Vehicle health status analysis method, device, system and engineering vehicle

Abstract

The present invention relates to the technical field of engineering machinery, and specifically to a vehicle health status analysis method, device, system and engineering vehicle, including establishing a correspondence between fault operating condition data and fault information; obtaining real-time operating condition data of the vehicle; and generating vehicle health information corresponding to the real-time operating condition data according to the correspondence. The present application trains and generates a fault prediction model through training sample data. The fault prediction model can judge the real-time operating condition data of the vehicle to generate corresponding health status information of the pump truck. Therefore, the fault prediction model trained with the training sample data has a higher accuracy rate of fault identification, and can more accurately and conveniently judge the specific circumstances of the fault occurring in the pump truck.

Description

Technical Field

[0001] The present application relates to the technical field of engineering machinery, and in particular to a vehicle health status analysis method, device, system and engineering vehicle. Background Art

[0002] Concrete pump trucks are engineering machinery that use pressure to transport pre-mixed concrete along pipelines to a certain height and distance. They are widely used in modern construction projects. As the core part of concrete pump trucks, the pumping system is a highly coupled nonlinear system with a complex structure, mutual interference between circuits, and complex and diverse failure modes and fault mechanisms of the main components. It is difficult to extract fault feature information and identify fault patterns, making it difficult to diagnose faults.

[0003] Therefore, in the prior art, when a concrete pump truck fails, it is difficult to accurately diagnose the failure. Summary of the invention

[0004] In view of this, the present application provides a vehicle health status analysis method, which solves the technical problem in the prior art that it is difficult to accurately diagnose the fault that occurs when a concrete pump truck fails.

[0005] According to a first aspect of the present application, the present application provides a vehicle health status analysis method, comprising:

[0006] Establish the corresponding relationship between fault condition data and fault information;

[0007] Obtain real-time vehicle operating data;

[0008] Vehicle health information corresponding to the real-time operating condition data is generated according to the corresponding relationship.

[0009] In a possible implementation of the present application, establishing a correspondence between fault condition data and fault information includes:

[0010] Acquire training sample data, wherein the training sample data includes fault condition data and fault information;

[0011] Constructing an initial fault model, and using the training sample data to train the initial fault model to generate a fault prediction model;

[0012] A corresponding relationship between the fault condition data and the fault information is established through the fault prediction model.

[0013] In a possible implementation of the present application, obtaining training sample data includes:

[0014] Establishing a fault information database, wherein the fault information database includes a plurality of fault description sheets, wherein the fault description sheets include a first fault period and fault information corresponding to the first fault period;

[0015] Establishing a fault condition database, the fault condition database including the fault condition data of the vehicle and a second fault time period, the second fault time period being a time period corresponding to the generation of the fault condition data;

[0016] Obtaining an intersecting time segment of the first fault period and the second fault period;

[0017] According to the intersecting time segment, the fault condition data and the fault information corresponding to the intersecting time segment are respectively acquired from the fault condition database and the fault information database.

[0018] In a possible implementation of the present application, the fault information includes fault location data and fault type data.

[0019] In a possible implementation of the present application, establishing a fault condition database includes:

[0020] Obtain the working condition data of the pump truck in the pumping state;

[0021] The operating condition data is divided according to a calibration period to generate a plurality of operating condition sub-data;

[0022] Performing feature extraction processing on the working condition sub-data to generate pre-processed data;

[0023] Calculate the prediction period corresponding to the preprocessed data according to the SVR model;

[0024] Calculating an absolute value of anomalies between the calibration period and the prediction period;

[0025] Determine that the absolute value of the abnormal value is greater than the abnormal threshold, and mark the calibration period corresponding to the preprocessed data as an isolated abnormal time;

[0026] It is determined that the continuous duration of a plurality of isolated abnormal times that are continuous in time is greater than a fault duration threshold, and the fault operating condition data is generated according to the pre-processed data corresponding to the plurality of isolated abnormal times that are continuous in time.

