A vehicle operation information evaluation management system and method based on big data

Abstract

The present invention discloses a vehicle operation information evaluation and management system and method based on big data, which relates to the field of fault monitoring technology. The present invention extracts key abnormal features that cause vehicle operation abnormalities and classifies the extracted key abnormal features; obtains potential correlations between different key abnormal features; uses a machine learning algorithm to build a fault prediction model and trains the fault prediction model; uses the changes and potential correlations of different key abnormal features when the vehicle is abnormal in history to generate a data prediction model; during the operation of the vehicle, key abnormal feature data is collected in real time and input into the trained fault prediction model to determine whether the vehicle has an abnormal risk; when it is determined that the vehicle has an abnormal risk, the time required for plan formulation is calculated, and the required time is input into the data prediction model to predict future key abnormal data as a basis for formulating an emergency plan.

Description

Technical Field

[0001] The present invention relates to the technical field of fault monitoring, and in particular to a vehicle operation information evaluation and management system and method based on big data. Background Art

[0002] With the increasing electronic and intelligentization of vehicles, and the widespread application of IoT technology in the automotive sector, vehicles generate a vast amount of data during operation, such as speed, fuel consumption, fault codes, and geographic location. This data provides a rich source of material for big data-based vehicle operation information evaluation and management. The development of intelligent transportation systems requires comprehensive and accurate evaluation and management of vehicle operation information to achieve goals such as optimizing traffic flow, improving traffic safety, and increasing travel efficiency. Big data-based systems and methods can better process and analyze massive amounts of vehicle data, providing strong support for intelligent transportation. With the advancement of algorithmic technology, more intelligent vehicle operation evaluation models and management systems have been developed based on advanced technologies such as deep learning. These models can automatically identify complex vehicle operation patterns and abnormal conditions, enabling automated decision-making and early warning.

[0003] However, in the current judgment of vehicle operation information, fault monitoring usually only performs threshold judgment on single data. However, in the actual complex vehicle operation, there is a single data that does not exceed the threshold. Due to the mutual influence between the data, a fault anomaly occurs when no data exceeds the original threshold, resulting in untimely and inaccurate judgment of vehicle operation information; and because the operation information changes rapidly during vehicle operation, when the vehicle operation is adjusted and optimized based on the evaluation results, due to the time difference between information transmission and decision execution, the adjustment measures may not keep up with the changes in the vehicle operation status in a timely manner. Summary of the Invention

[0004] The purpose of the present invention is to provide a vehicle operation information evaluation management system and method based on big data to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A vehicle operation information evaluation and management method based on big data, the method comprising the following steps:

[0007] S100, collecting records of abnormal vehicle operation history, extracting vehicle operation information from the records, extracting key abnormal features that cause the vehicle operation abnormality, and classifying the extracted key abnormal features;

[0008] Furthermore, the specific steps for classifying the extracted key abnormal features are as follows:

[0009] S101. Collecting, through a cloud platform in the vehicle, historical records of abnormal vehicle operation, extracting vehicle operation information from the records, and preprocessing the extracted vehicle operation information, including missing value processing, denoising, and standardization. Regarding missing value processing, collect the information intervals of all vehicle operation information, calculate the average of the information intervals, determine that information with an information interval greater than the average is missing, calculate the average of the information on both sides of the missing information as a fill value, and fill in the missing information with the fill value.

[0010] For denoising, the sliding average filter method is used to remove the noise in the vehicle operation information; the average value and standard deviation of all operation information are calculated and the operation information is standardized. The formula is:

[0011]

[0012] In the formula, x' represents the normalized running information, x represents the original running information, and x aver represents the average value of the running information, x stand Indicates the standard deviation of the running information;

[0013] S102. Segment the vehicle operation information at the time of the abnormality, extract a data window N seconds before and after the abnormality, perform time domain and frequency domain analysis on the operation information within the extracted data window, and obtain data value characteristics of the operation information through time domain analysis, including mean value, standard deviation, and peak value. In frequency domain analysis, use Fourier transform to extract the main frequency component of the operation information. Input the operation information characteristics after dual-domain analysis into the correlation model to calculate the correlation value between each type of operation information and the vehicle abnormality, using the formula:

[0014]

[0015] In the formula, r represents the correlation value between each type of operating information and vehicle anomaly, X represents each type of operating information feature, Y represents the vehicle anomaly label, and σX and σY represent the standard deviations of X and Y, respectively. The absolute values ​​of the correlation values ​​of all types of operating information are calculated and sorted from small to large. The differences between adjacent correlation values ​​are calculated and compared to determine the maximum difference. The maximum difference is used as the demarcation node, and the operating information with a value greater than the demarcation node is regarded as the key anomaly feature of the vehicle anomaly.

