New energy vehicle operation data analysis processing method and system

Abstract

The invention relates to the technical field of automobile operation data analysis, in particular to a new energy automobile operation data analysis processing method and system. Comprising the following steps: S1, collecting part data of the new energy automobile, and extracting state data and safety range data of each part from the part data; s2, collecting operation data of the new energy vehicle, performing time period classification on the state data in combination with the real-time operation data and the historical operation data, and performing state difference analysis on the two pieces of classified state data to obtain state change trends of the state data in the two states; by monitoring the loss condition of the parts in real time and feeding back the loss condition to a vehicle owner in time when the loss condition exceeds a normal range, the real-time performance and safety of the vehicle running state are improved, and by correcting the prediction maintenance model, the system can more accurately correct the prediction result according to the actual loss condition, so that the safety of the vehicle running state is improved. And the accuracy and reliability of fault time prediction are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile operation data analysis, and in particular to a method and system for analyzing and processing operation data of a new energy automobile. Background Art

[0002] New energy vehicles are often used in people's daily lives. At present, safety accidents involving new energy vehicles are mainly caused by excessive battery temperature leading to vehicle failure, insufficient brake sensitivity and excessive vehicle speed leading to safety accidents; At present, in the operation process of new energy vehicles, it is impossible to predict the failure time of automobile parts based on the operation data. Generally, the owner is reminded only when a failure occurs, which poses a great potential threat. Moreover, when the failure of automobile parts is serious, the cost of repair is also high. Therefore, a method and system for analyzing and processing the operation data of new energy vehicles are proposed. Summary of the invention

[0003] The purpose of the present invention is to provide a method and system for analyzing and processing operating data of new energy vehicles to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, one of the purposes of the present invention is to provide a method for analyzing and processing new energy vehicle operation data, comprising the following steps: S1. Collect the component data of new energy vehicles, and extract the status data and safety range data of each component from the component data; S2. Collect the operation data of new energy vehicles, and classify the state data into time periods by combining the real-time operation data and the historical operation data, and perform state difference analysis on the two state data after classification to obtain the state change trend of the state data under the two states; S3, combining the status data, safety range data and status change trend to establish a predictive maintenance model, and then inputting the real-time operation data into the predictive maintenance model for predictive analysis to obtain the predicted failure time of each component under the real-time operation data; S4. Perform wear analysis based on historical operation data combined with status data of each component, obtain the normal wear range of each component in different operation data, then monitor the maximum wear ratio of real-time operation data, and correct the maximum wear value combined with the fault time; S5. Compare the wear value of the real-time operation data with the normal wear range. When the wear value exceeds the normal wear range, stop the predicted failure time of the component, adjust the status data of the component to feedback the fault to the owner, and when the owner eliminates the fault display, input the wear value into S4 to update the maximum value of the normal wear range.

[0005] As a further improvement of the technical solution, the S1 signs a data control agreement with the vehicle computer management terminal, thereby extracting component data fed back by sensors installed on the surface of key components in the vehicle computer management terminal.

[0006] As a further improvement of the present technical solution, S1 extracts features related to status and safety according to the characteristics and working principles of each component, displays them as status data, and then determines the safety range of each component according to the design specifications and safety standards of the component, and converts the safety range into the same numerical form as the status data.

[0007] As a further improvement of the technical solution, the steps of S2 are as follows: S2.1. Extract the power consumption of each component from the vehicle management terminal, and then aggregate the power consumption of each component to form operation data; S2.2. According to the time periods of real-time operation data and historical operation data records, the corresponding status data is extracted, and then the extracted status data is analyzed for status difference, and the difference data of power consumption of each component corresponding to the difference data of component status consumption is obtained, so as to obtain the consumption value corresponding to the power consumption of each component, and use it as the status change trend.

[0008] As a further improvement of the technical solution, when the new energy vehicle is started for the first time, S2 directly uses the status data of the components when the new energy vehicle is not started as the historical operation data, and directly performs difference analysis with the real-time operation data.

