY - 2023

Y1 - 2023

N2 - In the manufacturing of injection-molded plastic parts, it is essential to perform a non-destructive (and, in some applications, contactless) three-dimensional measurement and surface inspection of the injection-molded part to monitor the part quality. This measurement should be done in real-time and close to the part’s production time to evaluate the quality of the produced parts for future online, closed-loop, and predictive quality control. Therefore, a novel contactless, three-dimensional measurement system using a multicolor confocal sensor was designed and manufactured. This system includes one linear and one cylindrical moving axis, as well as one confocal optical sensor for radial R-direction measurements. A 6 DOF (degrees of freedom) robot handles the part between the injection molding machine and the measurement system. An IPC coordinates the communications and system movements over the OPC UA (Open Platform Communications Unified Architecture) communication network protocol. For validation, several repeatability tests were performed at various speeds and directions. The results were compared using signal similarity methods, such as MSE, SSIM, and RMS difference. The repeatability of the system in all directions was found to be in the range of ±5 µm for the desired speed range (less than 60 mm/s–60 degrees/s). However, the error increases up to ±10 µm due to the fixture and the suction force effect.Automatic in-line process quality control plays a crucial role to enhance production efficiency in the injection molding industry. Industry 4.0 is leading the productivity and efficiency of companies to minimize scrap rates and strive for zero-defect production, especially in the injection molding industry. In this study, a fully automated closed-loop injection molding (IM) setup with a communication platform via OPC UA was built in compliance with Industry 4.0. The setup included fully automated inline measurements, in-line data analysis, and an AI (Artificial Intelligent) control system to set the new machine parameters via the OPC UA communication protocol.To facilitate the training of the AI models with the necessary data, an initial experimental design using a CCD (Central Composite Design) methodology type CCC was employed. Considering the specific mold-related problem, a new production window was found and a new experiment was conducted utilizing a CCI (Central Composite Investigation) approach, generating data for training the AI models. Subsequently, the results obtained from the CCI experiment were thoroughly examined through regression analysis and the utilization of AI models. The objective was to identify the most influential features and develop optimal models for predicting the dimensional, weight, and surface quality outputs. Through this analysis, the aim was to refine the models and achieve improved accuracy and reliability in predicting these key output parameters.The surface quality of the injection molded parts was rated using the ResNet-18 convolutional neural network, which was trained on data gathered by a heuristic approach. Further, eight different machine learning models for predicting the part quality (weight, surface quality, and dimensional properties) and for predicting sensor data were trained using data from a variety of production information sources, including in-mold sensors, injection molding machine (IMM) sensors, ambient sensors, and inline product quality measurements. These models are the backbone of the AI control system, which is a heuristic Data-driven control method. The control system and predictive models were successfully tested for two groups of quality features: Geometry control and surface quality control. Control parameters were limited to injection speed and holding pressure. Moreover, the geometry control was repeated with mold temperature as an additional control parameter.This project endeavors to advance the boundaries of development in the field of injection molding of plastics across several key domains. Firstly, it aims to explore and establish the viability of measuring dimensional properties of injection molded parts in as-molded state with high speed and precision, particularly in dealing with a hard example. Secondly, it seeks to demonstrate the feasibility of acquiring real-time data and conducting in-line analyses in training of AI models. Thirdly, it intends to validate the suitability of OPC UA as an advanced communication platform within the context of Industry 4.0 for the acquisition of machine data and enhancing safety protocols. Fourthly, it aims to investigate the generalizability of CCD and CCI experimental designs in creating accurate models for injection molded parts. Finally, the project endeavors to demonstrate the feasibility and precision of a data-driven AI-based controller for the application of process control in injection molding of plastics.

