CN118170125B - Mobile device for diagnosing new energy automobile faults based on embedded AI and diagnosis method - Google Patents
Mobile device for diagnosing new energy automobile faults based on embedded AI and diagnosis method Download PDFInfo
- Publication number
- CN118170125B CN118170125B CN202410594649.4A CN202410594649A CN118170125B CN 118170125 B CN118170125 B CN 118170125B CN 202410594649 A CN202410594649 A CN 202410594649A CN 118170125 B CN118170125 B CN 118170125B
- Authority
- CN
- China
- Prior art keywords
- embedded
- diagnosis
- diagnostic device
- diagnostic
- fault
- 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.)
- Active
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 182
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 9
- 238000012790 confirmation Methods 0.000 claims description 22
- 238000004891 communication Methods 0.000 claims description 18
- 239000013598 vector Substances 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000013480 data collection Methods 0.000 claims 1
- 238000007726 management method Methods 0.000 abstract description 40
- 238000013500 data storage Methods 0.000 abstract 1
- 238000012423 maintenance Methods 0.000 description 8
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012706 support-vector machine Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000003449 preventive effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012549 training 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
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0262—Confirmation of fault detection, e.g. extra checks to confirm that a failure has indeed occurred
-
- 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 the field of data processing, and discloses a mobile device and a diagnosis method for diagnosing faults of a new energy automobile based on an embedded AI, wherein the mobile device comprises an embedded AI diagnosis device management module, a cloud data server and a cloud data storage module, wherein the embedded AI diagnosis device management module obtains available embedded AI diagnosis device information according to embedded AI diagnosis device state data acquired by an embedded AI diagnosis device state data acquisition device, and a mobile diagnosis operation data container is generated according to positioning information of the embedded AI diagnosis device management module; the mobile diagnosis operation data container generates a planned path according to the returned information of the embedded AI diagnostic device, the embedded AI diagnostic device reaches the vehicle according to the planned path, and the embedded AI diagnostic device performs fault diagnosis on the vehicle according to the order information. The invention can realize rapid arrival to the site for fault diagnosis and improve the efficiency and accuracy of fault diagnosis.
Description
Technical Field
The invention relates to the field of data processing, in particular to a mobile device and a diagnosis method for diagnosing faults of a new energy automobile based on an embedded AI.
Background
Along with the progress of science and technology and the improvement of environmental awareness, new energy automobiles are gradually and widely popularized and applied in the global scope. However, the complexity and high integration of new energy automobiles also present challenges for fault diagnosis. Conventional fault diagnosis methods often rely on stationary diagnostic equipment and professionals, which have been plagued by elbows in the fault diagnosis of new energy vehicles. Therefore, the development of the portable, efficient and intelligent new energy automobile fault diagnosis device and method becomes an important direction of current technical development.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a mobile diagnosis method for diagnosing faults of a new energy automobile based on an embedded AI, which comprises the following steps:
Step one, an embedded AI diagnostic device management module obtains available embedded AI diagnostic device information according to the embedded AI diagnostic device state data acquired by an embedded AI diagnostic device state data acquisition device, and a cloud data server generates a mobile diagnosis operation data container according to the embedded AI diagnostic device management module positioning information;
Step two, the embedded AI diagnostic device management module sends the information of the available embedded AI diagnostic devices to a mobile diagnosis operation data container, the mobile diagnosis operation data container is in communication connection with the available embedded AI diagnostic devices, an available embedded AI diagnostic device list is generated according to the information of the available embedded AI diagnostic devices, and the generated available embedded AI diagnostic device list is sent to a cloud data server;
Thirdly, the cloud data server generates an embedded AI diagnostic device operation list corresponding to the type of the embedded AI diagnostic device according to the information of the available embedded AI diagnostic devices in each available embedded AI diagnostic device list;
Step four, the client module generates a fault diagnosis order and sends the fault diagnosis order to the order management module; the order management module is matched with an embedded AI diagnostic device operation list corresponding to the type of the embedded AI diagnostic device according to the mobile diagnostic requirement information in the fault diagnostic order, and the mobile diagnostic operation data container obtains a candidate embedded AI diagnostic device operation list according to the vehicle position information in the fault diagnostic order and the matched embedded AI diagnostic device operation list;
step five, obtaining predicted fault diagnosis waiting time according to the running states of all the embedded AI diagnostic devices in the candidate embedded AI diagnostic device running list and the distances between all the embedded AI diagnostic devices and the vehicle, generating an embedded AI diagnostic device recommendation list according to the predicted fault diagnosis waiting time of the vehicle, and sending the recommendation list to the client module;
Step six, according to the embedded AI diagnostic device confirmation information returned by the client, the order management module returns fault diagnostic device information in the embedded AI diagnostic device confirmation information, the cloud data server sends the order information to a corresponding mobile diagnosis operation data container, and the mobile diagnosis operation data container updates the order in a corresponding embedded AI diagnostic device operation task list and sends the order to a corresponding embedded AI diagnostic device; meanwhile, the mobile diagnosis operation data container generates a planned path according to the returned information of the embedded AI diagnostic device, the embedded AI diagnostic device reaches the vehicle according to the planned path, and the embedded AI diagnostic device performs fault diagnosis on the vehicle according to the order information;
And step seven, the embedded AI diagnostic device matches the fault resolution strategy corresponding to the fault data in a fault resolution strategy database in the cloud data server according to the obtained fault data, and performs fault removal on the vehicle according to the fault resolution strategy corresponding to the fault data.
Further, the embedded AI diagnosis device management module obtains usable information of the embedded AI diagnosis device according to the status data of the embedded AI diagnosis device collected by the status data collecting device of the embedded AI diagnosis device, and the method comprises the following steps:
And comparing the state data of the embedded AI diagnostic device acquired by the state data acquisition device of the embedded AI diagnostic device with the standard state data of the embedded AI diagnostic device, if the data difference value is within a set deviation range, the embedded AI diagnostic device is available, and otherwise, the embedded AI diagnostic device is unavailable.
Further, the list of available embedded AI diagnostic devices includes the type of the embedded AI diagnostic device and the basic information of the embedded AI diagnostic device.
Further, the cloud data server generates an embedded AI diagnosis device operation list of different types according to the information of the available embedded AI diagnosis devices in each available embedded AI diagnosis device list, including:
The method comprises the steps of acquiring type information of available embedded AI diagnostic devices in a list of available embedded AI diagnostic devices, and generating an embedded AI diagnostic device operation list corresponding to the types of the embedded AI diagnostic devices according to the embedded AI diagnostic device information of the available embedded AI diagnostic devices of the same type.
Further, the mobile diagnosis operation data container obtains a candidate embedded AI diagnosis device operation list according to the vehicle position information in the fault diagnosis order and the matched embedded AI diagnosis device operation list, and the mobile diagnosis operation data container comprises:
The mobile diagnosis operation data container obtains the remaining travelable distance according to the remaining electric quantity of the embedded AI diagnostic device and the historical unit power consumption, and the distance of each embedded AI diagnostic device in the operation list of the embedded AI diagnostic device matched according to the vehicle distance is not greater than the embedded AI diagnostic device of the remaining travelable distance, namely the candidate embedded AI diagnostic device, and all the candidate embedded AI diagnostic devices form the operation list of the candidate embedded AI diagnostic device.
Further, the obtaining the estimated fault diagnosis waiting time according to the running state of each embedded AI diagnosis device in the candidate embedded AI diagnosis device running list and the distance between each embedded AI diagnosis device and the vehicle, and generating the recommendation list of the embedded AI diagnosis device according to the estimated fault diagnosis waiting time of the vehicle includes:
The running state of the embedded AI diagnostic device comprises the number of orders in an embedded AI diagnostic device running task list of the embedded AI diagnostic device, the expected fault diagnosis time length is obtained according to the number of orders, the expected running time length is obtained according to the distance between the embedded AI diagnostic device and a vehicle, the difference value between the expected fault diagnosis time length and the expected running time length is the expected waiting time length, and the recommendation list of the embedded AI diagnostic device is generated according to the size of the expected waiting time length.
Further, the order management module returns fault diagnosis device information in the embedded AI diagnosis device confirmation information according to the embedded AI diagnosis device confirmation information returned by the client, including:
if the client receives and returns the confirmation information of the embedded AI diagnostic device within the set time length, the order management module sends the order information to a mobile diagnosis operation data container corresponding to the embedded AI diagnostic device according to the embedded AI diagnostic device information in the confirmation information of the embedded AI diagnostic device;
If the client does not receive the confirmation information of the embedded AI diagnostic device within the set time period, the embedded AI diagnostic device information of the first embedded AI diagnostic device in the recommendation list of the embedded AI diagnostic device is returned to the order management module, and the order management module sends the order information to a mobile diagnosis operation data container corresponding to the embedded AI diagnostic device according to the embedded AI diagnostic device information of the first embedded AI diagnostic device.
