CN117687382A - Vehicle fault checking method, system and computer medium - Google Patents
Vehicle fault checking method, system and computer medium Download PDFInfo
- Publication number
- CN117687382A CN117687382A CN202311702523.6A CN202311702523A CN117687382A CN 117687382 A CN117687382 A CN 117687382A CN 202311702523 A CN202311702523 A CN 202311702523A CN 117687382 A CN117687382 A CN 117687382A
- Authority
- CN
- China
- Prior art keywords
- fault
- variable group
- state
- sensor signal
- independent variable
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000001419 dependent effect Effects 0.000 claims abstract description 71
- 238000001514 detection method Methods 0.000 claims abstract description 7
- 238000012423 maintenance Methods 0.000 claims description 47
- 230000000875 corresponding effect Effects 0.000 claims description 44
- 230000002596 correlated effect Effects 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 7
- 230000001364 causal effect Effects 0.000 claims description 5
- 238000011835 investigation Methods 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 2
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000012938 design process Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0208—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the configuration of the monitoring system
- G05B23/0213—Modular or universal configuration of the monitoring system, e.g. monitoring system having modules that may be combined to build monitoring program; monitoring system that can be applied to legacy systems; adaptable monitoring system; using different communication protocols
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
Abstract
The invention relates to a vehicle fault checking method, a system and a computer medium, which belong to the technical field of electric digital data processing, and acquire an independent variable group and a dependent variable group, wherein the independent variable group is related to the dependent variable group, the independent variable group is a fault reason corresponding to a fault part, and the dependent variable group is a state of a sensor signal to be detected corresponding to the fault part; or the independent variable group is the state of the sensor signal to be screened, and the dependent variable group is the state of the associated sensor signal associated with the sensor signal to be screened; judging whether the state of the independent variable group corresponds to the state of the dependent variable group or not; and if the set of independent variables, the set of dependent variables or the combined fault alarm of the set of independent variables and the set of dependent variables is not corresponding, prompting the independent variable set, the set of dependent variables or the combined fault alarm of the two. The invention can prompt the early detection and early investigation of faults, and avoid serious faults from influencing driving safety.
Description
Technical Field
The invention relates to the technical field of electric digital data processing, in particular to a vehicle fault checking method, a vehicle fault checking system and a computer medium.
Background
In the aspect of fault detection of a related sensor of an automobile, the prior art depends on experience judgment of engineers and also depends on actual judgment of finding out the failure of the sensor, for example, after the automobile tire pressure sensor fails, the tire pressure sensor always displays the tire pressure as 2.5bar, if the automobile tire leaks and is repaired, an automobile owner only pays attention to the problem of the automobile tire, and the automobile owner and the repairing staff cannot find out the actual problem of the tire pressure sensor, so that the fault sensor cannot be repaired timely.
Disclosure of Invention
The invention aims to provide a vehicle fault checking method for solving the problem that a fault sensor cannot be repaired in time in the prior art.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
a method for checking account of vehicle faults,
acquiring an independent variable group and a dependent variable group, wherein the independent variable group is associated with the dependent variable group, the independent variable group is a fault reason corresponding to a fault part, and the dependent variable group is a state of a sensor signal to be detected corresponding to the fault part; or the independent variable group is the state of the sensor signal to be screened, and the dependent variable group is the state of the associated sensor signal associated with the sensor signal to be screened;
judging whether the state of the independent variable group corresponds to the state of the dependent variable group or not;
and if the set of independent variables, the set of dependent variables or the combined fault alarm of the set of independent variables and the set of dependent variables is not corresponding, prompting the independent variable set, the set of dependent variables or the combined fault alarm of the two.
Further, the method for acquiring the state of the sensor signal to be detected comprises the following steps:
the method comprises the steps of obtaining a maintenance work order, wherein the fault reasons of the fault parts are obtained through the maintenance work order;
obtaining a time sequence data set of the sensor signal to be detected according to the historical vehicle signal data;
setting a first sliding window, and obtaining the state of the to-be-detected sensor signal at any time point in the time sequence data set of the to-be-detected sensor signal intercepted by the first sliding window when the right pointer of the first sliding window coincides with the occurrence time of the maintenance work order.
