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 Arguments
Applicant's arguments filed June 1, 2026 have been fully considered but they are not persuasive.
In response to Applicant's argument on page 8 – 9 pertaining to “In Kale's architecture, the sensor generates its own data internally (i.e., images) and processes them via an inference engine to produce inference results. Critically, Kale's sensor does not receive real-time machine data from a plugin device communicatively coupled to a machine controller. Kale's architecture is fundamentally different from the claimed subject matter. Kale involves image-to-inference conversion within a single integrated device, not the claimed multidevice architecture where data reduction occurs because the first computing device filters real-time machine data received from a plugin device and transmits only interesting event data to a separate second computing device.”. The Examiner respectfully disagrees.
The claimed subject matter recites a first, second, and third computing device that are coupled and transmit data from the first, to the second, and to the third computing device. Kale teaches a multidevice architecture. Kale teaches, a first computing device (Fig. 3, ¶ 80 sensor(s) (e.g., 101)) coupled to a controller (Fig. 3, controller (102)) and a second computing device (Fig. 3, ¶ 80 computer system (131)) coupled to the first computing device.
In response to Applicant's argument on page 9 pertaining to “The combination of McCarson, Gandhi, Bergantz, and Kale fails to teach or suggest the amended subject matter requiring the specific data flow from a plugin device through the first computing device to the second computing device.”. The Examiner respectfully disagrees. McCarson teaches, first computing device (Fig. 1, example edge node 120).
Gandhi teaches, a second computing device (Fig. 1, processing device 150) coupled to a third computing device (Fig. 1, user on the graphical display medium 154), Bergantz teaches, specific data flow from device to device (Fig. 7, ¶ 95 predictive data 768). Kale teaches, a first computing device (Fig. 3, ¶ 80 sensor(s) (e.g., 101)) coupled to a second computing device (Fig. 3, ¶ 80 computer system (131)) coupled to the first computing device. Therefore, The combination of McCarson, Gandhi, Bergantz, and Kale teach specific data flow from a first computing device to a second computing device, and to a third computing device.
In response to Applicant's argument on page 10 pertaining to “McCarson's sensor interfacer 204 merely performs basic data cleaning operations, i.e., removing duplicate data, removing incomplete data, and removing data that does not correspond to an acceptable format type. (McCarson, paragraph [0025]). In contrast, claims 4 and 15 as amended specifies inputting the real-time data into "at least one local adaptive model" to determine which data is unnecessary, prior to inputting the data associated with the machine into the at least one low fidelity model. This is a fundamentally different operation where the local adaptive model is a machine learning model that makes intelligent, model-based determinations about data relevance for predicting machine failure, not simple data cleaning such as removing duplicates or formatting errors. None of the other cited references (Gandhi, Bergantz, Kale) cure this deficiency. Accordingly, claims 4 and 15 are patentable for at least these additional reasons.”. The Examiner respectfully disagrees.
Mcarson teaches using a local adaptive model to make determinations about data relevance (Fig. 2, ¶ 41 one or more machine learning algorithms to assist in the updated prediction. … fit the model to data points (observations)) as recited in claims 4 and 15.
In response to Applicant's argument on page 10 pertaining to “None of the cited references teach or suggest the specific feedback loop where the second computing device updates both a low fidelity model and a local adaptive model on the first computing device to improve the first computing device's ability to determine precedence, causality, and correlation of data as recited within the context of amended claim 11.”. The Examiner respectfully disagrees.
Gandhi teaches, updating both a low fidelity model (Fig. 1. Col. 7. Ln. 54 update the model 102) and a local adaptive model (Fig. 1. Col. 5. Ln. 58-59 send information to the model that is used to modify the model 102 to improve the first computing device's ability to determine precedence, causality, and correlation of data as recited within the context of amended claim 11. A feedback loop is used to update the low fidelity and local adaptive models.
