DETAILED ACTION
This is a non-final Office Action in response to communications received on 07/18/2024. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Priority or Provisional
Priority to 07/20/2023 is recognized.
Drawings
The drawings filed on 07/18/2024 are acknowledged.
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.
Claims 1, 3, and 6 are rejected under 35 U.S.C. 103 over LeFebvre (US 2010/0174428) in view of Yamaguchi (US 2022/0063688).
Regarding claim 1, LeFebvre discloses the limitations of claim 1 as follows:
A system for diagnosing operational safety of railcars, the system comprising: a vibration diagnosis module (110) configured to acquire a vibration signal by measuring vibrations generated from a running car (11) through one or more vibration sensors (101) installed in each car (11) of a train (10) and generate vibration data by analyzing the vibration signal; (LeFebvre, Paras. [0017]-[0025], [0033]-[0036], Abstract, teaches a railroad train monitoring system for monitoring conditions of railcars where instrument pads disposed on each truck of each railcar carrying multiple sensors measuring loads, lateral forces, truck hunting, vibration related conditions (i.e., measuring). And further teaches that the pad microprocessor samples the sensors, performs analysis, and generates processed monitoring data (i.e., generate vibration data)).
a car computer (100) installed in each car (11) and configured to receive the vibration data generated by the vibration diagnosis module (111) of the corresponding car (11) (LeFebvre, Paras. [0017]-[0025], [0033]-[0038], Abstract, teaches pad microprocessor 19, data control unit 23, and communication device 24, where the data control unit communicates with the pads and receives the processes monitoring information generated by the pad microprocessors).
and then generate running data by adding running information including a travel location and a travel speed of the car (11) to the vibration data; (LeFebvre, Paras. [0033]-[0038], teaches that the communication device includes GPS and provide vehicle speed data. where the data control unit aggregates the processes monitoring information with travel location and vehicle speed information).
a train control and monitoring system (TCMS) (12) configured to generate integrated running data by aggregating the running data received from the car computers (100) of the cars (11) constituting the train (10) (LeFebvre, Paras. [0033]-[0038], teaches that the data control unit collects monitoring information from all trucks of the railcar, and coordinates the monitoring process, and forwards the collected monitoring information to a remote monitoring device. Although it doesn’t explicitly disclose TCMS, the onboard data control unit performs the same monitoring and aggregation functions).
and then transmit the integrated running data to a central control system (1); (LeFebvre, Paras. [0025], [0033]-[0038], [0052], Abstract, teaches transmitting the monitoring information from the railcar to a locomotive, remote monitoring station, or remote data handling service).
LeFebvre does not explicitly disclose:
a server (2) configured to build big data by storing the integrated running data transmitted to the central control system (1);
and a big data analysis module (200) configured to estimate an abnormal part of a car or a track by analyzing the integrated running data
through pretrained artificial intelligence (AI) and transmit the estimated abnormal part to the central control system (1)
such that the AI is retrained using data which is acquired by comparing an estimation result with an actual measurement result of an abnormality check,
wherein the entire track on which the train (10) runs is divided into a certain number of sections,
and the vibration data measured from the car (11) is generated section by section
such that the big data analysis module (200) estimates an abnormal part of a specific car (11) or the track.
However, Yamaguchi teaches:
a server (2) configured to build big data by storing the integrated running data transmitted to the central control system (1); (Yamaguchi, Paras. [0008]-[0009], [0033]-[0042], [0080]-[0081], teaches an infrastructure factor DB construction unit 400 configured to store infrastructure factor evaluation data in an infrastructure factor database, compare newly acquired infrastructure factor data with stored data, register new infrastructure factor information, and updates stored infrastructure factor information).
and a big data analysis module (200) configured to estimate an abnormal part of a car or a track by analyzing the integrated running data (Yamaguchi, Paras. [0021]-[0039], [0043]-[0047], teaches a car factor estimation unit 100, an infrastructure factor extraction unit 200, an infrastructure factor estimation unit 300, an infrastructure factor analysis unit 500, and a car analysis unit 600 configured to estimate car factor evaluation data, estimate infrastructure factor evaluation data from measured railroad car data, analyze infrastructure factors, and analyze railroad car conditions based on infrastructure factor information. Therefore, teaches estimating whether an abnormal condition is attributable to the railroad car or to the railroad infrastructure).
