A case-based decision support model for semiconductor assembly

In order to meet the fast changing demands of the market, today's packaging technology must demonstrate ever-increasing performance, cost effectiveness and reliability. When a semiconductor package is assembled, a number of components must be selected, including the die attach adhesive, lead frame, epoxy molding compound (EMC), and gold wire. Unfortunately, the performance of the pack-age is not related to any individual component. Rather, the entire material set must be evaluated for compatibility and interaction. This is not a simple task, since package performance can be significantly impacted by many additional factors including: package design,substrate design, size, and treatment; and die size, thickness, and passivation. Additionally, customer requirements must be considered in packaging material selection. Therefore, in practice, many iterations of trial and error are performed to identify the appropriate materials needed to meet package reliability requirements. This is a very cumbersome process, which causes time delays and high costs, and can quickly lead to a dissatisfied customer. As one might imagine, an experienced engineer's knowledge and memory, of prior assembly experiences can be an invaluable resource in the selection of packaging materials. However, a highly experienced engineer is not always available and even when one is involved, the selection process is still a very challenging endeavor. Case-based reasoning (CBR) helps to resolve this issue: it provides support for decision-makers when solving new problems on the basis of past experiences (i.e., previous cases), Case-based reasoning is an artificial intelligence technology that helps to solve problems by storing, retrieving and adapting past situations or cases. In the case-based system, a case is usually a specific problem that has been previously encountered and solved. Like most humans, when faced with a new problem, a case-based system compares the current problem with cases encountered in the past to determine if one of the earlier experiences can provide a solution. If a similar case exists, the solution to complex problems is found in matter of seconds.