[0016] S103. Collect abnormal samples and divide them into training sets and test sets, build a logistic regression model h(x), use the training set to train the logistic regression model, input the extracted key abnormal features into the logistic regression model to classify the key abnormal features, and obtain different types of key abnormal features.

[0017] By extracting and classifying key abnormal features, the system or component where the vehicle fault is located can be quickly and accurately determined, helping maintenance personnel conduct targeted inspections and repairs, improving maintenance efficiency and reducing maintenance time and costs. Promptly identifying abnormal features in vehicle operation provides early warning of issues that may affect driving safety, such as braking system anomalies and steering system failures, enabling drivers to take appropriate measures to ensure driving safety.

[0018] S200, performing correlation analysis on different types of key abnormal features to obtain potential correlation relationships between different key abnormal features;

[0019] Furthermore, the specific steps for obtaining the potential correlation between different key abnormal features are as follows:

[0020] S201, collect key abnormality features when the vehicle has abnormalities in the history, perform discrete extraction on the collected key abnormality feature data, and convert them into discrete key abnormality feature data; extract two different key abnormality features as a combination to draw a scatter plot, and use polynomial regression to fit the points in the scatter plot to obtain the polynomial G i =β0+β1×G j +β2×G j 2 +…β n ×G j n , in the polynomial, G i and G j They represent the extraction of two different key abnormal features, β0 represents a constant term, β1 to β n Represents the coefficients of the first-order independent variable to the n-order independent variable in the polynomial;

[0021] After obtaining the fitted polynomial, substitute the horizontal coordinate of each point in the scatter plot into the polynomial to calculate the fitted value of each point. Correspondingly, collect the true value of each point in the scatter plot and calculate the mean square error in the scatter plot. The formula is:

[0022]

[0023] In the formula, MSE represents the mean square error of the calculation, m represents the number of points in the scatter plot, G u Represents the fitted value of the u-th point in the scatter plot, G' u Represents the true value of the u-th point in the scatter plot;

[0024] All key anomaly features are calculated pairwise to obtain polynomials and mean square errors, and the error threshold is set to MY. When the calculated mean square error (MSE) ≤ MY, it is determined that the two key anomaly features are associated. When MSE > MY, it is determined that the two key anomaly features are not associated.

[0025] S202: When it is determined that two key abnormal features are associated, the associated key abnormal features are combined to form an associated group, all associated groups are integrated and recorded, and the polynomials calculated in the associated groups are used as potential association relationships F(G).

[0026] Different key abnormal features may be interrelated and jointly cause vehicle failures. Through correlation analysis, these potential correlations can be discovered, and the complex causes of the failure can be deeply understood, rather than being limited to the influence of a single feature. For example, the discovery of a correlation between an abnormal increase in engine oil temperature and an abnormal decrease in cooling system fan speed can help to more fully understand the cause of engine overheating failures. In actual fault diagnosis, the joint analysis of multiple abnormal features can more accurately determine the type and location of the fault than the judgment of a single feature;

[0027] Correlation analysis can avoid misdiagnoses and missed diagnosis that can occur when diagnosing based on a single feature. The cross-correlation of multiple related features can improve the reliability of diagnostic results and ensure that vehicle faults are addressed promptly and accurately.

[0028] S300: Based on the potential correlations between the mined key abnormal features, a fault prediction model is constructed using a machine learning algorithm. Key abnormal features of abnormal operation in the vehicle's history are collected as a training set to train the fault prediction model.

[0029] Furthermore, the specific steps for training the fault prediction model are as follows:

[0030] S301, calculating the mean and standard deviation of each key abnormal feature data value when the vehicle abnormality occurred in the past, and subtracting the standard deviation from the mean to obtain the fault threshold value YG_d of each key abnormal feature;

[0031] In the association group, the fault thresholds of the two key abnormal features in the association group are respectively substituted into the potential association relationship, and the fitting values ​​of the two key abnormal features are respectively calculated. The fitting values ​​are used as the association fault threshold YG_g of the association group in the association group;

[0032] S302: Build a fault prediction model using a deep learning algorithm, and collect key abnormal features of abnormal operation in the vehicle history as a training set to train the fault prediction model.

[0033] Based on real-time monitoring of key abnormal characteristics and model prediction, it can issue early warnings before vehicle failure occurs, giving drivers or maintenance personnel enough time to take measures, such as arranging repairs and replacing parts, to reduce losses and safety risks caused by failures.

[0034] Accurate failure prediction models can help develop more reasonable maintenance plans, shifting from traditional scheduled maintenance to condition-based maintenance. Based on the model's predictions, maintenance is only performed on vehicles that are about to fail, avoiding unnecessary maintenance operations and saving maintenance resources and costs.

