DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
This Office Action is in response to communication filed on 10/30/2025, wherein Claims 1-8, 10-14, and 21-27 are pending.
Response to Arguments
Applicant’s arguments, filed on 10/30/2025, with respect to the rejection(s) of claim(s) 1-8, 10-14, and 21-27 under 35 USC 103, have been fully considered and are persuasive. Therefore, the rejection has been withdrawn. However, upon further consideration, a new ground(s) of rejection is made.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-4, 10-12, and 21-24 are rejected under 35 U.S.C. 103(a) as being unpatentable over US20180082826 to Guha et al. (hereinafter Guha) in view of US20240095432 to Sawlani et al. (hereinafter Sawlani) and in further view of US20230400847 to Guo et al. (hereinafter Guo).
Regarding Claim 1: Guha discloses:
“A method, comprising: obtaining, by a processor, a plurality of sensor values associated with a deposition process performed, according to a recipe, in a process chamber to deposit film on a surface of a substrate” (Figs. 1-2, para 0015 – “A plurality of sensors of the plasma reactor is included, and each of the plurality of sensors is configured to produce a data stream of information during operation of the plasma reactor for carrying out the plasma process”; para 0049 – “types of plasma chambers can include deposition chambers that utilize different types of deposition processes… Anyone of these chambers may be controlled by a controller 120 or a computer, so as to adjust system controls 124 of the plasma reactor 100… The plasma reactor 100 may also be associated with a plurality of sensors 132. In some embodiments, the sensors will vary depending on the structure of the plasma reactor 100, or additional sensors may be added to the plasma reactor 100 to capture specific types of data from the plasma 120 during processing”; para 0006 – “A plurality of data streams are received from the plasma reactor during the processing of the substrate. The plurality of data streams are used to identify current processing state values”; para 0011 – “the processing of the substrate is identified for a specific plasma reactor and a specific process recipe (i.e. film deposition, added by examiner)”);
“wherein the plurality of sensor values are obtained from a set of sensor associated with a sub-system of the process chamber” (para 0015 – “A plurality of sensors of the plasma reactor is included, and each of the plurality of sensors is configured to produce a data stream of information during operation of the plasma reactor for carrying out the plasma process.”);
“applying a machine-learning model to the plurality of sensor values, the machine-learning model trained based on historical sensor data of the sub-system and task data associated with the recipe for depositing the film” (Fig. 2; 136 – data streams from sensors; 180 – machine learning engine; para 0017; para 0039 – “in addition to comparing current processing states to desired processing states for a plasma process type and a plasma reactor type, a machine learning engine is configured to learn from past processing (i.e. historical sensor data, added by examiner), which produces adjustments and refinements to the desired processing state values. In one embodiment, the machine learning engine operates a mathematical model that is refined over time and is able to learn and correct not only the desired processing state values but also the compensation variables and its magnitude which upon translation into physical variables can be used as tuning knobs to physical controls, values, settings of a plasma reactor.”; para 0062 – “Data streams 136 from sensors of the plasma reactor 100 are provided to the machine learning engine 180 of the multivariate processing 150”; see also para 0052 for recipe operations).);
“generating an output of the machine-learning model, wherein the output is indicative of a health of the sub-system” (para 0072 – “The machine learning engine 180 is therefore configured to receive the defined sensitivity of the sensor signals in operation 182 with respect to the compensation values that are to be applied to the tuning knobs 134. As mentioned above, the machine learning engine 180 is configured to produce current processing state values 172 (interpreted as output, added by examiner), which are compared to the desired processing state values 170 (interpreted as the indication of a health of the sub-system, added by examiner”);
“reflected by one or more current sensor values of the sub-system compared to one or more expected sensor values of the sub-system; identifying, based on the output of the machine-learning model, a fault pattern associated with the sub-system” (para 0055 – “the multivariate processing 130 is configured to utilize machine learning to compare desired processing state values (i.e. expected values, added by examiner) detected from data streams captured by sensors (i.e. one or more current sensor values, added by examiner) of the plasma reactor, and utilize machine learning to determine (i.e. identifying, based on the machine learning output, added by examiner) what adjustments are required to the specific tuning knobs so that the current processing state values match or closely approximate the desired processing state values (interpreted as identifying the fault pattern, added by examiner)”; see also para 0038 – “The data analytics uses data streams from different sensors present (or new sensors incorporated) in a plasma reactor. Data is then analyzed to provide substantial real-time information about a plasma reactor's processing environment. Through this information it is possible to define deviations from an ideal behavior (i.e. fault pattern, added by examiner) and henceforth derive a set of compensation values that can be applied to tuning knobs of the plasma reactor to correct for that deviation.”)
