Yield loss root cause analysis method based on information fusion

Abstract

The invention discloses a yield loss root cause analysis method based on information fusion, and relates to the technical field of OLED, display, panel and semiconductor manufacturing industry. Aimingat the root cause analysis of yield loss, the invention constructs a problem parameter rapid automatic positioning method and a factor level automatic division method based on information fusion, andsolves the problems of low automation degree, low data information utilization rate and low problem positioning precision of a traditional analysis method. According to the method, the data is labeled and grouped, the pertinence of the data is improved, different rule combinations are designed, the information of reject ratio data and parameter data in all aspects is fused, and the relationship between the reject ratio data and the parameter data is comprehensively considered, so that the positioning analysis of problem parameters is more accurate and efficient. Meanwhile, in order to determine the abnormal fluctuation range of problem parameters, a clustering-based parameter level division method is provided, and the problems that an existing division method is low in speed, low in precision and not beneficial to big data analysis are solved.

Description

technical field [0001] The invention belongs to the technical fields of display panels, OLEDs, TFT-LCDs and semiconductor manufacturing, and specifically relates to a method for analyzing the root cause of yield loss based on information fusion. Background technique [0002] The manufacturing process in the field of semiconductors and panels involves complex processes and various processes. Each process and process involves different sites, units, machines, tools, etc., and these production equipments correspond to many related parameters. Generally, the above Tens of thousands, and the amount of data is huge. When a yield problem occurs, it is necessary to quickly locate the machine that caused the loss of yield and its corresponding parameters; adjust the abnormal parameters to ensure the normal operation of the machine and solve the problem of yield loss. At present, the problem parameter search and analysis methods for yield problems mainly rely on experienced engineers...

AI Technical Summary

Problems solved by technology

At present, the problem parameter search and analysis methods for yield problems mainly rely on experienced engineers to pick out the defect rate data and parameter data of problem products from the database, and perform parameter correlation analysis and problem troubleshooting, which belongs to post-event static analysis. The degree of automation is low, there is a large time lag, the positioning accuracy is rough, and the efficiency is low, time-consuming and labor-intensive

Images