[0027] In a possible implementation of the present application, the method further includes:

[0028] Obtain normal operating data of the pump truck under normal pumping status;

[0029] Dividing the normal operating condition data according to the calibration period to generate a plurality of normal operating condition sub-data;

[0030] The initial SVR model is trained using a plurality of normal operating condition sub-data to generate the SVR model.

[0031] In a possible implementation of the present application, feature extraction processing is performed on the operating condition sub-data, including:

[0032] Calculating characteristic values ​​of acquisition characteristics in the working condition sub-data;

[0033] The collected data in the working condition sub-data is replaced with the corresponding characteristic value.

[0034] In a possible implementation of the present application, the vehicle is a pump truck, and the collected characteristics include the pump truck main system pressure, engine speed, stirring pressure, accumulator pressure and engine torque.

[0035] According to a second aspect of the present application, the present application provides a vehicle health status analysis device for implementing the method, comprising:

[0036] A relationship establishing unit, used to establish a corresponding relationship between fault condition data and fault information;

[0037] A data acquisition unit, used to acquire real-time working condition data of the vehicle;

[0038] A result generating unit is used to generate vehicle health information corresponding to the real-time operating condition data according to the corresponding relationship. The result generating unit is communicatively connected with the relationship establishing unit and the data acquiring unit respectively.

[0039] According to a third aspect of the present application, the present application provides a vehicle health status analysis system for implementing the method, comprising:

[0040] Server; used to establish a corresponding relationship between fault condition data and fault information; and

[0041] Vehicle-side controller; the vehicle-side controller is communicatively connected to the cloud server, and the vehicle-side controller is used to obtain the real-time operating condition data of the vehicle and the corresponding relationship, and generate vehicle health information corresponding to the real-time operating condition data based on the corresponding relationship.

[0042] In a possible implementation of the present application, it also includes:

[0043] A display, wherein the display is communicatively connected to the vehicle-side controller, and the display is used to display the health status information of the pump truck sent by the vehicle-side controller.

[0044] According to a fourth aspect of the present application, the present application provides an engineering vehicle, comprising the vehicle health status analysis device or the vehicle health status analysis system.

[0045] The present application obtains the fault condition database and the intersecting time segments of the first fault period and the second fault period in the condition database, generates corresponding training sample data according to the intersecting time segments, and trains and generates a fault prediction model through the training sample data. The fault prediction model can judge the real-time condition data of the vehicle to generate corresponding pump truck health status information.

[0046] Therefore, the fault prediction model trained with training sample data has a higher accuracy rate in fault identification and can more accurately and conveniently judge the specific circumstances of the failure of the pump truck. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0048] Figure 1 Shown is a flow chart of a vehicle health status analysis method provided in one embodiment of the present application.

[0049] Figure 2 Shown is a schematic structural diagram of a vehicle health status analysis device provided in another embodiment of the present application.

[0050] Figure 3 Shown is a schematic diagram of the structure of a vehicle health status analysis system provided in another embodiment of the present application. DETAILED DESCRIPTION

[0051] In the description of the application, the meaning of "multiple" is at least two, for example, two, three, etc., unless otherwise clearly and specifically limited. In the embodiment of the present application, all directional indications (such as up, down, left, right, front, back, top, bottom ...) are only used to explain the relative position relationship, motion conditions, etc. between the components under a certain specific posture (as shown in the drawings). If the specific posture changes, the directional indication also changes accordingly. In addition, the terms "including" and "having" and any of their deformations are intended to cover non-exclusive inclusions. For example, the process, method, system, product or equipment comprising a series of steps or units are not limited to the steps or units listed, but optionally also include the steps or units not listed, or optionally also include other steps or units inherent to these processes, methods, products or equipment.

[0052] In addition, the reference to "embodiment" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiment may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] The technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0055] According to one aspect of the present application, Figure 1 As shown, the present application provides a vehicle health status analysis method, comprising:

[0056] Step S10: establishing a corresponding relationship between fault condition data and fault information;

[0057] Step S20: obtaining real-time operating data of the vehicle;

[0058] Step S30: Generate vehicle health information corresponding to the real-time operating condition data according to the corresponding relationship.