Guha does not specifically disclose:
“wherein the recipe defines a plurality of process chamber settings associated with the deposition process; and performing a corrective action, based on the fault pattern, to adjust one or more process chamber settings of the plurality of the process chamber settings defined by the recipe”.
However, Sawlani discloses:
“wherein the recipe defines a plurality of process chamber settings associated with the deposition process” (Claim 5 – “The method of claim 3, wherein the recipe features (i.e. plurality of process chamber settings, added by examiner) include one or more of the following parameters including workflow, gas flows, chamber temperature, chamber pressure, step durations, and radio-frequency (RF) values” (all of these are associated with the deposition process, added by examiner)).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Guha, as taught by Sawlani, in order to identify the process chamber settings defining a recipe.
Guha/Sawlani combination does not specifically disclose:
“performing a corrective action, based on the fault pattern, to adjust one or more process chamber settings of the plurality of the process chamber settings defined by the recipe”.
However, Guo discloses:
“performing a corrective action, based on the fault pattern” ,
“to adjust one or more process chamber settings of the plurality of the process chamber settings defined by the recipe” (para 0066 – “in response to identifying a particular RUL of a component that is less than a predetermined threshold time (e.g., less than ten days, less than twenty days, etc.), the predictive maintenance system can identify one or more actions that can be taken to increase the RUL of the component (i.e. corrective action, added by examiner)… the predictive maintenance system can identify a change to a recipe used by the manufacturing equipment (e.g., a temperature change, a pressure change, and/or any other suitable recipe change) (i.e. adjust the chamber settings, added by examiner) that is likely to extend the RUL of the component”; para 0067 – “the predictive maintenance system can perform a failure analysis (e.g., a fishbone analysis, a five why analysis, a fault tree analysis, (i.e. based on the fault pattern, added by examiner) etc.) to identify likely causes of the anomaly.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Guha/Sawlani combination, as taught by Guo, in order to correct the fault pattern of the chamber and make its performance more efficient.
Regarding Claim 2: Guha/Sawlani/Guo combination discloses the method of Claim 1 (see the rejection for Claim 1).
Guha further discloses:
“wherein the output comprises a scalar value indicative of a difference between measured values of a set of sensors associated with the sub-system and expected values of the set of sensors” (para 0040 – “the processing state is the desired processing state (i.e. expected values, added by examiner), which are measurable conditions within a processing environment of the plasma reactor. The conditions are, for example, measured by a plurality of sensors of the plasma reactor, which during processing, produce data streams. Each data stream, for example, can provide values read for a particular condition over time, and the changes in the values represent changes in said condition”; see also paras 0041 and 0043; para 0072 – “the machine learning engine 180 is configured to produce current processing state values 172, which are compared to the desired processing state values 170”).
Regarding Claim 3: Guha/Sawlani/Guo combination discloses the method of Claim 1 (see the rejection for Claim 1).
Guha further discloses:
“further comprising: converting, using a transform function, the output into a representative value within a predefined range” (para 0072 – “the machine learning engine 180 is configured to produce current processing state values 172 (i.e. output, added by examiner), which are compared to the desired processing state values 170 in order to identify and produce a compensation vector 194… . Compensation vector 194 is then processed through a transformation process 186 in order to produce compensation values 198. The transformation process includes converting the processing state value differences… The transformation 196, is therefore a conversion formula that converts the compensation vector values, which are in a virtual space (i.e., characterized in terms of sensor output values), to compensation values 188 that are in the real space (i.e., characterized in terms of real changes to one or more of the tuning knobs 184)”; para 0073 – “the compensation values K(r,t), are associated with a bound definition 197. The bound definition 197 (i.e. predefined range, added by examiner) identifies the amount by which the compensation values should be allowed to change in the given plasma reactor 100 ”).
Regarding Claim 4: Guha/Sawlani/Guo combination discloses the method of Claim 3 (see the rejection for Claim 3).
Guha further discloses:
“wherein the transform function comprises at least one of a linear function, a logit function, a sigmoid function, or an exponential function” (para 0083 – “There are several known machine learning algorithms that may be used. Without limitation, such examples may include linear/nonlinear regression”).
