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 .
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-4,6,7,10-14, and 18 are rejected under 35 U.S.C. 103(a) as being unpatentable over Lin (CN 117991742 A) (hereinafter Lin) in view of Moeykens (US 20230058992 A1) (hereinafter Moeykens).
Regarding claim 1.Lin teaches a vehicle system(Lin, paragraph 5, a system for online diagnosis and operation and maintenance of vehicle) comprising:
a vehicle including a vehicle body(Lin, paragraph 34, key component in the vehicle device),
a vehicle sensor that is disposed on said vehicle body(Lin, paragraph 34, electing a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device), and that is configured to detect an operation condition of said vehicle and to output a detection signal based on detection of the operation condition of said vehicle(Lin, paragraph 44, the operation state of the vehicle device is judged by the state data of the vehicle device, and an analysis report of the operation state of the vehicle device is generated),
a communication device that is disposed on said vehicle body(Lin, paragraph 17, a communication transmission device for transmitting the state data ), and
a controller that is disposed on said vehicle body, that is electrically connected to said vehicle sensor and said communication device(Lin discloses a system that comprises vehicle state data collection device and a communicated device that transmits the state data, which indicates a connection between the communication device and the vehicle state data collection device. Lin, paragraph 17, a system for vehicle online diagnosis and operation and maintenance, comprising: a vehicular information collecting device for collecting the state data of the vehicle device under the running state of the vehicle, a communication transmission device for transmitting the state data), and that is configured to receive the detection signal from said vehicle sensor, and to output, via said communication device(Lin, paragraph 17, a vehicular information collecting device for collecting the state data of the vehicle device under the running state of the vehicle, a communication transmission device for transmitting the state data; a data processing device, the data processing device is connected with the communication transmission device); and
an assessing device(Similar to the assessing device, Lin discloses a server that processors collected sensor data. Lin, paragraph 17, the data processing device comprises a data processing server and a central server) including
a processing unit that is electrically connected to said communication unit(Lin’s data processing server is similar to the processing unit, and it is connected to a communication device. Lin, paragraph 17, the data processing device is connected with the communication transmission device, the data processing device comprises a data processing server and a central server), and that stores a signal processing module(Lin, paragraph 35, state data of the vehicle device can be stored in the data storage module of the central server), a feature-extracting module(Lin, paragraph 45, performing cluster analysis and feature extraction on the pre-processed state data), and a health-assessing module(Lin discloses a diagnosis of operation state of a vehicle, which corresponds to health assessment. Lin, paragraph 84, a diagnosis module for diagnosing the running state of the vehicle device according to the state data Lin, paragraph 36, the operation state of the vehicle device is diagnosed according to the state data), said health-assessing module being implemented to include at least one assessment program(Similar to the neural network assessment program disclosed in the specification, Lin discloses a neural network model to assess the state of a vehicle component. Lin, Paragraph 69, wherein the preventative maintenance model is a neural network identification model of the preventative maintenance solution of the vehicle formed by combining the equipment history monitoring data, the component life tracking data and the residual service life prediction data and the integrated design, production, operation, maintenance and simulation test data ), said processing unit being configured to
perform signal processing on the detection signal carried by the signal by utilizing said signal processing module to obtain a first output(The converted usable sensor data of Lin corresponds to the first output. Lin, paragraph 47, firstly pre-processing the state data, the pre-processing comprises converting the state data, so as to convert the sensing device detection signal into the state data which can be directly used),
perform feature extraction on the first output by utilizing said feature-extracting module to obtain a second output(The feature extracted data of Lin is similar to the second output. Lin, paragraph 45, pre-processing the state data, wherein the pre-processing comprises converting, classifying and merging the state data; performing cluster analysis and feature extraction on the pre-processed state data), and
perform health assessment based on the second output by executing said at least one assessment program of said health-assessing module to obtain assessment data related to machine health of said vehicle(Lin, paragraph 45, the operation state of the vehicle device is diagnosed according to the state data, including: pre-processing the state data, wherein the pre-processing comprises converting, classifying and merging the state data; performing cluster analysis and feature extraction on the pre-processed state data. Lin, Paragraph 69, wherein the preventative maintenance model is a neural network identification model of the preventative maintenance solution of the vehicle formed by combining the equipment history monitoring data, the component life tracking data and the residual service life prediction data and the integrated design, production, operation, maintenance and simulation test data ).