[0009] As a further improvement of the technical solution, the steps of S3 are as follows: S3.1. Establish a predictive maintenance model by combining real-time status data with safety range data and status change trends; S3.2. Input the real-time operation data into the predictive maintenance model for predictive analysis, obtain the time required for the real-time status data of each component combined with the consumption value to exceed the safety range data under the operation data, and use this time as the failure time.

[0010] As a further improvement of the technical solution, the step of S4 is as follows: S4.1. Perform wear analysis based on historical operation data combined with status data of each component, extract operation data of adjacent recording periods in the historical operation data, obtain operation data of two adjacent recording periods and extract status data of the same component, then calculate the wear difference of the two status data, then calculate the proportion of the calculated wear value combined with the safety range of the component to obtain the wear ratio, then calculate all the operation data in the historical operation data to obtain multiple wear ratios, and then combine the multiple wear ratios to form a normal wear range; S4.2. Extract the maximum wear ratio within the normal wear range obtained in S4.1, and then send the maximum wear ratio to the predictive maintenance model, so that the predictive maintenance model corrects the predicted failure time of the parts.

[0011] As a further improvement of the technical solution, the step of S5 is as follows: S5.1. Compare the wear value of the real-time operation data with the normal wear range. When the wear value exceeds the normal wear range, stop predicting the failure time of the component, adjust the status data of the component to a fault and feedback it to the owner. When the owner eliminates the fault display, input the wear value into S4.1 to update the maximum value of the normal wear range. S5.2. When the comparison result of S5.1 shows that the loss value does not exceed the normal loss range, continue monitoring.

[0012] The second object of the present invention is to provide a new energy vehicle operation data analysis and processing system, including any one of the new energy vehicle operation data analysis and processing methods described above, including a data acquisition unit, a fault prediction unit and a prediction correction unit; The data acquisition unit is used to collect component data of new energy vehicles; The fault prediction unit is used to collect the operation data of the new energy vehicle, and to establish a predictive maintenance model by combining the operation data with the component data, so as to predict the failure time of the component; The prediction correction unit is used to calculate the wear value and the normal wear range by combining the operation data with the component data, and to correct the fault time predicted by the fault prediction unit by combining the wear value with the normal wear range.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: by real-time monitoring of the wear of parts and components and timely feedback to the owner when it exceeds the normal range, the real-time and safety of the vehicle's operating status are improved; by correcting the predictive maintenance model, the system can make more accurate corrections to the prediction results according to the actual wear and tear, thereby improving the accuracy and reliability of the predicted failure time; the real-time monitoring and correction functions help to achieve preventive maintenance, early detection and resolution of potential faults, reducing vehicle maintenance costs and avoiding possible losses; and by timely feedback of fault information and more accurate predictive maintenance results, the system can enhance the owner's experience of use and increase confidence and satisfaction in vehicle performance. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 It is the overall flow chart of the present invention; Figure 2 This is a flowchart of extracting the power consumption of each component from the vehicle management terminal of the present invention; Figure 3 A flowchart of establishing a predictive maintenance model for the present invention; Figure 4 A flowchart of the present invention for correcting the predicted failure time of a component; Figure 5 A flowchart for updating the maximum value of the normal wear range of the present invention; Figure 6 It is a structural principle diagram of the data acquisition unit of the present invention.