Regarding Claim 10: Guha discloses:
“A system comprising: a memory; and a processing device, operatively coupled to the memory” (para 0125 – “the controller 120, described with reference to FIG. 1 above may include a processor, memory, software logic, hardware logic and input and output subsystems from communicating with, monitoring and controlling a plasma processing system.”), to perform operations comprising:
“obtaining a plurality of sensor values associated with a deposition process performed, according to a recipe, in a process chamber to deposit film on a surface of a substrate” (Figs. 1-2, para 0015 – “A plurality of sensors of the plasma reactor is included, and each of the plurality of sensors is configured to produce a data stream of information during operation of the plasma reactor for carrying out the plasma process”; para 0049 – “types of plasma chambers can include deposition chambers that utilize different types of deposition processes… Anyone of these chambers may be controlled by a controller 120 or a computer, so as to adjust system controls 124 of the plasma reactor 100… The plasma reactor 100 may also be associated with a plurality of sensors 132. In some embodiments, the sensors will vary depending on the structure of the plasma reactor 100, or additional sensors may be added to the plasma reactor 100 to capture specific types of data from the plasma 120 during processing”; para 0006 – “A plurality of data streams are received from the plasma reactor during the processing of the substrate. The plurality of data streams are used to identify current processing state values”; para 0011 – “the processing of the substrate is identified for a specific plasma reactor and a specific process recipe”);
“wherein the plurality of sensor values are obtained from a set of sensor associated with a sub-system of the process chamber” (para 0015 – “A plurality of sensors of the plasma reactor is included, and each of the plurality of sensors is configured to produce a data stream of information during operation of the plasma reactor for carrying out the plasma process.”);
“applying a machine-learning model to the plurality of sensor values, the machine-learning model trained based on historical sensor data of the sub-system and task data associated with the recipe for depositing the film” (Fig. 2; 136 – data streams from sensors; 180 – machine learning engine; para 0017; para 0039 – “in addition to comparing current processing states to desired processing states for a plasma process type and a plasma reactor type, a machine learning engine is configured to learn from past processing, which produces adjustments and refinements to the desired processing state values. In one embodiment, the machine learning engine operates a mathematical model that is refined over time and is able to learn and correct not only the desired processing state values but also the compensation variables and its magnitude which upon translation into physical variables can be used as tuning knobs to physical controls, values, settings of a plasma reactor.”; para 0049 – “other types of plasma chambers can include deposition chambers that utilize different types of deposition processes (i.e. sub-system, added by examiner), other types of etching chambers, such as inductively coupled plasma (ICP) etching chambers, and the like.”; para 0062 – “Data streams 136 from sensors of the plasma reactor 100 are provided to the machine learning engine 180 of the multivariate processing 150”; see also para 0052 for recipe operations);
“generating an output of the machine-learning model, wherein the output is indicative of a health of the sub-system” (para 0072 – “The machine learning engine 180 is therefore configured to receive the defined sensitivity of the sensor signals in operation 182 with respect to the compensation values that are to be applied to the tuning knobs 134. As mentioned above, the machine learning engine 180 is configured to produce current processing state values 172 (interpreted as output, added by examiner), which are compared to the desired processing state values 170 (interpreted as the indication of a health of the sub-system, added by examiner”);
“reflected by one or more current sensor values of the sub-system compared to one or more expected sensor values of the sub-system; identifying, based on the output of the machine-learning model, a fault pattern associated with the sub-system” (para 0055 – “the multivariate processing 130 is configured to utilize machine learning to compare desired processing state values (i.e. expected values, added by examiner) detected from data streams captured by sensors (i.e. one or more current sensor values, added by examiner) of the plasma reactor, and utilize machine learning to determine (i.e. identifying, based on the machine learning output, added by examiner) what adjustments are required to the specific tuning knobs so that the current processing state values match or closely approximate the desired processing state values (interpreted as identifying the fault pattern, added by examiner)”; see also para 0038 – “The data analytics uses data streams from different sensors present (or new sensors incorporated) in a plasma reactor. Data is then analyzed to provide substantial real-time information about a plasma reactor's processing environment. Through this information it is possible to define deviations from an ideal behavior (i.e. fault pattern, added by examiner) and henceforth derive a set of compensation values that can be applied to tuning knobs of the plasma reactor to correct for that deviation.”).
Guha does not specifically disclose:
“wherein the recipe defines a plurality of process chamber settings associated with the deposition process; and performing a corrective action, based on the fault pattern, to adjust one or more process chamber settings of the plurality of the process chamber settings defined by the recipe”.