In response to Applicant's argument on page 11 pertaining to “Gandhi's model 102 is "a construct relating multi-dimensional associated process parameters (a repertoire of unique, multi-sensor, process states)", and thus it is an empirical process model of sensor data relationships, not CAD data. (Gandhi, Col. 5, Ln. 3). CAD data, as recited in claim 21 and described in the specification, refers to computer-aided design data associated with the physical design and geometry of the machine, e.g., data that represents the physical structure of the manufacturing cell, manufacturing station, and/or machine. (Paragraph [0037]).”. The Examiner respectfully disagrees.
Gandhi teaches receiving data that is compared with a physical model (Fig. 1. Col. 5. Ln. 3 a model 102). CAD models are physical models. The data taught by Gandhi are CAD data that is compared with the physical CAD model.
In response to Applicant's argument on page 11 – 12 pertaining to “New claim 22 has been added to depend from claim 1 and recites in part "wherein the second computing device transmits one or more alerts to the third computing device, and wherein the one or more alerts include a root cause analysis associated with abnormal operation of the machine and a downtime risk". None of the cited references teach or suggest alerts that include both a root cause analysis associated with abnormal operation of the machine and a downtime risk, transmitted from the second computing device to the third computing device as recited within the context of claim 22.”. The Examiner respectfully disagrees.
Gandhi teaches, wherein the second computing device transmits one or more alerts (Fig. 1. Col. 5. Ln. 16 generate alerts 152) to the third computing device, and wherein the one or more alerts include a root cause analysis associated with abnormal operation of the machine (Fig. 1. Col. 7. Ln. 66 alerts indicate that a mechanical component is failing) and a downtime risk.
In response to Applicant's argument on page 12 pertaining to “New claim 23 has been added to depend from claim 1 and recites in part "wherein the machine failure prediction includes timing information that the machine may experience a failure or need maintenance". None of the cited references teach or suggest a machine failure prediction that specifically includes timing information of when the machine may experience a failure or need maintenance.”. The Examiner respectfully disagrees.
Gandhi teaches, a machine failure prediction that specifically includes timing information of when the machine may experience a failure or need maintenance (Fig. 2, ¶ 23 future occurrences of such process activity can be detected in an effort to take preventative measures prior to the occurrence of process cycle time waste).
In response to Applicant's argument on page 12 pertaining to “New claim 23 has been added to depend from claim 1 and recites in part "wherein the machine failure prediction includes timing information that the machine may experience a failure or need maintenance". None of the cited references teach or suggest a machine failure prediction that specifically includes timing information of when the machine may experience a failure or need maintenance. Gandhi teaches determining that a component is near failure, but does not disclose that the prediction includes timing information about when the failure may occur or when maintenance is needed.”. The Examiner respectfully disagrees.
McCarson teaches, wherein the machine failure prediction includes timing information that the machine may experience a failure or need maintenance (Fig. 2, ¶ 23 future occurrences of such process activity can be detected in an effort to take preventative measures prior to the occurrence of process cycle time waste).
Claim Rejections - 35 USC § 103
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.
Claim(s) 1 – 5, 7 – 11, 13 – 19, 21 – 23 are rejected under 35 U.S.C. 103 as being unpatentable over McCarson et al (US 2019/0340843 A1) (herein after McCarson) in view of Gandhi et al (US 10,295,965 B2) (herein after Gandhi), in view of Bergantz et al (US 2020/0324410 A1) (herein after Bergantz), and further in view of Kale et al. (US 2022/0032932 A1) (herein after Kale).
Regarding Claim 1, McCarson teaches, a method for predicting machine failure (Fig. 1, ¶ 50 method actions may be implemented; ¶ 12 downtime and/or damage to process control equipment), the method comprising: collecting real-time (Fig. 1, ¶ 11 sensors and/or actuators) data associated with a machine (Fig. 1, ¶ 12 process control equipment); inputting the real-time data associated with the machine into at least one low fidelity model (Fig. 1, ¶ 11 model based control) of a first computing device (Fig. 1, example edge node 120) to determine an interesting event (Fig. 1, ¶ 26 determines one or more patterns) associated with the machine; —.
