US 12,411,479 B2
Method and apparatus for determining cause of abnormality in a semiconductor manufacturing chamber
Kazushi Shoji, Sapporo (JP); Shintaro Saruwatari, Sapporo (JP); Nobutoshi Terasawa, Sapporo (JP); and Motokatsu Miyazaki, Sapporo (JP)
Assigned to TOKYO ELECTRON LIMITED, Tokyo (JP)
Filed by Tokyo Electron Limited, Tokyo (JP)
Filed on Jun. 17, 2021, as Appl. No. 17/350,444.
Claims priority of application No. 2020-107706 (JP), filed on Jun. 23, 2020.
Prior Publication US 2021/0397169 A1, Dec. 23, 2021
Int. Cl. G05B 19/418 (2006.01); G05B 23/02 (2006.01); H01L 21/67 (2006.01)
CPC G05B 19/41875 (2013.01) [G05B 23/0275 (2013.01); H01L 21/67248 (2013.01); H01L 21/67276 (2013.01); G05B 2219/32368 (2013.01); G05B 2219/45031 (2013.01)] 10 Claims
OG exemplary drawing
 
1. An information processing apparatus comprising:
a memory;
and a processor, wherein the processor, when executing program instructions stored in the memory, is configured to perform:
a sensor data collecting operation to acquire sensor waveform data represented with respect to a sensor value axis and a time axis, measured by sensors in a plurality of semiconductor manufacturing apparatuses each of which executing processes according to a same recipe;
a monitoring band calculating operation to calculate each monitoring band for the sensor waveform data represented with respect to the sensor value axis and the time axis used in a waveform monitoring method from a predetermined number or more of the sensor waveform data;
an abnormality sign detecting operation to monitor a waveform of the sensor waveform data using each monitoring band for the sensor waveform data represented with respect to the sensor value axis and the time axis and detect an abnormality sign of the semiconductor manufacturing apparatus;
a score calculating operation to calculate a result of monitoring a waveform of the sensor waveform data using the monitoring band for the sensor waveform data as a score for each sensor and each processing step;
a correlation calculating operation to:
identify a target sensor showing abnormality and its corresponding processing step as a target pair based on the abnormality sign detection;
calculate correlation coefficients between scores of each combined pair of the sensors and the processing steps from the scores for both normal and abnormal time;
calculate a contribution rate for each combined pair based on:
(i) a difference between a latest degree of divergence and an average degree of divergence during learning, and
(ii) a difference between correlation coefficients at normal time and at abnormal time;
create a contribution rate table on combinations of sensors and processing steps that are highly related to behavior of the target sensor based on the calculated contribution rates;
a factor estimating operation to combine (i) the contribution rate table with (ii) a factor estimation rule stored in a factor estimation rule storage to estimate a cause of the abnormality sign;
and a notification operation to notify a user of the cause.