However, Sawlani discloses:
“wherein the recipe defines a plurality of process chamber settings associated with the deposition process” (Claim 5 – “The method of claim 3, wherein the recipe features (i.e. plurality of process chamber settings, added by examiner) include one or more of the following parameters including workflow, gas flows, chamber temperature, chamber pressure, step durations, and radio-frequency (RF) values” (all of these are associated with the deposition process, added by examiner)).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Guha, as taught by Sawlani, in order to identify the process chamber settings defining a recipe.
Guha/Sawlani combination does not specifically disclose:
“performing a corrective action, based on the fault pattern, to adjust one or more process chamber settings of the plurality of the process chamber settings defined by the recipe”.
However, Guo discloses:
“performing a corrective action, based on the fault pattern, to adjust one or more process chamber settings of the plurality of the process chamber settings defined by the recipe” (para 0066 – “in response to identifying a particular RUL of a component that is less than a predetermined threshold time (e.g., less than ten days, less than twenty days, etc.), the predictive maintenance system can identify one or more actions that can be taken to increase the RUL of the component (i.e. corrective action, added by examiner)… the predictive maintenance system can identify a change to a recipe used by the manufacturing equipment (e.g., a temperature change, a pressure change, and/or any other suitable recipe change) (i.e. adjust the chamber settings, added by examiner) that is likely to extend the RUL of the component”; para 0067 – “the predictive maintenance system can perform a failure analysis (e.g., a fishbone analysis, a five why analysis, a fault tree analysis, (i.e. based on the fault pattern, added by examiner) etc.) to identify likely causes of the anomaly.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Guha/Sawlani combination, as taught by Guo, in order to correct the fault pattern of the chamber and make its performance more efficient.
Regarding Claim 11: Guha/Sawlani/Guo combination discloses the method of Claim 10 (see the rejection for Claim 10).
Guha further discloses:
“wherein the output comprises a scalar value indicative of a difference between measured values of a set of sensors associated with the sub-system and expected values of the set of sensors” (para 0040 – “the processing state is the desired processing state (i.e. expected values, added by examiner), which are measurable conditions within a processing environment of the plasma reactor. The conditions are, for example, measured by a plurality of sensors of the plasma reactor, which during processing, produce data streams. Each data stream, for example, can provide values read for a particular condition over time, and the changes in the values represent changes in said condition”; see also paras 0041 and 0043; para 0072 – “the machine learning engine 180 is configured to produce current processing state values 172, which are compared to the desired processing state values 170”).
Regarding Claim 12: Guha/Sawlani/Guo combination discloses the method of Claim 10 (see the rejection for Claim 10).
Guha further discloses:
“wherein the processing device is to perform further operations comprising: converting, using a transform function, the output into a representative value within a predefined range” (para 0072 – “the machine learning engine 180 is configured to produce current processing state values 172 (i.e. output, added by examiner), which are compared to the desired processing state values 170 in order to identify and produce a compensation vector 194… . Compensation vector 194 is then processed through a transformation process 186 in order to produce compensation values 198. The transformation process includes converting the processing state value differences… The transformation 196, is therefore a conversion formula that converts the compensation vector values, which are in a virtual space (i.e., characterized in terms of sensor output values), to compensation values 188 that are in the real space (i.e., characterized in terms of real changes to one or more of the tuning knobs 184)”; para 0073 – “the compensation values K(r,t), are associated with a bound definition 197. The bound definition 197 (i.e. predefined range, added by examiner) identifies the amount by which the compensation values should be allowed to change in the given plasma reactor 100 ”).
Regarding Claim 21: Guha discloses:
“A non-transitory computer-readable storage medium comprising instructions that, when executed by a processing device operatively coupled to a memory, performs operations comprising” (para 0125 – “the controller 120, described with reference to FIG. 1 above may include a processor, memory, software logic, hardware logic and input and output subsystems from communicating with, monitoring and controlling a plasma processing system.”):
“obtaining a plurality of sensor values associated with a deposition process performed, according to a recipe, in a process chamber to deposit film on a surface of a substrate” (Figs. 1-2, para 0015 – “A plurality of sensors of the plasma reactor is included, and each of the plurality of sensors is configured to produce a data stream of information during operation of the plasma reactor for carrying out the plasma process”; para 0049 – “types of plasma chambers can include deposition chambers that utilize different types of deposition processes… Anyone of these chambers may be controlled by a controller 120 or a computer, so as to adjust system controls 124 of the plasma reactor 100… The plasma reactor 100 may also be associated with a plurality of sensors 132. In some embodiments, the sensors will vary depending on the structure of the plasma reactor 100, or additional sensors may be added to the plasma reactor 100 to capture specific types of data from the plasma 120 during processing”; para 0006 – “A plurality of data streams are received from the plasma reactor during the processing of the substrate. The plurality of data streams are used to identify current processing state values”; para 0011 – “the processing of the substrate is identified for a specific plasma reactor and a specific process recipe (i.e. film deposition, added by examiner)”);
“wherein the plurality of sensor values are obtained from a set of sensor associated with a sub-system of the process chamber” (para 0015 – “A plurality of sensors of the plasma reactor is included, and each of the plurality of sensors is configured to produce a data stream of information during operation of the plasma reactor for carrying out the plasma process.”);
“applying a machine-learning model to the plurality of sensor values, the machine-learning model trained based on historical sensor data of the sub-system and task data associated with the recipe for depositing the film” (Fig. 2; 136 – data streams from sensors; 180 – machine learning engine; para 0017; para 0039 – “in addition to comparing current processing states to desired processing states for a plasma process type and a plasma reactor type, a machine learning engine is configured to learn from past processing (i.e. historical sensor data, added by examiner), which produces adjustments and refinements to the desired processing state values. In one embodiment, the machine learning engine operates a mathematical model that is refined over time and is able to learn and correct not only the desired processing state values but also the compensation variables and its magnitude which upon translation into physical variables can be used as tuning knobs to physical controls, values, settings of a plasma reactor.”; para 0062 – “Data streams 136 from sensors of the plasma reactor 100 are provided to the machine learning engine 180 of the multivariate processing 150”; see also para 0052 for recipe operations).);
“generating an output of the machine-learning model, wherein the output is indicative of a health of the sub-system” (para 0072 – “The machine learning engine 180 is therefore configured to receive the defined sensitivity of the sensor signals in operation 182 with respect to the compensation values that are to be applied to the tuning knobs 134. As mentioned above, the machine learning engine 180 is configured to produce current processing state values 172 (interpreted as output, added by examiner), which are compared to the desired processing state values 170 (interpreted as the indication of a health of the sub-system, added by examiner”);
“reflected by one or more current sensor values of the sub-system compared to one or more expected sensor values of the sub-system; identifying, based on the output of the machine-learning model, a fault pattern associated with the sub-system” (para 0055 – “the multivariate processing 130 is configured to utilize machine learning to compare desired processing state values (i.e. expected values, added by examiner) detected from data streams captured by sensors (i.e. one or more current sensor values, added by examiner) of the plasma reactor, and utilize machine learning to determine (i.e. identifying, based on the machine learning output, added by examiner) what adjustments are required to the specific tuning knobs so that the current processing state values match or closely approximate the desired processing state values (interpreted as identifying the fault pattern, added by examiner)”; see also para 0038 – “The data analytics uses data streams from different sensors present (or new sensors incorporated) in a plasma reactor. Data is then analyzed to provide substantial real-time information about a plasma reactor's processing environment. Through this information it is possible to define deviations from an ideal behavior (i.e. fault pattern, added by examiner) and henceforth derive a set of compensation values that can be applied to tuning knobs of the plasma reactor to correct for that deviation.”).
Guha does not specifically disclose:
“wherein the recipe defines a plurality of process chamber settings associated with the deposition process; and performing a corrective action, based on the fault pattern, to adjust one or more process chamber settings of the plurality of the process chamber settings defined by the recipe”.
However, Sawlani discloses:
“wherein the recipe defines a plurality of process chamber settings associated with the deposition process” (Claim 5 – “The method of claim 3, wherein the recipe features (i.e. plurality of process chamber settings, added by examiner) include one or more of the following parameters including workflow, gas flows, chamber temperature, chamber pressure, step durations, and radio-frequency (RF) values” (all of these are associated with the deposition process, added by examiner)).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Guha, as taught by Sawlani, in order to identify the process chamber settings defining a recipe.
Guha/Sawlani combination does not specifically disclose:
“performing a corrective action, based on the fault pattern, to adjust one or more process chamber settings of the plurality of the process chamber settings defined by the recipe”.
However, Guo discloses:
“performing a corrective action, based on the fault pattern, to adjust one or more process chamber settings of the plurality of the process chamber settings defined by the recipe” (para 0066 – “in response to identifying a particular RUL of a component that is less than a predetermined threshold time (e.g., less than ten days, less than twenty days, etc.), the predictive maintenance system can identify one or more actions that can be taken to increase the RUL of the component (i.e. corrective action, added by examiner)… the predictive maintenance system can identify a change to a recipe used by the manufacturing equipment (e.g., a temperature change, a pressure change, and/or any other suitable recipe change) (i.e. adjust the chamber settings, added by examiner) that is likely to extend the RUL of the component”; para 0067 – “the predictive maintenance system can perform a failure analysis (e.g., a fishbone analysis, a five why analysis, a fault tree analysis, (i.e. based on the fault pattern, added by examiner) etc.) to identify likely causes of the anomaly.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Guha/Sawlani combination, as taught by Guo, in order to correct the fault pattern of the chamber and make its performance more efficient.