[0059] Specifically, the correspondence between fault condition data and fault information can be constructed through existing deep learning algorithms, that is, a prediction model can be established through existing deep learning algorithms, such as a prediction model constructed through a support vector regression algorithm. This prediction model can be used to determine the correspondence between fault condition data and fault information.

[0060] The acquired real-time operating condition data of the vehicle is then input into the corresponding prediction model to obtain fault information corresponding to the real-time operating condition data of the vehicle, thereby achieving real-time analysis and judgment of the health status of the vehicle.

[0061] In a possible implementation manner of the present application, step S10: establishing a correspondence between fault condition data and fault information includes:

[0062] Step S101: acquiring training sample data, where the training sample data includes fault condition data and fault information;

[0063] The fault condition data and corresponding fault information of the pump truck in the historical period are obtained as training sample data. As the pump truck is continuously used, the various equipment in the pump truck will also age to a certain extent. Therefore, when selecting the training sample data of the pump truck, the data of the most recent time period will also be selected, such as the data of the most recent 3-6 months. In this way, the fit between the information represented by the data and the actual situation of the vehicle can be improved to improve the accuracy of the data, thereby improving the accuracy of the fault prediction model established subsequently.

[0064] In addition, in order to overcome the problem of inaccurate prediction results of the fault prediction model caused by the aging of the pump truck, the training sample data can be updated at regular intervals. For example, every year, the fault condition data and corresponding fault information generated in the past 6 months are re-collected. In this way, the accuracy of the fault prediction model obtained by subsequent training can be guaranteed as the data is updated.

[0065] Since pump trucks generally have similar working principles, they have commonalities. Therefore, collecting historical operating data of multiple pump trucks for subsequent calculation and processing can not only ensure that the amount of data is sufficient, but also ensure the accuracy of the data. In order to further ensure the accuracy of the data, it is also possible to collect data from different pump trucks in the same production batch as training data used to build the prediction model of the batch of pump trucks, thereby further improving the accuracy of the data.

[0066] Step S102: construct an initial fault model, train the initial fault model using training sample data, and generate a fault prediction model;

[0067] Step S103: establishing a corresponding relationship between fault condition data and fault information through a fault prediction model.

[0068] The initial fault model used in this embodiment is an initial fault model constructed by a support vector regression algorithm, and then after training the initial fault model with a large amount of training sample data, a fault prediction model that meets the use requirements can be generated. The fault prediction model can be used to determine the corresponding relationship between fault condition data and fault information.

[0069] In a possible implementation of the present application, step S101: obtaining training sample data includes:

[0070] Step S1011: establishing a fault information database, wherein the fault information database includes a plurality of fault description sheets, each of which includes a first fault period and fault information corresponding to the first fault period;

[0071] The establishment of a fault information database is mainly to record and save the actual fault information of the pump truck. This is to facilitate the use of the fault location data and fault type data in the fault description form as data labels for training sample data in the later stage. In the establishment of the fault description form, the relevant information can be entered manually or automatically collected by other equipment. In actual use, the information is usually entered after the relevant fault engineer diagnoses and determines on site. Usually, when manually entering the information, it is not possible to accurately determine the time period when the pump truck failure occurs, so the first fault period is usually in days, that is, 0:00-24:00 is the time period of the day. The specific fault description form can be in the following form: First fault period: October 20, 2021, fault location data: main oil pump of the pumping system, fault type data: the seal of the oil cylinder is damaged.

[0072] Step S1012: establishing a fault condition information database, the fault condition information database including the fault condition data of the vehicle and the second fault time period, the second fault time period being the time period corresponding to the generation of the fault condition data;

[0073] The vehicle's fault condition data and second fault time period in the fault condition information library are data collected when a pump truck fails during its historical operation. Usually, when a pump truck fails, it does not stop working instantly, but stops working after the fault continues for a period of time. Therefore, the fault condition data when the fault occurs can be found in the fault condition information library of the pump truck, and the time period corresponding to the generation of the fault condition data is the second fault time period, which is usually a few seconds, for example: Second fault time period: 10:20:20 on October 20, 2021 to 10:20:25 on October 20, 2021.

