Recipe-independent Tool Health Indicator and Fault Prognosis

Advanced sensor and information technologies have made real-time tool data readily accessible to equipment and process engineers. With the real-time tool data, one can evaluate the overall tool condition so that tool maintenance can be more effectively scheduled and the post-maintenance tool condition can be more easily checked. However, due to the frequent change of the recipes and the diversity of operations, the overall tool health is very difficult to evaluate. This paper provides a recipe-independent health indicator to faithfully reflect the tool condition regardless of recipe/operation changes. A two-steps fault prognosis method is then developed to find the root causes when the tool health signals a problem. The proposed indicator and prognosis methods are tested and demonstrated through an applied materials PECVD tool data from a FAB in Taiwan.