CN114239734A - Distributed vehicle-mounted health management system - Google Patents
Distributed vehicle-mounted health management system Download PDFInfo
- Publication number
- CN114239734A CN114239734A CN202111570496.2A CN202111570496A CN114239734A CN 114239734 A CN114239734 A CN 114239734A CN 202111570496 A CN202111570496 A CN 202111570496A CN 114239734 A CN114239734 A CN 114239734A
- Authority
- CN
- China
- Prior art keywords
- fault
- health
- data
- vehicle
- faults
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
Abstract
The invention provides a distributed vehicle-mounted health management system, and belongs to the technical field of vehicle intelligent management. The system comprises: a plurality of sensors, input devices, and a plurality of health management subsystems; the sensor is used for collecting health data of each electronic subsystem on the vehicle and transmitting the health data to the corresponding health management subsystem; the input equipment is used for receiving vehicle maintenance information and repair information input by related personnel; each health management subsystem is used for managing the health states of different electronic subsystems according to the health data, the maintenance information and the repair information acquired by the corresponding sensors, and the management of the health states of the electronic subsystems comprises health state monitoring, state evaluation, fault diagnosis, fault trend analysis and/or fault grading management. The invention can monitor the health state of the vehicle in real time, realize early fault warning and guarantee the safety of the vehicle.
Description
Technical Field
The invention relates to the technical field of vehicle intelligent management, in particular to a distributed vehicle-mounted health management system.
Background
Safety and reliability are the most basic and important requirements of equipment on a vehicle, along with the development of technology, more and more electronic devices on the vehicle are provided, some electronic devices can realize more advanced functions, and some electronic devices can replace original manual mechanical devices to realize automation. In order to ensure the safe and reliable operation of the vehicle, the equipment of the vehicle needs to be overhauled and maintained, most of the prior processes are carried out manually at regular time, a large amount of labor cost is needed, and the safe and reliable performance of the vehicle cannot be ensured in a detection window period. In addition, the current vehicle detection is posterior, that is, only the condition that has occurred can be detected, for example, the fault occurs, the reason of the fault is detected according to the related data, and the fault is located.
Disclosure of Invention
Therefore, the technical problem to be solved by the embodiments of the present invention is to overcome the defects that manual vehicle detection in the prior art is high in labor cost and has a detection window period, and current detection can only detect a fault that has occurred, so that unexpected faults of a user still occur, and further the safety of a user is affected, thereby providing a distributed vehicle health management system.
To this end, the present invention provides a distributed vehicle health management system, comprising:
a plurality of sensors, input devices, and a plurality of health management subsystems;
the sensor is used for collecting health data of each electronic subsystem on the vehicle and transmitting the health data to the corresponding health management subsystem;
the input equipment is used for receiving vehicle maintenance information and repair information input by related personnel;
each health management subsystem is used for managing the health states of different electronic subsystems according to the health data, the maintenance information and the repair information acquired by the corresponding sensors, and the management of the health states of the electronic subsystems comprises health state monitoring, state evaluation, fault diagnosis, fault trend analysis and/or fault grading management.
Optionally, the health management subsystem is further configured to control a corresponding terminal to display at least part of the health data, the health status management result, and/or warning information determined according to the health status management result of the vehicle, where the terminal includes a terminal of an occupant, a terminal of a user, and/or a terminal of a maintenance person.
Optionally, the plurality of health management subsystems comprise: the system comprises a task health management subsystem, an operation health management subsystem and a chassis health management subsystem;
the task health management subsystem is used for managing the health state of a task subsystem in the electronic subsystem;
the operation health management subsystem is used for managing the health state of an operation subsystem in the electronic subsystem;
the chassis health management subsystem is used for managing the health state of the chassis subsystems in the electronic subsystems.
Optionally, the health management subsystem is further configured to match a fault phenomenon with a fault mode in a fault mode library, determine a fault reason according to the matched fault mode, and perform fault handling or push a fault handling method to a terminal of a maintenance worker, where each fault mode includes a fault phenomenon, a fault reason, and a fault handling method.
Optionally, the health management subsystem performs fault trend analysis by using a fault trend analysis model, where the fault trend analysis model is used to predict future possible faults according to the historical and/or current faults of the vehicle, and the training data of the fault trend analysis model is obtained by clustering the historical fault data of each sample vehicle, where the sample vehicle is a vehicle of the same type as the vehicle.
Optionally, the training data is obtained by:
for historical fault data of each sample vehicle, sequentially determining the clustering degree between each fault and the first fault from the second fault until the fault of which the clustering degree is greater than a preset value is obtained; the historical fault data includes a time of occurrence of each fault;
taking the fault with the clustering degree between the first fault and the preset value as a first target fault, and adding the first target fault and the first fault into a first fault group;
sequentially acquiring the clustering degrees between the faults after the first target fault and the faults in the first fault group until the faults with the clustering degrees larger than the preset value are acquired, and adding the faults with the clustering degrees larger than the preset value in the first fault group as the first target faults into the first fault group;
repeating the previous step until the last fault in the historical fault data;
and for the fault which is not added with the first fault group in the historical fault data, carrying out fault grouping according to the steps, and taking the historical fault data corresponding to the obtained fault group as the training data, wherein the fault group comprises the first fault group.
The invention also provides a distributed vehicle-mounted health management method, which comprises the following steps:
acquiring health data of a vehicle electronic subsystem acquired by a sensor and vehicle maintenance information and repair information input by related personnel and received by input equipment;
and managing the health state of the electronic subsystem according to the health data, the maintenance information and the repair information, wherein the management of the health state of the electronic subsystem comprises health state monitoring, state evaluation, fault diagnosis, fault trend analysis and/or fault grading management.
Optionally, after managing the health status of the electronic subsystem according to the health data, the maintenance information, and the repair information, the method further includes:
and controlling corresponding terminals to display at least part of the health data, the health state management result and/or alarm information determined according to the health state management result of the vehicle, wherein the terminals comprise terminals of passengers, terminals of users and/or terminals of maintenance personnel.
Optionally, the managing the health status of the electronic subsystem includes:
predicting future probable faults from the vehicle history and/or current faults using a fault trend analysis model; wherein the content of the first and second substances,
the training data of the fault trend analysis model is obtained by clustering historical fault data of each sample vehicle respectively, and the sample vehicles are the vehicles of the same type.
Optionally, the using the failure trend analysis model to predict a future possible failure according to the vehicle history and/or the current failure further includes:
for historical fault data of each sample vehicle, sequentially determining the clustering degree between each fault and the first fault from the second fault until the fault of which the clustering degree is greater than a preset value is obtained; the historical fault data includes a time of occurrence of each fault;
taking the fault with the clustering degree between the first fault and the preset value as a first target fault, and adding the first target fault and the first fault into a first fault group;
sequentially acquiring the clustering degrees between the faults after the first target fault and the faults in the first fault group until the faults with the clustering degrees larger than the preset value are acquired, and adding the faults with the clustering degrees larger than the preset value in the first fault group as the first target faults into the first fault group;
repeating the previous step until the last fault in the historical fault data;
as for the fault which is not added with the first fault group in the historical fault data, fault grouping is carried out according to the steps, the historical fault data corresponding to the obtained fault group is used as the training data, and the fault group comprises the first fault group;
training the fault trend analysis model using the training data.
The technical scheme of the embodiment of the invention has the following advantages:
the distributed vehicle-mounted health management system provided by the embodiment of the invention can realize the health state monitoring, state evaluation, fault diagnosis, fault trend analysis and/or fault grading management of each electronic subsystem on the vehicle, and the health management is real-time and automatic, so that the detection is uninterrupted, the vehicle health state is monitored in real time, and the vehicle safety is ensured while the labor cost is reduced. The failure trend analysis can realize early failure warning, and avoid the accident caused by the accident that the failure suddenly affects the use of the vehicle.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a block diagram of a specific example of a distributed vehicle health management system according to embodiment 1 of the present invention;
FIG. 2 is a diagram illustrating an exemplary embodiment of a plurality of health management subsystems and electronic subsystems managed thereby in accordance with embodiment 1 of the present invention;
fig. 3 is a flowchart of a specific example of a distributed vehicle health management method in embodiment 2 of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the accompanying drawings, and it should be understood that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In describing the present invention, it is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises" and/or "comprising," when used in this specification, are intended to specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. The term "and/or" includes any and all combinations of one or more of the associated listed items. The terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The terms "mounted," "connected," and "coupled" are to be construed broadly and may, for example, be fixedly coupled, detachably coupled, or integrally coupled; can be mechanically or electrically connected; the two elements can be directly connected, indirectly connected through an intermediate medium, or communicated with each other inside; either a wireless or a wired connection. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art.
In addition, the technical features involved in the different embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
Example 1
The present embodiment provides a distributed vehicle-mounted health management system 100, as shown in fig. 1, including: a plurality of sensors 101, an input device 102, and a plurality of health management subsystems 103;
the sensor 101 is used for collecting health data of each electronic subsystem on the vehicle and transmitting the health data to the corresponding health management subsystem 103;
the input device 102 is used for receiving vehicle maintenance information and repair information input by relevant personnel;
each health management subsystem 103 is configured to manage health states of different electronic subsystems according to the health data, the maintenance information, and the repair information acquired by the corresponding sensor 101, where managing the health states of the electronic subsystems includes health state monitoring, state evaluation, fault diagnosis, fault trend analysis, and/or fault classification management.
The electronic subsystem may also be referred to as a vehicle-mounted subsystem or a vehicle-mounted substation, and may be obtained by dividing an electronic system of a vehicle according to functions. The fault diagnosis includes typical fault diagnosis, correlation diagnosis and/or assisted (fault) localization. Fault classification is mainly based on the possible consequences of a fault, including primary, secondary and tertiary faults. The first-level fault can cause vehicle damage or personal injury; the secondary fault can cause the damage of the vehicle and cause the failure of the normal use of the important functions of the vehicle; the third-level fault can cause the fault of the electronic subsystem of the vehicle part, so that the general function of the vehicle part cannot be used.
The failure trend analysis (also referred to as failure prediction and derivation) means that failures occurring in the vehicle history and/or failures occurring at present are predicted or derived to be possible to occur in the future, including predicting or deriving the probability, trend, time and the like of the failure occurring at a higher level from the failure at a lower level, and may involve a plurality of failure modes (described in detail below), for example, a primary failure may be derived from a plurality of secondary failures.
The input device 102 may also receive fault information entered by a relevant person, which may be fault information manually diagnosed by the relevant person (e.g., a maintenance person).
The functions of each health management subsystem 103 may be implemented based on different functional software (i.e., health management software), which may be executed by different processors. For example, the functional software of the different health management subsystems 103 may be installed in and executed by a central control computer of the respective subsystem of the vehicle.
Of course, as an alternative embodiment, a plurality of the health management subsystems 103 may be executed by the same processor.
In addition, the distributed vehicle-mounted health management system is also used for managing and storing the health data, the maintenance information and the repair information.
The distributed vehicle-mounted health management system further comprises an information transmission interface, and the information transmission interface is used for exporting the health data acquired by the sensor 101 for use by other systems or software. The information transmission interface may be, for example, a USB interface, a network port, or the like.
The health management system in the embodiment adopts a layered fusion system architecture, can realize health state monitoring, state evaluation, fault diagnosis, fault trend analysis and/or fault hierarchical management of each electronic subsystem on the vehicle, and the health management is real-time and automatic, so that the detection is uninterrupted, the health state of the vehicle is monitored in real time, and the vehicle safety is guaranteed while the labor cost is reduced. The failure trend analysis can realize early failure warning, and avoid the accident caused by the accident that the failure suddenly affects the use of the vehicle.
Optionally, the health management subsystem 103 is further configured to control a corresponding terminal to display at least part of the health data, the health status management result, and/or warning information determined according to the health status management result of the vehicle, where the terminal includes a terminal of an occupant, a terminal of a user, and/or a terminal of a maintenance person.
Wherein at least part of the health data displayed at the terminal comprises some key health data. The health state management result comprises a health state monitoring result, a state evaluation result, a fault diagnosis result, a fault trend analysis result and/or a fault grading management result.
In addition, the health management subsystem 103 may be further configured to send the health status management result to the terminal according to the query information sent by the terminal.
Further optionally, the health management system may further push the trip log, the maintenance information, and/or the repair information to a terminal of a user, so that the user may refer to the trip log, the maintenance information, and/or the repair information from the terminal. The health management system can also push the driving log, the historical maintenance information and/or the historical repair information to a terminal of a maintenance person, so that the maintenance person can look up the driving log, the historical maintenance information and/or the historical repair information from the terminal.
Optionally, as shown in fig. 2, a plurality of the health management subsystems 103 includes: the system comprises a task health management subsystem, an operation health management subsystem and a chassis health management subsystem;
the task health management subsystem is used for managing the health state of a task subsystem in the electronic subsystem;
the operation health management subsystem is used for managing the health state of an operation subsystem in the electronic subsystem;
the chassis health management subsystem is used for managing the health state of the chassis subsystems in the electronic subsystems.
Specifically, the task subsystem mainly comprises a task central control computer (including an internal board card), a task display control terminal, a task system operation panel, a first task system electrical control box and a second task system electrical control box. The operation subsystem mainly comprises: the operation control system comprises an operation central control computer (comprising an internal board card), an operation system operation panel, a first operation control box and a second operation control box. The chassis subsystem mainly comprises: the system comprises a chassis central control computer (comprising an internal board card), a driving display control terminal, a power generation controller, a heating controller, an engine controller, a gearbox controller, a vehicle operation control panel and an electronic comprehensive control box.
Optionally, the health management subsystem 103 is further configured to match a fault phenomenon with a fault mode in a fault mode library, determine a fault reason according to the matched fault mode, and perform fault handling or push a fault handling method to a terminal of a maintenance worker, where each fault mode includes a fault phenomenon, a fault reason, and a fault handling method.
In this embodiment, when a fault occurs, the fault cause can be quickly located and the fault handling method can be searched based on the fault pattern library according to the fault phenomenon.
If the failure mode is not matched in the failure mode library after the failure occurs, the health management subsystem 103 records the time, the environmental condition, and the handling method performed for the failure, and searches the failure cause as much as possible, for example, after the failure, the failure is analyzed by using professional analysis software, the possible cause of the failure and other possible handling methods are searched, and the summarized possible failure modes are incorporated into the failure mode library to be verified, the validity and the correctness of the possible failure modes are verified through the subsequent use of the vehicle, and the verified possible failure modes are incorporated into the failure mode library management.
Optionally, the health management subsystem 103 performs fault trend analysis by using a fault trend analysis model, where the fault trend analysis model is used to predict future possible faults according to the historical faults and/or the currently occurring faults of the vehicle, and the training data of the fault trend analysis model is obtained by respectively clustering historical fault data (please refer to table 1 below, where the fault occurrence time is not shown in the table) of each sample vehicle, where the sample vehicle is a vehicle of the same type as the vehicle.
Table 1 fault example
The fault trend analysis model may be, for example, a support vector machine model.
In the embodiment, the training data of the fault trend analysis model is obtained by clustering the historical fault data of the sample vehicle, so that the associated fault data is divided from the discrete fault data, and the fault trend analysis model with high prediction accuracy is conveniently and quickly trained.
Optionally, the training data is obtained by:
for historical fault data of each sample vehicle, sequentially determining the clustering degree between each fault and the first fault from the second fault until the fault of which the clustering degree is greater than a preset value is obtained; the historical fault data includes a time of occurrence of each fault;
taking the fault with the clustering degree between the first fault and the preset value as a first target fault, and adding the first target fault and the first fault into a first fault group;
sequentially acquiring the clustering degrees between the faults after the first target fault and the faults in the first fault group until the faults with the clustering degrees larger than the preset value are acquired, and adding the faults with the clustering degrees larger than the preset value in the first fault group as the first target faults into the first fault group;
repeating the previous step until the last fault in the historical fault data;
and for the fault which is not added with the first fault group in the historical fault data, carrying out fault grouping according to the steps, and taking the historical fault data corresponding to the obtained fault group as the training data, wherein the fault group comprises the first fault group.
And the historical fault data corresponding to the fault grouping is the data of each fault in the fault grouping. The previous (in chronological order of occurrence of the faults) fault in one fault group may be the cause of the occurrence of the latter fault, which may be the result. Specifically, if there are N faults in a fault group, the first N-1 faults may be the cause of the nth fault, and N is less than or equal to N.
If the clustering degree between a certain fault (for example, the first fault in the historical fault data of the sample vehicle) and any other fault in the historical fault data is less than or equal to the preset value, the fault data is not subjected to grouping processing and is not used as training data of the fault trend analysis model. In this embodiment, the historical failure data of one sample vehicle may be divided into one failure group or a plurality of failure groups, or one failure group may not be divided.
Specifically, the clustering degree can be determined by the following method:
for the clustering degree between the faults, firstly, respectively obtaining the association scores on multiple dimensions between the two faults, and then carrying out weighted summation on the association scores on the multiple dimensions to obtain the clustering degree between the two faults;
and for the clustering degree between the faults and the fault groups, firstly calculating the clustering degree between the faults and each fault in the fault groups according to the method for calculating the clustering degree between the faults, and then calculating the clustering degree between the faults and the fault groups in a weighted summation mode. In this embodiment, for example, when the clustering degree between the faults and the fault groups is calculated, the faults in the fault groups all precede the individual faults, so that the weighting of the clustering degree between the faults and the individual faults in the fault groups gradually increases along with the chronological order of the faults.
The fault dimension when calculating the relevance score may include a fault reason, a fault level, a possible result, and the like.
Further optionally, after the fault groups are obtained, training a support vector machine model serving as the fault trend analysis model by using historical fault data corresponding to each fault group, and optimizing penalty parameters and kernel function parameters of the support vector machine by using a particle swarm algorithm, where a fitness function g of the particle swarm algorithm has a formula:
wherein, CjHistorical fault data, X, corresponding to the jth faulty packetiIs CjHistorical fault data for the first i faults in the past, Yj(i) Is XiActual output, Q, in the support vector machine modelj(i) Is CjHistorical fault data of the (i + 1) th fault and XiIn support vector machine modelsThe expected output, M, is the number of failures in the jth failure packet.
In other optional specific embodiments, the fault trend analysis model is obtained by the following training:
acquiring historical fault data corresponding to the fault groups in the training data as sample fault data, wherein each sample fault data comprises the occurrence time of each fault;
obtaining a graph structure corresponding to a knowledge graph of the sample fault data, and determining an initial knowledge characterization vector of each node and an initial state characterization vector of each node in the graph structure, wherein the graph structure consists of a plurality of nodes and edges;
inputting the initial knowledge characterization vector of each node in the graph structure into a graph attention neural network model to obtain the knowledge characterization vector of each node in the graph structure;
acquiring an initial state characterization vector of each node in the graph structure corresponding to the previous n faults in the graph structure and an activation vector of each node in the graph structure corresponding to the (n + 1) th fault, and inputting the initial state characterization vector and the activation vector into a recurrent neural network model to obtain a state characterization vector of each node in the graph structure;
and inputting the knowledge characterization vector and the state characterization vector of each node in the graph structure into a multilayer perceptron to obtain an incidence relation among faults in the training set, and training the fault trend analysis model according to the incidence relation.
The initial knowledge characterization vector of each node may be a random initialization vector, and the initial state characterization vector of each node may be a zero vector.
The vehicles involved in the training set include vehicles of the same type. The nodes of the graph structure are used to represent faults (see the fault example in table 1 above), and the edges are used to represent the association between the nodes.
In the embodiment of the invention, the fault prediction is realized by collecting a large amount of fault sample data, searching the relation among the faults by using a big data method, deducing and establishing the causal relationship among the discrete faults.
Optionally, the health management subsystem 103 may specifically perform health status evaluation on the electronic subsystem according to the following manners:
determining the influence weight of each data item in the health data, the maintenance information and the repair information on the health of the electronic subsystem by using a grey correlation analysis method, and then determining the current health state value of the electronic subsystem according to the determined influence weight.
Specifically, the influence weight may be determined by:
the health data, the maintenance information, and the repair information are obtained multiple times, specifically, the health data before each maintenance and repair, the maintenance information during the maintenance, and the repair information during the repair can be obtained respectively, and an observation matrix a is obtained:
wherein T represents the tth time, T is 1, 2, …, T, ft(1)，ft(2)，……，ft(B) B data items (including health data, maintenance information, and repair information) representing the t-th acquisition;
carrying out dimensionless processing on the observation matrix A to obtain the observation matrix A1：
Let an observation matrix A1The first column vector is an observation vector, the other column vectors are comparison vectors, the correlation coefficient of each sub-item in each comparison vector is obtained through calculation, and a correlation coefficient matrix G is formed:
b'＝2,3,......,B
the degree of association between each two data (health data, maintenance information, and repair information) items is calculated:
b1，b21, 21≠b2
Thereby obtaining a correlation matrix G' between each data item:
because the relevance matrix G ' is a non-negative symmetric matrix, according to the property of the non-negative symmetric matrix, the relevance matrix G ' has the maximum module characteristic value and is represented by a symbol lambda, so that lambda C is equal to G ' C, and C is a characteristic vector; obtaining the eigenvalue and eigenvector of the correlation matrix G' by using an extraction tool of the eigenvalue and eigenvector of the nonnegative symmetric matrix, representing the eigenvector corresponding to the maximum modulus eigenvalue lambda by a symbol W, wherein W belongs to C, and W is [ omega ]1,ω2,…,ωB]T，ω1,ω2,…,ωBRepresenting the weight of influence of each data item.
The health score may be performed for each of the health data, the maintenance information, and the repair information when the health status value is calculated according to the influence weight, and then the health status value may be calculated based on the health score and the influence weight.
Example 2
The embodiment provides a distributed vehicle-mounted health management method, as shown in fig. 3, including the following steps:
s1: acquiring health data of a vehicle electronic subsystem acquired by a sensor and vehicle maintenance information and repair information input by related personnel and received by input equipment;
s2: and managing the health state of the electronic subsystem according to the health data, the maintenance information and the repair information, wherein the management of the health state of the electronic subsystem comprises health state monitoring, state evaluation, fault diagnosis, fault trend analysis and/or fault grading management.
The distributed vehicle-mounted health management method provided by the embodiment of the invention can realize the health state monitoring, state evaluation, fault diagnosis, fault trend analysis and/or fault grading management of each electronic subsystem on the vehicle, and the health management is real-time and automatic, so that the detection is uninterrupted, the vehicle health state is monitored in real time, and the vehicle safety is ensured while the labor cost is reduced. The failure trend analysis can realize early failure warning, and avoid the accident caused by the accident that the failure suddenly affects the use of the vehicle.
Optionally, after managing the health status of the electronic subsystem according to the health data, the maintenance information, and the repair information, the method further includes:
and controlling corresponding terminals to display at least part of the health data, the health state management result and/or alarm information determined according to the health state management result of the vehicle, wherein the terminals comprise terminals of passengers, terminals of users and/or terminals of maintenance personnel.
Optionally, the managing the health status of the electronic subsystem includes:
predicting future probable faults from the vehicle history and/or current faults using a fault trend analysis model; wherein the content of the first and second substances,
the training data of the fault trend analysis model is obtained by clustering historical fault data of each sample vehicle respectively, and the sample vehicles are the vehicles of the same type.
Optionally, the using the failure trend analysis model to predict a future possible failure according to the vehicle history and/or the current failure further includes:
for historical fault data of each sample vehicle, sequentially determining the clustering degree between each fault and the first fault from the second fault until the fault of which the clustering degree is greater than a preset value is obtained; the historical fault data includes a time of occurrence of each fault;
taking the fault with the clustering degree between the first fault and the preset value as a first target fault, and adding the first target fault and the first fault into a first fault group;
sequentially acquiring the clustering degrees between the faults after the first target fault and the faults in the first fault group until the faults with the clustering degrees larger than the preset value are acquired, and adding the faults with the clustering degrees larger than the preset value in the first fault group as the first target faults into the first fault group;
repeating the previous step until the last fault in the historical fault data;
as for the fault which is not added with the first fault group in the historical fault data, fault grouping is carried out according to the steps, the historical fault data corresponding to the obtained fault group is used as the training data, and the fault group comprises the first fault group;
training the fault trend analysis model using the training data.
The present embodiment has the same inventive concept as the embodiment 1, and please refer to the embodiment 1 in detail, which is not described herein again.
It should be understood that the above examples are only for clarity of illustration and are not intended to limit the embodiments. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. And obvious variations or modifications therefrom are within the scope of the invention.
