A Novel Rolling-Window and Production-Maintenance-Based Machine Learning Approach to Virtual Metrology in Semiconductor Manufacturing

Virtual metrology enables semiconductor manufacturers to continuously monitor and predict the quality and performance of semiconductor production during the manufacturing process. This kind of real-time monitoring tool is essentially important for maintaining process stability and ensuring consistent product quality. In this paper, a new rolling-window and production-maintenance-based approach is proposed on a weekly basis to establish the virtual metrology system. The proposed thickening and dewatering framework serves as the central core of the virtual metrology model, enabling real-time information and feedback to aid in making timely adjustments to the processing tool within machinery limitations. A meticulous approach to addressing each component within this innovative framework has been instrumental in achieving exceptional VM performance. The training dataset is routinely updated as the production maintenance is taking place to facilitate model retraining. A practical challenge to the domain engineer under certain circumstances where the process parameter considered in the virtual metrology model is realistically run out of specification is also rigorously investigated in this research. For the evaluation purposes, a real-world industrial case of the chemical vapor deposition process in semiconductor manufacturing is presented to illustrate the proposed approach. The proposed virtual metrology approach shows a substantial improvement in mean absolute error with 39.99%, 26.26%, and 30.75% for three different recipes, respectively, as compared to the base model currently implemented on the operation site. Note to Practitioners—Virtual Metrology relies on advanced data analytics and machine learning algorithms to establish predictive models for production measurements. This kind of models leverage historical raw trace data, sensor readings, and other relevant information to estimate critical quality characteristics, such as film thickness, wafer properties, and critical dimensions. To respond to dynamic changes of processing specification and production conditions, the dataset is collected online on a weekly basis to train the predictive model. Practically, an occurrence of production maintenance to trigger the model re-training and feature selection between rolling windows are particularly designed in the proposed approach as well.