Regarding Claim 22: Guha/Sawlani/Guo combination discloses the non-transitory computer-readable storage medium of Claim 21 (see the rejection for Claim 21).
Guha further discloses:
“wherein the output comprises a scalar value indicative of a difference between measured values of a set of sensors associated with the sub-system and expected values of the set of sensors” (para 0040 – “the processing state is the desired processing state (i.e. expected values, added by examiner), which are measurable conditions within a processing environment of the plasma reactor. The conditions are, for example, measured by a plurality of sensors of the plasma reactor, which during processing, produce data streams. Each data stream, for example, can provide values read for a particular condition over time, and the changes in the values represent changes in said condition”; see also paras 0041 and 0043; para 0072 – “the machine learning engine 180 is configured to produce current processing state values 172, which are compared to the desired processing state values 170”).
Regarding Claim 23: Guha/Sawlani/Guo combination discloses the non-transitory computer-readable storage medium of Claim 21 (see the rejection for Claim 21).
Guha further discloses:
“further comprising: converting, using a transform function, the output into a representative value within a predefined range” (para 0072 – “the machine learning engine 180 is configured to produce current processing state values 172 (i.e. output, added by examiner), which are compared to the desired processing state values 170 in order to identify and produce a compensation vector 194… . Compensation vector 194 is then processed through a transformation process 186 in order to produce compensation values 198. The transformation process includes converting the processing state value differences… The transformation 196, is therefore a conversion formula that converts the compensation vector values, which are in a virtual space (i.e., characterized in terms of sensor output values), to compensation values 188 that are in the real space (i.e., characterized in terms of real changes to one or more of the tuning knobs 184)”; para 0073 – “the compensation values K(r,t), are associated with a bound definition 197. The bound definition 197 (i.e. predefined range, added by examiner) identifies the amount by which the compensation values should be allowed to change in the given plasma reactor 100 ”).
Regarding Claim 24: Guha/Sawlani/Guo combination discloses the non-transitory computer-readable storage medium of Claim 23 (see the rejection for Claim 23).
Guha further discloses:
“wherein the transform function comprises at least one of a linear function, a logit function, a sigmoid function, or an exponential function” (para 0083 – “There are several known machine learning algorithms that may be used. Without limitation, such examples may include linear/nonlinear regression”).
Claims 5-8, 13-14, and 25-27 are rejected under 35 U.S.C. 103(a) as being unpatentable over Guha in view of Sawlani, in further view of Guo, and in further view of JP2010225632A to Ikeuchi (hereinafter Ikeuchi).
Regarding Claim 5: Guha/Sawlani/Guo combination discloses the method of Claim 1 (see the rejection for Claim 1).
Guha does not explicitly disclose:
“wherein the output comprises a vector value indicative of the fault pattern”.
However, Ikeuchi discloses:
“wherein the output comprises a vector value indicative of the fault pattern” (para 0069 – “The failure prediction unit 24b predicts (i.e. outputs, added by examiner) failures of the devices included in the substrate processing apparatus 1a based on the parameter history table 23a and the failure pattern storage table 23b stored in the mass storage unit 23”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method, disclosed by Guha/Sawlani/Guo combination, as taught by Ikeuchi, in order to more efficiently monitor the fault pattern of the processing chamber with the goal to prevent abrupt stop of the processing or the damage to either chamber or substrate.
Regarding Claim 6: Guha/Sawlani/Guo/Ikeuchi combination discloses the method of Claim 5 (see the rejection for Claim 5).
Guha does not explicitly disclose:
“further comprising: using a classification algorithm to determine a type of failure experienced by the sub-system based on the fault pattern”.
