Study On Monitoring System Of The Injection Molding Process

In recent years, with the development of China’s economy, the plastics industry has developed greatly. As the main plastic products production machinery, the performance and automation level of Injection molding machine has also been improved. Mechanical arm is used to corporate with injection molding machine to complete production. After the products emerge, mechanical arm grabs the products. But often there are residual products, it will damage the mold of injection molding machine and affect the efficiency of injection molding production if not handled timely.According to the situation above and the actual situation of Injection molding factory, this thesis designed Injection molding machine mold image monitoring system. Based on digital image processing technology, this thesis researched actual issues such as contour extraction, image alignment, light compensation of injection molding machine mold images, designed Injection molding machine mold image monitoring system combined with hardware platform.The research mainly includes the following aspects:Firstly, this paper summarizes the concept and current development situation of Injection molding machine and injection molding process, introduces computer vision detection technology and digital image processing theory, proposing deficiencies in Injection molding machine automatic operation and the necessity of designing Injection molding machine mold image monitoring system.Secondly, this paper introduces hardware and software design of the image monitoring system, including the selection of the camera, selection of the processor in hardware aspects and execution flow of the system, algorithm platform, algorithm process and comparison with infrared image processing method in software aspects.Thirdly, we focus on image pre-processing algorithm and real-time detection algorithm contained in the detection algorithm, introduces image smoothing filter operation for light compensation, border contour extraction algorithm for position compensation and image segmentation algorithm for image difference in the pre-processing algorithm and light compensation algorithm based on gray histogram correction method, image alignment algorithm based on the affine transformation and image difference in the real-time detection algorithm and compare the differential results with direct differential results.The last part gives summary of the full text, analyzes the insufficient of the system and proposes future improvements.