Method for identifying abnormal modification of software in vehicle-mounted diagnostic system

A neural network-based method for analyzing emission and driving data improves the detection of abnormal software modifications in OBD systems, enhancing the reliability of exhaust emission monitoring.

CN119065880AActive Publication Date: 2024-12-03ZHILIAN WANWEI TECH CO LTD
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202411079921.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-07
Publication Date
2024-12-03
Estimated Expiration
2044-08-07

AI Technical Summary

Technical Problem

Existing on-board diagnostic systems (OBD) can be deceived by software modifications that falsely report normal exhaust emissions, compromising the accuracy of pollution detection.

Method used

A method using a neural network model to analyze emission data and driving information, calculating similarity and dispersion metrics to identify abnormal software modifications in OBD systems.

Benefits of technology

Enhances the accuracy and reliability of detecting abnormal software modifications in OBD systems, ensuring accurate exhaust emission monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119065880A_ABST
    Figure CN119065880A_ABST
Patent Text Reader

Abstract

The invention provides a method for identifying abnormal modification of software in a vehicle-mounted diagnostic system, and relates to the field of vehicle-mounted system safety, and the method comprises the steps: obtaining a to-be-confirmed emission data list uploaded by a target vehicle-mounted diagnostic system of a target vehicle, obtaining a target driving information list, inputting the target driving information list into the target neural network model, obtaining a target predicted emission data list, obtaining a target similarity between the to-be-confirmed emission data and the target predicted emission data so as to obtain a target similarity list, and determining the emission data to be confirmed based on the similarity list. Determining that software abnormal modification exists in the target vehicle-mounted diagnostic system of the target vehicle; according to the method, whether software abnormal modification exists or not is judged according to the similarity between the emission data to be confirmed and the target predicted emission data, so that the detection safety of the target vehicle-mounted diagnostic system is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of vehicle-mounted system safety, and in particular to a method for identifying abnormal software modification in a vehicle-mounted diagnostic system. Background Art

[0002] The on-board diagnostics system OBD (On-Board Diagnostics) is an electronic system installed in the car to monitor the performance of the vehicle engine and other systems; the main functions of the OBD system include: fault detection, fault indication, fault code storage, data flow monitoring, and driver behavior monitoring; currently, in China, many cities require new models to be equipped with OBD systems to detect exhaust emissions and reduce pollution.

[0003] Specifically, if the OBD system detects that exhaust emissions exceed the standard, the vehicle may not pass the annual inspection and will need to be repaired. However, in order to ensure that exhaust monitoring is always in a normal state, some people may take certain measures to deceive the OBD system and make it report a false healthy state, such as by invading the ECU software so that the OBD system does not report a fault or by adjusting the sensor to make it read incorrectly, thereby making the OBD system emissions normal.

[0004] Therefore, how to ensure that the exhaust emissions detected by the OBD system have not been abnormally modified by other software remains a problem. Summary of the invention

[0005] In view of the above technical problems, the technical solution adopted by the present invention is: a method for identifying abnormal software modification in an on-board diagnostic system, the method is used to identify whether there is abnormal software modification in the on-board diagnostic system, and the method comprises the following steps:

[0006] S100, obtaining a list of emission data to be confirmed uploaded by a target on-board diagnostic system of a target vehicle A = {A1, A2, ..., A i , …, A m}, A i is the target vehicle diagnostic system at the i-th target time point T i The uploaded emission data to be confirmed, i has a value range of 1 to m, m is the number of target time points, and the fields of the emission data to be confirmed include NOx emissions, CO emissions, and CO2 emissions;

[0007] S200, obtaining a target driving information list B = {B1, B2, ..., B i , …, B m}, and input the target driving information list B into the target neural network model to obtain the target predicted emission data list D = {D1, D2, ..., D i , …, Dm}, B i is the target vehicle at T i Driving information, D i is the target vehicle at T i The target predicted emission data has the same field as the field of the emission data to be confirmed;

[0008] S300, get A i and D i The target similarity E i , thereby obtaining the target similarity list E = {E1, E2, ..., E i , …, E m};

[0009] S400, obtain E0=(∑ m i=1 E i ) / m, based on E0, it is determined that there is abnormal software modification in the target on-board diagnostic system of the target vehicle.