McCarson fails to teach, — transmitting, via the first computing device, data associated with the interesting event to a second computing device; inputting the data associated with the interesting event into at least one high fidelity model of the second computing device to determine a machine failure prediction; transmitting, via the second computing device, the machine failure prediction to a third computing device; and displaying, via the third computing device, the machine failure prediction; wherein the interesting event includes a deviation from normal operation of the machine; and wherein a first amount of the real-time data associated with the machine received by the first computing device from a plugin device communicatively coupled to a controller of the machine is greater than a second amount of the data associated with the interesting event received by the second computing device from the first computing device.
In analogous art, Gandhi teaches, — transmitting, via the first computing device, data associated with the interesting event to a second computing device (Fig. 1, processing device 150); inputting the data associated with the interesting event into at least one high fidelity model (Fig. 1, modeling engine 104) of the second computing device to determine a machine failure prediction (Fig. 1. Col. 7. Ln. 66 mechanical component is failing); transmitting, via the second computing device, the machine failure prediction to a third computing device (Fig. 1, user on the graphical display medium 154); and displaying, via the third computing device, the machine failure prediction (Fig. 1. Col. 5. Ln. 16 generate alerts 152).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson by combining the method for predicting machine failure taught by McCarson with a method for, inputting the data associated with the machine into at least one low fidelity model of a first computing device to determine an interesting event associated with the machine; transmitting, via the first computing device, data associated with the interesting event to a second computing device; inputting the data associated with the interesting event into at least one high fidelity model of the second computing device to determine a machine failure prediction; transmitting, via the second computing device, the machine failure prediction to a third computing device; and displaying, via the third computing device, the machine failure prediction; taught by Gandhi for the benefit of minimal machine implementation cost and minimal continued maintenance [Gandhi: Col. 3, Ln. 33 – 36].
McCarson in view of Gandhi fail to teach, — wherein the interesting event includes a deviation from normal operation of the machine; and wherein a first amount of the real-time data associated with the machine received by the first computing device from a plugin device communicatively coupled to a controller of the machine is greater than a second amount of the data associated with the interesting event received by the second computing device from the first computing device.
In analogous art, Bergantz teaches, — wherein the interesting event (Fig. 7, ¶ 95 predictive data 768) includes a deviation from normal operation of the machine (Fig. 7, ¶ 95 predicted abnormality ( difference between directed position, and the actual location));
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi by combining the manufacturing process and component replacement prediction method taught by McCarson in view of Gandhi with a manufacturing process and component failure prediction method wherein, the interesting event includes a deviation from normal operation of the machine; taught by Bergantz for the benefit of performing corrective action (e.g. predicted operational maintenance, replacing components) to avoid the cost of unexpected component failure [Bergantz: ¶ 92 – 93].
McCarson in view of Gandhi in view of Bergantz fail to teach, — and wherein a first amount of the real-time data associated with the machine received by the first computing device from a plugin device communicatively coupled to a controller of the machine is greater than a second amount of the data associated with the interesting event received by the second computing device from the first computing device.
In analogous art, Kale teaches, and wherein a first amount of the real-time data (Fig. 3, ¶ 80 stream of real time sensor data) associated with the machine received by the first computing device (Fig. 3, ¶ 80 sensor(s) (e.g., 101)) from a plugin device communicatively coupled to a controller (Fig. 3, controller (102)) of the machine is greater than a second amount of the data (Fig. 3, ¶ 80 reduce or eliminate the need to transmit data) associated with the interesting event received by the second computing device (Fig. 3, ¶ 80 computer system (131)) from the first computing device.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi in view of Bergantz by combining the method performed by the first computing device and the second computing device taught by McCarson in view of Gandhi in view of Bergantz with the method performed by a first computing device and a second computing device, wherein a first amount of the real-time data associated with the machine received by the first computing device from a plugin device communicatively coupled to a controller of the machine is greater than a second amount of the data associated with the interesting event received by the second computing device from the first computing device; taught by Kale for the benefit of providing inference results from sensor data in order to transmit the sensor data between two computing devices with reduced bandwidth [Kale: ¶ 61].
Regarding Claim 2, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 1, which this claim depends on.
McCarson further teaches, the method of claim 1, wherein: the first computing device includes an edge computing device (Fig. 1, example edge node 120); the second computing device includes a remote computing device (Fig. 13, ¶ 73 external machines (e.g., computing devices of any kind); Note: Fig 13 is part of Fig 1, see ¶ 67); —
McCarson, Bergantz, and Kale fail to teach — and the third computing device includes a user device.
Gandhi further teaches, — and the third computing device includes a user device (Fig. 1, user on the graphical display medium 154).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi in view of Bergantz in view of Kale by combining the method for predicting machine failure taught by McCarson in view of Gandhi in view of Bergantz in view of Kale with a method wherein, the third computing device includes a user device; the second computing device includes a remote computing device; taught by Gandhi for the benefit of minimal machine implementation cost and minimal continued maintenance [Gandhi: Col. 3, Ln. 33 – 36].
Regarding Claim 3, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 1, which this claim depends on.
McCarson further teaches, the method of claim 1, wherein: the machine is used in connection with a manufacturing station (Fig. 1, ¶ 11 manufacturing stage); the data associated with the machine includes heterogeneous data (Fig. 1, ¶ 26 time window, one or more patterns); and the heterogeneous data includes timestamped data and parameter data (Fig. 1, ¶ 26 time window, one or more patterns).
Regarding Claim 4, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 1, which this claim depends on.
McCarson further teaches, 4. (Currently Amended) The method of claim 1, wherein, prior to inputting the data (Fig. 2, ¶ 25 retrieved sensor data) associated with the machine into the at least one low fidelity model of the first computing device, the method includes: inputting the real-time data into at least one local adaptive model (Fig. 2, ¶ 41 one or more machine learning algorithms to assist in the updated prediction. … fit the model to data points (observations)) of the first computing device to determine which of the real-time data associated with the machine is unnecessary data (Fig. 1, ¶ 25 duplicate data); and eliminating, via the first computing device, the unnecessary data (Fig. 1, ¶ 25 clean the retrieved sensor data; duplicate data to be removed).
Regarding Claim 5, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 1, which this claim depends on.
McCarson further teaches, the method of claim 1, including determining, via the first computing device, a first pattern (Fig. 1, ¶ 26 reference patterns) associated with performance of the machine.
5. (Currently Amended) The method of claim 1, including determining, via the first computing device, a first pattern (Fig. 1, ¶ 26 reference patterns) associated with performance of the machine and a second pattern associated (Fig. 1, ¶ 11 process excursions … an excursion is an instance of non-conformity of the product of interest) with the performance of the machine.
Regarding Claim 7, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 1, which this claim depends on.
McCarson further teaches, the method of claim 5, including comparing, via the first computing device, the first pattern and the second pattern; and wherein the deviation from normal operation of the interesting event (Fig. 1, ¶ 26 data patterns are compared, against one or more reference patterns) includes a difference (Fig. 1, ¶ 26 within a particular standard deviation) between the first pattern and the second pattern.
Regarding Claim 8, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 1, which this claim depends on.
McCarson further teaches, the method of claim 1, including generating, via the second computing device, a digital twin (Fig. 1, ¶ 17 digital twin 122) of the machine; and displaying, via the third computing device, at least a portion of the digital twin (Fig. 1, user on the graphical display medium 154).
Regarding Claim 9, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 1, which this claim depends on.
McCarson, Bergantz, and Kale fail to teach, the method of claim 1, including generating, via the second computing device, a high fidelity learned model; and storing, via the second computing device, the high fidelity learned model in a model archive connected to the second computing device.
Gandhi further teaches, the method of claim 1, including generating, via the second computing device, a high fidelity learned model (Fig. 1. Col. 7. Ln. 54 update the model 102); and storing, via the second computing device, the high fidelity learned model in a model archive (Fig. 1. Col. 7. Ln. 48-49 store it in a database) connected to the second computing device.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi in view of Bergantz in view of Kale by combining the method for predicting machine failure taught by McCarson in view of Gandhi in view of Bergantz in view of Kale with a method including generating, via the second computing device, a high fidelity learned model; and storing, via the second computing device, the high fidelity learned model in a model archive connected to the second computing device; taught by Gandhi for the benefit of minimal machine implementation cost and minimal continued maintenance [Gandhi: Col. 3, Ln. 33 – 36].
Regarding Claim 10, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 9, which this claim depends on.
McCarson, Bergantz, and Kale fail to teach, the method of claim 9, wherein generating the high fidelity learned model is triggered via the first computing device determining an additional interesting event.
Gandhi further teaches, the method of claim 9, wherein generating the high fidelity learned model is triggered (Fig. 1. Col. 5. Ln. 26-27 model 102 may be implemented in computer software) via the first computing device determining an additional interesting event (Fig. 1. Col. 6. Ln. 1-2 identifies observations ( e.g., asset state vectors) that).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi in view of Bergantz in view of Kale by combining the method for predicting machine failure taught by McCarson in view of Gandhi in view of Bergantz in view of Kale with a method wherein, generating the high fidelity learned model is triggered via the first computing device determining an additional interesting event; taught by Gandhi for the benefit of minimal machine implementation cost and minimal continued maintenance [Gandhi: Col. 3, Ln. 33 – 36].
Regarding Claim 11, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 9, which this claim depends on.
McCarson, Bergantz, and Kale fail to teach, 11. (Currently Amended) The method of claim 9, including updating, via the second computing device, the at least one low fidelity model and at least one local adaptive model of the first computing device such that the first computing device more effectively determines precedence, causality, and correlation of data received from the plugin device.
Gandhi further teaches, 11. (Currently Amended) The method of claim 9, including updating, via the second computing device, the at least one low fidelity model (Fig. 1. Col. 7. Ln. 54 update the model 102) and at least one local adaptive model (Fig. 1. Col. 5. Ln. 58-59 send information to the model that is used to modify the model 102) of the first computing device such that the first computing device more effectively determines precedence, causality, and correlation of data (Fig. 1. Col. 7. Ln. 24 The estimates are predicted values of the current process state based upon the model) received from the plugin device.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi in view of Bergantz in view of Kale by combining the method for predicting machine failure taught by McCarson in view of Gandhi in view of Bergantz in view of Kale a method including updating, 11. (Currently Amended) The method of claim 9, including updating, via the second computing device, the at least one low fidelity model and at least one local adaptive model of the first computing device such that the first computing device more effectively determines precedence, causality, and correlation of data received from the plugin device; taught by Gandhi for the benefit of minimal machine implementation cost and minimal continued maintenance [Gandhi: Col. 3, Ln. 33 – 36].
Regarding Claim 13, McCarson teaches, a system for predicting machine failure (Fig. 1, cyber physical system (CPS) 100; ¶ 12 downtime and/or damage to process control equipment), comprising: a controller (Fig. 2, sensor interfacer 204; Note: Fig 2 is part of Fig 1, see ¶ 18) for controlling a machine of a manufacturing station (Fig. 1, ¶ 11 manufacturing stage); a plurality of sensors (Fig. 1, sensors 114) disposed proximate the machine, the sensors communicatively coupled to the controller (Fig. 2, ¶ 19 FIG. 2 is communicatively connected (and/or interconnected)); a plugin device (Fig. 2, node interfacer 216) communicatively coupled to the controller; a first computing device (Fig. 1, example edge node 120) communicatively coupled to the plugin device, the plugin device transmits real-time (Fig. 1, ¶ 11 sensors and/or actuators) data associated with the machine to the first computing device (Fig. 2, ¶ 27 example node interfacer 216 transmits the, to other manufacturing cells (process control nodes)), and the first computing device executes at least one low fidelity model (Fig. 1, ¶ 11 model based control) to determine an interesting event (Fig. 1, ¶ 26 determines one or more patterns) associated with the machine; a second computing device (Fig. 13, ¶ 73 external machines (e.g., computing devices of any kind); Note: Fig 13 is part of Fig 1, see ¶ 67) communicatively coupled to the first computing device, the first computing device transmits data associated with the interesting event to the second computing device (Fig. 13, ¶ 73 facilitate exchange of data with external machines), —.