Further, the method for acquiring the correlation sensor signal comprises the following steps:
setting a second sliding window, wherein the second sliding window slides on the time sequence data set of the sensor signal to be screened according to a preset step length, and a region formed by a left pointer and a right pointer of the second sliding window covers a time point where the second sliding window is positioned;
and reading the state of the associated sensor signal of any time point of the time sequence data set of the associated sensor signal intercepted by the second sliding window.
Further, the sensor signal to be screened has at least one of a causal correlation, a time series correlation, a linear correlation, or a conditional correlation with an associated sensor signal.
A vehicle fault checking system based on the vehicle fault checking method,
the system comprises a signal state acquisition module, a detection module and a detection module, wherein the signal state acquisition module is configured to acquire an independent variable group and a dependent variable group, the independent variable group and the dependent variable group are associated, the independent variable group is a fault reason corresponding to a fault part, and the dependent variable group is a state of a sensor signal to be detected corresponding to the fault part; or the independent variable group is the state of the sensor signal to be screened, and the dependent variable group is the state of the associated sensor signal associated with the sensor signal to be screened;
a judging module configured to judge whether the state of the independent variable group corresponds to the state of the dependent variable group;
and the alarm module is configured to prompt fault alarm of the independent variable group, the dependent variable group or the combination of the independent variable group and the dependent variable group if the state of the independent variable group does not correspond to the state of the dependent variable group.
Further, the device also comprises an identification module which is configured to acquire a maintenance work order and identify the fault reason of the fault part according to the maintenance work order.
Further, the vehicle fault reconciliation system further comprises a knowledge base, which is established by:
and selecting all types of component fault sources as the independent variable groups, taking the states of sensor signals corresponding to the component fault sources of each type as the dependent variable groups, and storing the mapping relation between the independent variable groups and the dependent variable groups to form the knowledge base.
Further, the vehicle fault reconciliation system further comprises a knowledge base, which is established by:
selecting the sensor signal to be screened as the independent variable group;
calculating correlations between all other sensor signals and the sensor signals to be screened according to the vehicle history signal data;
selecting sensor signals greater than a correlation threshold as correlated sensor signals, defining the correlated sensor signals as a set of dependent variables;
and storing the mapping relation between the independent variable group and the dependent variable group to form the knowledge base.
Further, the judging module judges whether the fault reason of the fault part corresponds to the state of the sensor signal to be detected or not based on the knowledge base.
Further, the determination module determines whether a state of the sensor signal to be screened corresponds to a state of the associated sensor signal based on the knowledge base.
A computer medium, characterized by: in which a computer readable program is stored which, when called, is capable of performing the steps of the vehicle fault checking method described above.
The invention has the beneficial effects that:
according to the invention, by searching whether the fault reasons of the fault parts correspond to the states of the corresponding sensor signals to be detected or not, the fault problems of the vehicle sensors are detected based on the fault parts, and compared with the experience judgment of a single dependent engineer, the success rate of detecting the hidden problems of the vehicle sensors is improved;
according to the state of the sensor signal to be screened and the state of the associated sensor signal at the corresponding moment or time period, the potential hidden problem of the potential associated sensor and the belt screening sensor is tracked, the tracking analysis of faults of a plurality of automobile sensors at one time can be realized, the screening efficiency is improved, and meanwhile, maintenance personnel can be helped to detect and discover the root cause of the fault cause, so that valuable feedback is provided for manufacturers to improve the product design and manufacturing process; the method can also help the driver to find out the possible fault problem, prompt the driver to find out the early investigation and avoid serious faults and influence the driving safety.
Drawings
FIG. 1 is a flow chart of a method for timely finding out a problem sensor by timely acquiring a maintenance work order for investigation in embodiment 1;
FIG. 2 is a flow chart for comprehensively inspecting the fault condition of an automobile sensor by using a sensor signal with higher correlation in the embodiment 1;
FIG. 3 is a flow chart of the embodiment 1 for completing the acquisition of maintenance work orders for investigation, thereby timely finding out the problem sensor and comprehensively investigating the fault condition of the automobile sensor through the sensor signals with higher correlation;
FIG. 4 is a second sliding window schematic;
fig. 5 is a structural composition diagram of embodiment 2.
