Renesas Electronics Corporation

Hitachi, Ltd.

Toshihiro Nakajima

Kazuyuki Tokorozuki

Hisahiko Abe

Toshihiro Morisawa

Ryoichi Shinohara

Mikio Shimizu

Masahide Nakakuki

Kosaku Tachikawa

A sensor monitors a treatment status of a predetermined manufacturing device, and an abnormality detection device detects an abnormality of a sensor signal that is a monitoring result of the sensor. The sensor signal is a digital data group obtained by sampling an analog waveform at a predetermined sampling period. A management apparatus learns characteristics of a plurality of digital data groups accumulated in past times through use of artificial intelligence to generate a learned model. An abnormality detection device holds the learned model and determines whether an abnormality is present in the digital data group of a current processing target by using the learned model.

Production system

A monitoring method that can detect a sign of disconnection of a heat generation source is provided. Further, a highly reliable semiconductor device is provided. The monitoring method uses a first control device that samples outputs of a plurality of thermometers at a first frequency (100 Hz sampling in S) and controls a plurality of heat generation sources based on temperature information obtained by sampling, and a second control device that forms information based on temperature information obtained by sampling at the first frequency (100 Hz sampling in S) and pieces of heat-generation-source information obtained by sampling of outputs of the respective heat-generation sources at the first frequency (100 Hz sampling in S). Based on the temperature information obtained by sampling at the first frequency (100 Hz sampling in S) and the pieces of heat-generation-source information obtained by sampling at the first frequency (100 Hz sampling in S), states of the heat generation sources are monitored.

Monitoring method and manufacturing method of semiconductor device

In a wafer polishing method, a within-wafer distribution model of a removal rate and a within-wafer distribution model of a polishing process are selected, and a within-wafer distribution of a removal rate is obtained by determining parameters of a within-wafer distribution model of a removal rate based on the within-wafer distribution of the film thickness before/after CMP, polishing condition data, and the selected within-wafer distribution model of the polishing process of the polished wafer. Then, a film thickness in the polishing process is estimated from passage of time based on the obtained within-wafer distribution of the removal rate, the selected within-wafer distribution model of the polishing process, and the film thickness before CMP of the wafer to be processed, thereby determining the polishing conditions with a restriction that the film thickness at each position in the within-wafer distribution of the film thickness after CMP satisfies the control limit.

Method of polishing semiconductor wafer

Growing community of inventors

Hitachinaka, Japan

Toshihiro Nakajima