through pretrained artificial intelligence (AI) and transmit the estimated abnormal part to the central control system (1) (Yamaguchi, Paras. [0026], teaches that the car factor estimation function may be obtained using multivariant analysis, deep learning, and the like. Therefore, teaches the use of artificial intelligence for estimating railroad car condition based on measured operational data).
such that the AI is retrained using data which is acquired by comparing an estimation result with an actual measurement result of an abnormality check, (Yamaguchi, Paras. [0024]-[0026], [0035]-[0047], teaches estimating railroad car and infrastructure factor evaluation data using a function that may be obtained by deep learning and continuously updating an infrastructure factor database based on newly acquired measurement data and analysis results. Although it does not explicitly disclose retraining the learning model, it would have been obvious to one of ordinary skill in the art to update or retrain the model using acquired verified measurement data in order to improve the prediction accuracy of the condition monitoring system).
wherein the entire track on which the train (10) runs is divided into a certain number of sections, (Yamaguchi, Paras. [0029]-[0036], [0052]-[0055], teaches representing infrastructure factor evaluation data with respect to positions along the railway track, assigning evaluation data according to position, setting a position resolution, and expanding infrastructure factor evaluation data over positions of the railway track. Therefore, teaches analysis of the railway on a section by section basis).
and the vibration data measured from the car (11) is generated section by section (Yamaguchi, Paras. [0031]-[0036], [0052]-[0055], teaches generating infrastructure factor evaluation data corresponding to respective positions and position ranges of the railway track and performing analysis according to those position ranges).
such that the big data analysis module (200) estimates an abnormal part of a specific car (11) or the track. (Yamaguchi, Paras. [0029]-[0036], [0043]-[00147], teaches analyzing railroad car conditions using infrastructure factor analysis data and determining the influence of infrastructure factors on railroad car operation. Therefore, estimating whether an abnormal condition is associated with the railroad car or the railway infrastructure).
LeFebvre and Yamaguchi are combinable, because both are from the same field of railroad vehicle condition monitoring systems. It would have been obvious to a person having ordinary skill in the art before the effective filling date of the invention to modify the monitoring system of LeFebvre to incorporate the infrastructure factor analysis as taught by Yamaguchi , in order to improve the accuracy of abnormality detection by distinguishing the vehicle related condition from the track condition.
Regarding claim 3, LeFebvre and Yamaguchi disclose the limitations of claim 1. LeFebvre discloses:
The system of claim 1, wherein the vibration sensors (111) of the vibration diagnosis module (110) are installed on a main part of the car (11) including a wheelset or a bogie. (LeFebvre, Paras. [0017]-[0025], [0033]-[0036], Figs. 1-4, Abstract, teaches a railroad train monitoring system where instrumented pads 16 carrying sensors, are mounted within the truck pedestal jaws on the bearing adapters of each railcar truck. The bearing adapters are mounted on the axle bearing adjacent to the wheelsets of the truck (bogie), where the sensors measure loads, lateral forces, truck hunting, vibration related conditions, and other operating characteristics generated at the truck assembly. And further teaches that each truck carries instruments pads associated with sensors and control circuits, and that the instrumented pads are positioned on the bearing adapters between the axle bearings and the truck frame. Therefore, locating the sensors on the railroad car truck (bogie) and adjacent to the wheelsets).
Regarding claim 6, LeFebvre and Yamaguchi disclose the limitations of claim 1. LeFebvre discloses:
The system of claim 1, wherein the big data analysis module (200) builds an abnormality diagnosis map of the track and the cars (11) (Yamaguchi, Paras. [0029]-[0036], [0043]-[0047], teaches obtaining infrastructure factor evaluation data by comparing newly acquired vibration data with historical data, updating the infrastructure factor database, and estimating whether an abnormality is attributable to the track or the railcar. The track is divided into sections, and evaluation data is generated for each section, therefore, providing information corresponding to an abnormality diagnosis map).
by diagnosing a specific track section as a dangerous section when abnormal vibration data is measured from a plurality of trains running on the track section, or diagnosing a specific car (11) with an abnormality when abnormal vibration data is measured from the car (11) running on all track sections, (Yamaguchi, Paras. [0029]-[0036], [0041]-[0047], teaches evaluating infrastructure factors for corresponding track sections using vibration data collected from railcars and determining deterioration or abnormal conditions of the track (i.e., abnormal vibration data is measured ….. or …..)).
and estimates an abnormal part of the track or the car (11). (Yamaguchi, Paras. [0029]-[0036], [0041]-[0047], teaches determining whether an abnormality is attributable to the infrastructure track or the railcar based on the evaluation results).