Detailed Description
Further advantages and effects of the present invention will become readily apparent to those skilled in the art from the disclosure herein, by referring to the following description of the embodiments of the present invention with reference to the accompanying drawings and preferred examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be understood that the preferred embodiments are presented by way of illustration only and not by way of limitation.
It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, and only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
The embodiment provides a vehicle fault checking method, in fault checking between signals, whether the signal states are consistent or not is checked, if not, an alarm message is pushed, and whether a sensor is abnormal or not is checked. In checking the failure reason of the vehicle maintenance part and the vehicle signal, when the failure reason of the vehicle maintenance part is inconsistent with the state of the vehicle signal, an alarm message is pushed, and whether the sensor is abnormal is further checked. Therefore, whether the sensor is in a normal state or not is verified from the two aspects of maintenance failure reasons and vehicle end signals, the accuracy of uploading signals by the sensor is improved, the consistency of the vehicle state and cloud signals is ensured, hidden danger possibly existing in the vehicle failure is fundamentally solved, and time and resources are prevented from being wasted by maintenance personnel in maintenance.
Example 1
In the embodiment, the maintenance work orders are timely acquired for investigation, so that the problem sensor is timely found out.
As shown in fig. 1, the method specifically includes the following steps.
S11: and acquiring a maintenance work order, and identifying the fault reason of the fault part according to the maintenance work order.
The maintenance work order in the step comes from a maintenance center, when the maintenance center receives a fault vehicle, the maintenance center sends the maintenance work order according to the actual condition of the vehicle, fault reasons and maintenance time are marked on the maintenance work order, the maintenance center uploads the vehicle information, the fault reasons, the maintenance time and other information to the cloud end through a corresponding computer system, and the cloud end directly grabs the fault reasons by using a corresponding grabbing tool, so that the fault reasons are extracted.
In one embodiment, a classifier based on KNN, a clustering algorithm, a random forest and other algorithms is arranged at the cloud end, the maintenance master writing fault reasons uploaded by the maintenance work orders are classified into the fault reasons set at the cloud end, for example, the keywords are extracted to be attached values, and the distance between the keywords and the clustering center is calculated through a preset function, so that classification is achieved.
S21: and acquiring the state of the sensor signal to be detected corresponding to the fault part when the fault part is in fault according to the historical vehicle signal data.
In the step, the state of the fault part and the state of the signal of the sensor to be detected are in a corresponding relation, such as a tire and a tire pressure sensor, and when the tire leaks, the signal state value of the tire pressure sensor is 0; the door sensor displays that the door is open when the door is not closed to the vehicle body due to a problem of the door connecting member.
The historical vehicle signal data in this step is a time sequence data set, records the change data of the vehicle signal along with time, has a mapping relation with time points, such as sensor signal states of a vehicle door sensor, a tire pressure sensor and the like when the vehicle door sensor is at 11 months, 7 days, 12 points, 01 minutes and 5 seconds, and it is obvious to a person skilled in the art that the sensor states are represented by numerical values, such as the value of the vehicle door sensor is 1 when the vehicle door sensor is on, the value of the vehicle door sensor is closed to be 0, the number displayed by the tire pressure sensor is the actual value of the tire pressure, and the sensor signal states can be obtained by reading the sensor signal values, which can be realized by the person skilled in the art without creative labor.
However, in an actual process, the time point when the repair work sheet is generated during vehicle repair is often later than the time point when the fault part breaks down, for example, after the tire leaks, a driver often knows afterfeel, and abnormal conditions are generated during driving or the situation is known after stopping observation, so that the generation of the repair work sheet often has postponement property. Specific:
setting a first sliding window, and when the right pointer of the first sliding window coincides with the occurrence time of the maintenance work order on a time sequence data set of the sensor signals to be detected (obtained according to historical vehicle signal data), the state of the sensor signals to be detected at any time point of the time sequence data set of the sensor signals to be detected is the state of the sensor signals to be detected corresponding to the fault part.