[0035] S400, generating a data prediction model using the changes in different key abnormality characteristics and potential correlations during historical vehicle abnormalities;

[0036] Furthermore, the specific steps for generating a data prediction model using the changes in different key abnormality characteristics and potential correlations during vehicle abnormalities in history are as follows:

[0037] S401. Using the historical changes in different key abnormality characteristics during vehicle abnormalities, a curve is constructed showing the change of each key abnormality characteristic over time. The curve is interpreted using linear regression to obtain a time prediction function Gt=f(t) for each key abnormality characteristic.

[0038] Extract the potential correlation relationship within the correlation group and calculate the fitting value after the two key abnormal features influence each other, and use the potential correlation relationship as the correlation prediction function Gn=F(G);

[0039] S402 , combining the two prediction functions to obtain a data prediction model, specifically: Ga=Max(Gt, Gn).

[0040] S500: During vehicle operation, key abnormality feature data is collected in real time and input into a trained fault prediction model to determine whether the vehicle has abnormality risks;

[0041] Furthermore, the specific steps for determining whether a vehicle has abnormal risks are as follows:

[0042] S501. During vehicle operation, key abnormality feature data is collected in real time and input into the trained fault prediction model. Assuming that the real-time key abnormality feature data is Gs, the specific judgment rules are as follows:

[0043] Each key abnormal feature is judged separately. When Gs≥YG_d, it is judged that there is an abnormal risk in the vehicle operation process;

[0044] When Gs<YG_d, enter the association judgment mode, extract all the association groups in the vehicle operation data, and for each association group, set the real-time data values ​​of the two key abnormal characteristics in the association group as (Gs i , Gs j ), when (Gs i ≥YG_g i )|(Gs j ≥YG_g j), it is judged that there is an abnormal risk in the vehicle operation process.

[0045] S600: When it is determined that the vehicle has an abnormal risk, the time required for formulating a plan is calculated, and the required time is input into a data prediction model to predict future key abnormal data as a basis for formulating an emergency plan.

[0046] Furthermore, the required time is input into the data prediction model to predict future key abnormal data. The specific steps for formulating an emergency plan are as follows:

[0047] S601. Collect the analysis and transmission time of all operating information during the vehicle's operation history, calculate the average of all analysis and transmission times, and use the average as the standard time for vehicle information analysis. When it is determined that the vehicle has an abnormal risk, input the standard analysis time into the data prediction model to calculate a time prediction data value. Then, input the real-time data values ​​of two key abnormal characteristics within the association group into the data prediction model to calculate a correlation prediction data value. The maximum value of the time prediction data value and the correlation prediction data value is selected and output as the future data value.

[0048] S602: After determining that there is an abnormal risk during vehicle operation, replace the key abnormal feature data values ​​collected in real time with future data values ​​as a basis for formulating an emergency plan.

[0049] When judging whether a vehicle has abnormal risks and knowing the emergency plan, the analysis data is predicted, and the data value of the vehicle after the analysis data time is predicted in advance. When formulating the plan, the problem of plan lag is solved. As time goes by and new data is generated, the prediction results are continuously updated, and the emergency plan is dynamically adjusted and optimized to ensure that the plan always matches the actual situation of the vehicle and future development.

[0050] A vehicle operation information evaluation and management system based on big data, which includes a data collection module, a key abnormal feature search module, a correlation analysis module, a model building module, a fault judgment module and a data prediction module;

[0051] The data collection module is used to collect the operation information of the vehicle during its historical operation;

[0052] The key abnormal feature search module is used to collect records of abnormal operation in the vehicle history, extract vehicle operation information in the records, extract key abnormal features that cause the vehicle operation abnormality, and classify the extracted key abnormal features;

[0053] The association analysis module is used to perform association analysis on different types of key abnormal features to obtain potential association relationships between different key abnormal features;

[0054] The model building module is used to analyze key abnormal feature data when abnormalities occur in the vehicle in the past, and build a fault prediction model and a data prediction model respectively;

[0055] The fault judgment module is used to collect key abnormal feature data in real time during vehicle operation and input it into the trained fault prediction model to determine whether the vehicle has abnormal risks;

[0056] The data prediction module is used to input the information analysis standard time and real-time key abnormal feature data values ​​into the data prediction model to obtain future data values.

[0057] The association analysis module includes an association judgment unit and a potential association relationship calculation unit;

[0058] The association judgment unit is used to calculate the mean square error in the scatter plot to determine whether there is a correlation between two key abnormal features;

[0059] The potential correlation relationship calculation unit is used to extract two different key abnormal features as a combination to draw a scatter plot, and use polynomial regression to fit the points in the scatter plot to obtain a polynomial as the potential correlation relationship.

[0060] The model building module includes a fault prediction model unit and a data prediction model unit;

[0061] The fault prediction model unit uses a deep learning algorithm to build a fault prediction model, and collects key abnormal features of abnormal operation in the vehicle history as a training set to train the fault prediction model;

[0062] The data prediction model unit is used to calculate the time prediction function and the correlation prediction function respectively, and combine the two functions to obtain the data prediction model.

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] 1. Through correlation analysis, the present invention can avoid misjudgments and missed diagnosis that may occur when diagnosing based on only a single feature. The mutual verification of multiple related features can improve the reliability of the diagnosis results and ensure that vehicle faults are handled promptly and accurately.

[0065] 2. When judging that there is an abnormal risk in a vehicle and needing to know the emergency plan, the present invention predicts the analyzed data and predicts in advance the data value of the vehicle after the analysis data time. When formulating the plan, the problem of plan lag is solved. As time goes by and new data is generated, the prediction results are continuously updated, and the emergency plan is dynamically adjusted and optimized to ensure that the plan always matches the actual situation of the vehicle and future development. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 This is a module distribution diagram of a vehicle operation information evaluation and management system based on big data of the present invention;

[0067] Figure 2 This is a schematic diagram of the steps of a vehicle operation information evaluation and management method based on big data of the present invention. DETAILED DESCRIPTION

[0068] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0069] Example: Figure 1-Figure 2 As shown, the present invention provides a technical solution.

[0070] A vehicle operation information evaluation and management method based on big data, the method comprising the following steps:

[0071] S100, collecting records of abnormal vehicle operation history, extracting vehicle operation information from the records, extracting key abnormal features that cause the vehicle operation abnormality, and classifying the extracted key abnormal features;

[0072] The specific steps for classifying the extracted key abnormal features are:

[0073] S101. Collecting, through a cloud platform in the vehicle, historical records of abnormal vehicle operation, extracting vehicle operation information from the records, and preprocessing the extracted vehicle operation information, including missing value processing, denoising, and standardization. Regarding missing value processing, collect the information intervals of all vehicle operation information, calculate the average of the information intervals, determine that information with an information interval greater than the average is missing, calculate the average of the information on both sides of the missing information as a fill value, and fill in the missing information with the fill value.

[0074] For denoising, the sliding average filter method is used to remove the noise in the vehicle operation information; the average value and standard deviation of all operation information are calculated and the operation information is standardized. The formula is:

[0075]

[0076] In the formula, x' represents the normalized running information, x represents the original running information, and x aver represents the average value of the running information, x stand Indicates the standard deviation of the running information;

[0077] S102. Segment the vehicle operation information at the time of the abnormality, extract a data window N seconds before and after the abnormality, perform time domain and frequency domain analysis on the operation information within the extracted data window, and obtain data value characteristics of the operation information through time domain analysis, including mean value, standard deviation, and peak value. In frequency domain analysis, use Fourier transform to extract the main frequency component of the operation information. Input the operation information characteristics after dual-domain analysis into the correlation model to calculate the correlation value between each type of operation information and the vehicle abnormality, using the formula:

[0078]

[0079] In the formula, r represents the correlation value between each type of operating information and vehicle anomaly, X represents each type of operating information feature, Y represents the vehicle anomaly label, and σX and σY represent the standard deviations of X and Y, respectively. The absolute values ​​of the correlation values ​​of all types of operating information are calculated and sorted from small to large. The differences between adjacent correlation values ​​are calculated and compared to determine the maximum difference. The maximum difference is used as the demarcation node, and the operating information with a value greater than the demarcation node is regarded as the key anomaly feature of the vehicle anomaly.

[0080] S103. Collect abnormal samples and divide them into training sets and test sets, build a logistic regression model h(x), use the training set to train the logistic regression model, input the extracted key abnormal features into the logistic regression model to classify the key abnormal features, and obtain different types of key abnormal features.

[0081] By extracting and classifying key abnormal features, the system or component where the vehicle fault is located can be quickly and accurately determined, helping maintenance personnel conduct targeted inspections and repairs, improving maintenance efficiency and reducing maintenance time and costs. Promptly identifying abnormal features in vehicle operation provides early warning of issues that may affect driving safety, such as braking system anomalies and steering system failures, enabling drivers to take appropriate measures to ensure driving safety.

[0082] S200, performing correlation analysis on different types of key abnormal features to obtain potential correlation relationships between different key abnormal features;

[0083] The specific steps to obtain the potential correlation between different key abnormal features are:

[0084] S201, collect key abnormality features when the vehicle has abnormalities in the history, perform discrete extraction on the collected key abnormality feature data, and convert them into discrete key abnormality feature data; extract two different key abnormality features as a combination to draw a scatter plot, and use polynomial regression to fit the points in the scatter plot to obtain the polynomial G i =β0+β1×G j +β2×G j2 +…β n ×G j n , in the polynomial, G i and G j They represent the extraction of two different key abnormal features, β0 represents a constant term, β1 to β n Represents the coefficients of the first-order independent variable to the n-order independent variable in the polynomial;