The same motivation to combine utilized in claim 1 is equally applicable in the instant claim.
Claim 2 is rejected under 35 U.S.C. 103 over LeFebvre (US 2010/0174428) in view of Yamaguchi (US 2022/0063688), and further in view of Chen (CN115859467).
Regarding claim 2, LeFebvre and Yamaguchi disclose the limitations of claim 1. Chen discloses:
The system of claim 1, wherein the vibration diagnosis module (110) generates the vibration data using an analysis method based on any one of a root mean square (RMS), a vibration level, a ride comfort index, and a ride comfort level which are representative values of a dynamic state of the car (11). (Chen, Paras. [0018]-[0021], [0030]-[0039], teaches calculating weighted root mean square (RMS) values from vibration acceleration signals and evaluating ride comfort based on calculated weighted RMS values, which are respective values of the dynamic state of the vehicle).
LeFebvre, Yamaguchi and Chen are combinable, because all are from the same field of railroad vehicle condition monitoring systems. It would have been obvious to a person having ordinary skill in the art before the effective filling date of the invention to incorporate vibration analysis using representative vibration metrics as taught by Chen , in order to improve the evaluation of vehicle vibration detection.
Claims 4-5, 7-11 are rejected under 35 U.S.C. 103 over LeFebvre (US 2010/0174428) in view of Yamaguchi (US 2022/0063688), Deo (US 2019/0147371).
Regarding claim 4, LeFebvre and Yamaguchi disclose the limitations of claim 2. LeFebvre and Yamaguchi disclose:
The system of claim 1, wherein the vibration diagnosis module (110) determines whether the generated vibration data falls within a preset vibration value tolerance range for a corresponding track section, (LeFebvre, Paras. [0033]-[0038], teaches that the pad microprocessor periodically gathers sensor readings, performs analysis, detects indications of faults, and generates messages when monitored operating parameters depart from expected operating conditions. Therefore, teaches comparing measures operating data with predetermined criteria or thresholds to determine whether abnormal operating condition exist).
(Yamaguchi, Paras. [0033], [0036]-[0042], teaches determining whether infrastructure factor evaluation data exceeds threshold values, comparing newly acquired evaluation data, and determining whether deterioration or abnormal conditions exist based on the comparison).
transmits a determination result to the car computer (100) along with the vibration data, (LeFebvre, Paras. [0023]-[0026], [0033]-[0038], teaches that the pad microprocessor generates processed monitoring data and communicates the processed monitoring information and fault indications through the data control unit 23 and communication device 24 to the railcar monitoring system and remote monitoring equipment).
LeFebvre and Yamaguchi do not explicitly disclose:
feeds an AI retraining result based on big data analysis by the big data analysis module (200) back to continuously update the preset vibration value tolerance range.
However, Deo teaches:
feeds an AI retraining result based on big data analysis by the big data analysis module (200) back to continuously update the preset vibration value tolerance range. (Deo, Paras. [0013]-[0024], [0030]-[0034], teaches identifying training data from operational data, preprocessing and transforming the selected data, retraining AI and machine learning models, validating the retrained models, monitoring model performance, and continuously updating deployed models using newly acquired data).
(Yamaguchi, Paras. [0026], [0035]-[0047], teaches obtaining a car factor estimation function using deep learning model, continuously storing newly acquired infrastructure factor evaluation data, comparing new data with historical data, updating the infrastructure factor database, and improving infrastructure factor evaluation based on newly acquired information).
LeFebvre, Yamaguchi and Deo are combinable, because LeFebvre, Yamaguchi are from the same field of railroad vehicle condition monitoring systems, and Deo is directed to the well-known problem of improving AI model performance through retraining. It would have been obvious to a person having ordinary skill in the art before the effective filling date of the invention to incorporate the retraining AI model technique as taught by Deo into the system of LeFebvre-Yamaguchi so that the updated analysis results obtained from newly acquired operational data are used, in order to improve the accuracy of the condition monitoring system and the diagnostic performance by allowing the model to be updated.
Regarding claim 5, LeFebvre, Yamaguchi and Deo disclose the limitations of claim 4. LeFebvre and Yamaguchi disclose:
The system of claim 4, wherein the preset vibration value tolerance range is set depending on types including a vehicle type of the train (10) or cars (11), (LeFebvre, Paras. [0017]-[0025], [0033]-[0038], teaches monitoring operating conditions of railcars using pads mounted on each truck and selecting sampling and monitoring operations according to the type of behavior being monitored and the condition of the railcar. And further teaches that the monitoring depending on the type of railcar).
(Yamaguchi, Paras. [0021]-[0025], [0036]-[0047], teaches estimating railroad car factor evaluation data from measured car data representing of the condition of the railroad car based on results of evaluation data. it would have been obvious to configure threshold values according to the type of railroad vehicle being monitored since different railcar types exhibit different characteristics and different vibrations).
a format of the train (10) or the cars (11), or the number of organized cars (11), (LeFebvre, Paras. [0017]-[0025], [0040]-[0045], teaches that the monitoring system communicates between multiple railcars and the configuration depends on the type or the railcar. And further teaches identifying the pads associated with particular railcars, so that the monitoring information is correlated with the railcar).
and the integrated running data transmitted from the TCMS (12) to the central control system (1) includes type-specific data including the vehicle type of the train (10) or the cars (11), the format of the train (10) or the cars (11), or the number of organized cars (11). (LeFebvre, Paras. [0017]-[0025], [0033]-[0038], [0045]-[0052], teaches transmitting processed monitoring information together with identifying information associated with each railcars through the data control unit and communications device to a locomotive or remote monitoring station. And further teaches generating and analyzing railroad car evaluation data using car data including operating state, speed, acceleration, position and other information corresponding to the monitored car).
(Yamaguchi, Paras. [0021]-[0025], [0036]-[0047], teaches using specific information in evaluating railroad conditions, and it would be obvious to determine the preset vibration value tolerance range according to the type and configuration of the train being monitored, since different train type and configurations exhibit different vibration characteristics and conditions).
the same motivation to combine utilized in claim 4 is equally applicable in the instant claim.
Regarding claim 7, LeFebvre and Yamaguchi disclose the limitations of claim 1. Deo discloses:
The system of claim 1, wherein the big data analysis module (200) retrains the AI in order of an operation of selecting integrated running data stored in the server (2), an operation of preprocessing the selected data, an operation of converting the preprocessed data, a data mining operation, and a pattern analysis operation. LeFebvre teaches a big data analysis module that collects, stores, and classifies condition data received from monitors assets to determine faults and abnormal conditions.
(Deo, Paras. [0013]-[0024], [0030]-[0034], teaches retraining machine learning models using selected training data, and identifying training data for the model, processing the selected data using cleansing, transformation, and reduction techniques, generating processed training data, training and retraining AL models, validating the trained models, monitoring and updating the models using new data).
LeFebvre, Yamaguchi and Deo are combinable, because LeFebvre, Yamaguchi are from the same field of railroad vehicle condition monitoring systems, and Deo is directed to the well-known problem of improving AI model performance through retraining. It would have been obvious to a person having ordinary skill in the art before the effective filling date of the invention to incorporate the retraining the AI model as taught by Deo, in order to improve the accuracy of the condition monitoring system and the diagnostic performance by allowing the model to be updated.
Regarding claim 8, LeFebvre, Yamaguchi and Deo disclose the limitations of claim 7. Deo discloses:
The system of claim 7, wherein the pattern analysis operation is performed using any one selected from among linear regression, an artificial neural network, K-nearest neighbor, and unsupervised learning. (Deo, Paras. [0013]-[0024], [0030]-[0034], teaches that the machine learning models used during training and analysis includes various learning algorithms such as, an artificial intelligence model (e.g., a multiple regression analysis model, an artificial neural networks (ANNs) model, a case-based reasoning (CBR) model, and/or the like), a machine learning model (e.g., a supervised learning model, an unsupervised learning model, a linear regression model, a logistic regression model, a naïve Bayes model, and/or the like), a deep learning model (e.g., a recurrent neural network (RNN) model, a convolution deep neural network (CNN) model, and/or the like), and/or the like.)).
The same motivation to combine utilized in claim 7 is equally applicable in the instant claim.
Regarding claim 9, LeFebvre discloses the limitations of claim 9 as follows:
A method of diagnosing operational safety of railcars, the method comprising: a vibration data generation operation (S10) in which a vibration diagnosis module (110) receiving a measurement signal from one or more vibration sensors (111) installed in each car (11) of a train (10) acquires a vibration signal by measuring vibrations generated from the running car (11) and generates vibration data by analyzing the vibration signal; (LeFebvre, Paras. [0017]-[0025], [0033]-[0036], Abstract, teaches a railroad train monitoring system for monitoring conditions of railcars where instrument pads disposed on each truck of each railcar carrying multiple sensors measuring loads, lateral forces, truck hunting, vibration related conditions (i.e., measuring). And further teaches that the pad microprocessor samples the sensors, performs analysis, and generates processed monitoring data (i.e., generate vibration data)).
a running data generation operation (S20) in which a car computer (100) installed in the car (11) receives the vibration data generated by the vibration diagnosis module (110) of the car (11) (LeFebvre, Paras. [0017]-[0025], [0033]-[0038], Abstract, teaches pad microprocessor 19, data control unit 23, and communication device 24, where the data control unit communicates with the pads and receives the processes monitoring information generated by the pad microprocessors).
generates running data by adding running information including a travel location and a travel speed of the car (11) to the vibration data; (LeFebvre, Paras. [0033]-[0038], teaches that the communication device includes GPS and provide vehicle speed data. where the data control unit aggregates the processes monitoring information with travel location and vehicle speed information).
an integrated running data generation operation (S30) in which a train control and monitoring system (TCMS) generates integrated running data by aggregating the running data received from the car computers (100) of the cars (11) constituting the train (10) (LeFebvre, Paras. [0033]-[0038], teaches that the data control unit collects monitoring information from all trucks of the railcar, and coordinates the monitoring process, and forwards the collected monitoring information to a remote monitoring device. Although it doesn’t explicitly disclose TCMS, the onboard data control unit performs the same monitoring and aggregation functions).
and then transmits the integrated running data to a central control system; an abnormality estimation operation (S40) of storing the integrated running data transmitted to the central control system (1) in a server, (LeFebvre, Paras. [0025], [0033]-[0038], [0052], Abstract, teaches transmitting the monitoring information from the railcar to a locomotive, remote monitoring station, or remote data handling service).
LeFebvre does not explicitly disclose:
wherein the analyzing of the integrated running data comprises dividing an entire track on which the train (10) runs into a certain number of sections, separately generating vibration data measured from the car (11) section by section, diagnosing a specific track section as a dangerous section when abnormal vibration data is measured from a plurality of trains (10) running on the track section, or diagnosing a specific car (11) with an abnormality when abnormal vibration data is measured from the car (11) running on all track sections, and providing a result of estimating an abnormality in the track or the car (11) to the central control system; an abnormality handling operation (S50) in which the central control system (1) takes measures against an abnormal situation when an abnormality in the track or the car (11) is estimated; and a retraining operation (S60) of comparing the estimation result with an actual measurement result of an abnormality check to retrain the AI.
However, Yamaguchi teaches:
analyzing the transmitted integrated running data through pretrained artificial intelligence (AI) included in a big data analysis module (200), wherein the analyzing of the integrated running data comprises dividing an entire track on which the train (10) runs into a certain number of sections, separately generating vibration data measured from the car (11) section by section, diagnosing a specific track section as a dangerous section when abnormal vibration data is measured from a plurality of trains (10) running on the track section, or diagnosing a specific car (11) with an abnormality when abnormal vibration data is measured from the car (11) running on all track sections, and providing a result of estimating an abnormality in the track or the car (11) to the central control system; an abnormality handling operation (S50) in which the central control system (1) takes measures against an abnormal situation when an abnormality in the track or the car (11) is estimated; (Yamaguchi, Paras. [0027]-[0036], [0043]-[0055], teaches analyzing railroad car conditions using infrastructure factor analysis data, where infrastructure factor evaluation data is generated for each track position and stored in an infrastructure factor database. Therefore, dividing the track into sections and separately analyzing data for each section. And further teaches determining whether particular track section exhibits an abnormal condition based on vibration data collected from multiple cars and determining whether a specific car has an abnormality based on analysis data associated with the car. It also teaches providing the analysis and abnormality estimation results to an output device or central monitoring system for further evaluation, including determining whether an abnormal condition is associated with the railroad car or the railway infrastructure (track sections)).
LeFebvre and Yamaguchi are combinable, because both are from the same field of railroad vehicle condition monitoring systems. It would have been obvious to a person having ordinary skill in the art before the effective filling date of the invention to modify the monitoring system of LeFebvre to incorporate the infrastructure factor analysis as taught by Yamaguchi , in order to improve the accuracy of abnormality detection by distinguishing the vehicle related condition from the track condition.