[0010] The present invention has at least the following beneficial effects:

[0011] In summary, a list of emission data to be confirmed uploaded by a target on-board diagnostic system of a target vehicle is obtained, a target driving information list is obtained and the target driving information list is input into a target neural network model, a target predicted emission data list is obtained, a target similarity between the emission data to be confirmed and the target predicted emission data is obtained, thereby obtaining a target similarity list, and based on the similarity list, it is determined whether there is abnormal software modification in the target on-board diagnostic system of the target vehicle; the present invention determines whether there is abnormal software modification by the similarity between the emission data to be confirmed and the target predicted emission data, so as to improve the safety of detection of the target on-board diagnostic system. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A flowchart of a method for identifying abnormal software modification in an on-board diagnostic system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0014] 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0015] An embodiment of the present invention provides a method for identifying abnormal software modification in a vehicle-mounted diagnostic system, wherein the method is used to identify whether there is abnormal software modification in the vehicle-mounted diagnostic system, such as Figure 1 As shown, the method comprises the following steps:

[0016] S100, obtaining a list of emission data to be confirmed uploaded by a target on-board diagnostic system of a target vehicle A = {A1, A2, ..., A i , …, A m}, A i is the target vehicle diagnostic system at the i-th target time point T i The uploaded emission data to be confirmed, the value range of i is 1 to m, m is the number of target time points, wherein the fields of the emission data to be confirmed include NOx emissions, CO emissions, and CO2 emissions.

[0017] S200, obtaining a target driving information list B = {B1, B2, ..., B i , …, B m}, and input the target driving information list B into the target neural network model to obtain the target predicted emission data list D = {D1, D2, ..., D i , …, D m}, B i is the target vehicle at T i Driving information, D i is the target vehicle at T i The target predicted emission data has the same fields as the emission data to be confirmed. That is, the fields of the target predicted emission data include NOx emission, CO emission, and CO2 emission.

[0018] Specifically, the driving information field includes: vehicle model, vehicle mileage, engine speed. The driving information field also includes: duration of the engine speed.

[0019] Specifically, Bi is input into the target neural network model, and the target neural network model outputs B i The corresponding NOx emissions in the target predicted emission data, CO emissions in the target predicted emission data, and CO2 emissions in the target predicted emission data.

[0020] S300, get A i and D i The target similarity E i , thereby obtaining the target similarity list E = {E1, E2, ..., E i , …, E m}.

[0021] S400, obtain E0=(∑ m i=1 E i ) / m, based on E0, it is determined that there is abnormal software modification in the target on-board diagnostic system of the target vehicle.

[0022] In summary, a list of emission data to be confirmed uploaded by a target on-board diagnostic system of a target vehicle is obtained, a target driving information list is obtained and the target driving information list is input into a target neural network model, a target predicted emission data list is obtained, a target similarity between the emission data to be confirmed and the target predicted emission data is obtained, thereby obtaining a target similarity list, and based on the similarity list, it is determined whether there is abnormal software modification in the target on-board diagnostic system of the target vehicle; the present invention determines whether there is abnormal software modification by the similarity between the emission data to be confirmed and the target predicted emission data, so as to improve the safety of detection of the target on-board diagnostic system.

[0023] Specifically, S200 also includes:

[0024] S210, obtaining a historical training emission data list set C = {C1, C2, ..., C r , …, C s}, where C r =(C r1 , C r2 ), C r1 ={C r11 , C r12 , …, C r1g , …, C r1z}, C r2 ={C r21 , C r22 , …, C r2g , …, C r2z}, C r1g is the driving information of the rth historical vehicle in the gth historical time period, C r2g It is the actual emission data for training of the rth historical vehicle in the gth historical time period. The fields of the actual emission data for training include: NOx emission, CO emission, and CO2 emission.