[0015] The meaning of each number in the figure is: 10. Data acquisition unit; 20. Fault prediction unit; 30. Prediction correction unit. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] like Figure 1-6 As shown, one of the purposes of the present invention is to provide a method for analyzing and processing new energy vehicle operation data, comprising the following steps: S1. Collect the component data of new energy vehicles, and extract the status data and safety range data of each component from the component data; S1 signs a data control agreement with the vehicle management end to extract component data fed back by sensors mounted on the surface of key components in the vehicle management end. The steps are as follows: Formulate a data control agreement: determine the content of the data control agreement, including data collection frequency, transmission protocol, data format, security measures, etc., and determine the signatories of the data control agreement, including vehicle manufacturers, vehicle management providers, and data users such as data analysis platforms; Agreement signing and rights management: Negotiate and sign a data control agreement with vehicle manufacturers and vehicle management providers to clarify data acquisition rights and usage rules, ensure that the agreement contains data privacy and security protection clauses, and protect the security and privacy of user data; Data transmission and reception: According to the agreement, the vehicle management end transmits the component data fed back by the sensor to the data receiving end in the specified frequency and format, and adopts security encryption technology to ensure the security and integrity of the data transmission process; Data parsing and processing: At the data receiving end, the received data is parsed and processed to extract the data of key components. According to the data format and protocol agreement, the data is converted into a usable data format, such as JSON, CSV, etc.; Status data extraction: Extract the status data of each component, such as battery voltage, temperature, engine speed, etc., based on the data fed back by the sensor. Data processing and analysis tools, such as Python and MATLAB, can be used to process and extract the data. Safety range data extraction: Determine the safety range of each component based on the specifications and safety standards provided by the vehicle manufacturer, and compare the data fed back by the sensor with the safety range to determine whether the component is in a safe state.

[0018] S1 extracts the features related to status and safety according to the characteristics and working principles of each component, displays them as status data, and then determines the safety range of each component according to the design specifications and safety standards of the component, and converts the safety range into the same numerical form as the status data. The steps are as follows: Understand the characteristics and working principles of components: Each component has its own specific working principle and characteristics. For example, the data fed back by the sensor may include temperature, pressure, voltage, etc. Feature extraction: Select appropriate features for extraction based on the characteristics and working principles of the components. These features may include maximum value, minimum value, average value, volatility, etc. For example, for a temperature sensor, the maximum value, minimum value and average value of the temperature can be extracted as state data; Safety range determination: Determine the safety range of each component based on the design specifications and safety standards of the component. These safety ranges can be pre-defined thresholds or values ​​calculated based on the specifications provided by the manufacturer; Safety range conversion: convert the determined safety range into the same numerical form as the status data, so as to facilitate comparison and display with the status data. Normalization or standardization can be used to convert the safety range into the same numerical range as the status data. Status data display: The extracted status data is displayed in a visual form, making it convenient for users to monitor the status of each component.

[0019] S2. Collect the operation data of new energy vehicles, and classify the state data into time periods by combining the real-time operation data and the historical operation data, and perform state difference analysis on the two state data after classification to obtain the state change trend of the state data under the two states; The steps of S2 are as follows: S2.1. Extract the power consumption of each component from the vehicle management terminal, and then aggregate the power consumption of each component to form operation data. The steps are as follows: Data collection: Get the real-time power consumption data of each component from the vehicle management terminal. This can be achieved through sensors inside the vehicle or the vehicle diagnostic system; Power consumption aggregation: The power consumption data extracted from each component is aggregated to form the overall operating data. This can be achieved through a software program to collect and sum the power consumption data of each component.

[0020] S2.2. According to the time period of real-time operation data and historical operation data records, the corresponding state data is extracted, and then the state difference analysis is performed on the extracted state data to obtain the difference data of power consumption of each component and the proportion of the difference data of component state consumption, so as to obtain the consumption value corresponding to the power consumption of each component and use it as the state change trend. The steps are as follows: Status difference analysis: Perform difference analysis on the extracted status data to calculate the difference between real-time data and historical data. This can be achieved through a simple subtraction operation, that is, subtracting historical data from real-time data to obtain the status difference. Consumption value calculation: associate the state difference with the corresponding component power consumption data, and calculate the consumption value corresponding to the power consumption of each component. This can be achieved by multiplying the state difference by the corresponding power consumption data to obtain the consumption value of each component; Status change trend analysis: Analyze the trend of consumption values ​​to understand the usage of each component. This can be achieved by statistical and visual analysis of consumption values, such as drawing trend graphs or calculating change rates. Calculation of the percentage of difference data: Calculate the percentage of the difference data of the power consumption of each component corresponding to the difference data of the component status consumption. This can be done by comparing the consumption value of each component with the total consumption value, and calculating the percentage of the consumption value of each component in the total consumption value. The formula is as follows: C=(S N -S M )×P Among them, C is the consumption value corresponding to the power consumption of each component, S N For real-time operation data, S M is the historical operation data, and P is the historical operation data;

[0021] The difference in power consumption for each component corresponds to the difference in power consumption for each component state. Use the power consumption value corresponding to each component. Use the total consumption value corresponding to the power consumption of all components.

[0022] S2 When the new energy vehicle is started for the first time, the status data of the components when the new energy vehicle is not started is directly used as the historical operation data, and the difference analysis is directly performed with the real-time operation data.

[0023] S3, combining the status data, safety range data and status change trend to establish a predictive maintenance model, and then inputting the real-time operation data into the predictive maintenance model for predictive analysis to obtain the predicted failure time of each component under the real-time operation data; The steps for S3 are as follows: S3.1. Establish a predictive maintenance model by combining real-time status data with safety range data and status change trends; S3.2. Input the real-time operation data into the predictive maintenance model for predictive analysis, obtain the time required for the real-time status data of each component combined with the consumption value to exceed the safety range data under the operation data, and use this time as the failure time. The steps are as follows: Establish a predictive maintenance model: Use machine learning or statistical modeling techniques to establish a predictive maintenance model based on real-time status data, safety range data, and status change trends; Input real-time operation data: Use real-time operation data as input to the model, including status data of each component, consumption value, etc. Predictive analysis: Use the established predictive maintenance model to predict the real-time operation data to obtain the failure time of each component. This can be achieved through the output of the model, usually a time period or a specific time point; Calculation of the time required to exceed the safety range data: Compare the predicted failure time with the safety range data, and calculate the time required for each component to exceed the safety range data under the real-time operating data. This can be achieved through a simple subtraction operation. The formula is as follows: T 故障 =F(S,R,T) Among them, T 故障 is the predicted failure time, S is the real-time status data, R is the safety range data, T is the status change trend data, and F(*) is the predictive maintenance model function, which is specifically a machine learning model. This function converts the input parameters S, R and T into a predicted value T 故障 , that is, the predicted component failure time. In the model training stage, historical data is used to fit the model F(*) so that it can accurately predict the component failure time. This involves steps such as feature engineering, model selection, and parameter tuning. In the prediction process, the real-time status data S, safety range data R, and status change trend data T are input into the trained model F(*) to obtain the predicted failure time T 故障 ,This predicted failure time can indicate the time when component failure may occur under the current operating state.

[0024] S4. Perform wear analysis based on historical operation data combined with status data of each component, obtain the normal wear range of each component in different operation data, then monitor the maximum wear ratio of real-time operation data, and correct the maximum wear value combined with the fault time; The steps of S4 are as follows: S4.1. Perform wear analysis based on historical operation data combined with status data of each component. Extract operation data of adjacent recording periods in the historical operation data, obtain operation data of two adjacent recording periods and extract status data of the same component, then calculate the wear difference of the two status data, then calculate the proportion of the calculated wear value combined with the safety range of the component to obtain the wear ratio, then calculate all operation data in the historical operation data to obtain multiple wear ratios, then combine the multiple wear ratios to form a normal wear range, the steps are as follows: Historical operation data extraction: Extract the operation data of adjacent periods from the historical operation data to ensure data continuity; Status data extraction: For the operation data of adjacent time periods, extract the status data of the same components, such as temperature, pressure, vibration, etc.; Wear difference calculation: The wear difference of the status data of the same parts in adjacent time periods is calculated to obtain the wear value of each part; Wear ratio calculation: calculate the ratio of the calculated wear value to the safety range of each component to obtain the wear ratio of each component; Combining multiple loss ratios: Perform the same loss ratio calculation on multiple periods in the historical operation data to obtain multiple loss ratios. Then combine these loss ratios to form a normal loss range, the formula is as follows:

[0025] in, is the loss ratio, is the difference in status data of the same component in adjacent time periods, is the safety range of the components, and Represents the absolute value of the difference, ensuring that the loss ratio is always positive. Divide by The value obtained is the wear ratio of the parts , this ratio indicates the proportion of the change in the state of the component to its safety range in adjacent time periods. This formula can be used to analyze historical operation data and calculate the wear ratio of the component. By analyzing the wear ratio of multiple time periods, a normal wear range can be formed to determine whether the wear of the current component is abnormal.

[0026] S4.2. Extract the maximum wear ratio within the normal wear range obtained in S4.1, and then send the maximum wear ratio to the predictive maintenance model, so that the predictive maintenance model corrects the predicted failure time of the parts. The steps are as follows: Extract the maximum loss ratio: Extract the maximum loss ratio from the calculated normal loss range, which may involve sorting multiple loss ratios in the historical data or simply taking the maximum value; Sending to the predictive maintenance model: sending the extracted maximum loss ratio to the predictive maintenance model, which can be achieved by taking the maximum loss ratio as the input of the model; Correcting the predicted failure time of parts: After the predictive maintenance model receives the maximum wear ratio, it corrects the predicted failure time of the parts according to the algorithm or rules within the model. This will modify the previous prediction results to make it more accurately reflect the current status and wear of the parts.

[0027] S5. Compare the wear value of the real-time operation data with the normal wear range. When the wear value exceeds the normal wear range, stop the predicted failure time of the component, adjust the status data of the component to feedback the fault to the owner, and when the owner eliminates the fault display, input the wear value into S4 to update the maximum value of the normal wear range.

[0028] The steps of S5 are as follows: S5.1. Compare the wear value of the real-time operation data with the normal wear range. When the wear value exceeds the normal wear range, stop the predicted failure time of the component, adjust the status data of the component to the fault and feedback it to the owner. When the owner eliminates the fault display, input the wear value into S4.1 to update the maximum value of the normal wear range. The steps are as follows: Compare real-time wear and tear values ​​with normal wear and tear ranges: Obtain wear and tear values ​​from real-time operation data and compare them with the calculated normal wear and tear ranges; Determine whether it is out of range: If the real-time wear value exceeds the normal wear range, it means that the status of the component is abnormal, and it is necessary to stop predicting the failure time of the component and mark the status data of the component as faulty; Fault feedback to the owner: Feedback the fault information to the owner to remind him to pay attention and take appropriate maintenance measures. This can be achieved through warning lights, display screens or remote notifications inside the vehicle; Update the normal wear range after the owner eliminates the fault display: When the owner solves the fault, the new wear value is entered into the system and the maximum value of the normal wear range is updated. This ensures that the system can adapt to changes in component status in a timely manner and improve the accuracy of the prediction.

[0029] S5.2. When the comparison result of S5.1 shows that the loss value does not exceed the normal loss range, continue monitoring.

[0030] The second object of the present invention is to provide a new energy vehicle operation data analysis and processing system, including any one of the above-mentioned new energy vehicle operation data analysis and processing methods, including a data acquisition unit 10, a fault prediction unit 20 and a prediction correction unit 30; The data collection unit 10 is used to collect component data of new energy vehicles; The fault prediction unit 20 is used to collect the operation data of the new energy vehicle, and to establish a predictive maintenance model by combining the operation data with the component data, so as to predict the failure time of the component; The prediction correction unit 30 is used to calculate the wear value and the normal wear range by combining the operation data with the component data, and to correct the fault time predicted by the fault prediction unit 20 by combining the wear value with the normal wear range.

[0031] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A method for analyzing and processing new energy vehicle operation data, characterized in that: The steps include: S1. Collect the component data of new energy vehicles, and extract the status data and safety range data of each component from the component data; S2. Collect the operation data of new energy vehicles, and classify the state data into time periods by combining the real-time operation data and the historical operation data, and perform state difference analysis on the two state data after classification to obtain the state change trend of the state data under the two states; S3, combining the status data, safety range data and status change trend to establish a predictive maintenance model, and then inputting the real-time operation data into the predictive maintenance model for predictive analysis to obtain the predicted failure time of each component under the real-time operation data; S4. Perform wear analysis based on historical operation data combined with status data of each component, obtain the normal wear range of each component in different operation data, then monitor the maximum wear ratio of real-time operation data, and correct the maximum wear value combined with the fault time; S5. Compare the wear value of the real-time operation data with the normal wear range. When the wear value exceeds the normal wear range, stop the predicted failure time of the component, adjust the status data of the component to feedback the fault to the owner, and when the owner eliminates the fault display, input the wear value into S4 to update the maximum value of the normal wear range.

2. A method for analyzing and processing operation data of a new energy vehicle according to claim 1, characterized in that: The S1 signs a data control agreement with the vehicle computer management terminal, thereby extracting component data fed back by sensors installed on the surface of key components in the vehicle computer management terminal.

3. The method for analyzing and processing the operation data of a new energy vehicle according to claim 1, characterized in that: The S1 extracts the features related to status and safety according to the characteristics and working principles of each component, displays them as status data, and then determines the safety range of each component according to the design specifications and safety standards of the component, and converts the safety range into the same numerical form as the status data.

4. The method for analyzing and processing the operation data of a new energy vehicle according to claim 1, characterized in that: The steps of S2 are as follows: S2.

1. Extract the power consumption of each component from the vehicle management terminal, and then aggregate the power consumption of each component to form operation data; S2.

2. According to the time periods of real-time operation data and historical operation data records, the corresponding status data is extracted, and then the extracted status data is analyzed for status difference, and the difference data of power consumption of each component corresponding to the difference data of component status consumption is obtained, so as to obtain the consumption value corresponding to the power consumption of each component, and use it as the status change trend.

5. The method for analyzing and processing the operation data of a new energy vehicle according to claim 1, characterized in that: In the S2, when the new energy vehicle is started for the first time, the status data of the components when the new energy vehicle is not started is directly used as the historical operation data, and the difference analysis is directly performed with the real-time operation data.

6. A method for analyzing and processing operation data of new energy vehicles according to claim 1, characterized in that: The steps of S3 are as follows: S3.

1. Establish a predictive maintenance model by combining real-time status data with safety range data and status change trends; S3.

2. Input the real-time operation data into the predictive maintenance model for predictive analysis, obtain the time required for the real-time status data of each component combined with the consumption value to exceed the safety range data under the operation data, and use this time as the failure time.

7. The method for analyzing and processing the operation data of a new energy vehicle according to claim 1, characterized in that: The steps of S4 are as follows: S4.

1. Perform wear analysis based on historical operation data combined with status data of each component, extract operation data of adjacent recording periods in the historical operation data, obtain operation data of two adjacent recording periods and extract status data of the same component, then calculate the wear difference of the two status data, then calculate the proportion of the calculated wear value combined with the safety range of the component to obtain the wear ratio, then calculate all the operation data in the historical operation data to obtain multiple wear ratios, and then combine the multiple wear ratios to form a normal wear range; S4.

2. Extract the maximum wear ratio within the normal wear range obtained in S4.1, and then send the maximum wear ratio to the predictive maintenance model, so that the predictive maintenance model corrects the predicted failure time of the parts.

8. The method for analyzing and processing the operation data of a new energy vehicle according to claim 1, characterized in that: The steps of S5 are as follows: S5.

1. Compare the wear value of the real-time operation data with the normal wear range. When the wear value exceeds the normal wear range, stop predicting the failure time of the component, adjust the status data of the component to a fault and feedback it to the owner. When the owner eliminates the fault display, input the wear value into S4.1 to update the maximum value of the normal wear range. S5.

2. When the comparison result of S5.1 shows that the loss value does not exceed the normal loss range, continue monitoring.

9. A system for analyzing and processing operating data of a new energy vehicle is implemented, comprising a method for analyzing and processing operating data of a new energy vehicle according to any one of claims 1 to 8, characterized in that: It comprises a data collection unit (10), a fault prediction unit (20) and a prediction correction unit (30); The data collection unit (10) is used to collect component data of new energy vehicles; The fault prediction unit (20) is used to collect operation data of the new energy vehicle, and to establish a predictive maintenance model by combining the operation data with component data, thereby predicting the failure time of the component; The prediction correction unit (30) is used to calculate the wear value and the normal wear range by combining the operation data with the component data, and to correct the fault time predicted by the fault prediction unit (20) by combining the wear value with the normal wear range.

Images