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 .
Priority
Acknowledgment is made of applicant's claim for foreign priority based on an applications filed in Korea:
KR10-2024-0021747 (Filing Date 02/15/2024)
KR10-2023-0106181 (Filing Date08/14/2023)
It is noted, however, that applicant has not filed certified copies of these applications as required by 37 CFR 1.55.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 08/13/2024 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Application Status
This office action is issued in response to application filed 08/13/2024. Claims 1-20 are pending. Claims 1-20 are rejected. This action is non-final. A three-month Shortened Statutory Period for Response has been set.
Claim Rejections - 35 USC § 102
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 (i.e., changing from AIA to pre-AIA ) 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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-4, 12-14 and 20 are rejected under 35 U.S.C. §102 as being unpatentable over the combination of Kim et al. (“Fault Estimation of Rack-Driving Motor in Electrical Power Steering System Using an Artificial Neural Network Observer”, henceforth Kim).
Regarding Claim 1, Kim teaches the limitations: a device comprising: a memory configured to store one or more instructions {“implement it in the cost-effective ECU”, Pg. 3, ¶3}; and a processor configured to detect an abnormality of a motor of a column electric power steering (EPS) {“the immediate and accurate fault estimation/detection is an important step for further remedies and fault accommodations in EPS.”, Pg. 1, Section 1.} configured to provide an auxiliary steering force to a steering column of the vehicle and execute the one or more instructions {fault detection in an electrical power steering system, Abstract} comprising: inputting operation data related to steering wheel operation by a driver of the vehicle and state data indicating a state of the vehicle {“The ANN observer to estimate a fault in a motor in R-EPS is designed using the minimum sensor signal, the rotational angle of the motor measured by a rotational encoder.”, Pg. 3, ¶3; see also input parameters in Fig. 1} into an artificial neural network model {Fig. 2, Pg. 6} to obtain at least one estimated value of an output of the motor from the artificial neural network model {“Figure 2. Proposed ANN observer (four inputs, three hidden layers, one output).”, Pg. 6}, comparing the estimated value of the output of the motor estimated by the artificial neural network model with at least one measured value of the output of the motor sensed by a sensor {“Figure 1. Entire system diagram for fault estimation. (i) The sensor used here is only the rotational encoder measuring the rotational angle of a motor.”, Pg. 4}, and detecting the abnormality of the motor of the EPS based on comparison result between the estimated value of the output of the motor estimated by the artificial neural network model and the measured value of the output of the motor sensed by the sensor {as represented in Fig. 1, and provided immediately below; “(iii) The ANN observer for estimating a fault, fa(t), in a motor is proposed in Section 4. In addition, two representative model-based approaches, an adaptive observer and a Kalman filter, are presented to compare the estimation performance with the one via proposed ANN observer.”, Pg. 5}.
PNG
media_image1.png
450
902
media_image1.png
Greyscale
Regarding Claim 2, Kim discloses all the limitations of Claim 1, as discussed supra. In addition, Kim explicitly recites the limitation: wherein the operation data related to the steering wheel operation by the driver includes at least one of a steering angle, a steering angular velocity, and a steering torque {“The ANN observer to estimate a fault in a motor in R-EPS is designed using the minimum sensor signal, the rotational angle of the motor measured by a rotational encoder.”, Pg. 3, ¶3; see also input parameters in Fig. 1}.
Regarding Claim 3, Kim discloses all the limitations of Claim 1, as discussed supra. In addition, Kim explicitly recites the limitation: wherein the state data indicating the state of the vehicle includes at least one of a speed of the vehicle, a lateral acceleration of the vehicle, a yaw rate of the vehicle, and a wheel speed of the vehicle {“In the first phase, according to a given representative fault scenario, collecting and preprocessing the related data are conducted to secure the input data for the reference output.”, Pg. 6, Section 4.1; and “the angular position of motor, the angular rate and the control torque as well as the absolute error between desire trajectory and actual angular position of motor.”, Pg. 7, second paragraph; and Fig. 2 on Pg. 7}.
Regarding Claim 4, Kim discloses all the limitations of Claim 1, as discussed supra. In addition, Kim explicitly recites the limitation: wherein the operation data and the state data comprise signals that are obtainable through a controller area network (CAN) of the vehicle {“The ANN observer to estimate a fault in a motor in R-EPS is designed using the minimum sensor signal, the rotational angle of the motor measured by a rotational encoder.”, Pg. 3, ¶3; see also input parameters in Fig. 1, wherein one skilled in the art will appreciate that use of a CAN-bus is an industry standard}.
