CN117877256A - Vehicle fault prediction method and system based on digital twin - Google Patents
Vehicle fault prediction method and system based on digital twin Download PDFInfo
- Publication number
- CN117877256A CN117877256A CN202410053838.0A CN202410053838A CN117877256A CN 117877256 A CN117877256 A CN 117877256A CN 202410053838 A CN202410053838 A CN 202410053838A CN 117877256 A CN117877256 A CN 117877256A
- Authority
- CN
- China
- Prior art keywords
- data
- target vehicle
- vehicle
- fault
- digital twin
- 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 36
- 238000012544 monitoring process Methods 0.000 claims abstract description 66
- 238000004458 analytical method Methods 0.000 claims abstract description 41
- 238000004891 communication Methods 0.000 claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 18
- 238000004140 cleaning Methods 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 11
- 238000004088 simulation Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000000446 fuel Substances 0.000 description 5
- 238000002347 injection Methods 0.000 description 5
- 239000007924 injection Substances 0.000 description 5
- 238000013528 artificial neural network Methods 0.000 description 2
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 239000001301 oxygen Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012423 maintenance Methods 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
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Landscapes
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
Abstract
The invention discloses a vehicle fault prediction method and system based on digital twin, which relate to the technical field of vehicle fault prediction, and the method comprises the following steps: constructing a sensor communication group; the N data sensors are used for carrying out sensing record on the operation data of the target vehicle, and an operation sensing data set is obtained; acquiring an operation environment parameter set of the target vehicle according to the historical operation control parameters of the target vehicle; carrying out digital twin analysis according to the running sensing data set and the running environment parameter set, and constructing a digital twin body of the target vehicle; the digital twin body is monitored in real time, fault prediction is carried out on the monitoring result, and a fault cause data set is generated; the operation analysis optimization is carried out on the target vehicle based on the fault cause data set, so that the problem of low fault judgment accuracy caused by insufficient rigor and insufficient completeness of vehicle fault prediction in the prior art is solved, and the reliability and safety of the final vehicle running are improved.
Description
Technical Field
The invention relates to the technical field of vehicle fault prediction, in particular to a digital twinning-based vehicle fault prediction method and system.
Background
The vehicle fault prediction refers to predicting possible faults in advance by analyzing the performance data of the vehicle, so that measures are taken in time to carry out maintenance, the faults are avoided, and the reliability and the safety of the vehicle are improved. With the continuous development of modern technology, digital twin technology is gradually penetrating into various fields, including vehicle fault prediction. The traditional vehicle fault prediction method is mainly based on the diagnosis of a vehicle by an engineer with rich experience, and is time-consuming and difficult to accurately diagnose for complex vehicle faults.
The problem of low fault judgment accuracy caused by insufficient rigor and insufficient completeness of vehicle fault prediction in the prior art can not improve the reliability and safety of vehicle running finally.
Disclosure of Invention
The invention provides a vehicle fault prediction method and a vehicle fault prediction system based on digital twinning, which solve the problem of low fault judgment accuracy caused by insufficient rigor and insufficient completeness of vehicle fault prediction in the prior art, so that the reliability and safety of the final vehicle running are improved.
In view of the above, the present application provides a digital twinning-based vehicle failure prediction method.
In a first aspect, the present application provides a digital twinning-based vehicle fault prediction method, the method comprising: constructing a sensor communication group, wherein the sensor communication group comprises N data sensors, and N is an integer greater than 1; performing sensing record on the operation data of the target vehicle through the N data sensors to obtain an operation sensing data set, wherein the operation sensing data set has a corresponding relation with the N data sensors; acquiring an operation environment parameter set of the target vehicle according to the historical operation control parameters of the target vehicle; carrying out digital twin analysis according to the running sensing data set and the running environment parameter set, and constructing a digital twin body of the target vehicle; the digital twin body is monitored in real time, fault prediction is carried out on the monitoring result, and a fault cause data set is generated; and carrying out operation analysis optimization on the target vehicle based on the fault cause data set, and improving the vehicle operation efficiency.
In a second aspect, the present application provides a digital twinning-based vehicle fault prediction system, the system comprising: the sensor communication module: constructing a sensor communication group, wherein the sensor communication group comprises N data sensors, and N is an integer greater than 1; and a sensing data module: performing sensing record on the operation data of the target vehicle through the N data sensors to obtain an operation sensing data set, wherein the operation sensing data set has a corresponding relation with the N data sensors; and an operation environment module: acquiring an operation environment parameter set of the target vehicle according to the historical operation control parameters of the target vehicle; digital twin module: carrying out digital twin analysis according to the running sensing data set and the running environment parameter set, and constructing a digital twin body of the target vehicle; and a fault prediction module: the digital twin body is monitored in real time, fault prediction is carried out on the monitoring result, and a fault cause data set is generated; and an analysis optimization module: and carrying out operation analysis optimization on the target vehicle based on the fault cause data set, and improving the vehicle operation efficiency.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the vehicle fault prediction method and system based on digital twinning, through constructing the sensor communication group comprising N data sensors, the N data sensors are used for carrying out sensing record on the running data of the target vehicle, the running sensing data set with the corresponding relation with the N data sensors is obtained, the digital twinning analysis is carried out according to the running sensing data set and the running environment parameter set, the digital twinning body of the target vehicle is constructed, the digital twinning body is monitored in real time, the fault prediction is carried out on the monitoring result, the fault cause data set is generated, finally, the running analysis optimization is carried out on the target vehicle, the running efficiency of the vehicle is improved, the problem that the fault judgment accuracy is low due to insufficient rigor and insufficient completeness of the vehicle fault prediction in the prior art is solved, the reliability and the safety of the vehicle running are improved finally, and the safety of the vehicle in the running process is guaranteed.
Drawings
FIG. 1 is a schematic flow chart of a vehicle fault prediction method based on digital twinning;
fig. 2 is a schematic structural diagram of a digital twin-based vehicle fault prediction system provided in the present application.
Reference numerals illustrate: the system comprises a sensor communication module 11, a sensing data module 12, an operating environment module 13, a digital twin module 14, a fault prediction module 15 and an analysis optimization module 16.
Detailed Description
According to the method and the system for predicting the vehicle faults based on the digital twinning, through constructing a sensor communication group comprising N data sensors, carrying out sensing record on operation data of a target vehicle through the N data sensors, acquiring an operation sensing data set with a corresponding relation with the N data sensors, carrying out digital twinning analysis according to the operation sensing data set and an operation environment parameter set, constructing a digital twinning body of the target vehicle, carrying out real-time monitoring on the digital twinning body, carrying out fault prediction on a monitoring result, generating a fault cause data set, and finally carrying out operation analysis optimization on the target vehicle, thereby improving the vehicle operation efficiency. The problem of the vehicle fault prediction that exists in the prior art is low in fault judgment accuracy due to insufficient rigor and insufficient completeness is solved, and finally reliability and safety of vehicle running are improved.
Example 1
As shown in fig. 1, the present application provides a digital twin-based vehicle fault prediction method and system, the method comprising:
constructing a sensor communication group, wherein the sensor communication group comprises N data sensors, and N is an integer greater than 1;
the sensor communication group is formed by commonly connecting a plurality of sensors, and the number of the sensors is not less than two, and the formed sensors are all arranged in various positions of the automobile, including but not limited to an air flow sensor: detecting the air inflow of the engine and controlling the oil injection quantity; intake pressure sensor: detecting the vacuum degree of an intake manifold, and judging the air inflow; throttle position sensor: detecting the opening of a throttle valve and controlling the fuel injection quantity in the acceleration process; camshaft position sensor: detecting the position of a cam shaft, judging the top dead center of the compression stroke of one cylinder, and controlling sequential fuel injection and ignition; crank position sensor: detecting the position of a crankshaft and the rotating speed of an engine, and controlling fuel injection and ignition; oxygen sensor: detecting the oxygen content in the tail gas, judging the richness of the mixed gas, and correcting the air-fuel ratio; a water temperature sensor: detecting the water temperature of the engine, and correcting the ignition time and the fuel injection quantity; knock sensor: whether the engine knocks or not is detected, ignition time is retarded, and knocking is eliminated. The sensor communication group is used for providing a data basis for the subsequent sensing record of the operation data of the target vehicle through N data sensors and obtaining an operation sensing data set.
Performing sensing record on the operation data of the target vehicle through the N data sensors to obtain an operation sensing data set, wherein the operation sensing data set has a corresponding relation with the N data sensors;
when the automobile is in the running process, various data generated in the running process of the automobile are acquired through the data sensor, and the acquired data are collated to obtain a running sensing data set. And (3) carrying out independent classification on the data obtained by different sensors, namely, the sensor data sets and the data sensors have corresponding relations. The acquisition of the operation sensing data set provides a data basis for the subsequent digital twin analysis according to the operation sensing data set and the operation environment parameter set to construct a digital twin body of the target vehicle.
Acquiring an operation environment parameter set of the target vehicle according to the historical operation control parameters of the target vehicle;
because the loss degree of the vehicle in different road conditions is different, and the displayed running sensing data sets have certain difference, when the running sensing data sets in different environments are subjected to fault analysis, the required judgment standard also needs to be modified correspondingly, such as a stable road and a bumpy mountain road, and the running of the vehicle in the latter environment can cause faults more easily, so that the different environments need to be subjected to corresponding analysis. The historical operation control parameters are obtained, data classification retrieval is carried out according to the historical operation control parameters, the operation environment is used as a retrieval classification standard, an operation environment parameter set of the target vehicle is obtained, and vehicle fault prediction of the target vehicle can be more accurate.
Carrying out digital twin analysis according to the running sensing data set and the running environment parameter set, and constructing a digital twin body of the target vehicle;
digital twins refer to digital models that model and simulate, monitor and optimize objects or systems in the physical world in a virtual space. And acquiring various parameters of the target vehicle through a production platform of the target vehicle, constructing a three-dimensional model of the target vehicle according to the various parameters, and generating a digital twin body of the target vehicle in a virtual space. And the digital twin body of the target vehicle is fused by a neural network, each item of data is analyzed by the neural network, faults are predicted in time, fault reasons are generated, corresponding inspection is performed in time, and the running efficiency of the vehicle is improved.
The digital twin body is monitored in real time, fault prediction is carried out on the monitoring result, and a fault cause data set is generated;
carrying out multidimensional sensing monitoring on the digital twin body according to the sensor communication group to generate a multidimensional monitoring result;
the multi-dimensional monitoring result comprises target vehicle performance data, target vehicle state data and target vehicle behavior data;
performing live analysis on a target vehicle based on the target vehicle performance data, the target vehicle state data and the target vehicle behavior data to generate live monitoring parameters;
the live monitoring parameters are added to the monitoring results.
Extracting live performance monitoring data, live state monitoring data and live behavior monitoring data based on the live monitoring parameters;
constructing a plurality of vehicle operation prediction trends according to the live performance monitoring data, the live state monitoring data and the live behavior monitoring data;
presetting an operation fault threshold according to historical operation fault parameters of a target vehicle;
comparing the plurality of vehicle operation prediction trends with the preset operation fault threshold value in sequence;
when the vehicle operation prediction trend in the plurality of vehicle operation prediction trends reaches a preset operation fault threshold, backtracking is carried out according to the vehicle operation prediction trend, and the fault cause data set is determined according to backtracking data.
Performing multidimensional sensing monitoring on the digital twin body according to the sensor communication group to generate a multidimensional monitoring result, wherein the multidimensional monitoring result comprises target vehicle performance data and target vehicle state data, namely running states in different running environments; target vehicle behavior data, i.e., the current driving direction of the target vehicle. And carrying out real-time condition analysis, namely live analysis, on the target vehicle based on the target vehicle performance data, the target vehicle state data and the target vehicle behavior data to generate live monitoring parameters. The live monitoring parameters are added to the monitoring results. Based on the live monitoring parameters, corresponding to the target vehicle performance data, the target vehicle state data and the target vehicle behavior data, the live performance monitoring data, the live state monitoring data and the live behavior monitoring data are extracted. And constructing a plurality of vehicle operation prediction trends according to the live performance monitoring data, the live state monitoring data and the live behavior monitoring data. And presetting an operation fault threshold according to the historical operation fault parameters of the target vehicle, and indicating that a fault occurs when the operation fault threshold is exceeded and further processing is needed. Comparing the plurality of vehicle operation prediction trends with a preset operation fault threshold value in sequence, tracing back according to the vehicle operation prediction trend when the vehicle operation prediction trend reaches the preset operation fault threshold value in the plurality of vehicle operation prediction trends, determining the cause of the fault according to the tracing back data, and outputting the cause to obtain a fault cause data set. By comprehensively analyzing the live performance monitoring data, the live state monitoring data and the live behavior monitoring data, the accuracy of judging the faults of the vehicle can be improved, and the accuracy of judging the faults is improved.
And carrying out operation analysis optimization on the target vehicle based on the fault cause data set, and improving the vehicle operation efficiency.
Calculating the correlation degree of the fault cause data set and a plurality of vehicle operation prediction trends, and generating a correlation coefficient;
performing weighted calculation on the fault cause data set to obtain a weight sequence;
and combining the correlation coefficient and the weight sequence to perform operation analysis optimization on the target vehicle.
And calculating the relativity of the fault cause data set and a plurality of vehicle operation prediction trends, namely judging the relation between each fault cause in the fault cause data set and the vehicle operation prediction trend, judging the trend of the vehicle operation prediction caused by a certain fault cause, establishing the causal relation between the fault cause and the vehicle operation trend, and generating a correlation coefficient. And the fault cause data set is weighted and calculated, a plurality of fault causes are arranged in the fault cause data set, the running prediction trend of the vehicles caused by different fault causes is different, and the degree of the light and heavy caused results is different, so that analysis weight analysis is needed, more weight values are distributed to the fault causes with heavy influence on the running of the vehicles, a weight sequence is obtained, and the running analysis of the target vehicles is updated and supplemented by combining the correlation coefficient and the weight sequence, so that the running analysis of the target vehicles is optimized, and the running safety of the vehicles is improved.
Further, the method further comprises:
respectively carrying out data cleaning on the operation sensing data set and the operation environment parameter set according to the data availability to generate a plurality of operation sensing cleaning data and a plurality of operation environment cleaning parameters;
adopting the operation sensing cleaning data and the operation environment cleaning parameters as training data to perform simulation training convergence and establish a plurality of initial digital twin subnetworks;
and fusing the plurality of initial digital twin subnetworks to determine a digital twin.
The various data of the constructed network need to be preprocessed before the digital twins are constructed in the digital twins sub-network. And respectively carrying out data cleaning on the operation sensing data set and the operation environment parameter set according to the availability of the data, removing unnecessary data to generate a plurality of operation sensing cleaning data and a plurality of operation environment cleaning parameters, carrying out simulation training convergence on the operation sensing cleaning data and the operation environment cleaning parameters serving as training data, carrying out convergence verification on the obtained result, continuing training until convergence is not carried out on the result, and obtaining a plurality of initial digital twin sub-networks, wherein one initial digital twin sub-network is formed by one operation sensing cleaning data and one operation environment cleaning parameter, merging the plurality of initial digital twin sub-networks to obtain a digital twin sub-network, and carrying out three-dimensional modeling on the digital twin sub-network to obtain the digital twin body. By preprocessing the training data, a large amount of invalid data can be reduced, and the efficiency of network training is further improved.
Further, the method further comprises:
randomly extracting operation sensing data in the operation sensing data set and recording the operation sensing data as first operation sensing data;
presetting a vehicle operation data interval according to a historical operation parameter extremum of a target vehicle;
judging whether the first operation sensing data is in the preset vehicle operation data interval or not;
if yes, the first operation sensing data is considered to be available, the first operation sensing data is reserved, and the first operation sensing data is transferred to the second operation sensing data for judgment;
if not, the first operation sensing data is regarded as not having availability, and the first operation sensing data is deleted in the operation sensing data set;
and judging whether the M-th operation sensing data is in the preset vehicle operation data interval or not according to the iteration, and generating the operation sensing cleaning data.
Randomly extracting operation sensing data in the operation sensing data set, recording the operation sensing data as first operation sensing data, and presetting a vehicle operation data interval according to a historical operation parameter extremum of a target vehicle; judging whether the first operation sensing data is in a preset vehicle operation data interval or not, if so, judging that the first operation sensing data has availability, reserving the first operation sensing data, and randomly extracting operation sensing data in the operation sensing data set as second operation sensing data for judgment; if not, judging that the first operation sensing data has no availability, and deleting the first operation sensing data in the operation sensing data set. And judging whether the second operation sensing data to the Mth operation sensing data are in a preset vehicle operation data interval or not according to the iteration, namely judging all items in the whole data set to generate a plurality of operation sensing cleaning data, and similarly, performing data cleaning on the operation environment parameter set to obtain a plurality of operation environment cleaning parameters so as to provide a data basis for subsequently constructing a digital twin body of the target vehicle.
Example two
Based on the same inventive concept as the digital twinning-based vehicle failure prediction method in the foregoing embodiment, as shown in fig. 2, the present application provides a digital twinning-based vehicle failure prediction system, which includes:
sensor communication module 11: the sensor communication module 11 is configured to construct a sensor communication group, where the sensor communication group includes N data sensors, and N is an integer greater than 1;
the sensing data module 12: the sensing data module 12 is configured to perform sensing recording on operation data of the target vehicle through the N data sensors, and obtain an operation sensing data set, where the operation sensing data set has a corresponding relationship with the N data sensors;
the operation environment module 13: the operation environment module 13 is configured to obtain an operation environment parameter set of the target vehicle according to the historical operation control parameters of the target vehicle;
digital twin module 14: the digital twin module 14 is configured to perform digital twin analysis according to the running sensing data set and the running environment parameter set, and construct a digital twin body of the target vehicle;
the failure prediction module 15: the fault prediction module 15 is configured to monitor the digital twin in real time, predict a fault of a monitoring result, and generate a fault cause data set;
analysis optimization module 16: the analysis optimization module 16 is configured to perform operation analysis optimization on the target vehicle based on the fault cause data set, so as to improve vehicle operation efficiency.
Further, the digital twinning module 14 comprises the following execution steps:
respectively carrying out data cleaning on the operation sensing data set and the operation environment parameter set according to the data availability to generate a plurality of operation sensing cleaning data and a plurality of operation environment cleaning parameters;
adopting the operation sensing cleaning data and the operation environment cleaning parameters as training data to perform simulation training convergence and establish a plurality of initial digital twin subnetworks;
and fusing the plurality of initial digital twin subnetworks to determine a digital twin.
Further, the digital twinning module 14 comprises the following execution steps:
randomly extracting operation sensing data in the operation sensing data set and recording the operation sensing data as first operation sensing data;
presetting a vehicle operation data interval according to a historical operation parameter extremum of a target vehicle;
judging whether the first operation sensing data is in the preset vehicle operation data interval or not;
if yes, the first operation sensing data is considered to be available, the first operation sensing data is reserved, and the first operation sensing data is transferred to the second operation sensing data for judgment;
if not, the first operation sensing data is regarded as not having availability, and the first operation sensing data is deleted in the operation sensing data set;
and judging whether the M-th operation sensing data is in the preset vehicle operation data interval or not according to the iteration, and generating the operation sensing cleaning data.
Further, the fault prediction module 15 includes the following steps:
carrying out multidimensional sensing monitoring on the digital twin body according to the sensor communication group to generate a multidimensional monitoring result;
the multi-dimensional monitoring result comprises target vehicle performance data, target vehicle state data and target vehicle behavior data;
performing live analysis on a target vehicle based on the target vehicle performance data, the target vehicle state data and the target vehicle behavior data to generate live monitoring parameters;
the live monitoring parameters are added to the monitoring results.
Further, the fault prediction module 15 includes the following steps:
extracting live performance monitoring data, live state monitoring data and live behavior monitoring data based on the live monitoring parameters;
constructing a plurality of vehicle operation prediction trends according to the live performance monitoring data, the live state monitoring data and the live behavior monitoring data;
presetting an operation fault threshold according to historical operation fault parameters of a target vehicle;
comparing the plurality of vehicle operation prediction trends with the preset operation fault threshold value in sequence;
when the vehicle operation prediction trend in the plurality of vehicle operation prediction trends reaches a preset operation fault threshold, backtracking is carried out according to the vehicle operation prediction trend, and the fault cause data set is determined according to backtracking data.
Further, the analysis optimization module 16 includes the following steps:
calculating the correlation degree of the fault cause data set and a plurality of vehicle operation prediction trends, and generating a correlation coefficient;
performing weighted calculation on the fault cause data set to obtain a weight sequence;
and combining the correlation coefficient and the weight sequence to perform operation analysis optimization on the target vehicle.
The foregoing detailed description of the method for predicting a vehicle fault based on digital twin will be clear to those skilled in the art, and the device disclosed in this embodiment is relatively simple to describe, and the relevant places refer to the method part for description.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A digital twinning-based vehicle fault prediction method, the method comprising:
constructing a sensor communication group, wherein the sensor communication group comprises N data sensors, and N is an integer greater than 1;
performing sensing record on the operation data of the target vehicle through the N data sensors to obtain an operation sensing data set, wherein the operation sensing data set has a corresponding relation with the N data sensors;
acquiring an operation environment parameter set of the target vehicle according to the historical operation control parameters of the target vehicle;
carrying out digital twin analysis according to the running sensing data set and the running environment parameter set, and constructing a digital twin body of the target vehicle;
the digital twin body is monitored in real time, fault prediction is carried out on the monitoring result, and a fault cause data set is generated;
and carrying out operation analysis optimization on the target vehicle based on the fault cause data set, and improving the vehicle operation efficiency.
2. The method of claim 1, wherein performing a digital twin analysis from the operational sensing dataset and the operational environment parameter set to construct a digital twin of the target vehicle, the method comprising:
respectively carrying out data cleaning on the operation sensing data set and the operation environment parameter set according to the data availability to generate a plurality of operation sensing cleaning data and a plurality of operation environment cleaning parameters;
adopting the operation sensing cleaning data and the operation environment cleaning parameters as training data to perform simulation training convergence and establish a plurality of initial digital twin subnetworks;
and fusing the plurality of initial digital twin subnetworks to determine a digital twin.
3. The method of claim 2, wherein the method comprises:
randomly extracting operation sensing data in the operation sensing data set and recording the operation sensing data as first operation sensing data;
presetting a vehicle operation data interval according to a historical operation parameter extremum of a target vehicle;
judging whether the first operation sensing data is in the preset vehicle operation data interval or not;
if yes, the first operation sensing data is considered to be available, the first operation sensing data is reserved, and the first operation sensing data is transferred to the second operation sensing data for judgment;
if not, the first operation sensing data is regarded as not having availability, and the first operation sensing data is deleted in the operation sensing data set;
and judging whether the M-th operation sensing data is in the preset vehicle operation data interval or not according to the iteration, and generating the operation sensing cleaning data.
4. The method of claim 1, wherein the digital twin is monitored in real time, the method comprising:
carrying out multidimensional sensing monitoring on the digital twin body according to the sensor communication group to generate a multidimensional monitoring result;
the multi-dimensional monitoring result comprises target vehicle performance data, target vehicle state data and target vehicle behavior data;
performing live analysis on a target vehicle based on the target vehicle performance data, the target vehicle state data and the target vehicle behavior data to generate live monitoring parameters;
the live monitoring parameters are added to the monitoring results.
5. The method of claim 4, wherein the monitoring results are subjected to fault prediction to generate a fault cause dataset, the method comprising:
extracting live performance monitoring data, live state monitoring data and live behavior monitoring data based on the live monitoring parameters;
constructing a plurality of vehicle operation prediction trends according to the live performance monitoring data, the live state monitoring data and the live behavior monitoring data;
presetting an operation fault threshold according to historical operation fault parameters of a target vehicle;
comparing the plurality of vehicle operation prediction trends with the preset operation fault threshold value in sequence;
when the vehicle operation prediction trend in the plurality of vehicle operation prediction trends reaches a preset operation fault threshold, backtracking is carried out according to the vehicle operation prediction trend, and the fault cause data set is determined according to backtracking data.
6. The method of claim 1, wherein the target vehicle is optimized for operational analysis based on the fault cause data set, the method comprising:
calculating the correlation degree of the fault cause data set and a plurality of vehicle operation prediction trends, and generating a correlation coefficient;
performing weighted calculation on the fault cause data set to obtain a weight sequence;
and combining the correlation coefficient and the weight sequence to perform operation analysis optimization on the target vehicle.
7. A digital twinning-based vehicle fault prediction system, the system comprising:
the sensor communication module: constructing a sensor communication group, wherein the sensor communication group comprises N data sensors, and N is an integer greater than 1;
and a sensing data module: performing sensing record on the operation data of the target vehicle through the N data sensors to obtain an operation sensing data set, wherein the operation sensing data set has a corresponding relation with the N data sensors;
and an operation environment module: acquiring an operation environment parameter set of the target vehicle according to the historical operation control parameters of the target vehicle;
digital twin module: carrying out digital twin analysis according to the running sensing data set and the running environment parameter set, and constructing a digital twin body of the target vehicle;
and a fault prediction module: the digital twin body is monitored in real time, fault prediction is carried out on the monitoring result, and a fault cause data set is generated;
and an analysis optimization module: and carrying out operation analysis optimization on the target vehicle based on the fault cause data set, and improving the vehicle operation efficiency.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2023114827112 | 2023-11-09 | ||
| CN202311482711 | 2023-11-09 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117877256A true CN117877256A (en) | 2024-04-12 |
Family
ID=90576964
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410053838.0A Pending CN117877256A (en) | 2023-11-09 | 2024-01-15 | Vehicle fault prediction method and system based on digital twin |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117877256A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118167790A (en) * | 2024-05-15 | 2024-06-11 | 摩多利智能传动(江苏)有限公司 | Monitoring protection method and system for speed reducer |
-
2024
- 2024-01-15 CN CN202410053838.0A patent/CN117877256A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118167790A (en) * | 2024-05-15 | 2024-06-11 | 摩多利智能传动(江苏)有限公司 | Monitoring protection method and system for speed reducer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110954312B (en) | Reciprocating mechanical fault diagnosis method based on keyless phase whole-cycle signal | |
| CN109581871B (en) | Industrial control system intrusion detection method of immune countermeasure sample | |
| US10922906B2 (en) | Monitoring and diagnosing vehicle system problems using machine learning classifiers | |
| CN117877256A (en) | Vehicle fault prediction method and system based on digital twin | |
| Wang et al. | Research on the fault monitoring method of marine diesel engines based on the manifold learning and isolation forest | |
| CN105814583B (en) | Method for monitoring component operation | |
| CN110826772A (en) | Vehicle exhaust emission prediction method, device, equipment and storage medium | |
| CN112528519A (en) | Method, system, readable medium and electronic device for engine quality early warning service | |
| CN103969052B (en) | Diagnosis Method of Diesel Fault based on Outlier Analysis | |
| CN114856811B (en) | Diesel engine air system health assessment method | |
| CN115510926B (en) | Cross-machine type diesel engine combustion chamber fault diagnosis method and system | |
| CN114925536A (en) | Airborne system PHM testability modeling and diagnosis strategy optimization method and device | |
| CN114372489A (en) | Diesel engine working condition identification and abnormity diagnosis method | |
| CN112267949A (en) | Fault-tolerant control method and control system for atmospheric pressure sensor of diesel engine | |
| CN115586009A (en) | Fault diagnosis and health management system and method | |
| Devasenapati et al. | Hybrid fuzzy model based expert system for misfire detection in automobile engines | |
| CN112487709B (en) | Marine diesel engine fault tracing method based on sensitivity analysis | |
| CN114962031B (en) | Method and system for detecting coking of pipeline of air inlet system of internal combustion engine and vehicle | |
| CN115615696A (en) | Diesel engine gear chamber fault diagnosis method based on sound vibration information fusion | |
| KR102300965B1 (en) | Misfire diagnosis method and device of Multi cylinder four-stroke engine | |
| CN113283516A (en) | Multi-sensor data fusion method based on reinforcement learning and D-S evidence theory | |
| CN115467752A (en) | Method, system and computer storage medium for diagnosing and analyzing fire of automobile engine | |
| Canal et al. | Torque Regression Using Machine Learning Techniques in Automotive ECUs | |
| US11721141B2 (en) | Method of AI-based vehicle diagnosis using CAN data and device thereof | |
| US10983029B2 (en) | Engine misfire detection |
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 |