McCarson fails to teach, — and the second computing device executes at least one high fidelity model to determine a machine failure prediction; and a third computing device communicatively coupled to the second computing device, the second computing device transmits the machine failure prediction to the third computing device, and the third computing device displays the machine failure prediction; wherein the interesting event includes a deviation from normal operation of the manufacturing station and/or the machine; and wherein a first amount of the real-time data associated with the machine received by the first computing device from the plugin device is greater than a second amount of the data associated with the interesting event received by the second computing device from the first computing device.
In analogous art, Gandhi teaches, — and the second computing device (Fig. 1, processing device 150) executes at least one high fidelity model (Fig. 1, modeling engine 104) to determine a machine failure prediction (Fig. 1. Col. 7. Ln. 66 mechanical component is failing); and a third computing device (Fig. 1, user on the graphical display medium 154) communicatively coupled to the second computing device, the second computing device transmits the machine failure prediction to the third computing device, and the third computing device displays the machine failure prediction (Fig. 1. Col. 5. Ln. 16 generate alerts 152).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson by combining the second computing device taught by McCarson with a second computing device taught by Gandhi wherein, the second computing device executes at least one high fidelity model to determine a machine failure prediction; and a third computing device communicatively coupled to the second computing device, the second computing device transmits the machine failure prediction to the third computing device, and the third computing device displays the machine failure prediction; taught by Gandhi for the benefit of minimal machine implementation cost and minimal continued maintenance [Gandhi: Col. 3, Ln. 33 – 36].
McCarson in view of Gandhi fail to teach, — wherein the interesting event includes a deviation from normal operation of the manufacturing station and/or the machine; and wherein a first amount of the real-time data associated with the machine received by the first computing device from the plugin device is greater than a second amount of the data associated with the interesting event received by the second computing device from the first computing device.
In analogous art, Bergantz teaches, — wherein the interesting event (Fig. 7, ¶ 95 predictive data 768) includes a deviation from normal operation of the manufacturing station and/or the machine (Fig. 7, ¶ 95 predicted abnormality (difference between directed position, and the actual location));
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi by combining the manufacturing process and component replacement prediction first computing device taught by McCarson in view of Gandhi with a manufacturing process and component replacement prediction first computing device taught by Bergantz for the benefit of performing corrective action (e.g. predicted operational maintenance, replacing components) to avoid the cost of unexpected component failure [Bergantz: ¶ 92 – 93].
McCarson in view of Gandhi in view of Bergantz— and wherein a first amount of the real-time data associated with the machine received by the first computing device from the plugin device is greater than a second amount of the data associated with the interesting event received by the second computing device from the first computing device.
In analogous art, Kale teaches,— and wherein a first amount of the real-time data (Fig. 3, ¶ 80 stream of real time sensor data) associated with the machine received by the first computing device (Fig. 3, ¶ 80 sensor(s) (e.g., 101)) from the plugin device is greater than a second amount of the data (Fig. 3, ¶ 80 reduce or eliminate the need to transmit data) associated with the interesting event received by the second computing device (Fig. 3, ¶ 80 computer system (131)) from the first computing device.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi in view of Bergantz by combining the by the first computing device and the second computing device taught by McCarson in view of Gandhi in view of Bergantz with a first computing device and a second computing device, wherein a first amount of the real-time data associated with the machine received by the first computing device from the plugin device is greater than a second amount of the data associated with the interesting event received by the second computing device from the first computing device; taught by Kale for the benefit of providing inference results from sensor data in order to transmit the sensor data between two computing devices with reduced bandwidth [Kale: ¶ 61].
Regarding Claim 14, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 13, which this claim depends on.