[0074] Step S1013: obtaining the intersecting time segment of the first fault period and the second fault period;

[0075] Find the intersecting time segment of the first fault period and the second fault period corresponding to each pump truck in the fault information database and the fault operating condition database. Taking the first fault period and the second fault period illustrated in this embodiment as an example, the intersecting time segment of the first fault period and the second fault period is: 10:20:20 on October 20, 2021 to 10:20:25 on October 20, 2021.

[0076] Step S1014: According to the intersecting time segments, the fault condition data and the fault information corresponding to the intersecting time segments are respectively obtained from the fault condition information library and the fault condition information library.

[0077] The training sample data corresponding to the intersecting time segments are obtained from the fault information database and the fault condition database, wherein the training sample data include the fault condition data, fault location data and fault type data corresponding to the intersecting time segments; the data content of the training sample data is the fault condition data corresponding to the intersecting time segments, and the data label of the training sample data is the fault location data and fault type data corresponding to the intersecting time segments.

[0078] In this embodiment, for example, the data content of the training sample data is the working condition data in the period from 10:20:20 on October 20, 2021 to 10:20:25 on October 20, 2021, and the corresponding data label of the training sample data is the fault location data: the main oil pump of the pumping system, and the fault type data: the seal of the oil cylinder is damaged. Therefore, by performing the above steps S1011 to S1014 on multiple groups of pump trucks, a large amount of training sample data can be generated to facilitate the subsequent training of the initial fault model to improve the accuracy of the initial fault model.

[0079] In a possible implementation manner of the present application, the fault information includes fault location data and fault type data.

[0080] In a possible implementation manner of the present application, step S1012: establishing a fault condition information library includes:

[0081] Step S10121: Acquire the working condition data of the pump truck in the pumping state;

[0082] The method for obtaining the operating condition data in this step may be the same as the method for obtaining the training sample data in step S101, and will not be described in detail here.

[0083] Step S10122: dividing the operating condition data according to the calibration period to generate a plurality of operating condition sub-data;

[0084] The calibration cycle is the duration of an actual cycle in the actual operation of the pump truck, so the historical working condition data can be divided into multiple working condition sub-data, and the data label corresponding to each working condition sub-data is the duration of the calibration cycle.

[0085] Step S10123: performing feature extraction processing on the working condition sub-data to generate pre-processed data;

[0086] Since the amount of high-quality real-time working condition sub-data is very large and difficult to transmit through the existing Internet of Things, the data generated in a calibration cycle is subjected to feature extraction and processing, and the characteristic values ​​are calculated for subsequent calculations. This can greatly reduce the amount of data transmission and the amount of data calculation in the SVR model, reducing the calculation time.

[0087] Step S10124: Calculate the prediction period corresponding to the preprocessed data according to the SVR model;

[0088] Step S10125: Calculate the absolute value of the abnormal value between the calibration period and the prediction period;

[0089] The length of time it takes for the pump truck to switch direction, that is, the length of the calibration cycle, can roughly indicate whether a fault has occurred. The calculation formula for the abnormal value between the calibration cycle and the prediction cycle is as follows:

[0090] Y=Log2 (X / W) ;

[0091] Among them, Y is the outlier; X is the calibration period; W is the prediction period.

[0092] Step S10126: Determine that the absolute value of the abnormal value is greater than the abnormal threshold, and mark the calibration period corresponding to the preprocessed data as an isolated abnormal time;

[0093] The abnormal threshold needs to be determined according to actual usage. The method for determining the abnormal threshold is well known to those skilled in the art and will not be described in detail here. Optionally, the abnormal threshold in this embodiment is 0.25.

[0094] Since most of the training data used in constructing and training the SVR model are data from the pump truck during normal operation, the prediction period of the normal working condition data calculated by the SVR model is closer to the actual calibration period, while the prediction period of the fault working condition data calculated is far different from the actual calibration period. This can determine which pre-processed data is the data generated during a fault.

[0095] Step S10127: determine whether the continuous duration of a plurality of isolated abnormal times that are continuous in time is greater than a fault duration threshold, and generate fault condition data according to preprocessed data corresponding to the plurality of isolated abnormal times that are continuous in time.

[0096] Since the pump truck failure will only occur after the pump truck abnormality continues for a period of time, rather than at the moment the abnormality occurs. Therefore, when judging the abnormal data as the data corresponding to the occurrence of the fault, it is required that the continuous duration of multiple isolated abnormal times that are continuous in time is greater than the fault duration threshold. The fault duration threshold needs to be determined based on the average duration of the isolated abnormal time when the fault occurs in actual usage, and the method for setting the fault duration threshold is a technology well known to those skilled in the art, which will not be repeated here. The fault duration threshold in this embodiment can be 3 seconds, 4 seconds, 5 seconds or 6 seconds.

[0097] Through step S10127, scattered and isolated fault points can be filtered out. Thus, the occurrence of noise data can be minimized, and the noise data generated by short-term system fluctuations caused by misoperation of the pump truck in actual use can be reduced. Thus, the correspondence between the fault condition data screened out and the data generated when the pump truck fails can be improved. Thus, the accuracy of the fault prediction model trained subsequently can be improved.

[0098] The data content of the fault condition data is the union of pre-processed data corresponding to multiple isolated abnormal times, and the calibration period corresponding to the fault condition data is the union of multiple isolated abnormal times;

[0099] In a possible implementation of the present application, the method further includes:

[0100] Step S40: acquiring normal operating data of the pump truck in a normal pumping state;

[0101] The method for obtaining the operating condition data in this step may be the same as the method for obtaining the training sample data in step S101, and will not be described in detail here.

[0102] Step S50: dividing the normal operating condition data according to the calibration period to generate a plurality of normal operating condition sub-data;

[0103] The method for obtaining the operating condition data in this step may be the same as the processing method in step S10122, and will not be repeated here.

[0104] Step S60: training the initial SVR model with a plurality of normal operating condition sub-data to generate an SVR model.

[0105] The SVR model used in step S10124 is the SVR model in this embodiment. The SVR model generated after training with the normal working condition sub-data generates a prediction period for the pre-processed data in a normal state that is closer to the calibration period corresponding to the pre-processed data. However, the prediction period generated for the pre-processed data in an abnormal state is significantly different from the calibration period corresponding to the pre-processed data.

[0106] In a possible implementation of the present application, step S10123: performing feature extraction processing on the operating condition sub-data includes:

[0107] Step S104: Calculate the characteristic value of the collected characteristics in the working condition sub-data;

[0108] Step S105: Replace the collected data in the operating condition sub-data with the corresponding characteristic values.

[0109] Since there are multiple collected data uploaded by the sensor of a certain collection feature in a calibration cycle, in order to reduce the amount of data processing of the collected data, it is necessary to calculate the characteristic value of the collected data of each collection feature, and use the characteristic value as the value of the subsequent calculation of the working condition sub-data. By calculating the characteristic value, not only the amount of data can be reduced, but also the error of the data can be reduced.

[0110] Optionally, the characteristic value is the root mean square value, mean, variance value, maximum value or minimum value of the collected data.

[0111] In a possible implementation of the present application, the vehicle is a pump truck, and the collected characteristics include the pump truck main system pressure, engine speed, stirring pressure, accumulator pressure and engine torque.

[0112] According to the second aspect of the present application, Figure 2 As shown, the present application provides a vehicle health status analysis device for implementing the method, comprising:

[0113] A relationship establishing unit, used to establish a corresponding relationship between fault condition data and fault information;

[0114] A data acquisition unit, used to acquire real-time working condition data of the vehicle;

[0115] The result generating unit is used to generate vehicle health information corresponding to the real-time working condition data according to the corresponding relationship. The result generating unit is respectively connected to the relationship establishing unit and the data acquiring unit for communication.

[0116] According to the third aspect of this application, Figure 3 As shown, the present application provides a vehicle health status analysis system for implementing the method, comprising:

[0117] Server; used to establish a corresponding relationship between fault condition data and fault information; and

[0118] Vehicle-side controller: The vehicle-side controller is connected to the cloud server for communication. The vehicle-side controller is used to obtain the real-time operating condition data and corresponding relationships of the vehicle, and generate vehicle health information corresponding to the real-time operating condition data based on the corresponding relationships.

[0119] In a possible implementation of the present application, it also includes:

[0120] The display is connected to the vehicle-side controller for communication, and is used to display the health status information of the pump truck sent by the vehicle-side controller.

[0121] According to a fourth aspect of the present application, the present application provides an engineering vehicle, including a vehicle health status analysis device, or a vehicle health status analysis system.

[0122] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program information, which, when executed by a processor, enables the processor to execute the steps of a vehicle health status analysis method described in this specification according to various embodiments of the present application.

[0123] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0124] In addition, the embodiments of the present application may also be a computer-readable storage medium on which computer program information is stored. When the computer program information is executed by a processor, the processor executes the steps of the method for monitoring the pressure in a powder tank according to various embodiments of the present application.

[0125] Computer readable storage media can adopt any combination of one or more readable media. The readable medium can be a readable signal medium or a readable storage medium. The readable storage medium can include, for example, but is not limited to, a system, device or device of electricity, magnetism, light, electromagnetic, infrared, or semiconductor, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0126] The basic principles of the present application are described above in conjunction with specific embodiments. However, it should be noted that the advantages, strengths, effects, etc. mentioned in the present application are only examples and not limitations, and it cannot be considered that these advantages, strengths, effects, etc. are required by each embodiment of the present application. In addition, the specific details disclosed above are only for the purpose of illustration and ease of understanding, not for limitation, and the above details do not limit the present application to being implemented by adopting the above specific details.

[0127] The block diagrams of the devices, apparatuses, equipment, and systems involved in this application are only illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagram. As will be appreciated by those skilled in the art, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open words, referring to "including but not limited to", and can be used interchangeably with them. The words "or" and "and" used here refer to the words "and / or" and can be used interchangeably with them, unless the context clearly indicates otherwise. The words "such as" used here refer to the phrase "such as but not limited to", and can be used interchangeably with them.

[0128] It should also be noted that in the apparatus, device and method of the present application, each component or each step can be decomposed and / or recombined. Such decomposition and / or recombination should be regarded as equivalent solutions of the present application.

[0129] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other aspects without departing from the scope of the present application. Therefore, the present application is not intended to be limited to the aspects shown herein, but rather to the widest scope consistent with the principles and novel features of the present invention.

[0130] The above are only preferred embodiments of the invention of this application and are not intended to limit the invention of this application. Any modifications, equivalent substitutions, etc. made within the spirit and principles of the invention of this application should be included in the protection scope of the invention of this application.

Claims

1. A vehicle health status analysis method, characterized in that: include: Establish the corresponding relationship between fault condition data and fault information; Obtain real-time vehicle operating data; Generate vehicle health information corresponding to the real-time operating condition data according to the corresponding relationship; Establishing the corresponding relationship between fault condition data and fault information includes: Acquire training sample data, wherein the training sample data includes fault condition data and fault information; Constructing an initial fault model, and using the training sample data to train the initial fault model to generate a fault prediction model; Establishing a corresponding relationship between the fault condition data and the fault information through the fault prediction model; Obtaining training sample data includes: Establishing a fault information database, wherein the fault information database includes a plurality of fault description sheets, wherein the fault description sheets include a first fault period and fault information corresponding to the first fault period; Establishing a fault condition database, the fault condition database including the fault condition data of the vehicle and a second fault time period, the second fault time period being a time period corresponding to the generation of the fault condition data; Obtaining an intersecting time segment of the first fault period and the second fault period; According to the intersecting time segment, respectively acquiring the fault condition data and the fault information corresponding to the intersecting time segment from the fault condition database and the fault information database; The establishment of the fault condition database comprises: Obtain the working condition data of the pump truck in the pumping state; The operating condition data is divided according to a calibration period to generate a plurality of operating condition sub-data; Performing feature extraction processing on the working condition sub-data to generate pre-processed data; Calculate the prediction period corresponding to the preprocessed data according to the SVR model; Calculating an absolute value of anomalies between the calibration period and the prediction period; Determine that the absolute value of the abnormal value is greater than the abnormal threshold, and mark the calibration period corresponding to the preprocessed data as an isolated abnormal time; It is determined that the continuous duration of a plurality of isolated abnormal times that are continuous in time is greater than a fault duration threshold, and the fault operating condition data is generated according to the pre-processed data corresponding to the plurality of isolated abnormal times that are continuous in time.

2. The vehicle health status analysis method according to claim 1, characterized in that: The fault information includes fault location data and fault type data.

3. The vehicle health status analysis method according to claim 1, characterized in that: The method further comprises: Obtain normal operating data of the pump truck under normal pumping status; Dividing the normal operating condition data according to the calibration period to generate a plurality of normal operating condition sub-data; The initial SVR model is trained using a plurality of normal operating condition sub-data to generate the SVR model.

4. The vehicle health status analysis method according to claim 1, characterized in that: Performing feature extraction processing on the working condition sub-data, including: Calculating characteristic values ​​of acquisition characteristics in the working condition sub-data; The collected data in the working condition sub-data is replaced with the corresponding characteristic value.

5. The vehicle health status analysis method according to claim 4, characterized in that: The vehicle is a pump truck, and the collected characteristics include the pump truck main system pressure, engine speed, stirring pressure, accumulator pressure and engine torque.

6. A vehicle health status analysis device for implementing the method according to any one of claims 1 to 5, characterized in that: include: A relationship establishing unit, used to establish a corresponding relationship between fault condition data and fault information; Establishing the corresponding relationship between fault condition data and fault information includes: Acquire training sample data, wherein the training sample data includes fault condition data and fault information; Constructing an initial fault model, and using the training sample data to train the initial fault model to generate a fault prediction model; Establishing a corresponding relationship between the fault condition data and the fault information through the fault prediction model; Obtaining training sample data includes: Establishing a fault information database, wherein the fault information database includes a plurality of fault description sheets, wherein the fault description sheets include a first fault period and fault information corresponding to the first fault period; Establishing a fault condition database, the fault condition database including the fault condition data of the vehicle and a second fault time period, the second fault time period being a time period corresponding to the generation of the fault condition data; Obtaining an intersecting time segment of the first fault period and the second fault period; According to the intersecting time segment, respectively acquiring the fault condition data and the fault information corresponding to the intersecting time segment from the fault condition database and the fault information database; The establishment of the fault condition database comprises: Obtain the working condition data of the pump truck in the pumping state; The operating condition data is divided according to a calibration period to generate a plurality of operating condition sub-data; Performing feature extraction processing on the working condition sub-data to generate pre-processed data; Calculate the prediction period corresponding to the preprocessed data according to the SVR model; Calculating an absolute value of anomalies between the calibration period and the prediction period; Determine that the absolute value of the abnormal value is greater than the abnormal threshold, and mark the calibration period corresponding to the preprocessed data as an isolated abnormal time; Determine that the continuous duration of a plurality of the isolated abnormal times that are continuous in time is greater than a fault duration threshold, and generate the fault condition data according to the pre-processed data corresponding to the plurality of the isolated abnormal times that are continuous in time; A data acquisition unit, used to acquire real-time working condition data of the vehicle; A result generating unit is used to generate vehicle health information corresponding to the real-time operating condition data according to the corresponding relationship. The result generating unit is communicatively connected with the relationship establishing unit and the data acquiring unit respectively.

7. A vehicle health status analysis system for implementing the method according to any one of claims 1 to 5, characterized in that: include: server; Used to establish the corresponding relationship between fault condition data and fault information; as well as Vehicle-side controller; the vehicle-side controller is communicatively connected to the server, and the vehicle-side controller is used to obtain the real-time operating condition data of the vehicle and the corresponding relationship, and generate vehicle health information corresponding to the real-time operating condition data based on the corresponding relationship.

8. The vehicle health status analysis system according to claim 7, characterized in that: Also includes: A display, wherein the display is communicatively connected to the vehicle-side controller, and the display is used to display the health status information of the pump truck sent by the vehicle-side controller.

9. An engineering vehicle, characterized in that: It includes the vehicle health status analysis device as described in claim 6, or the vehicle health status analysis system as described in claim 7 or claim 8.

Images