Response surface methodology (RSM) is an important tool for process parameter optimization, robust design and other quality improvement efforts. When the relationship between influential factors and output response is very complex, it's hard to find the real response surface by using RSM. In recent years Artificial Neural Networks (ANN) has been used in RSM. But the classical ANN does not work well under the constraints of real applications. An algorithm is proposed in this paper, which is a supplement of the classical ANN methodology. It makes networks closer to the response surface, so that training time is reduced and robustness is strengthened. The procedure of improving ANN by regressions is put forward and the comparisons among the three methods are computed graphically in three examples. Our research shows that the regression-based ANN methodology is a good supplement to the RSM and classical ANN methodology, which can yield satisfied results under condition that the scope of experiments is rigidly restricted.

How to continuously improve product and process quality has been a focus of research in quality management. A company that is going to set up its CAQ or establish an effective quality system should make sure that the CAQ or quality system will lead to continuous quality improvement so as to meet customer's growing demand for quality. Based on Juran's quality loop philosophy, the paper presents how to utilize continuous quality improvement tools in product design and manufacturing. It addresses the application of QFD and design of experiment to optimize product/process design and how to integrate quality tools. Based on the philosophy of concurrent quality engineering and successful experience of some world class businesses, the paper presents a continuous quality improvement flowchart and puts forward to the strategies to implement continuous quality improvement.