McCarson further teaches, the system of claim 13, wherein: the first computing device includes an edge computing device (Fig. 1, example edge node 120) disposed proximate the machine; the second computing device includes a remote computing device (Fig. 13, ¶ 73 external machines (e.g., computing devices of any kind); Note: Fig 13 is part of Fig 1, see ¶ 67) that is not disposed proximate the machine, the second computing device is communicatively coupled to the first computing device via a cloud server (Fig. 13, ¶ 67 a server; Note: Fig 13 is part of Fig 1, see ¶ 67); —
Gandhi further teaches, — and the third computing device includes a user device (Fig. 1, user on the graphical display medium 154) and the third computing device is communicatively coupled to the second computing device via the cloud server.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi in view of Bergantz in view of Kale by combining the first computing device and second computing device taught by McCarson in view of Gandhi in view of Bergantz in view of Kale with a first computing device and second computing device respectively taught by Gandhi wherein, the third computing device includes a user device and the third computing device is communicatively coupled to the second computing device via the cloud server; taught by Gandhi for the benefit of minimal machine implementation cost and minimal continued maintenance [Gandhi: Col. 3, Ln. 33 – 36].
Regarding Claim 15, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 13, which this claim depends on.
McCarson further teaches, 15. (Currently Amended) The system of claim 13, wherein, prior to the first computing device executing the at least one low fidelity to determine the interesting event, the first computing device inputs the real-time data into at least one local adaptive model (Fig. 2, ¶ 41 one or more machine learning algorithms to assist in the updated prediction. … fit the model to data points (observations)) to determine which of the real-time data associated with the machine is unnecessary data (Fig. 1, ¶ 25 duplicate data), and the first computing device eliminates the unnecessary data (Fig. 1, ¶ 25 clean the retrieved sensor data; duplicate data to be removed) prior to inputting remaining data into the at least one low fidelity model.
Regarding Claim 16, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 13, which this claim depends on.
McCarson further teaches, the system of claim 13, wherein: the first computing device determines a first pattern (Fig. 1, ¶ 26 reference patterns) associated with performance of the machine; the first computing device determines a second pattern (Fig. 1, ¶ 26 data patterns) associated with the performance of the machine; and wherein the deviation from normal operation of the interesting event (Fig. 1, ¶ 26 data patterns are compared, against one or more reference patterns) includes a difference (Fig. 1, ¶ 26 within a particular standard deviation) between the first pattern and the second pattern.
Regarding Claim 17, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 13, which this claim depends on.
McCarson further teaches, the system of claim 13, wherein the second computing device generates a digital twin (Fig. 1, ¶ 17 digital twin 122) of the machine; and the third computing device displays at least a portion of the digital twin (Fig. 1, user on the graphical display medium 154).
Regarding Claim 18, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 13, which this claim depends on.
McCarson, Bergantz, and Kale fail to teach, the system of claim 13, wherein the second computing device generates a high fidelity learned model via inputting the data associated with the interesting event into the at least one high fidelity model; and the second computing device stores the high fidelity learned model in a model archive connected to the second computing device.
Gandhi further teaches, the system of claim 13, wherein the second computing device generates a high fidelity learned model (Fig. 1. Col. 7. Ln. 54 update the model 102) via inputting the data associated with the interesting event into the at least one high fidelity model; and the second computing device stores the high fidelity learned model in a model archive (Fig. 1. Col. 7. Ln. 48-49 store it in a database) connected to the second computing device.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi in view of Bergantz in view of Kale by combining the first computing device and second computing device taught by McCarson in view of Gandhi in view of Bergantz in view of Kale with a first computing device and second computing device respectively taught by Gandhi wherein, the second computing device generates a high fidelity learned model via inputting the data associated with the interesting event into the at least one high fidelity model; and the second computing device stores the high fidelity learned model in a model archive connected to the second computing device; taught by Gandhi for the benefit of minimal machine implementation cost and minimal continued maintenance [Gandhi: Col. 3, Ln. 33 – 36].
Regarding Claim 19, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 18, which this claim depends on.
McCarson, Bergantz, and Kale fail to teach, the system of claim 18, wherein at least one of: generating the high fidelity learned model is triggered via the first computing device determining an additional interesting event; and the second computing device populates the model archive with a plurality of high fidelity learned models.
