Method for process control of semiconductor manufacturing equipment
View Patent ↗A method of fault identification on a semiconductor manufacturing tool includes monitoring tool sensor output, establishing a fingerprint of tool states based on the plurality of sensors outputs, capturing sensor data indicative of fault conditions, building a library of such fault fingerprints, comparing present tool fingerprint with fault fingerprints to identify a fault condition and estimating the effect of such a fault condition on process output. The fault library is constructed by inducing faults in a systematic way or by adding fingerprints of known faults after they occur.
1. A method of fault detection in a semiconductor substrate chamber processing tool having at least one sensor providing a plurality of data sensitive to tool-state and process-state changes, the method comprising the steps of:
(a) establishing a set of vectors representing the magnitude and direction of the deviation of sensor data from nominal values for a state of the tool under a fault condition, said fault condition generating a recordable fault fingerprint,
(b) performing step (a) a plurality of times for a plurality of different fault conditions respectively and storing the resultant sets of vectors in a fault fingerprint library, the fault fingerprints being substantially invariant across different tools built to the same nominal specification and running the same nominal process,
(c) determining a set of vectors representing the deviation of sensor data from nominal values for the present state of the tool, and
(d) detecting a fault based on a comparison of the present state set of vectors with at least one fault fingerprint in the fault fingerprint library.
2. The method claimed in claim 1 , wherein the nominal values used for calculating the set of vectors for the present state are nominal values of the sensor data from the sensor of the said tool.
3. The method claimed in claim 1 , wherein the nominal values used for calculating the set of vectors for the present state are nominal values of the sensor data from the sensor of different manufacturing equipment built to the same nominal specification and running the same nominal process as the first mentioned manufacturing equipment.
4. The method claimed in claim 1 , wherein the comparison is made by correlation between the sets of fault fingerprint and present state vectors.
5. The method claimed in claim 1 , wherein the comparison is made by calculating a Euclidean distance between the sets of fault fingerprint and present state vectors.
6. The method claimed in claim 1 , further comprising the step of predicting the impact of the fault on a particular process output.
7. The method claimed in claim 1 , further comprising the step of controlling at least one tool input to compensate for the fault.
8. The method claimed in claim 1 , wherein the fault fingerprint is derived from a tool profile comprising a set of tool input versus sensor response curves.
9. The method claimed in claim 1 , wherein the tool comprises a plasma chamber.
10. A computer readable medium containing program instruction which, when executed by a data processing device, perform the method steps claimed in claim 1 .