However, Ikeuchi discloses:
“further comprising: using a classification algorithm to determine a type of failure experienced by the sub-system based on the fault pattern” (para 0070 – “FIG. 6 is a diagram showing an example of the data structure of the failure pattern storage tables 23b… The failure pattern storage tables 23b and 73a are tables that classify failures that occur in each device according to the failure condition, and store each classified failure in association with a plurality of patterns (in this embodiment, patterns 1 to 3) that indicate precursors to the failure. As shown in FIG. 6, the failure pattern storage tables 23b and 73a have similar data structures. Moreover, the failure pattern storage tables 23 b and 73 a are managed in a unified manner (i.e. using an algorithm, added by examiner) by the failure pattern server 7”; para 0074 – “The field relating to failure patterns stores multiple (three in this embodiment) patterns that are used to determine whether or not a precursor to each failure has appeared for each failure classified according to the failure condition (patterns 1 to 3 in FIG. 6)”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method, disclosed by Guha/Sawlani/Guo combination, as taught by Ikeuchi, in order to more efficiently monitor the fault pattern of the processing chamber with the goal to prevent abrupt stop of the processing or the damage to either chamber or substrate.
Regarding Claim 7: Guha/Sawlani/Guo/Ikeuchi combination discloses the method of Claim 6 (see the rejection for Claim 6).
Guha does not explicitly disclose:
“wherein the classification algorithm compares the fault pattern against a library of known fault patterns”.
However, Ikeuchi discloses:
“wherein the classification algorithm compares the fault pattern against a library of known fault patterns” (para 0070 – “FIG. 6 is a diagram showing an example of the data structure of the failure pattern storage tables 23b… The failure pattern storage tables 23b and 73a are tables that classify failures that occur in each device according to the failure condition, and store each classified failure in association with a plurality of patterns (in this embodiment, patterns 1 to 3) that indicate precursors to the failure. As shown in FIG. 6, the failure pattern storage tables 23b and 73a have similar data structures. Moreover, the failure pattern storage tables 23 b and 73 a are managed in a unified manner (i.e. using an algorithm, added by examiner) by the failure pattern server 7”; para 0074 – “The field relating to failure patterns stores multiple (three in this embodiment) patterns that are used to determine whether or not a precursor to each failure has appeared for each failure classified according to the failure condition (patterns 1 to 3 in FIG. 6)”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method, disclosed by Guha/Sawlani/Guo combination, as taught by Ikeuchi, in order to more efficiently monitor the fault pattern of the processing chamber with the goal to prevent abrupt stop of the processing or the damage to either chamber or substrate.
Regarding Claim 8: Guha/Sawlani/Guo/Ikeuchi combination discloses the method of Claim 6 (see the rejection for Claim 6).
Guha further discloses:
“wherein the classification algorithm comprises a Radial Basis Function (RBF) network or a neural network” (para 0083 – “There are several known machine learning algorithms that may be used. Without limitation, such examples may include linear/nonlinear regression, stepwise regression, decision tree learning (e.g., CART, Random Forest, Boosted Trees, etc.), association rule learning, artificial neural networks”).
Regarding Claim 13: Guha/Sawlani/Guo combination discloses the method of Claim 10 (see the rejection for Claim 10).
Guha does not explicitly disclose:
“wherein the output comprises a vector value indicative of the fault pattern”.
However, Ikeuchi discloses:
“wherein the output comprises a vector value indicative of the fault pattern” (para 0069 – “The failure prediction unit 24b predicts (i.e. outputs, added by examiner) failures of the devices included in the substrate processing apparatus 1a based on the parameter history table 23a and the failure pattern storage table 23b stored in the mass storage unit 23”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method, disclosed by Guha/Sawlani/Guo combination, as taught by Ikeuchi, in order to more efficiently monitor the fault pattern of the processing chamber with the goal to prevent abrupt stop of the processing or the damage to either chamber or substrate.
Regarding Claim 14: Guha/Sawlani/Guo/Ikeuchi combination discloses the method of Claim 13 (see the rejection for Claim 13).
Guha does not explicitly disclose:
“wherein the processing device is to perform further operations comprising: using a classification algorithm to determine a type of failure experienced by the sub-system based on the fault pattern”.
However, Ikeuchi discloses:
“further comprising: using a classification algorithm to determine a type of failure experienced by the sub-system based on the fault pattern” (para 0070 – “FIG. 6 is a diagram showing an example of the data structure of the failure pattern storage tables 23b… The failure pattern storage tables 23b and 73a are tables that classify failures that occur in each device according to the failure condition, and store each classified failure in association with a plurality of patterns (in this embodiment, patterns 1 to 3) that indicate precursors to the failure. As shown in FIG. 6, the failure pattern storage tables 23b and 73a have similar data structures. Moreover, the failure pattern storage tables 23 b and 73 a are managed in a unified manner (i.e. using an algorithm, added by examiner) by the failure pattern server 7”; para 0074 – “The field relating to failure patterns stores multiple (three in this embodiment) patterns that are used to determine whether or not a precursor to each failure has appeared for each failure classified according to the failure condition (patterns 1 to 3 in FIG. 6)”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method, disclosed by Guha/Sawlani/Guo combination, as taught by Ikeuchi, in order to more efficiently monitor the fault pattern of the processing chamber with the goal to prevent abrupt stop of the processing or the damage to either chamber or substrate.