[0085] After obtaining the fitted polynomial, substitute the horizontal coordinate of each point in the scatter plot into the polynomial to calculate the fitted value of each point. Correspondingly, collect the true value of each point in the scatter plot and calculate the mean square error in the scatter plot. The formula is:

[0086]

[0087] In the formula, MSE represents the mean square error of the calculation, m represents the number of points in the scatter plot, G u Represents the fitted value of the u-th point in the scatter plot, G' u Represents the true value of the u-th point in the scatter plot;

[0088] All key anomaly features are calculated pairwise to obtain polynomials and mean square errors, and the error threshold is set to MY. When the calculated mean square error (MSE) ≤ MY, it is determined that the two key anomaly features are associated. When MSE > MY, it is determined that the two key anomaly features are not associated.

[0089] S202: When it is determined that two key abnormal features are associated, the associated key abnormal features are combined to form an associated group, all associated groups are integrated and recorded, and the polynomials calculated in the associated groups are used as potential association relationships F(G).

[0090] Different key abnormal features may be interrelated and jointly cause vehicle failures. Through correlation analysis, these potential correlations can be discovered, and the complex causes of the failure can be deeply understood, rather than being limited to the influence of a single feature. For example, the discovery of a correlation between an abnormal increase in engine oil temperature and an abnormal decrease in cooling system fan speed can help to more fully understand the cause of engine overheating failures. In actual fault diagnosis, the joint analysis of multiple abnormal features can more accurately determine the type and location of the fault than the judgment of a single feature;

[0091] Correlation analysis can avoid misdiagnoses and missed diagnosis that can occur when diagnosing based on a single feature. The cross-correlation of multiple related features can improve the reliability of diagnostic results and ensure that vehicle faults are addressed promptly and accurately.

[0092] S300: Based on the potential correlations between the mined key abnormal features, a fault prediction model is constructed using a machine learning algorithm. Key abnormal features of abnormal operation in the vehicle's history are collected as a training set to train the fault prediction model.

[0093] The specific steps for training the fault prediction model are:

[0094] S301, calculating the mean and standard deviation of each key abnormal feature data value when the vehicle abnormality occurred in the past, and subtracting the standard deviation from the mean to obtain the fault threshold value YG_d of each key abnormal feature;

[0095] In the association group, the fault thresholds of the two key abnormal features in the association group are respectively substituted into the potential association relationship, and the fitting values ​​of the two key abnormal features are respectively calculated. The fitting values ​​are used as the association fault threshold YG_g of the association group in the association group;

[0096] S302: Build a fault prediction model using a deep learning algorithm, and collect key abnormal features of abnormal operation in the vehicle history as a training set to train the fault prediction model.

[0097] Based on real-time monitoring of key abnormal characteristics and model prediction, it can issue early warnings before vehicle failure occurs, giving drivers or maintenance personnel enough time to take measures, such as arranging repairs and replacing parts, to reduce losses and safety risks caused by failures.

[0098] Accurate failure prediction models can help develop more reasonable maintenance plans, shifting from traditional scheduled maintenance to condition-based maintenance. Based on the model's predictions, maintenance is only performed on vehicles that are about to fail, avoiding unnecessary maintenance operations and saving maintenance resources and costs.

[0099] S400, generating a data prediction model using the changes in different key abnormality characteristics and potential correlations during historical vehicle abnormalities;

[0100] The specific steps for generating a data prediction model using the changes in different key abnormal characteristics and potential correlations during vehicle abnormalities in history are as follows:

[0101] S401. Using the historical changes in different key abnormality characteristics during vehicle abnormalities, a curve is constructed showing the change of each key abnormality characteristic over time. The curve is interpreted using linear regression to obtain a time prediction function Gt=f(t) for each key abnormality characteristic.

[0102] Extract the potential correlation relationship within the correlation group and calculate the fitting value after the two key abnormal features influence each other, and use the potential correlation relationship as the correlation prediction function Gn=F(G);

[0103] S402 , combining the two prediction functions to obtain a data prediction model, specifically: Ga=Max(Gt, Gn).

[0104] S500: During vehicle operation, key abnormality feature data is collected in real time and input into a trained fault prediction model to determine whether the vehicle has abnormality risks;

[0105] The specific steps to determine whether a vehicle has abnormal risks are as follows:

[0106] S501. During vehicle operation, key abnormality feature data is collected in real time and input into the trained fault prediction model. Assuming that the real-time key abnormality feature data is Gs, the specific judgment rules are as follows:

[0107] Each key abnormal feature is judged separately. When Gs≥YG_d, it is judged that there is an abnormal risk in the vehicle operation process;

[0108] When Gs<YG_d, enter the association judgment mode, extract all the association groups in the vehicle operation data, and for each association group, set the real-time data values ​​of the two key abnormal characteristics in the association group as (Gs i , Gs j ), when (Gs i ≥YG_g i )|(Gs j ≥YG_g j ), it is judged that there is an abnormal risk in the vehicle operation process.