Gandhi further teaches, the system of claim 18, wherein at least one of: generating the high fidelity learned model is triggered (Fig. 1. Col. 5. Ln. 26-27 model 102 may be implemented in computer software) via the first computing device determining an additional interesting event (Fig. 1. Col. 6. Ln. 1-2 identifies observations (e.g., asset state vectors) that) ; and the second computing device populates the model archive (Fig. 1. Col. 7. Ln. 48-49 store it in a database) with a plurality of high fidelity learned models (Fig. 1. Col. 5. Ln. 58-59 send information to the model that is used to modify the model 102).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi in view of Bergantz in view of Kale by combining the first computing device and second computing device taught by McCarson in view of Gandhi in view of Bergantz in view of Kale with a first computing device and second computing device respectively taught by Gandhi wherein, generating the high fidelity learned model is triggered via the first computing device determining an additional interesting event; and the second computing device populates the model archive with a plurality of high fidelity learned models; taught by Gandhi for the benefit of minimal machine implementation cost and minimal continued maintenance [Gandhi: Col. 3, Ln. 33 – 36].
Regarding Claim 21, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 1, which this claim depends on.
McCarson, Bergantz, and Kale fail to teach, 21. (Currently Amended) The method of claim 1, wherein the second computing device receives CAD data associated with the machine, wherein the second computing device utilizes the CAD data in accordance with determining the machine failure prediction.
Gandhi further teaches, 21. (Currently Amended) The method of claim 1, wherein the second computing device receives CAD data (Fig. 1. Col. 5. Ln. 3 a model 102) associated with the machine, wherein the second computing device utilizes the CAD data in accordance with determining the machine failure prediction (Fig. 1. Col. 7. Ln. 66 alerts indicate that a mechanical component is failing).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi in view of Bergantz in view of Kale by combining the second computing device taught by McCarson in view of Gandhi in view of Bergantz in view of Kale with a second computing device taught by Gandhi, wherein, the second computing device receives CAD data associated with the machine, wherein the second computing device utilizes the CAD data in accordance with determining the machine failure prediction; taught by Gandhi for the benefit of minimal machine implementation cost and minimal continued maintenance [Gandhi: Col. 3, Ln. 33 – 36].
Regarding Claim 22, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 1, which this claim depends on.
McCarson, Bergantz, and Kale fail to teach, 22. (New) The method of claim 1, wherein the second computing device transmits one or more alerts to the third computing device, and wherein the one or more alerts include a root cause analysis associated with abnormal operation of the machine and a downtime risk.
Gandhi further teaches, 22. (New) The method of claim 1, wherein the second computing device transmits one or more alerts (Fig. 1. Col. 5. Ln. 16 generate alerts 152) to the third computing device, and wherein the one or more alerts include a root cause analysis associated with abnormal operation of the machine (Fig. 1. Col. 7. Ln. 66 alerts indicate that a mechanical component is failing) and a downtime risk.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify McCarson in view of Gandhi in view of Bergantz in view of Kale by combining the second computing device taught by McCarson in view of Gandhi in view of Bergantz in view of Kale with a second computing device taught by Gandhi, wherein, the second computing device transmits one or more alerts to the third computing device, and wherein the one or more alerts include a root cause analysis associated with abnormal operation of the machine and a downtime risk; taught by Gandhi for the benefit of minimal machine implementation cost and minimal continued maintenance [Gandhi: Col. 3, Ln. 33 – 36].
Regarding Claim 23, McCarson in view of Gandhi in view of Bergantz in view of Kale teach the limitations of claim 1, which this claim depends on.
McCarson further teaches, 23. (New) The method of claim 1, wherein the machine failure prediction includes timing information that the machine may experience a failure or need maintenance (Fig. 2, ¶ 23 future occurrences of such process activity can be detected in an effort to take preventative measures prior to the occurrence of process cycle time waste).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
LAVID BEN LULU et al. (US 2021/0157310 A1) teaches, a system for predicting machine failure (Fig. 1, network diagram 100, ¶ 37 failure predictions).
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSEPH O. NYAMOGO whose telephone number is (469)295-9276. The examiner can normally be reached 9:00 A to 5:00 P CT.
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, EMAN ALFAKAWI can be reached at 571-272-4448. 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.
/JOSEPH O. NYAMOGO/
Examiner
Art Unit 2858
/FARHANA A HOQUE/Primary Examiner, Art Unit 2858
Prosecution Insights