Proactive Statistical Process Control Using AI: A Time Series Forecasting Approach for Semiconductor Manufacturing

2025-09-19

AI Summary

Traditional statistical process control (SPC) relies on reactive, post-event interventions, leading to material waste and unplanned line stoppages. To address this, we propose a proactive, AI-enhanced SPC framework that tightly integrates time-series forecasting with classical SPC rules for early quality anomaly detection in semiconductor manufacturing. Specifically, we employ Facebook Prophet to model irregularly sampled industrial time-series data and forecast critical quality parameters; risk levels are then dynamically assigned based on prediction intervals and SPC criteria. Our key contributions are: (i) the first prospective SPC paradigm supporting irregular sampling—extending beyond conventional real-time monitoring; and (ii) empirical validation on real wafer fabrication data, achieving a 32% reduction in forecasting error and 94.7% risk identification accuracy. This significantly enhances early fault intervention capability, thereby reducing unplanned downtime and defect rates.

Technology Category

• Machine Learning: Time-Series/Data Streams
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

In the manufacturing industry, it is very important to keep machines and processes running smoothly and without unexpected problems. One of the most common tools used to check if everything is working properly is called Statistical Process Control (SPC). Traditional SPC methods work by checking whether recent measurements are within acceptable limits. However, they only react after a problem has already occurred. This can lead to wasted materials, machine downtime, and increased costs. In this paper, we present a smarter way to use SPC. Instead of just reacting to issues after they happen, our system can predict future problems before they occur. We use a machine learning tool called Facebook Prophet, which is designed to work with time-series data (data that changes over time). Prophet looks at past data and forecasts what the next value will be. Then, we use SPC rules to decide if the predicted value is in a Safe zone (no problem), a Warning zone (needs attention), or a Critical zone (may require shutting down the process). We applied this system to real data from a semiconductor manufacturing company. One of the challenges with this data is that the measurements are not taken at regular time intervals. This makes it harder to predict future values accurately. Despite this, our model was able to make strong predictions and correctly classify the risk level of future measurements. The main benefit of our system is that it gives engineers and technicians a chance to act early - before something goes wrong. This helps reduce unexpected failures and improves the overall stability and reliability of the production process. By combining machine learning with traditional SPC, we make quality control more proactive, accurate, and useful for modern industry.

Problem

• Predicting manufacturing issues before they occur using AI forecasting
• Overcoming irregular time intervals in semiconductor production data
• Transforming reactive statistical control into proactive risk prevention

Innovation

• Uses Facebook Prophet for time series forecasting
• Applies SPC rules to predicted values for proactive alerts
• Handles irregular time intervals in manufacturing data