Control method for fabrication technology of analysis estimation-correcting integrated circuit by time series

Abstract

The invention discloses a method for predicting and correcting an integrated circuit (IC) manufacturing process based on time series analysis, which belongs to the field of IC manufacturing techniques. The data related to the IC manufacturing results are separated by establishing a process model to extract the easy-to-control process parameters related to the manufacturing results; the influence values of the other parameters are arranged in time order to form a time sequence; the overall change trend of the time sequence (potential change trend of the manufacturing results) is predicted by using the time series analysis algorithm such as autoregressive integrated moving average (ARMA) model; the predicted process fluctuation is compensated by regulating the easy-to-control process parameters to stabilize the manufacturing result and thus to realize the dynamic treatment of process parameters. The invention optimizes the process control without hardware investment and increase in manufacturing cost, and greatly increases the stability of manufacturing results.

Description

technical field [0001] The invention belongs to the technical scope of integrated circuit manufacturing, and in particular relates to a control method for predicting and correcting integrated circuit manufacturing processes by using time series analysis. Background technique [0002] The background of the present invention has two aspects, one is in the field of mathematics, has carried out many years of research on wide stationary random time series, and has formed many algorithms for time series prediction; the other is in the field of integrated circuit manufacturing, the process results of each step Objectively, it is fluctuating, and the effect of the process constitutes a time series that fluctuates over time. The introduction of time series analysis technology into the process control of integrated circuit manufacturing will make it possible to predict process fluctuations, so that the process conditions can be corrected in advance before the actual fluctuations occur...

AI Technical Summary

Problems solved by technology

[0012] Second, common forecasting applications, such as predicting the sunspot activity cycle, all have an implicit premise that the data sequence will not be disturbed artificially, otherwise the data sequence will not be wide, stable and random, and the prediction algorithm will not be correct and accurate applied

[0013] Although the idea of ​​applying a relatively mature time series prediction algorithm to the advanced process control field of integrated circuit manufacturing is very simple, in practice, it is necessary to deal with the logical self-consistency between the algorithm and the application.

Images