Regarding Claim 12, Kim teaches the limitations: method of detecting an abnormality of a motor of a column electric power steering (EPS) {fault detection in an electrical power steering system, Abstract} configured to provide an auxiliary steering force to a steering column of a vehicle {“the immediate and accurate fault estimation/detection is an important step for further remedies and fault accommodations in EPS.”, Pg. 1, Section 1.}, the method comprising: obtaining, by a processor {“implement it in the cost-effective ECU”, Pg. 3, ¶3}, at least one estimated value of an output of the motor from the artificial neural network model by inputting operation data related to steering wheel operation by a driver of the vehicle and state data indicating a state of the vehicle into the artificial neural network model {“Figure 2. Proposed ANN observer (four inputs, three hidden layers, one output).”, Pg. 6}; and detecting, by the processor, the abnormality of the motor by comparing {“Figure 1. Entire system diagram for fault estimation. (i) The sensor used here is only the rotational encoder measuring the rotational angle of a motor.”, Pg. 4} the estimated value of the output of the motor estimated by the artificial neural network model with at least one measured value of the output of the motor sensed by a sensor {as represented in Fig. 1, and provided immediately below; “(iii) The ANN observer for estimating a fault, fa(t), in a motor is proposed in Section 4. In addition, two representative model-based approaches, an adaptive observer and a Kalman filter, are presented to compare the estimation performance with the one via proposed ANN observer.”, Pg. 5}.
PNG
media_image1.png
450
902
media_image1.png
Greyscale
Regarding Claim 13, Kim discloses all the limitations of Claim 12, as discussed supra. In addition, Kim explicitly recites the limitation: wherein the operation data related to the steering wheel operation by the driver includes at least one of a steering angle, a steering angular velocity, and a steering torque {“The ANN observer to estimate a fault in a motor in R-EPS is designed using the minimum sensor signal, the rotational angle of the motor measured by a rotational encoder.”, Pg. 3, ¶3; see also input parameters in Fig. 1}.
Regarding Claim 14, Kim discloses all the limitations of Claim 12, as discussed supra. In addition, Kim explicitly recites the limitation: wherein the state data indicating the state of the vehicle includes at least one of a speed of the vehicle, a lateral acceleration of the vehicle, a yaw rate of the vehicle, and a wheel speed of the vehicle {“In the first phase, according to a given representative fault scenario, collecting and preprocessing the related data are conducted to secure the input data for the reference output.”, Pg. 6, Section 4.1; and “the angular position of motor, the angular rate and the control torque as well as the absolute error between desire trajectory and actual angular position of motor.”, Pg. 7, second paragraph; and Fig. 2 on Pg. 7}.
Regarding Claim 20, Kim teaches the limitations: non-transitory computer-readable medium configured to store at least one instruction, that when executed by a processor {“implement it in the cost-effective ECU”, Pg. 3, ¶3}, causes the processor to perform operations of detecting an abnormality of a motor of a column electric power steering (EPS) {“the immediate and accurate fault estimation/detection is an important step for further remedies and fault accommodations in EPS.”, Pg. 1, Section 1.} configured to provide an auxiliary steering force to a steering column of a vehicle {fault detection in an electrical power steering system, Abstract}, the operations comprising: obtaining at least one estimated value of an output of the motor from the artificial neural network model by inputting operation data related to steering wheel operation by a driver of the vehicle and state data indicating a state of the vehicle into the artificial neural network model {“Figure 2. Proposed ANN observer (four inputs, three hidden layers, one output).”, Pg. 6}; and detecting the abnormality of the motor by comparing {“Figure 1. Entire system diagram for fault estimation. (i) The sensor used here is only the rotational encoder measuring the rotational angle of a motor.”, Pg. 4} the estimated value of the output of the motor estimated by the artificial neural network model with at least one measured value of the output of the motor sensed by a sensor {as represented in Fig. 1, and provided immediately below; “(iii) The ANN observer for estimating a fault, fa(t), in a motor is proposed in Section 4. In addition, two representative model-based approaches, an adaptive observer and a Kalman filter, are presented to compare the estimation performance with the one via proposed ANN observer.”, Pg. 5}.
PNG
media_image1.png
450
902
media_image1.png
Greyscale
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 (i.e., changing from AIA to pre-AIA ) 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.
Claims 5-11 and 15-19 are rejected under 35 U.S.C. §103 as being unpatentable over the combination of Kim and Lee (KR 20230017677 A).
Regarding Claim 5, Kim discloses all the limitations of Claim 1, as discussed supra. Kim does not appear to explicitly recite the limitations: wherein the artificial neural network model includes a generative adversarial network (GAN) including a generator configured to receive the operation data related to the steering wheel operation by the driver and the state data indicating the state of the vehicle and generate the estimated value of the output of the motor.
However, Lee explicitly recites the limitation: wherein the artificial neural network model includes a generative adversarial network (GAN) {“The present invention relates to a method for evaluating a vehicle controller based on a generative adversarial network.”, Abstract} including a generator configured to receive the operation data related to the steering wheel operation by the driver and the state data indicating the state of the vehicle and generate the estimated value of the output of the motor {“In the method for evaluating a vehicle controller based on a generative adversarial network according to an embodiment of the present invention, a step of generating a real vehicle simulation signal using a time-series generative adversarial network (S110) and determining whether the vehicle controller is abnormal through abnormality detection (S120) is included.”, ¶[0041], associated with Fig. 2}.
Kim and Lee are analogous art because they both deal with detecting abnormalities in normal vehicle operation.
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, having the teachings of Kim and Lee before them, to modify the teachings of Kim to include the teachings of Lee to increase the reliability of a fault detection system {¶[0038]}.
Regarding Claim 6, the combination of Kim and Lee discloses all the limitations of Claim 5, as discussed supra. Kim does not appear to explicitly recite the limitations: wherein the artificial neural network model further includes a discriminator configured to receive measurement data including the operation data, the state data, and the measured value of the output of the motor and output a discrimination value for the measurement data.
However, Lee explicitly recites the limitations: wherein the artificial neural network model further includes a discriminator configured to receive measurement data including the operation data, the state data, and the measured value of the output of the motor and output a discrimination value for the measurement data {“The discrimination unit 108 to which the encoder structure is applied distinguishes the generated simulated input value from the actual vehicle input, and classification is performed by the classification unit 109, so that learning is possible to distinguish between the actual vehicle signal and the simulated generated signal. is carried out”, ¶[0053]}.
Regarding Claim 7, the combination of Kim and Lee discloses all the limitations of Claim 6, as discussed supra. Kim does not appear to explicitly recite the limitations: wherein the processor is configured to input error data related to a difference between the estimated value of the output of the motor estimated by the artificial neural network model and the measured value of the output of the motor sensed by the sensor into an abnormality detection model to detect the abnormality of the motor .
However, Lee explicitly recites the limitations: wherein the processor is configured to input error data related to a difference between the estimated value of the output of the motor estimated by the artificial neural network model and the measured value of the output of the motor sensed by the sensor into an abnormality detection model {“abnormality detection network”, Abstract, and 200 Fig. 4, in which the output from GAN 100 is input into 200} to detect the abnormality of the motor {“step (a) embeds the actual vehicle input data to obtain a latent code, restores the size of the feature reduced in the embedding process, and learns the network to enable regeneration of the actual vehicle input data. The step (a) generates a random vehicle input using a random vector, and learns to distinguish between a simulated input value and an actual vehicle input.”, ¶[0010-0011]}.
Regarding Claim 8, the combination of Kim and Lee discloses all the limitations of Claim 7, as discussed supra. Kim does not appear to explicitly recite the limitation: wherein the abnormality detection model uses a one-class support vector machine (OCSVM) algorithm.
However, Lee explicitly recites the limitations: wherein the abnormality detection model uses a one-class support vector machine (OCSVM) algorithm {anomaly detection process, implementation and algorithms: “In the method for evaluating a vehicle controller based on a generative adversarial network according to an embodiment of the present invention, a step of generating a real vehicle simulation signal using a time-series generative adversarial network (S110) and determining whether the vehicle controller is abnormal through abnormality detection (S120) is included.”, ¶[0041], and “The anomaly detection network 200 is used to determine whether input/output data is similar to a data set measured in a real vehicle.”, ¶[0058]; see also ¶[0037]}.
Regarding Claim 9, the combination of Kim and Lee discloses all the limitations of Claim 7, as discussed supra. Kim does not appear to explicitly recite the limitations: the at least one estimated value of the output of the motor estimated by the artificial neural network model comprises a plurality of estimated values, the at least one measured value of the output of the motor sensed by the sensor comprises a plurality of measured values, and a plurality of data sets include the operation data, the state data, the plurality of measured values, and the plurality of estimated values; and the error data input into the abnormality detection model includes a mean and standard deviation of errors between the plurality of measured values and the plurality of estimated values that are obtained from the plurality of data sets, a maximum absolute error among the errors between the plurality of measured values and the plurality of estimated values of the plurality of data sets, and a discrimination value of the discriminator for the measurement data.
However, Lee explicitly recites the limitations: the at least one estimated value of the output of the motor estimated by the artificial neural network model comprises a plurality of estimated values, the at least one measured value of the output of the motor sensed by the sensor comprises a plurality of measured values, and a plurality of data sets include the operation data, the state data, the plurality of measured values, and the plurality of estimated values {the combined GAN 100 and abnormality detection network 220 is represented in Fig. 4; one skilled in the art will appreciate that a plurality of input and output data is standard for robust results from neural network type systems}; and the error data input into the abnormality detection model includes a mean and standard deviation of errors between the plurality of measured values and the plurality of estimated values that are obtained from the plurality of data sets, a maximum absolute error among the errors between the plurality of measured values and the plurality of estimated values of the plurality of data sets {with respect to Fig. 4, output from time-series GAN is directed to abnormality/anomaly detection network 200; one skilled in the art will appreciate that manipulating data in the form of calculating mean-values, standard deviations and maximum values is well known in the art} and a discrimination value of the discriminator for the measurement data {“In addition, by applying a decoder structure that restores the size of the feature reduced in the embedding process to the restoration unit 104, the network is trained to enable reproduction of the input actual vehicle signal. The generating unit 106 to which the decoder structure is applied to generate a random vehicle input generates a simulated signal using a random vector. The discrimination unit 108 to which the encoder structure is applied distinguishes the generated simulated input value from the actual vehicle input, and classification is performed by the classification unit 109, so that learning is possible to distinguish between the actual vehicle signal and the simulated generated signal is carried out Referring to FIG. 3, the path including the embedding unit 102 and the restoration unit 104 is trained to compress and restore the vehicle signal into a latent code, and the generation unit 106 and the classification unit 109 The containing path is learned to perform the function of generating simulated signals and discriminating between real vehicle signals and simulated signals. According to the embodiment of the present invention, in relation to the vehicle controller evaluation input, the output of the time-series generative adversarial neural network generation unit 106 for which learning has been completed is used as a real vehicle simulation signal.”, ¶[0051-0054]}.
Regarding Claim 10, the combination of Kim and Lee discloses all the limitations of Claim 6, as discussed supra. Kim does not appear to explicitly recite the limitations: wherein the discriminator is configured to additionally receive estimate data including the operation data related to the steering wheel operation, the state data indicating the state of the vehicle, and the estimated value of the output of the motor estimated by the artificial neural network model, and additionally output discrimination value for the estimate data.
However, Lee explicitly recites the limitations: wherein the discriminator {discrimination unit 108, Fig. 4 and ¶[0053]} is configured to additionally receive estimate data including the operation data related to the steering wheel operation, the state data indicating the state of the vehicle {with respect to Fig. 4, vehicle input data reproduction unit 101 inputs data to time-series GAN 200}, and the estimated value of the output of the motor estimated by the artificial neural network model, and additionally output discrimination value for the estimate data {with respect to Fig. 4, output from time-series GAN is directed to abnormality/anomaly detection network 200}.
Regarding Claim 11, the combination of Kim and Lee discloses all the limitations of Claim 10, as discussed supra. Kim does not appear to explicitly recite the limitations: the artificial neural network model has the generator and the discriminator alternately performing learning, and the artificial neural network model is configured to perform the learning using the operation data, the state data, and the measured value which are obtained when the motor is in a normal state.
However, Lee explicitly recites the limitations: the artificial neural network model has the generator {generation unit 106, Fig. 4 and ¶[0052]} and the discriminator {discrimination unit 108, Fig. 4 and ¶[0053]} alternately performing learning {iterative , Fig. 4 and ¶[0052]} and the artificial neural network model is configured to perform the learning using the operation data, the state data, and the measured value which are obtained when the motor is in a normal state {operation of time-series GAN portion of Fig. 4 is described in ¶[0050-0054]}.
Regarding Claim 15, Kim discloses all the limitations of Claim 12, as discussed supra. Kim does not appear to explicitly recite the limitations: wherein the artificial neural network model comprises a generative adversarial network (GAN) including: a generator configured to receive the operation data related to the steering wheel operation by the driver and the state data indicating the state of the vehicle and generate the estimated value of the output of the motor, and a discriminator configured to receive measurement data including the operation data, the state data, and the measured value of the output of the motor and output a discrimination value for the measurement data.
However, Lee explicitly recites the limitations: wherein the artificial neural network model includes a generative adversarial network (GAN) {“The present invention relates to a method for evaluating a vehicle controller based on a generative adversarial network.”, Abstract} including a generator configured to receive the operation data related to the steering wheel operation by the driver and the state data indicating the state of the vehicle and generate the estimated value of the output of the motor {“In the method for evaluating a vehicle controller based on a generative adversarial network according to an embodiment of the present invention, a step of generating a real vehicle simulation signal using a time-series generative adversarial network (S110) and determining whether the vehicle controller is abnormal through abnormality detection (S120) is included.”, ¶[0041], associated with Fig. 2}, and a discriminator {discrimination unit 108, Fig. 4 and ¶[0053]} configured to receive measurement data including the operation data, the state data {with respect to Fig. 4, vehicle input data reproduction unit 101 inputs data to time-series GAN 200}, and the measured value of the output of the motor and output a discrimination value for the measurement data {with respect to Fig. 4, output from time-series GAN is directed to abnormality/anomaly detection network 200}.
Regarding Claim 16, the combination of Kim and Lee discloses all the limitations of Claim 15, as discussed supra. Kim does not appear to explicitly recite the limitations: wherein the obtaining of the at least one estimated value of the output of the motor from the artificial neural network model comprises inputting the operation data and the state data into the generator and obtaining the estimated value of the output of the motor generated by the generator.
However, Lee explicitly recites the limitation: wherein the obtaining of the at least one estimated value of the output of the motor from the artificial neural network model comprises inputting the operation data and the state data {with respect to Fig. 4, vehicle input data reproduction unit 101 inputs data to time-series GAN 200} into the generator and obtaining the estimated value of the output of the motor generated by the generator {with respect to Fig. 4, the input and output from generating unit 106 of GAN 100; also see ¶[0051-0054] for additional description of GAN 100}.
Regarding Claim 17, the combination of Kim and Lee discloses all the limitations of Claim 16, as discussed supra. Kim does not appear to explicitly recite the limitations: wherein the detecting of the abnormality of the motor includes: inputting, by the processor, measurement data including the operation data, the state data, and the measured value of the output of the motor into the discriminator and obtaining, by the processor, the discrimination value for the measurement data generated by the discriminator; and inputting, by the processor, error data including the discrimination value for the measurement data and a value related to a difference between the estimated value and the measured value into an abnormality detection model and obtaining, by the processor, an output of the abnormality detection model.
However, Lee explicitly recites the limitations: wherein the detecting of the abnormality of the motor includes: inputting, by the processor, measurement data including the operation data, the state data {with respect to Fig. 4, vehicle input data reproduction unit 101 inputs data to time-series GAN 200}, and the measured value of the output of the motor into the discriminator and obtaining, by the processor, the discrimination value for the measurement data generated by the discriminator {“The discrimination unit 108 to which the encoder structure is applied distinguishes the generated simulated input value from the actual vehicle input, and classification is performed by the classification unit 109, so that learning is possible to distinguish between the actual vehicle signal and the simulated generated signal. is carried out”, ¶[0053]}; and inputting, by the processor, error data including the discrimination value for the measurement data and a value related to a difference between the estimated value and the measured value into an abnormality detection model {“abnormality detection network”, Abstract, and 200 Fig. 4, in which the output from GAN 100 is input into 200} and obtaining, by the processor, an output of the abnormality detection model {“step (a) embeds the actual vehicle input data to obtain a latent code, restores the size of the feature reduced in the embedding process, and learns the network to enable regeneration of the actual vehicle input data. The step (a) generates a random vehicle input using a random vector, and learns to distinguish between a simulated input value and an actual vehicle input.”, ¶[0010-0011]}.
Regarding Claim 18, the combination of Kim and Lee discloses all the limitations of Claim 17, as discussed supra. Kim does not appear to explicitly recite the limitations: wherein: the at least one estimated value of the output of the motor estimated by the artificial neural network model comprises a plurality of estimated values, the at least one measured value of the output of the motor sensed by the sensor comprises a plurality of measured values, and a plurality of data sets include the operation data, the state data, the plurality of estimated values, and the plurality of measured values; and the error data input into the abnormality detection model includes a mean and standard deviation of errors between the plurality of measured values and the plurality of estimated values that are obtained from the plurality of data sets, a maximum absolute error among the errors between the plurality of measured values and the plurality of estimated values of the plurality of data sets, and a discrimination value of the discriminator for the measurement data
However, Lee explicitly recites the limitations: wherein: the at least one estimated value of the output of the motor estimated by the artificial neural network model comprises a plurality of estimated values, the at least one measured value of the output of the motor sensed by the sensor comprises a plurality of measured values, and a plurality of data sets include the operation data, the state data, the plurality of estimated values, and the plurality of measured values {the combined GAN 100 and abnormality detection network 220 is represented in Fig. 4; one skilled in the art will appreciate that a plurality of input and output data is standard for robust results from neural network type systems}; and the error data input into the abnormality detection model includes a mean and standard deviation of errors between the plurality of measured values and the plurality of estimated values that are obtained from the plurality of data sets, a maximum absolute error among the errors between the plurality of measured values and the plurality of estimated values of the plurality of data sets {with respect to Fig. 4, output from time-series GAN is directed to abnormality/anomaly detection network 200; one skilled in the art will appreciate that manipulating data in the form of calculating mean-values, standard deviations and maximum values is well known in the art} and a discrimination value of the discriminator for the measurement data {“In addition, by applying a decoder structure that restores the size of the feature reduced in the embedding process to the restoration unit 104, the network is trained to enable reproduction of the input actual vehicle signal. The generating unit 106 to which the decoder structure is applied to generate a random vehicle input generates a simulated signal using a random vector. The discrimination unit 108 to which the encoder structure is applied distinguishes the generated simulated input value from the actual vehicle input, and classification is performed by the classification unit 109, so that learning is possible to distinguish between the actual vehicle signal and the simulated generated signal is carried out Referring to FIG. 3, the path including the embedding unit 102 and the restoration unit 104 is trained to compress and restore the vehicle signal into a latent code, and the generation unit 106 and the classification unit 109 The containing path is learned to perform the function of generating simulated signals and discriminating between real vehicle signals and simulated signals. According to the embodiment of the present invention, in relation to the vehicle controller evaluation input, the output of the time-series generative adversarial neural network generation unit 106 for which learning has been completed is used as a real vehicle simulation signal.”, ¶[0051-0054]}.
Regarding Claim 19, the combination of Kim and Lee discloses all the limitations of Claim 15, as discussed supra. Kim does not appear to explicitly recite the limitations: the artificial neural network model has the generator and the discriminator alternately performing learning, and the artificial neural network model is configured to perform the learning using the operation data, the state data, and the measured value which are obtained when the motor is in a normal state.
However, Lee explicitly recites the limitations: the artificial neural network model has the generator {generation unit 106, Fig. 4 and ¶[0052]} and the discriminator {discrimination unit 108, Fig. 4 and ¶[0053]} alternately performing learning {iterative , Fig. 4 and ¶[0052]} and the artificial neural network model is configured to perform the learning using the operation data, the state data, and the measured value which are obtained when the motor is in a normal state {operation of time-series GAN portion of Fig. 4 is described in ¶[0050-0054]}.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
“A Deep Learning Approach to Detect Anomalies in an Electric Power Steering System” (Lawal Wale Alabe, Kimleang Kea, Youngsun Han, Young Jae Min and Taekyung Kim) Sensors 2022, 22(22), 8981 (20 November 2022).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RICHARD EDWIN GEIST whose telephone number is (703)756-5854. The examiner can normally be reached Monday-Friday, 9am-6pm.
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, Christian Chace can be reached at (571) 272-4190. 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.
/R.E.G./Examiner, Art Unit 3665
/CHRISTIAN CHACE/ Supervisory Patent Examiner, Art Unit 3665