Regarding Claim 25: Guha/Sawlani/Guo combination discloses the non-transitory computer-readable storage medium of Claim 21 (see the rejection for Claim 21).
Guha does not explicitly disclose:
“wherein the output comprises a vector value indicative of the fault pattern”.
However, Ikeuchi discloses:
“wherein the output comprises a vector value indicative of the fault pattern” (para 0069 – “The failure prediction unit 24b predicts (i.e. outputs, added by examiner) failures of the devices included in the substrate processing apparatus 1a based on the parameter history table 23a and the failure pattern storage table 23b stored in the mass storage unit 23”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method, disclosed by Guha/Sawlani/Guo combination, as taught by Ikeuchi, in order to more efficiently monitor the fault pattern of the processing chamber with the goal to prevent abrupt stop of the processing or the damage to either chamber or substrate.
Regarding Claim 26: Guha/Sawlani/Guo combination discloses the non-transitory computer-readable storage medium of Claim 21 (see the rejection for Claim 21).
Guha does not explicitly disclose:
“further comprising: using a classification algorithm to determine a type of failure experienced by the sub-system based on the fault pattern”.
However, Ikeuchi discloses:
“further comprising: using a classification algorithm to determine a type of failure experienced by the sub-system based on the fault pattern” (para 0070 – “FIG. 6 is a diagram showing an example of the data structure of the failure pattern storage tables 23b… The failure pattern storage tables 23b and 73a are tables that classify failures that occur in each device according to the failure condition, and store each classified failure in association with a plurality of patterns (in this embodiment, patterns 1 to 3) that indicate precursors to the failure. As shown in FIG. 6, the failure pattern storage tables 23b and 73a have similar data structures. Moreover, the failure pattern storage tables 23 b and 73 a are managed in a unified manner (i.e. using an algorithm, added by examiner) by the failure pattern server 7”; para 0074 – “The field relating to failure patterns stores multiple (three in this embodiment) patterns that are used to determine whether or not a precursor to each failure has appeared for each failure classified according to the failure condition (patterns 1 to 3 in FIG. 6)”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method, disclosed by Guha/Sawlani/Guo combination, as taught by Ikeuchi, in order to more efficiently monitor the fault pattern of the processing chamber with the goal to prevent abrupt stop of the processing or the damage to either chamber or substrate.
Regarding Claim 27: Guha/Sawlani/Guo/Ikeuchi combination discloses the non-transitory computer-readable storage medium of Claim 26 (see the rejection for Claim 26).
Guha does not explicitly disclose:
“wherein the classification algorithm compares the fault pattern against a library of known fault patterns”.
However, Ikeuchi discloses:
“wherein the classification algorithm compares the fault pattern against a library of known fault patterns” (para 0070 – “FIG. 6 is a diagram showing an example of the data structure of the failure pattern storage tables 23b… The failure pattern storage tables 23b and 73a are tables that classify failures that occur in each device according to the failure condition, and store each classified failure in association with a plurality of patterns (in this embodiment, patterns 1 to 3) that indicate precursors to the failure. As shown in FIG. 6, the failure pattern storage tables 23b and 73a have similar data structures. Moreover, the failure pattern storage tables 23 b and 73 a are managed in a unified manner (i.e. using an algorithm, added by examiner) by the failure pattern server 7”; para 0074 – “The field relating to failure patterns stores multiple (three in this embodiment) patterns that are used to determine whether or not a precursor to each failure has appeared for each failure classified according to the failure condition (patterns 1 to 3 in FIG. 6)”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method, disclosed by Guha/Sawlani/Guo combination, as taught by Ikeuchi, in order to more efficiently monitor the fault pattern of the processing chamber with the goal to prevent abrupt stop of the processing or the damage to either chamber or substrate.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Lyudmila Zaykova-Feldman whose telephone number is (469)295-9269. The examiner can normally be reached 7:30am - 4:30pm, Monday through Friday.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Arleen Vazquez, can be reached on 571-272-2619. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/LYUDMILA ZAYKOVA-FELDMAN/
Examiner Art Unit 2857
/LINA CORDERO/ Primary Examiner, Art Unit 2857