LeFebvre and Yamaguchi do not explicitly disclose:
analyzing the transmitted integrated running data through pretrained artificial intelligence (AI)…..
and a retraining operation (S60) of comparing the estimation result with an actual measurement result of an abnormality check to retrain the AI.
However, Deo discloses:
analyzing the transmitted integrated running data through pretrained artificial intelligence (AI) included in a big data analysis module (200),
and a retraining operation (S60) of comparing the estimation result with an actual measurement result of an abnormality check to retrain the AI. (Deo, Paras. [0013]-[0024], [0030]-[0034], teaches training, validating, monitoring, and retraining machine learning models using feedback and evaluation results. And further teaches comparing model estimation abnormality results with actual measurement results).
LeFebvre, Yamaguchi and Deo are combinable, because LeFebvre, Yamaguchi are from the same field of railroad vehicle condition monitoring systems, and Deo is directed to the well-known problem of improving AI model performance through retraining. It would have been obvious to a person having ordinary skill in the art before the effective filling date of the invention to incorporate the retraining the AI model as taught by Deo, in order to improve the accuracy of the condition monitoring system and the diagnostic performance by allowing the model to be retrained.
Regarding claim 10, LeFebvre, Yamaguchi and Deo disclose the limitations of claim 9. LeFebvre, Yamaguchi and Deo disclose:
The method of claim 9, wherein the vibration data generation operation (S10) comprises determining, by the vibration diagnosis module (200), whether the measured vibration data falls within a preset vibration value tolerance range for a corresponding track section and transmitting a determination result to the car computer (100) along with the vibration data, and the retraining operation (S60) comprises feeding an AI retraining result based on big data analysis by the big data analysis module (200) back to the vibration diagnosis module (110) to continuously update the preset vibration value tolerance range. (LeFebvre, Paras. [0017]-[0025], [0033]-[0038], [0052], teaches transmitting vibration/monitoring data and centralized processing).
(Yamaguchi, Paras. [0027]-[0036], [0043]-[0055], teaches determining whether measured data exceeds a threshold for a track section (vibration tolerance range)).
(Deo, Paras. [0013]-[0024], [0030]-[0034], teaches training, and retraining AI model and updating the model).
The same motivation to combine utilized in claim 9 is equally applicable in the instant claim.
Regarding claim 11, LeFebvre, Yamaguchi and Deo disclose the limitations of claim 9. LeFebvre, Yamaguchi and Deo disclose:
The method of claim 9, wherein the retraining operation (S60) comprises retraining, by the big data analysis module (200), the AI in order of an operation of selecting integrated running data stored in the server (2) (S61), an operation of preprocessing the selected data (S62), an operation of converting the preprocessed data (S63), a data mining operation (S64), and a pattern analysis operation (S65), and the pattern analysis operation (S65) is performed using any one selected from among linear regression, an artificial neural network, K-nearest neighbor, and unsupervised learning. (LeFebvre, Paras. [0017]-[0025], [0033]-[0038], [0052], teaches collecting, transmitting, and analyzing railroad monitoring data at a central monitoring system for condition monitoring).
(Yamaguchi, Paras. [0027]-[0036], [0043]-[0055], teaches processing collected railroad condition data, generating infrastructure factor evaluation data, and analyzing the processed data to determine abnormal conditions of a track section or railroad car).
(Deo, Paras. [0013]-[0024], [0030]-[0034], teaches training, and retraining AI model and updating the model using techniques such as artificial neural networks, linear regression, K-nearest neighbor, and unsupervised learning).
The same motivation to combine utilized in claim 9 is equally applicable in the instant claim.
References Considered But Not Relied Upon
Lang (US 11,447,166) teaches a railway track condition monitoring system including a plurality of sensors installed on a rail of the track and spaced by a predetermined distance from each other.
Yuan (US 2021/0182296) teaches machine condition monitoring to determine state estimation and anomaly localization jointly. Systems configured using at least a synthetic training dataset including sensor output data that incorporates synthetic a random amount of noise to each one of multiple sensor devices that probe an industrial machine
Conclusion
Accordingly, claims 1-11 are rejected.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PEGAH BARZEGAR whose telephone number is (703)756-4755.
The examiner can normally be reached M-F, 9:00 - 5:00. Examiner interviews are available via telephone 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, Samuel Morano can be reached on 571-272-6684. 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/patentcenter 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.
/P.B./Examiner, Art Unit 3615
/S. Joseph Morano/Supervisory Patent Examiner, Art Unit 3615
Prosecution Insights