While Lin discloses processing sensor data using feature extraction to determine the operation state of a vehicle, it fails to disclose a communication unit that is configured to wirelessly communicate with said communication device, receive the wireless signal via said communication unit, a wireless signal carrying the detection signal.
However, Moeykens, which is in the same analogous art and that teaches about aircraft fleet management, discloses a wireless signal carrying the detection signal(Lin discloses a wireless module, but does not specifically teach a wireless communication between the server and the vehicle. Moeykens addresses this deficiency as it discloses a wireless communication between multiple devices. Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication. In general, any network topology may be used. Information (e.g., data, software 1920, etc.) may be communicated to and/or from computer system 1900 via network interface device), a communication unit that is configured to wirelessly communicate with said communication device and(Moeykens, paragraph 184, a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. The network may include any network topology and can may employ a wired and/or a wireless mode of communication), receive the wireless signal via said communication unit(Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication. In general, any network topology may be used. Information (e.g., data, software 1920, etc.) may be communicated to and/or from computer system 1900 via network interface device),
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Lin with Moeykens to establish a wireless communication between a vehicle and an assessing device/server. By establishing a wireless communication between a vehicle and a server, it is possible to communicate with a remote server that can process large amount of data such as training dataset for a neural network model. Remote storage unit and processing devices have a dedicated computers and storage unit that process large amount of data compared to processors and storage units located in a vehicle. Increased training and testing dataset corresponds to improved neural network accuracy.
Regarding claim 2, the combination of Lin and Moeykens teaches the vehicle system as claimed in claim 1(Lin, paragraph 5, a system for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), wherein said vehicle sensor is a vibration sensor configured to detect vibration of said vehicle body(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data….the sensing device comprises a vibration data sensor) and to output a vibration signal as the detection signal based on detection of the vibration of said vehicle body(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data, so as to convert the state data into the state data which can be directly used).
Regarding claim 3, , the combination of Lin and Moeykens teaches the vehicle system as claimed in claim 1(Lin, paragraph 5, a system for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), wherein said vehicle sensor is a current-detecting circuit configured to detect an operation current of said vehicle(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data….the sensing device comprises current sensor) and to output a current signal as the detection signal based on detection of the operation current(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data, so as to convert the state data into the state data which can be directly used).
Regarding claim 4, the combination of Lin and Moeykens teaches the vehicle system as claimed in claim 1(Lin, paragraph 5, a system for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), wherein said vehicle sensor is a thermometer configured to detect a temperature of said vehicle body(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data….the sensing device comprises a temperature sensor) and to output a temperature signal as the detection signal based on detection of the temperature(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data, so as to convert the state data into the state data which can be directly used).
Regarding claim 6, the combination of Lin and Moeykens teaches the vehicle system as claimed in claim 1(Lin, paragraph 5, a system for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), wherein said assessing device further includes a display that is electrically connected to said processing unit(Moeykens, paragraph 55, a display in communication with computing device), and said processing unit is further configured to display the assessment data via said display(Moeykens, paragraph 58, display the aircraft performance model output 136 by a graphical user interface (GUI)).
Regarding claim 7, the combination of Lin and Moeykens teaches the vehicle system as claimed in claim 1(Lin, paragraph 5, a system for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), wherein said processing unit of said assessing device further stores a performance-predicting module(Lin discloses neural network model to predict the status of a vehicle component. Lin, Paragraph 69, wherein the preventative maintenance model is a neural network identification model of the preventative maintenance solution of the vehicle formed by combining the equipment history monitoring data, the component life tracking data and the residual service life prediction data and the integrated design, production, operation, maintenance and simulation test data), and is further configured to perform prediction by utilizing said performance-predicting module based on the second output to obtain prediction data related to performance of said vehicle(Lin, Paragraph 64, the component life tracking data and the residual service life prediction data, performing performance analysis, state prediction and operation condition evaluation on the vehicle device, and generating a device pre-warning state report. Lin, Paragraph 12, wherein the fault processing model is a neural network identification model for processing decision of the vehicle under different faults by integrating different fault mechanisms, fault reasons and fault processing methods of the vehicle device).