The mobile device for diagnosing the new energy automobile fault based on the embedded AI comprises a cloud data server, an embedded AI diagnosis device management module, an embedded AI diagnosis device and an order management module;
The cloud data server, the embedded AI diagnostic device management module and the embedded AI diagnostic device are connected in sequence; the order management module is in communication connection with the cloud data server.
Preferably, the embedded AI diagnosis device comprises an embedded AI diagnosis device state data acquisition device, an AI fault diagnosis data module, a communication module and a data processing module;
The embedded AI diagnostic device state data acquisition device, the AI fault diagnosis data module and the communication module are respectively connected with the data processing module; the communication module is connected with the embedded AI diagnostic device management module;
The AI fault diagnosis data module is used for cleaning, denoising and normalizing the operation data of each part of the new energy automobile, which are acquired in real time by the state data acquisition device of the embedded AI diagnosis device, so as to obtain preprocessed data;
Performing feature extraction on the preprocessed data through an embedded AI chip in the AI fault diagnosis data module to form a feature vector; classifying and identifying the feature vectors based on a trained new energy fault AI diagnosis model, and determining the fault type and position;
And displaying the diagnosis result and the fault information to a user through a display screen, and sending the diagnosis result to a remote server or a maintenance person by a user communication module.
The beneficial effects of the invention are as follows: the technical scheme provided by the invention can realize rapid on-site fault diagnosis and improve the efficiency and accuracy of fault diagnosis. Meanwhile, the device also has comprehensive fault diagnosis capability, can cover various fault types of the new energy automobile, and ensures the comprehensiveness and accuracy of fault diagnosis.
Drawings
FIG. 1 is a flow chart of a mobile diagnosis method for diagnosing a new energy automobile fault based on an embedded AI;
fig. 2 is a schematic diagram of a mobile device for diagnosing a fault of a new energy automobile based on an embedded AI.
Detailed Description
The technical solution of the present invention will be described in further detail with reference to the accompanying drawings, but the scope of the present invention is not limited to the following description.
The features and capabilities of the present invention are described in further detail below in connection with the examples.
As shown in fig. 1, the mobile diagnosis method for diagnosing a new energy automobile fault based on an embedded AI includes the following steps:
Step one, an embedded AI diagnostic device management module obtains available embedded AI diagnostic device information according to the embedded AI diagnostic device state data acquired by an embedded AI diagnostic device state data acquisition device, and a cloud data server generates a mobile diagnosis operation data container according to the embedded AI diagnostic device management module positioning information;
Step two, the embedded AI diagnostic device management module sends the information of the available embedded AI diagnostic devices to a mobile diagnosis operation data container, the mobile diagnosis operation data container is in communication connection with the available embedded AI diagnostic devices, an available embedded AI diagnostic device list is generated according to the information of the available embedded AI diagnostic devices, and the generated available embedded AI diagnostic device list is sent to a cloud data server;
Thirdly, the cloud data server generates an embedded AI diagnostic device operation list corresponding to the type of the embedded AI diagnostic device according to the information of the available embedded AI diagnostic devices in each available embedded AI diagnostic device list;
Step four, the client module generates a fault diagnosis order and sends the fault diagnosis order to the order management module; the order management module is matched with an embedded AI diagnostic device operation list corresponding to the type of the embedded AI diagnostic device according to the mobile diagnostic requirement information in the fault diagnostic order, and the mobile diagnostic operation data container obtains a candidate embedded AI diagnostic device operation list according to the vehicle position information in the fault diagnostic order and the matched embedded AI diagnostic device operation list;
step five, obtaining predicted fault diagnosis waiting time according to the running states of all the embedded AI diagnostic devices in the candidate embedded AI diagnostic device running list and the distances between all the embedded AI diagnostic devices and the vehicle, generating an embedded AI diagnostic device recommendation list according to the predicted fault diagnosis waiting time of the vehicle, and sending the recommendation list to the client module;
Step six, according to the embedded AI diagnostic device confirmation information returned by the client, the order management module returns fault diagnostic device information in the embedded AI diagnostic device confirmation information, the cloud data server sends the order information to a corresponding mobile diagnosis operation data container, and the mobile diagnosis operation data container updates the order in a corresponding embedded AI diagnostic device operation task list and sends the order to a corresponding embedded AI diagnostic device; meanwhile, the mobile diagnosis operation data container generates a planned path according to the returned information of the embedded AI diagnostic device, the embedded AI diagnostic device reaches the vehicle according to the planned path, and the embedded AI diagnostic device performs fault diagnosis on the vehicle according to the order information;
And step seven, the embedded AI diagnostic device matches the fault resolution strategy corresponding to the fault data in a fault resolution strategy database in the cloud data server according to the obtained fault data, and performs fault removal on the vehicle according to the fault resolution strategy corresponding to the fault data.
The embedded AI diagnostic device management module obtains the information of the available embedded AI diagnostic device according to the status data of the embedded AI diagnostic device collected by the status data collecting device of the embedded AI diagnostic device, and comprises the following steps:
And comparing the state data of the embedded AI diagnostic device acquired by the state data acquisition device of the embedded AI diagnostic device with the standard state data of the embedded AI diagnostic device, if the data difference value is within a set deviation range, the embedded AI diagnostic device is available, and otherwise, the embedded AI diagnostic device is unavailable.
The list of available embedded AI diagnostic devices includes the type of the embedded AI diagnostic device and the basic information of the embedded AI diagnostic device.
The cloud data server generates an embedded AI diagnostic device operation list of different types according to the information of the available embedded AI diagnostic devices in each available embedded AI diagnostic device list, and the cloud data server comprises:
The method comprises the steps of acquiring type information of available embedded AI diagnostic devices in a list of available embedded AI diagnostic devices, and generating an embedded AI diagnostic device operation list corresponding to the types of the embedded AI diagnostic devices according to the embedded AI diagnostic device information of the available embedded AI diagnostic devices of the same type.
The mobile diagnosis operation data container obtains a candidate embedded AI diagnosis device operation list according to the vehicle position information in the fault diagnosis order and the matched embedded AI diagnosis device operation list, and comprises the following steps:
The mobile diagnosis operation data container obtains the remaining travelable distance according to the remaining electric quantity of the embedded AI diagnostic device and the historical unit power consumption, and the distance of each embedded AI diagnostic device in the operation list of the embedded AI diagnostic device matched according to the vehicle distance is not greater than the embedded AI diagnostic device of the remaining travelable distance, namely the candidate embedded AI diagnostic device, and all the candidate embedded AI diagnostic devices form the operation list of the candidate embedded AI diagnostic device.
The method for obtaining the estimated fault diagnosis waiting time according to the running states of the embedded AI diagnostic devices in the candidate embedded AI diagnostic device running list and the distance between the embedded AI diagnostic devices and the vehicle, and generating an embedded AI diagnostic device recommendation list according to the estimated fault diagnosis waiting time of the vehicle comprises the following steps:
The running state of the embedded AI diagnostic device comprises the number of orders in an embedded AI diagnostic device running task list of the embedded AI diagnostic device, the expected fault diagnosis time length is obtained according to the number of orders, the expected running time length is obtained according to the distance between the embedded AI diagnostic device and a vehicle, the difference value between the expected fault diagnosis time length and the expected running time length is the expected waiting time length, and the recommendation list of the embedded AI diagnostic device is generated according to the size of the expected waiting time length.
The order management module returns fault diagnosis device information in the embedded AI diagnosis device confirmation information according to the embedded AI diagnosis device confirmation information returned by the client, and the order management module comprises:
if the client receives and returns the confirmation information of the embedded AI diagnostic device within the set time length, the order management module sends the order information to a mobile diagnosis operation data container corresponding to the embedded AI diagnostic device according to the embedded AI diagnostic device information in the confirmation information of the embedded AI diagnostic device;
If the client does not receive the confirmation information of the embedded AI diagnostic device within the set time period, the embedded AI diagnostic device information of the first embedded AI diagnostic device in the recommendation list of the embedded AI diagnostic device is returned to the order management module, and the order management module sends the order information to a mobile diagnosis operation data container corresponding to the embedded AI diagnostic device according to the embedded AI diagnostic device information of the first embedded AI diagnostic device.
As shown in fig. 2, the mobile device for diagnosing the new energy automobile fault based on the embedded AI applies the mobile diagnosis method for diagnosing the new energy automobile fault based on the embedded AI, and the mobile device comprises a cloud data server, an embedded AI diagnosis device management module, an embedded AI diagnosis device and an order management module;
The cloud data server, the embedded AI diagnostic device management module and the embedded AI diagnostic device are connected in sequence; the order management module is in communication connection with the cloud data server.
The embedded AI diagnostic device comprises an embedded AI diagnostic device state data acquisition device, an AI fault diagnosis data module, a communication module and a data processing module;
The embedded AI diagnostic device state data acquisition device, the AI fault diagnosis data module and the communication module are respectively connected with the data processing module; the communication module is connected with the embedded AI diagnostic device management module;
The AI fault diagnosis data module is used for cleaning, denoising and normalizing the operation data of each part of the new energy automobile, which are acquired in real time by the state data acquisition device of the embedded AI diagnosis device, so as to obtain preprocessed data;
Performing feature extraction on the preprocessed data through an embedded AI chip in the AI fault diagnosis data module to form a feature vector; classifying and identifying the feature vectors based on a trained new energy fault AI diagnosis model, and determining the fault type and position;
And displaying the diagnosis result and the fault information to a user through a display screen, and sending the diagnosis result to a remote server or a maintenance person by a user communication module.
Specifically, first, the embedded AI diagnostic device collects state data of the device itself, such as electric quantity, temperature, running state, etc., in real time through its built-in state data collecting device. The embedded AI diagnostic device management module may receive these data and compare them to standard state data to determine which devices are available. The information of these available devices is then sent to a cloud data server for subsequent use.
The cloud data server generates an available embedded AI diagnostic device list according to the received information of the available embedded AI diagnostic devices. The list contains the types of the devices, basic information and the like, and is convenient for subsequent matching according to requirements.
The cloud data server further processes the list of available embedded AI diagnostic devices and generates a running list of different types of embedded AI diagnostic devices according to the type information of the devices. This has the advantage that a suitable diagnostic device can be matched to the type of fault more quickly.
Based on the neural network failure prediction model, a neural network structure in deep learning, in particular a Convolutional Neural Network (CNN) or a cyclic neural network (RNN), is employed for processing the time series data collected from the vehicle sensors. Through training, the model can learn the mode difference between the normal running state and the abnormal state of the vehicle, so that the potential faults are predicted. The accuracy of the model can reach more than 90%, early warning is provided before the fault occurs, and the risk of unexpected parking is reduced.
Based on the decision tree or the support vector machine fault diagnosis model, after the fault prediction model gives out a warning, the fault diagnosis model further analyzes the data to determine the specific fault type. The model may employ conventional machine learning algorithms, such as decision trees or Support Vector Machines (SVMs), which perform well in dealing with classification problems. By comparing the data characteristics of the normal state and the abnormal state, the model can accurately identify the fault part, and provide clear guidance for maintenance personnel.
The proposed model is maintained based on a clustering algorithm that groups and analyzes historical maintenance data of the vehicle using a clustering algorithm, such as K-means or DBSCAN. By identifying different maintenance modes, the model can provide personalized maintenance suggestions for each vehicle, and the service life of the vehicle is prolonged. This not only reduces maintenance costs, but also improves reliability and stability of the vehicle. The vehicle-mounted sensors are utilized to collect running data of the vehicle in real time, including temperature, pressure, current and the like. The data is cleaned, normalized and feature extracted for use by the AI model. The AI model is trained using a large amount of historical data, enabling it to accurately identify various failure modes. And (3) regularly optimizing and updating the model to adapt to the changes of the new energy automobile technology and the fault mode. The trained AI model is embedded into an embedded AI diagnostic device. The device processes the data of the vehicle-mounted sensor in real time, and performs fault prediction and diagnosis through an AI model. And sending the diagnosis result to the cloud server and the user terminal through wireless communication. And providing maintenance and preventive measures for the user according to the diagnosis result.
After the client module generates a fault diagnosis order and sends the fault diagnosis order to the order management module, the order management module can be matched with a corresponding embedded AI diagnosis device operation list according to the mobile diagnosis requirement information in the order. Meanwhile, a candidate embedded AI diagnostic device operation list is screened out according to the vehicle position information and the matched device list.
After screening candidate devices, the system estimates an estimated fault diagnosis waiting period according to the running state of each device and the distance from the vehicle. Then, a recommendation list of the embedded AI diagnostic apparatus is generated according to the waiting time length and sent to the client module for selection by the user.
After receiving the recommendation list, the client selects and confirms an appropriate embedded AI diagnosis apparatus. After receiving the confirmation information, the order management module sends the order information to a corresponding mobile diagnosis operation data container, updates the order information in a corresponding embedded AI diagnosis device operation task list and sends the order information to the corresponding embedded AI diagnosis device. Meanwhile, the system can generate a planning path to guide the embedded AI diagnostic device to quickly reach the vehicle position for fault diagnosis.
After arriving at the vehicle, the embedded AI diagnosis device performs detailed fault diagnosis on the vehicle according to the order information. After diagnosis is completed, the device matches the corresponding fault resolution strategy in the fault resolution strategy database of the cloud data server according to the obtained fault data, and performs fault removal on the vehicle according to the strategy.
The foregoing is merely a preferred embodiment of the invention, and it is to be understood that the invention is not limited to the form disclosed herein but is not to be construed as excluding other embodiments, but is capable of numerous other combinations, modifications and environments and is capable of modifications within the scope of the inventive concept, either as taught or as a matter of routine skill or knowledge in the relevant art. And that modifications and variations which do not depart from the spirit and scope of the invention are intended to be within the scope of the appended claims.
Claims (9)
1. The mobile diagnosis method for diagnosing the faults of the new energy automobile based on the embedded AI is characterized by comprising the following steps:
Step one, an embedded AI diagnostic device management module obtains available embedded AI diagnostic device information according to the embedded AI diagnostic device state data acquired by an embedded AI diagnostic device state data acquisition device, and a cloud data server generates a mobile diagnosis operation data container according to the embedded AI diagnostic device management module positioning information;
Step two, the embedded AI diagnostic device management module sends the information of the available embedded AI diagnostic devices to a mobile diagnosis operation data container, the mobile diagnosis operation data container is in communication connection with the available embedded AI diagnostic devices, an available embedded AI diagnostic device list is generated according to the information of the available embedded AI diagnostic devices, and the generated available embedded AI diagnostic device list is sent to a cloud data server;
Thirdly, the cloud data server generates an embedded AI diagnostic device operation list corresponding to the type of the embedded AI diagnostic device according to the information of the available embedded AI diagnostic devices in each available embedded AI diagnostic device list;
Step four, the client module generates a fault diagnosis order and sends the fault diagnosis order to the order management module; the order management module is matched with an embedded AI diagnostic device operation list corresponding to the type of the embedded AI diagnostic device according to the mobile diagnostic requirement information in the fault diagnostic order, and the mobile diagnostic operation data container obtains a candidate embedded AI diagnostic device operation list according to the vehicle position information in the fault diagnostic order and the matched embedded AI diagnostic device operation list;
step five, obtaining predicted fault diagnosis waiting time according to the running states of all the embedded AI diagnostic devices in the candidate embedded AI diagnostic device running list and the distances between all the embedded AI diagnostic devices and the vehicle, generating an embedded AI diagnostic device recommendation list according to the predicted fault diagnosis waiting time of the vehicle, and sending the recommendation list to the client module;
Step six, according to the embedded AI diagnostic device confirmation information returned by the client, the order management module returns fault diagnostic device information in the embedded AI diagnostic device confirmation information, the cloud data server sends the order information to a corresponding mobile diagnosis operation data container, and the mobile diagnosis operation data container updates the order in a corresponding embedded AI diagnostic device operation task list and sends the order to a corresponding embedded AI diagnostic device; meanwhile, the mobile diagnosis operation data container generates a planned path according to the returned information of the embedded AI diagnostic device, the embedded AI diagnostic device reaches the vehicle according to the planned path, and the embedded AI diagnostic device performs fault diagnosis on the vehicle according to the order information to obtain fault data;
And step seven, the embedded AI diagnostic device matches the fault resolution strategy corresponding to the fault data in a fault resolution strategy database in the cloud data server according to the obtained fault data, and performs fault removal on the vehicle according to the fault resolution strategy corresponding to the fault data.
2. The mobile diagnosis method for diagnosing a new energy automobile fault based on an embedded AI of claim 1, wherein the embedded AI diagnosis device management module obtains available embedded AI diagnosis device information according to the embedded AI diagnosis device status data collected by the embedded AI diagnosis device status data collection device, comprising:
And comparing the state data of the embedded AI diagnostic device acquired by the state data acquisition device of the embedded AI diagnostic device with the standard state data of the embedded AI diagnostic device, if the data difference value is within a set deviation range, the embedded AI diagnostic device is available, and otherwise, the embedded AI diagnostic device is unavailable.
3. The mobile diagnosis method for diagnosing new energy automobile faults based on embedded AI of claim 1, wherein the list of available embedded AI diagnosis devices comprises embedded AI diagnosis device types and embedded AI diagnosis device basic information.
4. The mobile diagnosis method for diagnosing a new energy automobile fault based on an embedded AI of claim 3, wherein the cloud data server generates a running list of embedded AI diagnosis devices of different types according to the information of the available embedded AI diagnosis devices in each available embedded AI diagnosis device list, comprising:
The method comprises the steps of acquiring type information of available embedded AI diagnostic devices in a list of available embedded AI diagnostic devices, and generating an embedded AI diagnostic device operation list corresponding to the types of the embedded AI diagnostic devices according to the embedded AI diagnostic device information of the available embedded AI diagnostic devices of the same type.
5. The mobile diagnosis method for diagnosing a new energy automobile fault based on the embedded AI of claim 4, wherein the mobile diagnosis operation data container obtains a candidate embedded AI diagnosis device operation list according to the vehicle position information in the fault diagnosis order and the matched embedded AI diagnosis device operation list, comprising:
The mobile diagnosis operation data container obtains the remaining travelable distance according to the remaining electric quantity of the embedded AI diagnostic device and the historical unit power consumption, and the distance of each embedded AI diagnostic device in the operation list of the embedded AI diagnostic device matched according to the vehicle distance is not greater than the embedded AI diagnostic device of the remaining travelable distance, namely the candidate embedded AI diagnostic device, and all the candidate embedded AI diagnostic devices form the operation list of the candidate embedded AI diagnostic device.
6. The mobile diagnosis method for diagnosing a new energy vehicle fault based on the embedded AI of claim 5, wherein the obtaining the estimated fault diagnosis waiting time based on the operation states of each embedded AI diagnosis device in the candidate embedded AI diagnosis device operation list and the distances between each embedded AI diagnosis device and the vehicle, and generating the recommendation list of the embedded AI diagnosis devices based on the estimated fault diagnosis waiting time of the vehicle, comprises:
The running state of the embedded AI diagnostic device comprises the number of orders in an embedded AI diagnostic device running task list of the embedded AI diagnostic device, the expected fault diagnosis time length is obtained according to the number of orders, the expected running time length is obtained according to the distance between the embedded AI diagnostic device and a vehicle, the difference value between the expected fault diagnosis time length and the expected running time length is the expected waiting time length, and the recommendation list of the embedded AI diagnostic device is generated according to the size of the expected waiting time length.
7. The mobile diagnosis method for diagnosing a fault of a new energy automobile based on an embedded AI according to claim 1, wherein the order management module returns the fault diagnosis device information in the embedded AI diagnosis device confirmation information according to the embedded AI diagnosis device confirmation information returned by the client, comprising:
if the client receives and returns the confirmation information of the embedded AI diagnostic device within the set time length, the order management module sends the order information to a mobile diagnosis operation data container corresponding to the embedded AI diagnostic device according to the embedded AI diagnostic device information in the confirmation information of the embedded AI diagnostic device;
If the client does not receive the confirmation information of the embedded AI diagnostic device within the set time period, the embedded AI diagnostic device information of the first embedded AI diagnostic device in the recommendation list of the embedded AI diagnostic device is returned to the order management module, and the order management module sends the order information to a mobile diagnosis operation data container corresponding to the embedded AI diagnostic device according to the embedded AI diagnostic device information of the first embedded AI diagnostic device.
8. The mobile device for diagnosing the new energy automobile fault based on the embedded AI is characterized by comprising a cloud data server, an embedded AI diagnosis device management module, an embedded AI diagnosis device and an order management module, wherein the mobile diagnosis method for diagnosing the new energy automobile fault based on the embedded AI is applied to any one of claims 1-7;
The cloud data server, the embedded AI diagnostic device management module and the embedded AI diagnostic device are connected in sequence; the order management module is in communication connection with the cloud data server.
9. The mobile device for diagnosing a new energy automobile fault based on the embedded AI of claim 8, wherein the embedded AI diagnostic device comprises an embedded AI diagnostic device status data acquisition device, an AI fault diagnostic data module, a communication module and a data processing module;
The embedded AI diagnostic device state data acquisition device, the AI fault diagnosis data module and the communication module are respectively connected with the data processing module; the communication module is connected with the embedded AI diagnostic device management module;
The AI fault diagnosis data module is used for cleaning, denoising and normalizing the operation data of each part of the new energy automobile, which are acquired in real time by the state data acquisition device of the embedded AI diagnosis device, so as to obtain preprocessed data;
Performing feature extraction on the preprocessed data through an embedded AI chip in the AI fault diagnosis data module to form a feature vector; and classifying and identifying the feature vectors based on the trained new energy failure AI diagnostic model, and determining the failure type and position.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410594649.4A CN118170125B (en) | 2024-05-14 | 2024-05-14 | Mobile device for diagnosing new energy automobile faults based on embedded AI and diagnosis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410594649.4A CN118170125B (en) | 2024-05-14 | 2024-05-14 | Mobile device for diagnosing new energy automobile faults based on embedded AI and diagnosis method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118170125A CN118170125A (en) | 2024-06-11 |
| CN118170125B true CN118170125B (en) | 2024-07-05 |
Family
ID=91359089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410594649.4A Active CN118170125B (en) | 2024-05-14 | 2024-05-14 | Mobile device for diagnosing new energy automobile faults based on embedded AI and diagnosis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118170125B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110962866A (en) * | 2018-09-29 | 2020-04-07 | 比亚迪股份有限公司 | Vehicle fault diagnosis method and device, storage medium and electronic equipment |
| CN116691351A (en) * | 2023-08-03 | 2023-09-05 | 四川吉利学院 | Intelligent monitoring and management method, device and system for safety of new energy automobile battery |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5536736B2 (en) * | 2011-10-24 | 2014-07-02 | 本田技研工業株式会社 | Vehicle diagnostic method and external diagnostic device |
| US9047722B2 (en) * | 2013-10-03 | 2015-06-02 | GM Global Technology Operations LLC | Vehicle location and fault diagnostic systems and methods |
| CN214311434U (en) * | 2021-04-06 | 2021-09-28 | 深圳市瀚智科技有限公司 | On-line fault monitoring and diagnosing device for automobile |
| US20220340220A1 (en) * | 2021-04-27 | 2022-10-27 | Bamidele Herbert Ali | Mobile Servicing Center |
| CN216067442U (en) * | 2021-08-06 | 2022-03-18 | 浙江吉利控股集团有限公司 | Intelligent robot for equipment fault diagnosis of automobile manufacturing workshop |
-
2024
- 2024-05-14 CN CN202410594649.4A patent/CN118170125B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110962866A (en) * | 2018-09-29 | 2020-04-07 | 比亚迪股份有限公司 | Vehicle fault diagnosis method and device, storage medium and electronic equipment |
| CN116691351A (en) * | 2023-08-03 | 2023-09-05 | 四川吉利学院 | Intelligent monitoring and management method, device and system for safety of new energy automobile battery |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118170125A (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111947928B (en) | Multi-source information fusion bearing fault prediction system and method | |
| US20230013544A1 (en) | Method, Apparatus and System for Detecting Abnormal Operating States of a Device | |
| JP7269437B2 (en) | Battery performance management system and method using electric vehicle charging station | |
| CN107479540B (en) | Method for diagnosing faults and system | |
| CN110728300A (en) | Method and system for identifying fault type based on turnout action current curve | |
| CN112418524A (en) | Method, device, equipment and storage medium for predicting available state of charging station | |
| CN111831430A (en) | Electrical equipment defect identification system based on edge calculation | |
| CN113283491A (en) | Fault diagnosis method of electric vehicle alternating current charging pile based on optimized deep confidence network | |
| CN111260822A (en) | Rail transit vehicle health state analysis method and terminal based on big data | |
| CN116880454A (en) | Intelligent diagnosis system and method for vehicle faults | |
| CN114371353A (en) | Power equipment abnormity monitoring method and system based on voiceprint recognition | |
| CN117829296A (en) | Charging pile fault diagnosis model based on large language model | |
| CN111597948A (en) | Fault detection and classification method for bearing vibration signals | |
| CN117610971B (en) | Highway electromechanical system health index evaluation method | |
| CN115083161A (en) | Vehicle stopping point evaluation method and device, electronic equipment and readable storage medium | |
| CN118014404A (en) | Intelligent optimization method and system based on parking lot system | |
| CN118170125B (en) | Mobile device for diagnosing new energy automobile faults based on embedded AI and diagnosis method | |
| CN117036732B (en) | Electromechanical equipment detection system, method and equipment based on fusion model | |
| CN117171506A (en) | IMU-based engineering vehicle running state monitoring method and device | |
| CN113010394A (en) | Machine room fault detection method for data center | |
| CN117150340A (en) | Method and device for diagnosing faults of small samples of switch machine | |
| CN115051474B (en) | Power distribution network line switch state identification method and system | |
| CN116127324A (en) | Fault detection method and device for key components in uninterruptible power supply | |
| CN116434368A (en) | Multifunctional handheld inspection instrument and inspection method | |
| CN107943002B (en) | Sanitation equipment fault diagnosis method and system |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |