Yield prediction models for optimization of high-speed micro-processor manufacturing processes

Neural network based yield prediction models are developed to optimize high-speed microprocessor manufacturing processes. Based on sixty measured ET (electrical test) data, wafer level parametric yield prediction models are developed. In this work, manufacturing yield was considered as a manufacturing performance index because it is critical to overall manufacturing cost and product quality. The prediction results show 41.09% improvement as compared to a statistical prediction model using multiple regression. These modeling approaches are applied to predict final chip yield and speed, and ultimately, this neural prediction model is used to find optimal process conditions. With the successful implementation of this work, it can serve as a catalyst to improve productivity and product quality.