AB - In the manufacturing of injection-molded plastic parts, it is essential to perform a non-destructive (and, in some applications, contactless) three-dimensional measurement and surface inspection of the injection-molded part to monitor the part quality. This measurement should be done in real-time and close to the part’s production time to evaluate the quality of the produced parts for future online, closed-loop, and predictive quality control. Therefore, a novel contactless, three-dimensional measurement system using a multicolor confocal sensor was designed and manufactured. This system includes one linear and one cylindrical moving axis, as well as one confocal optical sensor for radial R-direction measurements. A 6 DOF (degrees of freedom) robot handles the part between the injection molding machine and the measurement system. An IPC coordinates the communications and system movements over the OPC UA (Open Platform Communications Unified Architecture) communication network protocol. For validation, several repeatability tests were performed at various speeds and directions. The results were compared using signal similarity methods, such as MSE, SSIM, and RMS difference. The repeatability of the system in all directions was found to be in the range of ±5 µm for the desired speed range (less than 60 mm/s–60 degrees/s). However, the error increases up to ±10 µm due to the fixture and the suction force effect.Automatic in-line process quality control plays a crucial role to enhance production efficiency in the injection molding industry. Industry 4.0 is leading the productivity and efficiency of companies to minimize scrap rates and strive for zero-defect production, especially in the injection molding industry. In this study, a fully automated closed-loop injection molding (IM) setup with a communication platform via OPC UA was built in compliance with Industry 4.0. The setup included fully automated inline measurements, in-line data analysis, and an AI (Artificial Intelligent) control system to set the new machine parameters via the OPC UA communication protocol.To facilitate the training of the AI models with the necessary data, an initial experimental design using a CCD (Central Composite Design) methodology type CCC was employed. Considering the specific mold-related problem, a new production window was found and a new experiment was conducted utilizing a CCI (Central Composite Investigation) approach, generating data for training the AI models. Subsequently, the results obtained from the CCI experiment were thoroughly examined through regression analysis and the utilization of AI models. The objective was to identify the most influential features and develop optimal models for predicting the dimensional, weight, and surface quality outputs. Through this analysis, the aim was to refine the models and achieve improved accuracy and reliability in predicting these key output parameters.The surface quality of the injection molded parts was rated using the ResNet-18 convolutional neural network, which was trained on data gathered by a heuristic approach. Further, eight different machine learning models for predicting the part quality (weight, surface quality, and dimensional properties) and for predicting sensor data were trained using data from a variety of production information sources, including in-mold sensors, injection molding machine (IMM) sensors, ambient sensors, and inline product quality measurements. These models are the backbone of the AI control system, which is a heuristic Data-driven control method. The control system and predictive models were successfully tested for two groups of quality features: Geometry control and surface quality control. Control parameters were limited to injection speed and holding pressure. Moreover, the geometry control was repeated with mold temperature as an additional control parameter.This project endeavors to advance the boundaries of development in the field of injection molding of plastics across several key domains. Firstly, it aims to explore and establish the viability of measuring dimensional properties of injection molded parts in as-molded state with high speed and precision, particularly in dealing with a hard example. Secondly, it seeks to demonstrate the feasibility of acquiring real-time data and conducting in-line analyses in training of AI models. Thirdly, it intends to validate the suitability of OPC UA as an advanced communication platform within the context of Industry 4.0 for the acquisition of machine data and enhancing safety protocols. Fourthly, it aims to investigate the generalizability of CCD and CCI experimental designs in creating accurate models for injection molded parts. Finally, the project endeavors to demonstrate the feasibility and precision of a data-driven AI-based controller for the application of process control in injection molding of plastics.

KW - Cylindrical three-dimensional measurement

KW - OPC UA communication protocol

KW - injection molding of plastics

KW - closed-loop quality control

KW - in-line quality control

KW - AI quality control

KW - data-driven control

KW - surface quality prediction

KW - dimensional features prediction

KW - weight prediction

KW - Zylindrische dreidimensionale Messung

KW - OPC UA Kommunikationsprotokoll

KW - Kunststoffspritzguss

KW - Qualitätskontrolle im geschlossenen Regelkreis

KW - Inline-Qualitätskontrolle

KW - KI-Qualitätskontrolle

KW - datengesteuerte Kontrolle

KW - Vorhersage der Oberflächenqualität

KW - Vorhersage von Dimensionsmerkmalen

KW - Gewichtsvorhersage

U2 - 10.34901/mul.pub.2024.004

DO - 10.34901/mul.pub.2024.004

M3 - Doctoral Thesis

ER -