[0025] S220, based on the historical data list set C, training the preset neural network model to obtain the target neural network model.

[0026] Furthermore, S220 also includes:

[0027] S221, divide the historical training emission data list set C into s1 training sets and s2 test sets.

[0028] S222, using s1 training sets to train the preset neural network model to obtain an intermediate neural network model.

[0029] S223, evaluate the intermediate neural network model, and determine the model whose evaluation result meets the first preset condition as the neural network model to be tested. Specifically, the first preset condition can be determined according to actual needs, and the evaluation result is the difference between the training predicted emission data and the training actual data of the driving information in the s1 training sets.

[0030] S224, inputting s2 test sets into the neural network model to be tested to obtain a test result. Specifically, the second preset condition can be determined according to actual needs, and the test result is the difference between the predicted emission data for training and the actual data for training of driving information in the s2 test sets.

[0031] S225, when the test result meets the second preset condition, the trained neural network model is determined as the target neural network model.

[0032] Specifically, determining in S400 based on E0 that there is abnormal software modification in the target onboard diagnostic system of the target vehicle also includes:

[0033] S410: If E0 is less than the preset similarity threshold TE, it is determined that there is abnormal software modification in the target on-board diagnostic system of the target vehicle.

[0034] S420, if E0≥TE, obtain the preset time interval T0, and execute S430.

[0035] S430, based on A1 to A m , get [T i , T i +T0] Emission data to be confirmed within A i The degree of dispersion F i .

[0036] Specifically, those skilled in the art know that any method for obtaining the degree of dispersion in the prior art belongs to the protection scope of the present invention. For example, in one embodiment of the present invention, the target time point is taken as the horizontal axis and A is taken as the horizontal axis. 11 To A m1 As the vertical axis, the function of the NOx emission to be confirmed is constructed; and with the target time point as the horizontal axis, A 12 To A m2As the vertical axis, the CO emission function to be confirmed is constructed; with the target time point as the horizontal axis, A 13 To A m3 As the vertical axis, construct the CO2 emission function to be confirmed; obtain the NOx emission function to be confirmed in [T i , T i +T0] within the mean square error K i1 , obtain the CO emission function to be confirmed in [T i , T i +T0] within the mean square error K i2 , obtain the CO2 emission function to be confirmed in [T i , T i +T0] within the mean square error K i3 , F i =(K i1 +K i2 +K i3 ) / 3.

[0037] Among them, A i =(A i1 , A i2 , A i3 ), A i1 is the NOx emission in the emission data to be confirmed uploaded at the i-th target time point, A i2 is the CO emission in the emission data to be confirmed uploaded at the i-th target time point, A i3 It is the CO2 emission in the emission data to be confirmed uploaded at the i-th target time point.

[0038] S440, based on E i and F i , it is determined that there is abnormal software modification in the target on-board diagnostic system of the target vehicle, wherein the greater the dispersion of the emission data to be confirmed, the lower the probability that there is abnormal software modification in the target on-board diagnostic system of the target vehicle. It can be understood that when using other methods to deceive the OBD system, emission data with smaller fluctuations that meet exhaust gas monitoring are often used. Therefore, the higher the dispersion of the emission data to be confirmed, the lower the probability that there is abnormal software modification in the OBD system.

[0039] Further, S440 includes the following steps:

[0040] S441, obtaining the judgment value G i , where G i Meet the following conditions: G i =k1×E i +k2×F i, k1 is a first preset weight factor, k2 is a second preset weight factor, and k1>0, k2>0. Specifically, the first weight factor and the second weight factor can be determined according to actual conditions.

[0041] S442, when the judgment value G i When the judgment value G0 is less than the preset judgment threshold, it is determined that there is abnormal software modification in the target vehicle's onboard diagnostic system. It can be understood that the greater the target similarity and the greater the dispersion, the smaller the probability that there is abnormal software modification in the target vehicle's onboard diagnostic system. Therefore, when the judgment value G0 is less than the preset judgment threshold, it is determined that there is abnormal software modification in the target vehicle's onboard diagnostic system. i Less than G0, it is determined that there is abnormal software modification in the target vehicle diagnostic system.

[0042] In one embodiment of the present invention, T i+1 -T i =Preset fixed collection interval T a .

[0043] In summary, if E0 ≥ TE, obtain the preset time interval based on A1 to A m , get [T i , T i +T0] Emission data to be confirmed within A i The degree of dispersion F i , based on E i and F i Get the judgment value G i , when the judgment value G i If the target similarity and the dispersion degree of the emission data to be confirmed are smaller than the preset judgment threshold G0, it is determined that there is abnormal software modification in the target on-board diagnostic system of the target vehicle, and the target similarity and the dispersion degree of the emission data to be confirmed are used to determine that there is abnormal software modification in the target on-board diagnostic system of the target vehicle, so as to improve the accuracy of the judgment.

[0044] Furthermore, after S442, the method further includes: obtaining TS=T0+e×|T2-T1|, and using TS as a preset fixed acquisition interval between adjacent target time points when identifying abnormal software modification in the on-board diagnostic system next time, wherein e is the interval from G1 to G2. m Medium G i It can be understood that according to the number of G1 to G0 in the vehicle diagnostic system, m Medium G i The number that is less than the preset judgment threshold G0, that is, the number that is judged to have software abnormal modification. The more the number that is judged to have software abnormality in the on-board diagnostic system, the larger the preset fixed collection interval is at the next identification, to avoid the situation where the normal value of the software abnormality is modified to a smaller value to lower the average value so as to meet the exhaust gas detection requirements, thereby improving the detection efficiency and improving the detection accuracy.

[0045] Specifically, in S300, A is obtained through the following steps:i and D i The target similarity E i :

[0046] S001, with the target time point as the horizontal axis and A 11 To A m1 As the vertical axis, the function of the NOx emission to be confirmed is constructed; and with the target time point as the horizontal axis, A 12 To A m2 As the vertical axis, the CO emission function to be confirmed is constructed; with the target time point as the horizontal axis, A 13 To A m3 Specifically, those skilled in the art know that any method of obtaining a function based on discrete points in the prior art belongs to the protection scope of the present invention and will not be described in detail here.

[0047] Among them, A i =(A i1 , A i2 , A i3 ), A i1 is the NOx emission in the emission data to be confirmed uploaded at the i-th target time point, A i2 is the CO emission in the emission data to be confirmed uploaded at the i-th target time point, A i3 It is the CO2 emission in the emission data to be confirmed uploaded at the i-th target time point.

[0048] S002, obtain [T i , T i+1 ) The maximum value MN of the NOx emission function to be confirmed i , the minimum value NN of the NOx emission function to be confirmed i , the maximum value MC of the CO emission function to be confirmed i 、The minimum value NC of the CO emission function to be confirmed i , the maximum value MO of the CO2 emission function to be confirmed i 、The minimum value of CO2 emission function to be confirmed NO i .

[0049] S003, with the target time point as the horizontal axis and D 11 To D m1 As the vertical axis, a function for predicting NOx emissions is constructed; and with the target time point as the horizontal axis and D 12 To D m2 As the vertical axis, a function for predicting CO emissions is constructed; and with the target time point as the horizontal axis and D 13 To D m3 As the vertical axis, a function for predicting CO2 emissions is constructed.

[0050] Among them, D i =(D i1 , D i2 , D i3 ), D i1 is the NOx emission in the target predicted emission data uploaded at the i-th target time point, D i2 is the CO emission in the target forecast emission data uploaded at the i-th target time point, D i3 is the CO2 emission in the target predicted emission data uploaded at the i-th target time point.

[0051] S004, obtain [T i , T i+1 ) The maximum value of the function for predicting NOx emissions within i , predict the minimum value of NOx emission function BN i , the maximum value AC of the predicted CO emission function i , the minimum value BC of the predicted CO emission function i , the maximum value of the predicted CO2 emission function AO i , predict the maximum value of CO2 emission function BO i .

[0052] S005, establish a three-dimensional coordinate system with NOx emissions as the X-axis, CO emissions as the Y-axis, and CO2 emissions as the Z-axis.

[0053] S006, when i≠m, based on MN i NN i , MC i , NC i 、MO i 、NO i , construct A i The corresponding geometric object H i , based on AN i , BN i , AC i , B.C. i , AO i , BO i , construct D i The corresponding geometric object J i , based on H i and J i , get A i and D i The corresponding target similarity E i ;

[0054] S007, when i=m, A m and D m The distance is taken as the target similarity E mSpecifically, those skilled in the art know that any method for obtaining the distance between two points in the prior art falls within the protection scope of the present invention and will not be described in detail herein.

[0055] Specifically, when i≠m, E i The following conditions are met: i =VH i / VJ i , VH i Yes H i Volume, VJ i It's J i volume.

[0056] In summary, with the target time point as the horizontal axis and A 11 To A m1 As the vertical axis, the function of the NOx emission to be confirmed is constructed, and the target time point is taken as the horizontal axis. 12 To A m2 As the vertical axis, the CO emission function to be confirmed is constructed; with the target time point as the horizontal axis, A 13 To A m3 As the vertical axis, construct the CO2 emission function to be confirmed and obtain [T i , T i+1 ) The maximum value MN of the NOx emission function to be confirmed i , the minimum value NN of the NOx emission function to be confirmed i , the maximum value MC of the CO emission function to be confirmed i 、The minimum value NC of the CO emission function to be confirmed i , the maximum value MO of the CO2 emission function to be confirmed i 、The minimum value of CO2 emission function to be confirmed NO i ; With the target time point as the horizontal axis and D 11 To D m1 As the vertical axis, a function for predicting NOx emissions is constructed, with the target time point as the horizontal axis and D 12 To D m2 As the vertical axis, a function for predicting CO emissions is constructed, with the target time point as the horizontal axis and D 13 To D m3 As the vertical axis, construct a function to predict CO2 emissions and obtain [T i , T i+1 ) The maximum value of the function for predicting NOx emissions within i , predict the minimum value of NOx emission function BN i , the maximum value AC of the predicted CO emission function i , the minimum value BC of the predicted CO emission function i , the maximum value of the predicted CO2 emission function AO i, predict the maximum value of CO2 emission function BO i , with NOx emissions as the X-axis, CO emissions as the Y-axis, and CO2 emissions as the Z-axis, a three-dimensional coordinate system is established. When i≠m, based on MN i NN i , MC i , NC i 、MO i 、NO i , construct A i The corresponding geometric object H i , based on AN i , BN i , AC i , B.C. i , AO i , BO i , construct D i The corresponding geometric object J i , based on H i and J i , get A i and D i The corresponding target similarity E i ; When i = m, A m and D m The distance is taken as the target similarity E m ; By establishing a three-dimensional coordinate system, the corresponding volume ratio is obtained as the similarity.

[0057] An embodiment of the present invention also provides a non-transitory computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to implementing a method in a method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the method provided in the above embodiment.

[0058] An embodiment of the present invention further provides an electronic device, comprising a processor and the aforementioned non-transitory computer-readable storage medium.

[0059] Although some specific embodiments of the present invention have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are only for illustration, not for limiting the scope of the present invention. It should also be understood by those skilled in the art that various modifications may be made to the embodiments without departing from the scope and spirit of the present invention.

Claims

1. A method for identifying abnormal software modification in an on-board diagnostic system, the method being used to identify whether there is abnormal software modification in the on-board diagnostic system, It is characterized in that The method comprises the following steps: S100, obtaining a list of emission data to be confirmed uploaded by a target on-board diagnostic system of a target vehicle A = {A 1 , A 2 , …, A i , …, A m }, A i is the target vehicle diagnostic system at the i-th target time point T i The uploaded emission data to be confirmed, i has a value range of 1 to m, m is the number of target time points, and the fields of the emission data to be confirmed include NOx emissions, CO emissions, and CO2 emissions; S200, obtaining target driving information list B = {B 1 , B 2 , …, B i , …, B m }, and input the target driving information list B into the target neural network model to obtain the target predicted emission data list D = {D 1 , D 2 , …, D i , …, D m }, B i is the target vehicle at T i Driving information, D i is the target vehicle at T i The target predicted emission data has the same field as the field of the emission data to be confirmed; S300, get A i and D i The target similarity E i , thereby obtaining the target similarity list E = {E 1 , E 2 ,…,E i ,…,E m }; S400, Get E 0 =(∑ m i=1 E i ) / m, based on E 0 It is determined that there is an abnormal software modification in the target on-board diagnostic system of the target vehicle.

2. The method for identifying abnormal software modification in an on-board diagnostic system according to claim 1, It is characterized in that The S200 also includes: S210, obtaining a historical training emission data list set C = {C 1 , C 2 , …, C r , …, C s }, where C r =(C r1 , C r2 ), C r1 ={C r11 , C r12 , …, C r1g , …, C r1z }, C r2 ={C r21 , C r22 , …, C r2g , …, C r2z }, C r1g It is the rth The driving information of historical vehicles in the gth historical time period, C r2g is the actual emission data used for training of the rth historical vehicle in the gth historical time period; S220, based on the historical data list set C, training the preset neural network model to obtain the target neural network model.

3. The method for identifying abnormal software modification in an on-board diagnostic system according to claim 2, It is characterized in that The S220 also includes: S221, divide the historical training emission data list set C into s 1 training set and s 2 test sets; S222, using s 1 The preset neural network model is trained with a training set to obtain an intermediate neural network model; S223, evaluating the intermediate neural network model, and determining the model whose evaluation result meets the first preset condition as the neural network model to be tested; S224, will s 2 A test set is input into the neural network model to be tested to obtain a test result; S225, when the test result meets the second preset condition, the trained neural network model is determined as the target neural network model.

4. The method for identifying abnormal software modification in an on-board diagnostic system according to claim 1, It is characterized in that The fields of the driving information include: vehicle model, vehicle mileage, and engine speed.

5. The method for identifying abnormal software modification in an on-board diagnostic system according to claim 1, It is characterized in that S400 is based on E 0 Determine that there is abnormal software modification in the target vehicle's onboard diagnostic system, including: S410, if E 0 <preset similarity threshold TE, determining that there is abnormal software modification in the target on-board diagnostic system of the target vehicle; S420, if E 0 ≥TE, get the preset time interval T 0 , execute S430; S430, based on A 1 To A m , get [T i , T i +T 0 ] Emission data to be confirmed A i The degree of dispersion F i ; S440, based on E i and F i , determining that there is abnormal software modification in the target on-board diagnostic system of the target vehicle, wherein the greater the dispersion of the emission data to be confirmed, the lower the probability that there is abnormal software modification in the target on-board diagnostic system of the target vehicle.

6. The method for identifying abnormal software modification in an on-board diagnostic system according to claim 5, It is characterized in that S440 includes the following steps: S441, obtaining the judgment value G i , where G i Meet the following conditions: G i =k 1 ×E i +k 2 ×F i , k 1 is the first preset weight factor, k 2 is the second preset weight factor, and k 1 >0,k 2 >0; S442, when the judgment value G i Less than the preset judgment threshold G 0 , it is determined that there is an abnormal software modification in the target on-board diagnostic system of the target vehicle.

7. The method for identifying abnormal software modification in an on-board diagnostic system according to claim 6, It is characterized in that T i+1 -T i =Preset fixed collection interval T a .

8. The method for identifying abnormal software modification in an on-board diagnostic system according to claim 6, It is characterized in that After S442, the following steps are also included: obtaining TS=T 0 +e×|T 2 -T 1 |, TS is used as the preset fixed acquisition interval between adjacent target time points when the next identification of abnormal software modification in the on-board diagnostic system is performed, where e is G 1 To G m Medium G i Less than the preset judgment threshold G 0 The number of 9. The method for identifying abnormal software modification in an on-board diagnostic system according to claim 1, It is characterized in that In S300, A is obtained by the following steps i and D i The target similarity E i : S001, with the target time point as the horizontal axis and A 11 To A m1 As the vertical axis, the function of NOx emission to be confirmed is constructed; and with the target time point as the horizontal axis, A 12 To A m2 As the vertical axis, the CO emission function to be confirmed is constructed; with the target time point as the horizontal axis, A 13 To A m3 As the vertical axis, construct the function of CO2 emissions to be confirmed; Among them, A i =(A i1 , A i2 , A i3 ), A i1 is the NOx emission in the emission data to be confirmed uploaded at the i-th target time point, A i2 is the CO emission in the emission data to be confirmed uploaded at the i-th target time point, A i3 is the CO2 emission in the emission data to be confirmed uploaded at the i-th target time point; S002, obtain [T i , T i+1 ) The maximum value MN of the NOx emission function to be confirmed i , the minimum value NN of the NOx emission function to be confirmed i , the maximum value MC of the CO emission function to be confirmed i 、The minimum value NC of the CO emission function to be confirmed i , the maximum value MO of the CO2 emission function to be confirmed i 、The minimum value of CO2 emission function to be confirmed NO i ; S003, with the target time point as the horizontal axis and D 11 To D m1 As the vertical axis, a function for predicting NOx emissions is constructed; and with the target time point as the horizontal axis and D 12 To D m2 As the vertical axis, a function for predicting CO emissions is constructed; and with the target time point as the horizontal axis and D 13 To D m3 As the vertical axis, construct the function of predicting CO2 emissions; Among them, D i =(D i1 , D i2 , D i3 ), D i1 is the NOx emission in the target predicted emission data uploaded at the i-th target time point, D i2 is the CO emission in the target forecast emission data uploaded at the i-th target time point, D i3 is the CO2 emission in the target forecast emission data uploaded at the i-th target time point; S004, obtain [T i , T i+1 ) within the predicted NOx emission function AN i , predict the minimum value of NOx emission function BN i , the maximum value AC of the predicted CO emission function i , the minimum value BC of the predicted CO emission function i , the maximum value of the predicted CO2 emission function AO i , predict the maximum value of CO2 emission function BO i ; S005, establish a three-dimensional coordinate system with NOx emissions as the X-axis, CO emissions as the Y-axis, and CO2 emissions as the Z-axis; S006, when i≠m, based on MN i NN i , MC i , NC i 、MO i 、NO i , construct A i The corresponding geometric object H i , based on AN i , BN i , AC i , B.C. i , AO i , BO i , construct D i The corresponding geometric object J i , based on H i and J i , get A i and D i The corresponding target similarity E i ; S007, when i=m, A m and D m The distance is taken as the target similarity E m .

10. The method for identifying abnormal software modification in an on-board diagnostic system according to claim 9, It is characterized in that When i≠m, E i The following conditions are met: i =VH i / VJ i , VH i Yes H i Volume, VJ i It's J i volume.

Citation Information

Patent Citations

  • Residual error posterior-based abnormal value online detection and confidence degree assessment method

    CN107092582A

  • Online prediction method for actual road particulate matter emission of heavy diesel vehicle

    CN112964476A

  • Motor vehicle driving carbon emission prediction method, electronic equipment and storage medium

    CN116229607A

  • Method for detecting counterfeit data

    CN117237165A

  • Abnormal vehicle traveling detection method, and electronic device and storage medium

    WO2023201904A1