The complicated systems for casting, anodizing, machining (drilling, milling, turning), high-pressure water jet (HPWJ) deburring, and brushing processes create many different kinds of particles: burr, cast and chip. These particles lodge inside the tr...
The complicated systems for casting, anodizing, machining (drilling, milling, turning), high-pressure water jet (HPWJ) deburring, and brushing processes create many different kinds of particles: burr, cast and chip. These particles lodge inside the transmission, engine and crankshaft, and then damage the functions of these components, posing risks to drivers. Many researchers have endeavored to minimize these negative effects without clear understanding of the main sources. This investigation aims at clear recognition of these problems and suggests solutions to minimize or remove each kind of particle with high reliability based on experimental databases. By understanding the generation mechanism of each particle, a particle classification algorithm is developed and verified by comparison between the results from simulation and experiment. This research contributes to building a classification algorithm for specific parts like transmissions and engines by suggesting the source of each particle which is very important in cleanability. A particle expert system (PES) was developed to improve particle classification for burrs, casts, and chips in the automotive production process. Image processing techniques were deployed to extract particle information and remove noise from industrial filters and lighting systems. An advanced model of a particle classification algorithm (PCA) was built with 12 particle classes and a vii particle expert system (PES) algorithm was developed to train the PCA parameters to achieve the target success rate. The particle expert system will help the user locate the source of particles with high reliability and a stable success rate immediately after image processing and training the PCA parameters.