Process design of microchip encapsulation : a case based reasoning with fuzzy retrieval approach

摘要

The microelectronic industry continues to grow rapidly in size and importance. The industry has already reached the size of other major industries with sales of product and equipment totalling billions of dollars a year. Among all the options available for semiconductor assembly, plastic packaging by using epoxy based encapsulation process is less expensive and accounts for approximately 80% of the worldwide packaging share and this percentage is increasing. Microchip encapsulation based on transfer molding is one of the important processes of semiconductor manufacturing. Quality is heavily dependent on the encapsulation mold design, selection of molding compound and process parameter setting of encapsulation molding. In current practice, encapsulation mold design and parameter setting of the transfer molding are done manually in a trial-and-error manner which would result in long lead time for obtaining acceptable molding quality. In this paper, an artificial intelligence technique, Case Based Reasoning with Fuzzy Retrieval, is described to perform process design of microchip encapsulation from which a case based system for microchip encapsulation, named CBS-ME, was developed. The system aims to automate the design of the key elements of encapsulation molds, suggest process parameters for transfer molding and improve its own design know-how through a learning process. A validation test was performed and the system solutions were benchmarked with the solutions obtained from the actual molding. Deviation of the two sets of solutions for mold design parameter setting and process parameter setting are 3.5% and 6% respectively.