Breakdown diagnosis method for semiconductor devices

Abstract

The invention discloses a breakdown diagnosis method for semiconductor devices. The method includes the following steps: firstly establishing an expert system which includes a fuzzy rule database and an inference engine; further, conducting fuzzy processing on a semiconductor device real-time monitoring parameter to generate a fuzzy fact; the inference engine, on the basis of the fuzzy fact, performing fuzzy processing by interacting with the fuzzy rule database to generate a breakdown diagnosis result; and on the basis of actual application conditions of the breakdown diagnosis result, carrying out rule intensity self-learning correction targeted at the fuzzy rule database. According to the invention, the method performs fuzzy inference and further obtains the breakdown diagnosis result based on the rete algorithm, and carries out rule intensity self-learning correction on the fuzzy rule database in combination with the actual application of the breakdown diagnosis result, so that the method increases the precision and automation of the breakdown diagnosis for semiconductor devices and ensures efficient and stable operation of the semiconductor technology.

Description

technical field [0001] The invention belongs to the field of semiconductor manufacturing, and in particular relates to a fault diagnosis method for semiconductor process equipment. Background technique [0002] The operating status of process equipment in semiconductor enterprises has a great impact on the production capacity of the enterprise, and the cost of semiconductor process equipment is extremely expensive. Improving equipment maintenance efficiency and reducing equipment downtime is an important way to improve enterprise production capacity and control production costs. Therefore, it has become an urgent need for semiconductor companies to provide convenient, practical and reliable fault diagnosis for semiconductor process equipment, and the increasingly complex structure of equipment has also brought great challenges to fault diagnosis. Intelligent fault diagnosis technology has opened up a new way for this requirement, and it is of high value to apply intelligent ...

AI Technical Summary

Problems solved by technology

[0004] Most of the current expert systems use forward reasoning. When the number of knowledge rules is large, explosive combinations of knowledge are likely to occur, resulting in low pattern matching efficiency. On the other hand, the construction of fuzzy knowledge bases in expert systems mainly depends on experts Experience, in the process of using the fuzzy reasoning system, it also mainly relies on experts to maintain the knowledge base, lacking a self-learning correction mechanism based on reasoning result samples

Images