According to the embodiment, a sliding window algorithm is cited, a first sliding window is set, the length between a left pointer and a right pointer of the first sliding window is the length of the window, the right pointer of the first sliding window coincides with the time of a maintenance work order, or after the allowable error time is exceeded, time sequence data intercepted by the first sliding window are read, and the state of a sensor signal to be detected can be the state of any time point.
S31: and judging whether the fault reason of the fault part corresponds to the state of the sensor signal to be detected.
In S31, the correspondence between the failure cause of the failed component and the state of the sensor signal to be detected may be interpreted that, when the failed component fails, the corresponding state value of the sensor signal to be detected is changed, if the state value of the sensor signal to be detected does not change, which indicates that the first sensor fails, for example, after the tire leaks, the value signal of the tire pressure sensor should be 0, which indicates that the tire leaking corresponds to the state of the sensor signal to be detected, and in the data intercepted by the first sliding window, there is a period of time sequence data indicating that the value signal of the tire pressure sensor at the corresponding time point is 2.5, which obviously does not conform to the situation state of the tire leaking, so that the failure cause of the failed component does not correspond to the state of the sensor signal to be detected, and the first sensor may have a risk of failure.
S41: if not, prompting the fault alarm of the sensor to be detected, and if so, not prompting the fault.
In the embodiment, the vehicle maintenance work order parts and the signal state reconciliation task are automatically generated at the cloud. Based on actual conditions, the corresponding relation between the fault reasons of the vehicle maintenance parts and the corresponding signals and states of the related sensors is constructed. And when the failure cause of the maintenance part is monitored, checking the data in corresponding time or time range in the historical vehicle signal data, judging whether the signal state of the corresponding sensor is consistent with the failure cause data of the maintenance part, and prompting the corresponding sensor to alarm information if the signal state of the corresponding sensor is inconsistent with the failure cause data of the maintenance part.
According to the embodiment, the fault condition of the automobile sensor is comprehensively checked through the sensor signals with higher correlation. As shown in fig. 2, the method specifically comprises:
s12: and acquiring a sensor signal to be screened and a related sensor signal corresponding to the moment or the time period, which are sent by the vehicle, according to the historical vehicle signal data.
In this step, the correlation of the sensor signal to be screened and the signal of its associated sensor is obtained by:
automated signal data correlation analysis. A certain fault scene specific signal is selected as an independent variable group, and a signal with strong correlation possibly exists is selected as the dependent variable group. All element signals and element signal combination correlation values of the independent variable group and the dependent variable group are calculated respectively based on the vehicle signal history data using an automated program, wherein the calculated correlation relationship includes a causal correlation, a time series correlation, a linear correlation, a conditional correlation, and the like. A range of correlation values 0-1 is defined, and when the correlation value is greater than 0.6, a correlation of the independent variable signal and the dependent variable signal with the correlation is defined.
In this embodiment, when the vehicle is in a certain working condition, the state values of the sensor signals of the vehicle are correlated, and when the vehicle is in a high-speed running working condition, for example, if the signal value of the received vehicle speed sensor exceeds a certain value, the state of the vehicle door sensor is closed, and the engine speed identified by the engine speed sensor is also in a certain section.
In this embodiment, by a statistical method, in the vehicle signal history data, an associated sensor signal associated with each sensor signal to be screened is generated, and specifically, the acquisition of the type of the associated sensor signal is implemented by a calculation manner of correlation in statistics, for example: according to historical vehicle signal data, time sequence data sets of all sensor signals in the same period are intercepted, correlations among state values of all sensor signals are calculated, if the correlations among the two sensor signals are larger than 0.6, the correlation among the two sensor signals is indicated, and the type of the correlation is at least one of causal correlation, time sequence correlation, linear correlation or conditional correlation.
In this embodiment, the acquisition of the associated sensor signal is achieved by a window algorithm. The method comprises the following steps:
setting a second sliding window, wherein the second sliding window slides on a time sequence data set of a sensor signal to be screened according to a preset step length, and a time point where the second sliding window is located is covered by a region formed by a left pointer and a right pointer of the second sliding window;
the state of the associated sensor signal at any point in time of the portion of the time series dataset of associated sensor signals intercepted by the second sliding window is read.
As shown in fig. 4, where a represents a time series data set of associated sensor signals in the historical vehicle signal data, B represents a time series data set of signal states of sensors to be screened in the historical vehicle signal data, a middle triangle represents a second sliding window, a solid line represents a position where the second sliding window is experiencing, and a dotted line represents a position where a corresponding time period is experienced before and after, in this embodiment, a region formed by a left pointer and a right pointer of the second sliding window covers a time point where the second sliding window is located, that is, when the second time window slides to a 2S of the B time series data, the state of 1S-4S of the a time series data is actually viewed, so that influence on a detection result due to hysteresis induced by the sensor is avoided. In this embodiment, the state of the associated sensor at any time point when the second sliding window of the triangle is cut on the a time sequence data may be the state of the associated sensor at the time, for example, the second sliding window slides to the 3 rd S, but is on the a time sequence data. The state of the associated sensor signal at any point in time within the 2 nd-5S may be defined as the state of the associated sensor signal of the 3 rd S.
S22: judging whether the state of the associated sensor signal corresponds to the state of the sensor signal to be screened, if not, prompting the fault alarm of the associated sensor, prompting the fault alarm of the sensor to be screened, or prompting both. The associated sensor signal is associated with the sensor signal to be screened.
The embodiment automatically generates signal data to monitor the reconciliation task. And generating a data monitoring reconciliation task by using the signal data with correlation, opening a sliding window in the real-time monitoring task, and monitoring whether the signal state values of the independent variable group signal and the dependent variable signal group signal are consistent. If the sensor alarm information is inconsistent, prompting the corresponding sensor alarm information. For example, when a vehicle speed high-speed running signal and an engine starting signal are received at the cloud end and a vehicle door opening signal are also received, at this time, the situation that the signal and the signal account checking are inconsistent exists, namely, in the high-speed running of the vehicle, the vehicle door sensor should not upload the vehicle door opening signal, the vehicle door sensor should be prompted to give an alarm about the faults of the vehicle door sensor, or the engine starting sensor, the vehicle speed sensor and the vehicle door sensor should be prompted to give an alarm about the faults of the vehicle door sensor, so that a maintenance engineer can carry out comprehensive screening.
In at least one embodiment, the maintenance work order is obtained for investigation, so that the problem sensor can be found out timely, and the fault condition of the automobile sensor can be comprehensively investigated by using the sensor signals with higher correlation, as shown in fig. 3, specifically:
and S1, accessing a vehicle end signal, finishing cloud loading of a vehicle end sensor signal through a tbox, and writing the cloud end signal into a cloud message middleware for storage.
And S2, accessing the data of the maintenance work station, inputting the fault reasons of the vehicle maintenance parts by the vehicle maintenance station system, and writing the system data into the cloud message middleware for storage.
S3, dividing the fault signal and other signals into independent variable groups and dependent variable groups, performing program calculation, performing correlation calculation on all signals of the independent variable groups and the dependent variable groups respectively, and determining that the independent variable signals and the dependent variable signals have correlation when the correlation value is larger than 0.6.
And S4, writing the corresponding relation of the correlation between the independent variable signal and the dependent variable signal into a knowledge base.
S5, generating the independent variable number and the dependent variable signal checking task at the same time, opening a sliding window in the real-time checking task, checking whether the states of the independent variable signal and the corresponding variable signal are consistent, and pushing the corresponding sensor fault alarm message if the states of the independent variable signal and the corresponding variable signal are inconsistent.
And S6, constructing a knowledge base of the corresponding relation between the fault reasons of the parts and the signal states.
And S7, simultaneously generating a real-time checking task of the fault reasons and the signal states of the parts, accessing the maintenance work order data in real time, opening a sliding window in the real-time checking task, checking whether the time for generating the fault reasons of the parts is consistent with the signal state of the corresponding time range in the corresponding signal history data, and pushing the corresponding sensor fault alarm message if the time for generating the fault reasons of the parts is inconsistent with the signal state of the corresponding time range in the corresponding signal history data.
And S8, pushing fault warning information to a message engine by the real-time reconciliation task, and distributing the fault warning information to vehicle users, after-sales customer service and vehicle maintenance points.
S9, after-sales customer service prompts a vehicle user to enter a station for diagnosis, and corresponding signals are checked for the sensor with the fault alarm prompt. If the sensor has no fault, updating the knowledge base of the independent variable signal and the dependent variable signal, and confirming that the state of the independent variable signal and the dependent variable signal has no sensor abnormality.
And S10, if diagnosis and investigation are carried out, the sensor is abnormal, and the sensor is maintained.
Example 2
Based on embodiment 1, this embodiment proposes a vehicle fault accounting system, as shown in fig. 5, including a signal state obtaining module 1 configured to obtain an independent variable group and a dependent variable group, where the independent variable group is a fault cause corresponding to a fault component, and the dependent variable group is a state of a sensor signal to be detected corresponding to the fault component; or the independent variable group is the state of the sensor signal to be screened, and the dependent variable group is the state of the associated sensor signal associated with the sensor signal to be screened;
a judging module 2 configured to judge whether the state of the independent variable group corresponds to the state of the dependent variable group;
and the alarm module 3 is configured to prompt fault alarm of the independent variable group, the dependent variable group or the combination of the independent variable group and the dependent variable group if the state of the independent variable group does not correspond to the state of the dependent variable group.
The identification module 4 is configured to acquire a maintenance work order and identify the fault reason of the fault part according to the maintenance work order;
the method for obtaining the state of the sensor signal to be detected by the signal state obtaining module comprises the following steps:
the method comprises the steps that a maintenance work order is obtained through an identification module, and the fault reasons of the fault parts are obtained through the maintenance work order;
obtaining a time sequence data set of the sensor signal to be detected according to the historical vehicle signal data;
setting a first sliding window, and when the right pointer of the first sliding window coincides with the occurrence time of the maintenance work order, obtaining the state of the to-be-detected sensor signal of any time point in the time sequence data set of the to-be-detected sensor signal intercepted by the first sliding window.
The method for acquiring the associated sensor signals by the signal state acquisition module comprises the following steps:
setting a second sliding window, wherein the second sliding window slides on the time sequence data set of the sensor signal to be screened according to a preset step length, and a region formed by a left pointer and a right pointer of the second sliding window covers a time point where the second sliding window is positioned;
and reading the state of the associated sensor signal of any time point of the time sequence data set of the associated sensor signal intercepted by the second sliding window.
The sensor signal to be screened has at least one of a causal correlation, a time series correlation, a linear correlation, or a conditional correlation with the associated sensor signal.
In this embodiment, the vehicle fault reconciliation system further includes a first knowledge base and a second knowledge base, where the first knowledge base is established by:
and selecting all types of component fault sources as a first independent variable group, taking the state of a sensor signal corresponding to each type of component fault source as the first dependent variable group, and storing the mapping relation between the first independent variable group and the first dependent variable group into a first database to form a first knowledge base.
The second knowledge base is established by:
selecting the sensor signal to be screened as a second independent variable group;
calculating correlations between all other sensor signals and the sensor signals to be screened according to the vehicle history signal data;
sensor signals greater than the correlation threshold are selected as correlated sensor signals, and correlated sensor signals are defined as the second set of dependent variables, the correlation threshold in this embodiment being 0.6.
And storing the mapping relation between the second independent variable group and the second dependent variable group into a second database to form the second knowledge base.
The judging module 2 judges whether the fault reason of the fault part corresponds to the state of the sensor signal to be detected or not based on the first knowledge base; and judging whether the state of the sensor signal to be screened corresponds to the state of the associated sensor signal or not based on the second knowledge base.
Example 3
The present embodiment proposes a computer medium in which a computer-readable program is stored, the computer-readable program being capable of executing the steps of the vehicle trouble checking method as described in embodiment 1 when called.
The above embodiments are merely preferred embodiments for fully explaining the present invention, and the scope of the present invention is not limited thereto. Equivalent substitutions and modifications will occur to those skilled in the art based on the present invention, and are intended to be within the scope of the present invention.
Claims (11)
1. A vehicle fault checking method is characterized in that:
acquiring an independent variable group and a dependent variable group, wherein the independent variable group is associated with the dependent variable group, the independent variable group is a fault reason corresponding to a fault part, and the dependent variable group is a state of a sensor signal to be detected corresponding to the fault part; or the independent variable group is the state of the sensor signal to be screened, and the dependent variable group is the state of the associated sensor signal associated with the sensor signal to be screened;
judging whether the state of the independent variable group corresponds to the state of the dependent variable group or not;
and if the set of independent variables, the set of dependent variables or the combined fault alarm of the set of independent variables and the set of dependent variables is not corresponding, prompting the independent variable set, the set of dependent variables or the combined fault alarm of the two.
2. The vehicle fault reconciliation method of claim 1, wherein: the method for acquiring the state of the sensor signal to be detected comprises the following steps:
the method comprises the steps of obtaining a maintenance work order, wherein the fault reasons of the fault parts are obtained through the maintenance work order;
obtaining a time sequence data set of the sensor signal to be detected according to the historical vehicle signal data;
setting a first sliding window, and obtaining the state of the to-be-detected sensor signal at any time point in the time sequence data set of the to-be-detected sensor signal intercepted by the first sliding window when the right pointer of the first sliding window coincides with the occurrence time of the maintenance work order.
3. The vehicle fault reconciliation method of claim 1, wherein: the method for acquiring the associated sensor signal comprises the following steps:
setting a second sliding window, wherein the second sliding window slides on the time sequence data set of the sensor signal to be screened according to a preset step length, and a region formed by a left pointer and a right pointer of the second sliding window covers a time point where the second sliding window is positioned;
and reading the state of the associated sensor signal of any time point of the time sequence data set of the associated sensor signal intercepted by the second sliding window.
4. The vehicle fault reconciliation method of claim 1, wherein: the sensor signal to be screened has at least one of a causal correlation, a time series correlation, a linear correlation, or a conditional correlation with an associated sensor signal.
5. A vehicle fault reconciliation system based on the vehicle fault reconciliation method of any one of claims 1-4, wherein:
the system comprises a signal state acquisition module, a detection module and a detection module, wherein the signal state acquisition module is configured to acquire an independent variable group and a dependent variable group, the independent variable group and the dependent variable group are associated, the independent variable group is a fault reason corresponding to a fault part, and the dependent variable group is a state of a sensor signal to be detected corresponding to the fault part; or the independent variable group is the state of the sensor signal to be screened, and the dependent variable group is the state of the associated sensor signal associated with the sensor signal to be screened;
a judging module configured to judge whether the state of the independent variable group corresponds to the state of the dependent variable group;
and the alarm module is configured to prompt fault alarm of the independent variable group, the dependent variable group or the combination of the independent variable group and the dependent variable group if the state of the independent variable group does not correspond to the state of the dependent variable group.
6. The vehicle fault reconciliation system of claim 5, wherein:
the system further comprises an identification module which is configured to acquire a maintenance work order and identify the fault reason of the fault part according to the maintenance work order.
7. The vehicle fault reconciliation system of claim 5, wherein: the vehicle fault reconciliation system further comprises a knowledge base, wherein the knowledge base is established by the following steps:
and selecting all types of component fault sources as the independent variable groups, taking the states of sensor signals corresponding to the component fault sources of each type as the dependent variable groups, and storing the mapping relation between the independent variable groups and the dependent variable groups to form the knowledge base.
8. The vehicle fault reconciliation system of claim 5, wherein: the vehicle fault reconciliation system further comprises a knowledge base, wherein the knowledge base is established by the following steps:
selecting the sensor signal to be screened as the independent variable group;
calculating correlations between all other sensor signals and the sensor signals to be screened according to the vehicle history signal data;
selecting sensor signals greater than a correlation threshold as correlated sensor signals, defining the correlated sensor signals as a set of dependent variables;
and storing the mapping relation between the independent variable group and the dependent variable group to form the knowledge base.
9. The vehicle fault reconciliation system of claim 7, wherein: and the judging module judges whether the fault reason of the fault part corresponds to the state of the sensor signal to be detected or not based on the knowledge base.
10. The vehicle fault reconciliation system of claim 8, wherein: the judging module judges whether the state of the sensor signal to be screened corresponds to the state of the associated sensor signal or not based on the knowledge base.
11. A computer medium, characterized by: a computer readable program stored therein, which when invoked is capable of performing the steps of the vehicle fault checking method according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311702523.6A CN117687382A (en) | 2023-12-12 | 2023-12-12 | Vehicle fault checking method, system and computer medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311702523.6A CN117687382A (en) | 2023-12-12 | 2023-12-12 | Vehicle fault checking method, system and computer medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117687382A true CN117687382A (en) | 2024-03-12 |
Family
ID=90131472
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311702523.6A Pending CN117687382A (en) | 2023-12-12 | 2023-12-12 | Vehicle fault checking method, system and computer medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117687382A (en) |
-
2023
- 2023-12-12 CN CN202311702523.6A patent/CN117687382A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102096760B (en) | Detecting anomalies in field failure data | |
| CN101514942B (en) | Vehicle diagnosing apparatus, vehicle diagnosing system, and diagnosing method | |
| US8463485B2 (en) | Process for service diagnostic and service procedures enhancement | |
| CN102375452B (en) | Event-driven data mining method for improving fault code settings and isolating faults | |
| CA2508008C (en) | A method for developing a unified quality assessment and providing an automated fault diagnostic tool for turbine machine systems and the like | |
| EP3156862B1 (en) | Methods and apparatus for the creation and use of reusable fault model components in fault modeling and complex system prognostics | |
| CN108027611B (en) | Decision assistance system and method for machine maintenance using expert opinion supervised decision mode learning | |
| US7877636B2 (en) | System and method for detecting temporal relationships uniquely associated with an underlying root cause | |
| EP2948744B1 (en) | Determining a remedial action for a motorized vehicle based on sensed vibration | |
| CN106441928A (en) | Method, device and system for vehicle fault detection | |
| US8621305B2 (en) | Methods systems and apparatus for determining whether built-in-test fault codes are indicative of an actual fault condition or a false alarm | |
| CN113902233A (en) | Vehicle safety early warning method, big data platform device, vehicle-mounted terminal and vehicle | |
| CN116880454A (en) | Intelligent diagnosis system and method for vehicle faults | |
| US20170176985A1 (en) | Method for predicting end of line quality of assembled product | |
| CN114323671A (en) | Method and device for determining the remaining service life by means of an artificial intelligence method on the basis of a predictive diagnosis of a component of an electric drive system | |
| ITCO20090068A1 (en) | METHOD AND SYSTEM FOR DIAGNOSTICATING COMPRESSORS | |
| CN117671818B (en) | Management system for vehicle data | |
| CN117687382A (en) | Vehicle fault checking method, system and computer medium | |
| KR102470804B1 (en) | Method and system for comprehensive diagnosis defects in rotating machinery | |
| CN112446980B (en) | Enhanced component fault diagnosis method for providing minimum probability fault | |
| KR20220096794A (en) | Method and system for diagnosing defects in rotating machinery | |
| CN118210787A (en) | Real-time vehicle condition automatic detection method based on multidimensional vehicle big data and vehicle condition intelligent defect inference technology | |
| CN108415401A (en) | A kind of engineering truck Measuring error data managing method and system | |
| CN117132266B (en) | Block chain-based automobile service security guarantee method and system | |
| CN110176087A (en) | Method for being diagnosed in the car |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |