Intelligent control system and method for semiconductor manufacturing device and technology

Abstract

The invention provides an intelligent control system and method for the semiconductor manufacturing device and technology, and the system comprises a data clustering processing unit, a data classification processing unit, a data marking unit, a support vector machine training and testing verification unit, an intelligent monitoring unit, and a continuous learning unit. The data clustering processing unit carries out the preprocessing of data through a K-mean clustering algorithm, and carries out the outlier judgment algorithm to obtain a candidate set of outliers. The data classification processing unit carries out the classification processing of the candidate set of outliers through a local outlier factor method, and obtains a sample data set. The support vector machine training and testing verification unit is used for dividing the sample data set into a training sample set and a test sample set, carrying out the training of a support vector machine through the training sample set, and obtaining a training result. The system is built through the machine learning based on the support vector machine, and achieves the intelligent control of the semiconductor manufacturing device and technology.

Description

technical field [0001] The invention relates to the technical field of control of semiconductor manufacturing equipment and processes, in particular to an intelligent control system and method for semiconductor manufacturing equipment and processes. Background technique [0002] The manufacturing process of semiconductor materials and devices involves various physical and chemical processes of different sizes from macroscopic to microscopic to atomic and electronic levels. The performance of semiconductor materials is based on the characterization of atomic behavior, and the performance of semiconductor devices is based on the characterization of electronic behavior. Existing semiconductor manufacturing equipment can detect and control macroscopic temperature, pressure, flow, chemical composition and microscopic physical and chemical processes in the manufacturing process of semiconductor materials and devices; with the development of automation technology, sensing technology...

AI Technical Summary

Problems solved by technology

[0004] a. The influence of human factors is large: In the above mode, the use method and effect of the test data of the conductor manufacturing equipment and process are determined by the experience and judgment of the technicians themselves, so the process results after the occurrence of abnormal events are very different. , and different engineers also have different differences with each other, especially the difference in process results between the less experienced and the more experienced engineers is very large;

[0005] b. Lack of coherent learning mechanism: the handling of each abnormal event is also a learning opportunity, which can provide help for future handling of related events, but due to the lack of system support, the historical data of each abnormal event processing, including abnormal event phenomenon analysis and handling opinions The execution effect is scattered in different spaces and cannot form a continuous learning mechanism;

[0006] c. It takes a long time to manually process data: technicians may spend several hours on the decision of an appropriate control parameter, which seriously reduces production capacity;

Images