Regarding claim 10. A method for assessing machine health of a vehicle(Lin, paragraph 1, method…for online diagnosis and operation and maintenance of vehicle.), to be implemented by an assessing device(Similar to the assessing device, Lin discloses a server that processors collected sensor data. Lin, paragraph 17, the data processing device comprises a data processing server and a central server), the vehicle including a vehicle body(Lin, paragraph 34, key component in the vehicle device), the assessing device including a processing unit and a communication unit that are electrically connected to each other(Lin’s data processing server is similar to the processing unit, and it is connected to a communication device. Lin, paragraph 17, the data processing device is connected with the communication transmission device, the data processing device comprises a data processing server and a central server), the processing unit storing a signal processing module(Lin, paragraph 35, state data of the vehicle device can be stored in the data storage module of the central server), a feature-extracting module and a health-assessing module(Lin, paragraph 45, performing cluster analysis and feature extraction on the pre-processed state data; Lin discloses a diagnosis of operation state of a vehicle, which corresponds to health assessment. Lin, paragraph 84, a diagnosis module for diagnosing the running state of the vehicle device according to the state data Lin, paragraph 36, the operation state of the vehicle device is diagnosed according to the state data), the method comprising:
the communication unit receiving a signal that carries a detection signal related to detection of an operation condition of the vehicle(Lin, paragraph 17, a vehicular information collecting device for collecting the state data of the vehicle device under the running state of the vehicle, a communication transmission device for transmitting the state data; a data processing device, the data processing device is connected with the communication transmission device);
the processing unit obtaining a first output by utilizing the signal processing module to perform signal processing on the detection signal(The converted usable sensor data of Lin corresponds to the first output. Lin, paragraph 47, firstly pre-processing the state data, the pre-processing comprises converting the state data, so as to convert the sensing device detection signal into the state data which can be directly used);
the processing unit obtaining a second output by utilizing the feature-extracting module to perform feature extraction on the first output(The feature extracted data of Lin is similar to the second output. Lin, paragraph 45, pre-processing the state data, wherein the pre-processing comprises converting, classifying and merging the state data; performing cluster analysis and feature extraction on the pre-processed state data); and
the processing unit obtaining assessment data related to the machine health of the vehicle by utilizing the health-assessing module to perform health assessment based on the second output(Lin, paragraph 45, the operation state of the vehicle device is diagnosed according to the state data, including: pre-processing the state data, wherein the pre-processing comprises converting, classifying and merging the state data; performing cluster analysis and feature extraction on the pre-processed state data. Lin, Paragraph 69, wherein the preventative maintenance model is a neural network identification model of the preventative maintenance solution of the vehicle formed by combining the equipment history monitoring data, the component life tracking data and the residual service life prediction data and the integrated design, production, operation, maintenance and simulation test data).
While Lin discloses processing sensor data using feature extraction to determine the operation state of a vehicle, it fails to disclose a communication unit outputting the wireless signal to the processing unit(Lin discloses a wireless module, but does not specifically teach a wireless communication between the server and the vehicle. Moeykens addresses this deficiency as it discloses a wireless communication between multiple devices. Moeykens, paragraph 184, a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. The network may include any network topology and can may employ a wired and/or a wireless mode of communication); output carried by the wireless signal().
However, Moeykens, which is in the same analogous art and that teaches about aircraft fleet management, discloses disclose a communication unit outputting the wireless signal to the processing unit(); output carried by the wireless signal(Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication. In general, any network topology may be used. Information (e.g., data, software 1920, etc.) may be communicated to and/or from computer system 1900 via network interface device).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Lin with Moeykens to establish a wireless communication between a vehicle and an assessing device/server. By establishing a wireless communication between a vehicle and a server, it is possible to communicate with a remote server that can process large amount of data such training dataset for a neural network model. Remote storage unit and processing devices have a dedicated computers and storage unit that process large amount of data compared to processors and storage units located in a vehicle. Increased training and testing dataset corresponds to improved neural network accuracy.
Regarding claim 11, the combination of Lin and Moeykens teaches the method as claimed in claim 10(Lin, paragraph 1, method…for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), wherein:
the communication unit receiving a wireless signal is the communication unit receiving the wireless signal(Moeykens, paragraph 184, a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. The network may include any network topology and can may employ a wired and/or a wireless mode of communication) that carries a vibration signal related to vibration of the vehicle body as the detection signal(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data….the sensing device comprises a vibration data sensor); and
the processing unit obtaining a first output is to utilize the signal processing module to perform signal processing on the vibration signal(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data, so as to convert the state data into the state data which can be directly used) carried by the wireless signal(Moeykens, paragraph 184, a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. The network may include any network topology and can may employ a wired and/or a wireless mode of communication).
Regarding claim 12, the combination of Lin and Moeykens teaches the method as claimed in claim 10(Lin, paragraph 1, method…for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), wherein:
the communication unit receiving a wireless signal is the communication unit receiving the wireless signal(Moeykens, paragraph 184, a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. The network may include any network topology and can may employ a wired and/or a wireless mode of communication) that carries a current signal related to an operation current of the vehicle as the detection signal(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data….the sensing device comprises current sensor); and
the processing unit obtaining a first output is to utilize the signal processing module to perform signal processing on the current signal(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data, so as to convert the state data into the state data which can be directly used) carried by the wireless signal(Moeykens, paragraph 184, a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. The network may include any network topology and can may employ a wired and/or a wireless mode of communication).
Regarding claim 13, the combination of Lin and Moeykens teaches the method as claimed in claim 10(Lin, paragraph 1, method…for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), wherein:
the communication unit receiving a wireless signal is the communication unit receiving the wireless signal(Moeykens, paragraph 184, a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. The network may include any network topology and can may employ a wired and/or a wireless mode of communication) that carries a temperature signal related to a temperature of the vehicle body as the detection signal(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data….the sensing device comprises a temperature sensor); and
the processing unit obtaining a first output is to utilize the signal processing module to perform signal processing on the temperature signal(Lin, paragraph 34, selecting a specific sensor in the sensing device according to the requirement target, so as to collect the special state data of the vehicle device, and can process the state data, so as to convert the state data into the state data which can be directly used)carried by the wireless signal(Moeykens, paragraph 184, a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. The network may include any network topology and can may employ a wired and/or a wireless mode of communication).
Regarding claim 14, the combination of Lin and Moeykens teaches the method as claimed in claim 10(Lin, paragraph 1, method…for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), the processing unit further storing a performance-predicting module(Lin discloses neural network model to predict the status of a vehicle component. Lin, Paragraph 69, wherein the preventative maintenance model is a neural network identification model of the preventative maintenance solution of the vehicle formed by combining the equipment history monitoring data, the component life tracking data and the residual service life prediction data and the integrated design, production, operation, maintenance and simulation test data), the method further comprising:
the processing unit obtaining prediction data related to performance of the vehicle by utilizing the performance-predicting module to perform prediction based on the second output(Lin, Paragraph 64, the component life tracking data and the residual service life prediction data, performing performance analysis, state prediction and operation condition evaluation on the vehicle device, and generating a device pre-warning state report. Lin, Paragraph 12, wherein the fault processing model is a neural network identification model for processing decision of the vehicle under different faults by integrating different fault mechanisms, fault reasons and fault processing methods of the vehicle device).
Regarding claim 18, the combination of Lin and Moeykens teaches the method as claimed in claim 10(Lin, paragraph 1, method…for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), the assessing device further including a display that is electrically connected to the processing unit(Moeykens, paragraph 55, a display in communication with computing device), the method further comprising:
the processing unit displaying the assessment data via the display(Moeykens, paragraph 58, display the aircraft performance model output 136 by a graphical user interface (GUI)).
Claims 5 and 17 are rejected under 35 U.S.C. 103(a) as being unpatentable over Lin (CN 117991742 A) (hereinafter Lin) in view of Moeykens (US 20230058992 A1) (hereinafter Moeykens) in further view of Chattopadhyay (US 20190099886 A1) (hereinafter Chattopadhyay).
Regarding claim 5, the combination of Lin and Moeykens teaches the vehicle system as claimed in claim 1(Lin, paragraph 5, a system for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), wherein said processing unit of said assessing device is further configured to calculate a statistical value based on the detection signal by utilizing said signal processing module and (Lin, paragraph 77, comparing the processed state data with the limit target value detected in the pre-established model base, judging the running condition of the device in the running process of the train, and obtaining the diagnosis result).
While the combination of Lin and Moeykens teaches about an alerting/warning system, it specifically fails to disclose a system to output a warning signal in response to determining that the statistical value does not satisfy a predetermined criterion.
However, Chattopadhyay, which is in the same analogous art and that teaches about health monitoring of a robot in manufacturing environment, discloses a system to output a warning signal in response to determining that the statistical value does not satisfy a predetermined criterion(Chattopadhyay discloses outputting an alert when user defined criteria is met. For example, a criteria can include a feature extraction result that breaches a user defined threshold. Chattopadhyay, paragraph 51, a user may configure one or more of the criteria (e.g., the threshold) for detecting an outlier. Chattopadhyay, paragraph 94, the health monitor is to extract a feature from the vibration signal, compare the feature to a threshold, and, in response to determining the feature satisfies the threshold, transmit an alert.).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Lin and Moeykens with Chattopadhyay to output an alert/warning signal when a user defined criteria is met. By outputting an alert signal when health evaluation result of a vehicle component is exceeded, it is possible give a user an early indication of decreasing performance of a vehicle component before a complete damage of the component occurs. This gives the user enough time to fix the component, reducing the risk of hazardous failure.
Regarding claim 17, the combination of Lin and Moeykens teaches the method as claimed in claim 10(Lin, paragraph 1, method…for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), further comprising:
the processing unit utilizing the signal processing module to calculate a statistical value based on the detection signal(Lin, paragraph 77, comparing the processed state data with the limit target value detected in the pre-established model base, judging the running condition of the device in the running process of the train, and obtaining the diagnosis result)carried by the wireless signal and(Moeykens, paragraph 184, a telephone network, a data network associated with a telephone/voice provider (e.g., a mobile communications provider data and/or voice network), a direct connection between two computing devices, and any combinations thereof. The network may include any network topology and can may employ a wired and/or a wireless mode of communication);
While the combination of Lin and Moeykens teaches about an alerting/warning system, it specifically fails to disclose the processing unit outputting a warning signal in response to determining that the statistical value does not satisfy a predetermined criterion.
However, Chattopadhyay, which is in the same analogous art and that teaches about health monitoring of a robot in manufacturing environment, discloses the processing unit outputting a warning signal in response to determining that the statistical value does not satisfy a predetermined criterion(Chattopadhyay discloses outputting an alert when user defined criteria is met. For example, a criteria can include a feature extraction result that breaches a user defined threshold. Chattopadhyay, paragraph 51, a user may configure one or more of the criteria (e.g., the threshold) for detecting an outlier. Chattopadhyay, paragraph 94, the health monitor is to extract a feature from the vibration signal, compare the feature to a threshold, and, in response to determining the feature satisfies the threshold, transmit an alert).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Lin and Moeykens with Chattopadhyay to output an alert/warning signal when a user defined criteria is met. By outputting an alert signal when health evaluation result of a vehicle component is exceeded, it is possible give a user an early indication of decreasing performance of a vehicle component before a complete damage of the component occurs. This gives the user enough time to fix the component, reducing the risk of hazardous failure.
Claims 8 and 15 are rejected under 35 U.S.C. 103(a) as being unpatentable over Lin (CN 117991742 A) (hereinafter Lin) in view of Moeykens (US 20230058992 A1) (hereinafter Moeykens) in further view of Moreira (EP 2251835 A1) (hereinafter Moreira) in further view of Catusseau (WO 2016083687 A1) (hereinafter Catusseau).
Regarding claim 8, the combination of Lin and Moeykens teaches the vehicle system as claimed in claim 7(Lin, paragraph 5, a system for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), wherein said performance-predicting module includes prediction program of logistic regression(Moeykens discloses a logistic regression algorithm to determine performance of an aircraft. Logistic regression algorithms inherently have predictive capability, which can be used to determine predictive performance of the aircraft/vehicle. Moeykens, paragraph 181, Autonomous machine-learning process may include… logistic regression), a prediction program of a neural network (NN)( Lin, Paragraph 69, wherein the preventative maintenance model is a neural network identification model of the preventative maintenance solution of the vehicle formed by combining the equipment history monitoring data, the component life tracking data and the residual service life prediction data and the integrated design, production, operation, maintenance and simulation test data), and wherein said processing unit is configured to execute one of the prediction programs of said performance-predicting module based on the second output to obtain the prediction data(Lin, Paragraph 64, the component life tracking data and the residual service life prediction data, performing performance analysis, state prediction and operation condition evaluation on the vehicle device, and generating a device pre-warning state report. Lin, Paragraph 12, wherein the fault processing model is a neural network identification model for processing decision of the vehicle under different faults by integrating different fault mechanisms, fault reasons and fault processing methods of the vehicle device).
While the combination of Lin and Moeykens discloses different prediction programs to determine vehicle body health status, it specifically fails disclose a prediction program of statistical pattern recognition, a prediction program of a Gaussian mixture model.
However, Moreira, which is in the same analogous art and that teaches about a system and method for the tele-maintenance of vehicles, discloses a prediction program of statistical pattern recognition(Moreira discloses using pattern recognition to analyze trends of data and evaluate performance, indicating a prediction based on gathered data. Moreira, paragraph 80, the integration of the tools of pattern recognition, the technologies of Condition Based Maintenance (CBM) used for the analyses of the trends for the main physical variables that translate the performance of the train).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Lin and Moeykens with Moreira to determine the performance of a vehicle component based on trends analyzed using pattern recognition system. By using pattern recognition system, it is possible to detect small changes in gathered data to identify difference in the output of vehicle component, that allows a system to construct a predicting model indicating future performance of the component and before failure.
The combination of Lin, Moeykens, and Moreira specifically fails to disclose a prediction program of a Gaussian mixture model.
However, Catusseau, which is in the same analogous art and that teaches about malfunction diagnostics of motor vehicles, discloses a prediction program of a Gaussian mixture model(Catusseau discloses using Gaussian mixture model for classification in the diagnosis of a vehicle component. Its classification algorithm indicates its predictive capability. Catusseau, paragraph 22, these characteristics are hierarchical according to the storage structure of the database, or are used to build and optimize a parametric model according to the classification method chosen, especially for the case of using an HMM - Hidden Markov Model in English, Hidden Markov Model in French - in the case of a GMM - Gaussian Mixture Model in English).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Lin, Moeykens, and Moreira with Catusseau to diagnose a vehicle using classification method to predict the status of its vehicle component. By using a prediction program of a Gaussian mixture model, it is possible to predict performance of a vehicle component by incorporating large vehicle data gathered by the sensor. Furthermore, Gaussian mixture model, can be trained with data from different sensor data such as vibration and temperature data to construct a comprehensive model with increased accuracy.
Regarding claim 15, the combination of Lin and Moeykens teaches the method as claimed in claim 14(Lin, paragraph 1, method…for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), the performance-predicting module including a prediction program of logistic regression(Moeykens discloses a logistic regression algorithm to determine performance of an aircraft. Logistic regression algorithms inherently have predictive capability, which can be used to determine predictive performance of the aircraft/vehicle. Moeykens, paragraph 181, Autonomous machine-learning process may include… logistic regression), and a prediction program of a neural network (NN)( Lin, Paragraph 69, wherein the preventative maintenance model is a neural network identification model of the preventative maintenance solution of the vehicle formed by combining the equipment history monitoring data, the component life tracking data and the residual service life prediction data and the integrated design, production, operation, maintenance and simulation test data), wherein the processing unit obtaining prediction data is to execute one of the prediction programs of the performance-predicting module based on the second output(Lin, Paragraph 64, the component life tracking data and the residual service life prediction data, performing performance analysis, state prediction and operation condition evaluation on the vehicle device, and generating a device pre-warning state report. Lin, Paragraph 12, wherein the fault processing model is a neural network identification model for processing decision of the vehicle under different faults by integrating different fault mechanisms, fault reasons and fault processing methods of the vehicle device).
While the combination of Lin and Moeykens discloses different prediction programs to determine vehicle body health status, it specifically fails disclose a prediction program of statistical pattern recognition, a prediction program of a Gaussian mixture model (GMM).
However, Moreira, which is in the same analogous art and that teaches about a system and method for the tele-maintenance of vehicles, discloses a prediction program of statistical pattern recognition(Moreira discloses using pattern recognition to analyze trends of data and evaluate performance, indicating a prediction based on gathered data. Moreira, paragraph 80, the integration of the tools of pattern recognition, the technologies of Condition Based Maintenance (CBM) used for the analyses of the trends for the main physical variables that translate the performance of the train).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Lin and Moeykens with Moreira to determine the performance of a vehicle component based on trends analyzed using pattern recognition system. By using pattern recognition system, it is possible to detect small changes in gathered data to identify difference in the output of vehicle component, that allows a system to construct a predicting model indicating future performance of the component and before failure.
The combination of Lin, Moeykens, and Moreira specifically fails to disclose a prediction program of a Gaussian mixture model (GMM).
However, Catusseau, which is in the same analogous art and that teaches about malfunction diagnostics of motor vehicles, discloses a prediction program of a Gaussian mixture model(GMM) (Catusseau discloses using Gaussian mixture model for classification in the diagnosis of a vehicle component. Its classification algorithm indicates its predictive capability. Catusseau, paragraph 22, these characteristics are hierarchical according to the storage structure of the database, or are used to build and optimize a parametric model according to the classification method chosen, especially for the case of using an HMM - Hidden Markov Model in English, Hidden Markov Model in French - in the case of a GMM - Gaussian Mixture Model in English).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Lin, Moeykens, and Moreira with Catusseau to diagnose a vehicle using classification method to predict the status of its vehicle component. By using a prediction program of a Gaussian mixture model, it is possible to predict performance of a vehicle component by incorporating large vehicle data gathered by the sensor. Furthermore, Gaussian mixture model, can be trained with data from different sensor data such as vibration and temperature data to construct a comprehensive model with increased accuracy.
Claims 9 and 16 are rejected under 35 U.S.C. 103(a) as being unpatentable over Lin (CN 117991742 A) (hereinafter Lin) in view of Moeykens (US 20230058992 A1) (hereinafter Moeykens) in further view of Moreira (EP 2251835 A1) (hereinafter Moreira) in further view of Catusseau (WO 2016083687 A1) (hereinafter Catusseau) in further view of Yang (CN 110530650 A) (hereinafter Yang).
Regarding claim 9, the combination of Lin and Moeykens teaches the vehicle system as claimed in claim 1(Lin, paragraph 5, a system for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), wherein said at least one assessment program includes an assessment program of k-means clustering(Moeykens discloses different machine learning models to determine the performance of an aircraft/vehicle. Moeykens, paragraph 51, flight controller 120 is configured to generate an aircraft performance model 136 as a function of a machine-learning algorithm 132 based on the plurality of measured aircraft operation datum and the selected training set. Moeykens, paragraph 139, Data clustering model 1308 may utilize other forms of data clustering algorithms including for example, hierarchical clustering, k-means), an assessment program of a self-organizing map (SOM)( Moeykens, paragraph 141, machine-learning model 1300 may include… self-organizing maps), an assessment program of a support vector machine (SVM)( Moeykens, paragraph 181, Autonomous machine-learning process may include… support vector machines ), an assessment program of a genetic algorithm (GA)( Moreira discloses an expert system to diagnose failure in a vehicle, indicating an assessment of a vehicle component. The expert system can be based on genetic algorithm. Moreira, paragraph 2, a system for the expert tele-maintenance and diagnosis of failures in vehicles. Moreira, paragraph 6, Expert system based in genetic algorithms.), an assessment program of a k-nearest neighbors algorithm (k-NN) and (Moeykens, paragraph 181, Autonomous machine-learning process may include… K-nearest neighbors) and wherein said processing unit is configured to execute one of the assessment programs of said health-assessing module based on the second output to obtain the assessment data(Moeykens, paragraph 51, flight controller 120 is configured to generate an aircraft performance model 136 as a function of a machine-learning algorithm 132 based on the plurality of measured aircraft operation datum and the selected training set).
While the combination of Lin, Moeykens, Moreira, and Catusseau discloses different assessment programs, it specifically fails disclose an assessment program of a generalized regression neural network (GRNN).
However, Yang, which is in a similar analogous art and that teaches about the monitoring of heavy gas turbine performance, discloses an assessment program of a generalized regression neural network (GRNN)( Yang, paragraph 5, a heavy duty gas turbine performance state monitoring method based on generalized regression neural network with the box diagram analysis).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Lin, Moeykens, Moreira, and Catusseau with Yang to determine the health status of a vehicle component using generalized regression neural network (GRNN). By using an assessment program of a generalized regression neural network, it is possible evaluate the performance of a vehicle component with a limited data collected by the sensor. Furthermore, generalized regression neural network is advantageous for handling large sensor data while possessing increased computation speed.
Regarding claim 16, the combination of Lin and Moeykens teaches the method as claimed in claim 10(Lin, paragraph 1, method…for online diagnosis and operation and maintenance of vehicle; Moeykens, paragraph 216, A network, such as network 1044, may employ a wired and/or a wireless mode of communication), the health-assessing module including an assessment program of k-means clustering(Moeykens discloses different machine learning models to determine the performance of an aircraft/vehicle. Moeykens, paragraph 51, flight controller 120 is configured to generate an aircraft performance model 136 as a function of a machine-learning algorithm 132 based on the plurality of measured aircraft operation datum and the selected training set. Moeykens, paragraph 139, Data clustering model 1308 may utilize other forms of data clustering algorithms including for example, hierarchical clustering, k-means), an assessment program of a self-organizing map (SOM)( Moeykens, paragraph 141, machine-learning model 1300 may include… self-organizing maps), an assessment program of a support vector machine (SVM)( Moeykens, paragraph 181, Autonomous machine-learning process may include… support vector machines), an assessment program of a genetic algorithm (GA)( Moreira discloses an expert system to diagnose failure in a vehicle, indicating an assessment of a vehicle component. The expert system can be based on genetic algorithm. Moreira, paragraph 2, a system for the expert tele-maintenance and diagnosis of failures in vehicles. Moreira, paragraph 6, Expert system based in genetic algorithms.), an assessment program of a k-nearest neighbors algorithm (k-NN) and( Moeykens, paragraph 181, Autonomous machine-learning process may include… K-nearest neighbors), wherein the processing unit obtaining assessment data is to execute one of the assessment programs of the health-assessing module based on the second output(Moeykens, paragraph 51, flight controller 120 is configured to generate an aircraft performance model 136 as a function of a machine-learning algorithm 132 based on the plurality of measured aircraft operation datum and the selected training set).
While the combination of Lin, Moeykens, Moreira, and Catusseau discloses different assessment programs, it specifically fails disclose an assessment program of a generalized regression neural network (GRNN).
However, Yang, which is in a similar analogous art and that teaches about the monitoring of heavy gas turbine performance, discloses an assessment program of a generalized regression neural network (GRNN)( Yang, paragraph 5, a heavy duty gas turbine performance state monitoring method based on generalized regression neural network with the box diagram analysis).
Therefore, it would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Lin, Moeykens, Moreira, and Catusseau with Yang to determine the health status of a vehicle component using generalized regression neural network (GRNN). By using an assessment program of a generalized regression neural network, it is possible evaluate the performance of a vehicle component with limited data collected by the sensor. Furthermore, generalized regression neural network is advantageous for handling large sensor data while possessing increased computation speed.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to BESUFEKAD LEMMA TESSEMA whose telephone number is (571)272-6850. The examiner can normally be reached Monday - Friday 9:00 am - 5:00 pm.
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, Hunter Lonsberry can be reached at 5712727298. 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.
/BESUFEKAD LEMMA TESSEMA/Examiner, Art Unit 3665
/HUNTER B LONSBERRY/Supervisory Patent Examiner, Art Unit 3665