[0109] S600: When it is determined that the vehicle has an abnormal risk, the time required for formulating a plan is calculated, and the required time is input into a data prediction model to predict future key abnormal data as a basis for formulating an emergency plan.

[0110] Input the required time into the data prediction model to predict future key abnormal data and use it as a basis for formulating an emergency plan. The specific steps are as follows:

[0111] S601. Collect the analysis and transmission time of all operating information during the vehicle's operation history, calculate the average of all analysis and transmission times, and use the average as the standard time for vehicle information analysis. When it is determined that the vehicle has an abnormal risk, input the standard analysis time into the data prediction model to calculate a time prediction data value. Then, input the real-time data values ​​of two key abnormal characteristics within the association group into the data prediction model to calculate a correlation prediction data value. The maximum value of the time prediction data value and the correlation prediction data value is selected and output as the future data value.

[0112] S602: After determining that there is an abnormal risk during vehicle operation, replace the key abnormal feature data values ​​collected in real time with future data values ​​as a basis for formulating an emergency plan.

[0113] When judging whether a vehicle has abnormal risks and knowing the emergency plan, the analysis data is predicted, and the data value of the vehicle after the analysis data time is predicted in advance. When formulating the plan, the problem of plan lag is solved. As time goes by and new data is generated, the prediction results are continuously updated, and the emergency plan is dynamically adjusted and optimized to ensure that the plan always matches the actual situation of the vehicle and future development.

[0114] A vehicle operation information evaluation and management system based on big data, which includes a data collection module, a key abnormal feature search module, a correlation analysis module, a model building module, a fault judgment module and a data prediction module;

[0115] The data collection module is used to collect the operation information of the vehicle during its historical operation;

[0116] The key abnormal feature search module is used to collect records of abnormal operation in the vehicle history, extract vehicle operation information in the records, extract key abnormal features that cause the vehicle operation abnormality, and classify the extracted key abnormal features;

[0117] The association analysis module is used to perform association analysis on different types of key abnormal features to obtain potential association relationships between different key abnormal features;

[0118] The model building module is used to analyze key abnormal feature data when abnormalities occur in the vehicle in the past, and build a fault prediction model and a data prediction model respectively;

[0119] The fault judgment module is used to collect key abnormal feature data in real time during vehicle operation and input it into the trained fault prediction model to determine whether the vehicle has abnormal risks;

[0120] The data prediction module is used to input the information analysis standard time and real-time key abnormal feature data values ​​into the data prediction model to obtain future data values.

[0121] The association analysis module includes an association judgment unit and a potential association relationship calculation unit;

[0122] The association judgment unit is used to calculate the mean square error in the scatter plot to determine whether there is a correlation between two key abnormal features;

[0123] The potential correlation relationship calculation unit is used to extract two different key abnormal features as a combination to draw a scatter plot, and use polynomial regression to fit the points in the scatter plot to obtain a polynomial as the potential correlation relationship.

[0124] The model building module includes a fault prediction model unit and a data prediction model unit;

[0125] The fault prediction model unit uses a deep learning algorithm to build a fault prediction model, and collects key abnormal features of abnormal operation in the vehicle history as a training set to train the fault prediction model;

[0126] The data prediction model unit is used to calculate the time prediction function and the correlation prediction function respectively, and combine the two functions to obtain the data prediction model.

[0127] Example: Real-time evaluation of vehicle operation information is performed to extract key abnormality features affecting vehicle abnormalities, namely temperature, vibration, and speed; correlation analysis is performed to determine the correlation between temperature and speed, and a correlation group is constructed;

[0128] A fault prediction model and a data prediction model are constructed based on historical data;

[0129] The real-time collection of three key abnormal characteristic data values ​​of temperature, vibration, and speed is 50, 20, and 3000. The individual fault thresholds of the three data are 70, 30, and 5000 respectively. When judged individually, the vehicle does not have abnormal risk. The associated fault thresholds calculated in the associated group are 40 and 4000.

[0130] In the associated group, it is determined that the vehicle has abnormal risks due to temperature reasons;

[0131] When formulating the emergency plan later, set the standard time to 1s, input the standard time, real-time temperature and speed into the data prediction model, and obtain the time prediction temperature as 52 and the associated prediction temperature as 60; when formulating the plan, it is necessary to formulate the emergency plan based on 60.

[0132] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A vehicle operation information evaluation and management method based on big data, characterized by: The method comprises the following steps: S100, collecting records of abnormal vehicle operation history, extracting vehicle operation information from the records, extracting key abnormal features that cause the vehicle operation abnormality, and classifying the extracted key abnormal features; S200, performing correlation analysis on different types of key abnormal features to obtain potential correlation relationships between different key abnormal features; S201. Perform pairwise calculations on all key abnormal features to obtain polynomials and mean square errors, and set the error threshold to MY. When the calculated mean square error (MSE) ≤ MY, it is determined that the two key abnormal features are associated; when MSE > MY, it is determined that the two key abnormal features are not associated. S202: When it is determined that two key abnormal features are associated, the associated key abnormal features are combined to form an associated group, all associated groups are integrated and recorded, and the polynomials calculated in the associated groups are used as the potential association relationship F(G); S300: Based on the potential correlations between the mined key abnormal features, a fault prediction model is constructed using a machine learning algorithm. Key abnormal features of abnormal operation in the vehicle's history are collected as a training set to train the fault prediction model. S400, generating a data prediction model using the changes in different key abnormality characteristics and potential correlations during historical vehicle abnormalities; The specific steps for generating a data prediction model using the changes in different key abnormal characteristics and potential correlations during vehicle abnormalities in history are as follows: S401. Using the historical changes in different key abnormality characteristics during vehicle abnormalities, a curve is constructed showing the change of each key abnormality characteristic over time. The curve is interpreted using linear regression to obtain a time prediction function Gt=f(t) for each key abnormality characteristic. Extract the potential correlation relationship within the correlation group and calculate the fitting value after the two key abnormal features influence each other, and use the potential correlation relationship as the correlation prediction function Gn=F(G); S402, combining the two prediction functions to obtain a data prediction model, specifically: Ga = Max (Gt, Gn); S500: During vehicle operation, key abnormality feature data is collected in real time and input into a trained fault prediction model to determine whether the vehicle has abnormality risks; S600: When it is determined that the vehicle has an abnormal risk, the time required for formulating a plan is calculated, and the required time is input into a data prediction model to predict future key abnormal data as a basis for formulating an emergency plan.

2. The vehicle operation information evaluation and management method based on big data according to claim 1, characterized in that: The specific steps of classifying the extracted key abnormal features in S100 are: S101. Collecting, through a cloud platform in the vehicle, historical records of abnormal vehicle operation, extracting vehicle operation information from the records, and preprocessing the extracted vehicle operation information, including missing value processing, denoising, and standardization. For missing value processing, the information intervals of all vehicle operation information are collected, and the average value of the information intervals is calculated. Information with an information interval greater than the average value is considered missing. The average value of the information on both sides of the missing part is calculated as the filling value, and the missing information is filled with the filling value; For denoising, the sliding average filter method is used to remove the noise in the vehicle operation information; Calculate the mean and standard deviation of all running information and standardize the running information. The formula is: In the formula, x' represents the normalized running information, x represents the original running information, and x aver represents the average value of the running information, x stand Indicates the standard deviation of the running information; S102. Segment the vehicle operation information at the time of the abnormality, extract a data window N seconds before and after the abnormality, perform time domain and frequency domain analysis on the operation information within the extracted data window, and obtain data value characteristics of the operation information through time domain analysis, including mean value, standard deviation, and peak value. In frequency domain analysis, use Fourier transform to extract the main frequency component of the operation information. Input the operation information characteristics after dual-domain analysis into the correlation model to calculate the correlation value between each type of operation information and the vehicle abnormality, using the formula: In the formula, r represents the correlation value between each type of operating information and vehicle anomaly, X represents each type of operating information feature, Y represents the vehicle anomaly label, and σX and σY represent the standard deviations of X and Y, respectively. The absolute values ​​of the correlation values ​​of all types of operating information are calculated and sorted from small to large. The differences between adjacent correlation values ​​are calculated and compared to determine the maximum difference. The maximum difference is used as the demarcation node, and the operating information with a value greater than the demarcation node is regarded as the key anomaly feature of the vehicle anomaly. S103. Collect abnormal samples and divide them into training sets and test sets, build a logistic regression model h(x), use the training set to train the logistic regression model, input the extracted key abnormal features into the logistic regression model to classify the key abnormal features, and obtain different types of key abnormal features.

3. The vehicle operation information evaluation and management method based on big data according to claim 2 is characterized by: The specific steps of S201 are: S211. Collect key abnormality features when the vehicle has abnormalities in the past, perform discrete extraction on the collected key abnormality feature data, and convert them into discrete key abnormality feature data; extract two different key abnormality features as a combination to draw a scatter plot, and use polynomial regression to fit the points in the scatter plot to obtain the polynomial G. i =β0+β1×G j +β2×G j 2 +…β n ×G j n , in the polynomial, G i and G j They represent the extraction of two different key abnormal features, β0 represents a constant term, β1 to β n Represents the coefficients of the first-order independent variable to the n-order independent variable in the polynomial; After obtaining the fitted polynomial, substitute the horizontal coordinate of each point in the scatter plot into the polynomial to calculate the fitted value of each point. Correspondingly, collect the true value of each point in the scatter plot and calculate the mean square error in the scatter plot. The formula is: In the formula, MSE represents the mean square error of the calculation, m represents the number of points in the scatter plot, G u Represents the fitted value of the u-th point in the scatter plot, G' u Represents the true value of the u-th point in the scatter plot.

4. The vehicle operation information evaluation and management method based on big data according to claim 3 is characterized by: The specific steps of training the fault prediction model in S300 are: S301, calculating the mean and standard deviation of each key abnormal feature data value when the vehicle abnormality occurred in the past, and subtracting the standard deviation from the mean to obtain the fault threshold value YG_d of each key abnormal feature; In the association group, the fault thresholds of the two key abnormal features in the association group are respectively substituted into the potential association relationship, and the fitting values ​​of the two key abnormal features are respectively calculated. The fitting values ​​are used as the association fault threshold YG_g of the association group in the association group; S302: Build a fault prediction model using a deep learning algorithm, and collect key abnormal features of abnormal operation in the vehicle history as a training set to train the fault prediction model.

5. The vehicle operation information evaluation and management method based on big data according to claim 4 is characterized by: The specific steps of determining whether the vehicle has abnormal risk in S500 are: S501. During vehicle operation, key abnormality feature data is collected in real time and input into the trained fault prediction model. Assuming that the real-time key abnormality feature data is Gs, the specific judgment rules are as follows: Each key abnormal feature is judged separately. When Gs≥YG_d, it is judged that there is an abnormal risk in the vehicle operation process; When Gs<YG_d, enter the association judgment mode, extract all the association groups in the vehicle operation data, and for each association group, set the real-time data values ​​of the two key abnormal characteristics in the association group as (Gs i , Gs j ), when (Gs i ≥YG_g i )|(Gs j ≥YG_g j ), it is judged that there is an abnormal risk in the vehicle operation process.

6. The vehicle operation information evaluation and management method based on big data according to claim 5 is characterized by: The specific steps of inputting the required time into the data prediction model in S600 to predict future key abnormal data and formulate an emergency plan based on it are as follows: S601. Collect the analysis and transmission time of all operating information during the vehicle's operation history, calculate the average of all analysis and transmission times, and use the average as the standard time for vehicle information analysis. When it is determined that the vehicle has an abnormal risk, input the standard analysis time into the data prediction model to calculate a time prediction data value. Then, input the real-time data values ​​of two key abnormal characteristics within the association group into the data prediction model to calculate a correlation prediction data value. The maximum value of the time prediction data value and the correlation prediction data value is selected and output as the future data value. S602: After determining that there is an abnormal risk during vehicle operation, replace the key abnormal feature data values ​​collected in real time with future data values ​​as a basis for formulating an emergency plan.

7. A vehicle operation information evaluation and management system based on big data, applying the vehicle operation information evaluation and management method based on big data according to any one of claims 1 to 6, characterized in that: The vehicle operation information evaluation and management system includes a data collection module, a key abnormality feature search module, a correlation analysis module, a model building module, a fault judgment module, and a data prediction module; The data collection module is used to collect the operation information of the vehicle during its historical operation; The key abnormal feature search module is used to collect records of abnormal operation in the vehicle history, extract vehicle operation information in the records, extract key abnormal features that cause the vehicle operation abnormality, and classify the extracted key abnormal features; The association analysis module is used to perform association analysis on different types of key abnormal features to obtain potential association relationships between different key abnormal features; The model building module is used to analyze key abnormal feature data when the vehicle has abnormalities in the past, and to build a fault prediction model and a data prediction model respectively; The fault judgment module is used to collect key abnormal feature data in real time during vehicle operation and input it into the trained fault prediction model to determine whether the vehicle has abnormal risks; The data prediction module is used to input the information analysis standard time and real-time key abnormal feature data values ​​into the data prediction model to obtain future data values.

8. The vehicle operation information evaluation and management system based on big data according to claim 7, characterized in that: The association analysis module includes an association judgment unit and a potential association relationship calculation unit; The association judgment unit is used to calculate the mean square error in the scatter plot to determine whether there is a correlation between two key abnormal features; The potential correlation relationship calculation unit is used to extract two different key abnormal features as a combination to draw a scatter plot, and use polynomial regression to fit the points in the scatter plot to obtain a polynomial as the potential correlation relationship.

9. The vehicle operation information evaluation and management system based on big data according to claim 7, characterized in that: The model building module includes a fault prediction model unit and a data prediction model unit; The fault prediction model unit uses a deep learning algorithm to build a fault prediction model, and collects key abnormal features of abnormal operation in the vehicle history as a training set to train the fault prediction model; The data prediction model unit is used to calculate the time prediction function and the correlation prediction function respectively, and combine the two functions to obtain the data prediction model.

Images