Anomaly Source Identification in Multi-Apparatus Manufacturing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In semiconductor manufacturing systems, identifying the source of anomalies in manufacturing processes is time-consuming and inefficient due to manual identification by engineers, especially in complex processes involving multiple apparatuses.
Innovation Solution
A method that involves receiving sensor data and measurement data to determine an anomaly index, identifying candidate processing apparatuses, and using machine learning models to generate likelihood indices for each apparatus, facilitating quicker identification of the anomaly source.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If manual identification of anomaly sources by engineers is used, then the manufacturing process can be managed with simple systems, but the troubleshooting time and downtime increase significantly
Solution Approach 1:
An anomaly determination device is introduced as an intermediary system between the manufacturing apparatuses and engineers. This device receives sensor data from multiple apparatuses, performs automated analysis to determine anomaly sources, and presents findings to engineers, thereby reducing their manual investigation time while maintaining system manageability
Solution Approach 2:
The manual mechanical process of engineers physically inspecting and analyzing data from multiple apparatuses is replaced by an automated electronic system that collects sensor data, processes it through analysis algorithms, and automatically determines anomaly sources, significantly reducing troubleshooting time
2Measurement precision
If multiple sensors and data collection points are deployed across processing apparatuses, then the precision of anomaly source identification improves, but the complexity of data management and processing increases
Solution Approach 1:
The anomaly determination device is designed as a universal system that can handle sensor data from multiple different types of processing apparatuses through a standardized interface. It performs multiple functions including data collection, preprocessing, anomaly detection, and source identification, thereby managing complex multi-source data through a single multi-functional platform
Solution Approach 2:
Data from multiple sensors and processing apparatuses are merged into a unified analysis framework. The system combines sensor data, measurement data, and process parameters into a single dataset that is processed together, enabling comprehensive anomaly source identification while simplifying data management through integration
Data Source
AI summary
A method for determining a source of an anomaly in manufacturing processes can include obtaining measurement data of features of each product in a set of products, upon detection of the anomaly in a target product, identifying processing apparatuses among the processing apparatuses that have been traversed by the target product as candidate processing apparatuses, determining, for each candidate processing apparatus, a measurement data index indicating a degree of likelihood of the candidate processing apparatus being the source of the anomaly in the target product based on the measurement data obtained for a subset of products among the set of products that have traversed the candidate processing apparatus and a reference set of the measurement data obtained for the remaining products among the set of products, and outputting an indication of candidate processing apparatuses as the source of the anomaly in the target product based on the measurement data index.