Sequence-Aware Inline Measurement Attribution for Good-Bad Wafer Diagnosis
This addresses root cause analysis for wafer defects in semiconductor manufacturing, which is incremental as it builds on existing Shapley values.
The paper tackles the problem of identifying problematic upstream processes for wafer defects in semiconductor manufacturing by proposing Trajectory Shapley Attribution (TSA), an extension of Shapley values, which overcomes limitations like ignoring sequence and arbitrary reference points, and applied it to experimental front-end-of-line processes at a fab to identify relevant measurement items.
How can we identify problematic upstream processes when a certain type of wafer defect starts appearing at a quality checkpoint? Given the complexity of modern semiconductor manufacturing, which involves thousands of process steps, cross-process root cause analysis for wafer defects has been considered highly challenging. This paper proposes a novel framework called Trajectory Shapley Attribution (TSA), an extension of Shapley values (SV), a widely used attribution algorithm in explainable artificial intelligence research. TSA overcomes key limitations of standard SV, including its disregard for the sequential nature of manufacturing processes and its reliance on an arbitrarily chosen reference point. We applied TSA to a good-bad wafer diagnosis task in experimental front-end-of-line processes at the NY CREATES Albany NanoTech fab, aiming to identify measurement items (serving as proxies for process parameters) most relevant to abnormal defect occurrence.