Claims (10)
1. A distributed vehicle health management system, comprising:
a plurality of sensors, input devices, and a plurality of health management subsystems;
the sensor is used for collecting health data of each electronic subsystem on the vehicle and transmitting the health data to the corresponding health management subsystem;
the input equipment is used for receiving vehicle maintenance information and repair information input by related personnel;
each health management subsystem is used for managing the health states of different electronic subsystems according to the health data, the maintenance information and the repair information acquired by the corresponding sensors, and the management of the health states of the electronic subsystems comprises health state monitoring, state evaluation, fault diagnosis, fault trend analysis and/or fault grading management.
2. The system of claim 1, wherein the health management subsystem is further configured to control the corresponding terminal to display at least a part of the health data, the health status management result, and/or the warning information determined according to the health status management result of the vehicle, and the terminal comprises a terminal of an occupant, a terminal of a user, and/or a terminal of a maintenance person.
3. The system of claim 1, wherein a plurality of said health management subsystems comprise: the system comprises a task health management subsystem, an operation health management subsystem and a chassis health management subsystem;
the task health management subsystem is used for managing the health state of a task subsystem in the electronic subsystem;
the operation health management subsystem is used for managing the health state of an operation subsystem in the electronic subsystem;
the chassis health management subsystem is used for managing the health state of the chassis subsystems in the electronic subsystems.
4. The system of claim 1, wherein the health management subsystem is further configured to match a fault with a fault pattern in a fault pattern library, determine a fault cause according to the matched fault pattern, and perform fault handling or push a fault handling method to a terminal of a maintenance worker, where each fault pattern includes a fault, a fault cause, and a fault handling method.
5. The system of claim 1, wherein the health management subsystem performs fault trend analysis using a fault trend analysis model for predicting future possible faults based on historical and/or current faults of the vehicle, the training data of the fault trend analysis model being obtained by clustering historical fault data of each sample vehicle, the sample vehicles being vehicles of the same type as the vehicle.
6. The system of claim 5, wherein the training data is obtained by:
for historical fault data of each sample vehicle, sequentially determining the clustering degree between each fault and the first fault from the second fault until the fault of which the clustering degree is greater than a preset value is obtained; the historical fault data includes a time of occurrence of each fault;
taking the fault with the clustering degree between the first fault and the preset value as a first target fault, and adding the first target fault and the first fault into a first fault group;
sequentially acquiring the clustering degrees between the faults after the first target fault and the faults in the first fault group until the faults with the clustering degrees larger than the preset value are acquired, and adding the faults with the clustering degrees larger than the preset value in the first fault group as the first target faults into the first fault group;
repeating the previous step until the last fault in the historical fault data;
and for the fault which is not added with the first fault group in the historical fault data, carrying out fault grouping according to the steps, and taking the historical fault data corresponding to the obtained fault group as the training data, wherein the fault group comprises the first fault group.
7. A distributed vehicle-mounted health management method is characterized by comprising the following steps:
acquiring health data of a vehicle electronic subsystem acquired by a sensor and vehicle maintenance information and repair information input by related personnel and received by input equipment;
and managing the health state of the electronic subsystem according to the health data, the maintenance information and the repair information, wherein the management of the health state of the electronic subsystem comprises health state monitoring, state evaluation, fault diagnosis, fault trend analysis and/or fault grading management.
8. The method of claim 7, further comprising, after managing the health status of the electronic subsystem based on the health data and the maintenance information and the repair information:
and controlling corresponding terminals to display at least part of the health data, the health state management result and/or alarm information determined according to the health state management result of the vehicle, wherein the terminals comprise terminals of passengers, terminals of users and/or terminals of maintenance personnel.
9. The method of claim 7, wherein said managing the health of said electronic subsystem comprises:
predicting future probable faults from the vehicle history and/or current faults using a fault trend analysis model; wherein the content of the first and second substances,
the training data of the fault trend analysis model is obtained by clustering historical fault data of each sample vehicle respectively, and the sample vehicles are the vehicles of the same type.
10. The method of claim 9, wherein using the fault trend analysis model to predict future probable faults based on the vehicle history and/or current faults further comprises:
for historical fault data of each sample vehicle, sequentially determining the clustering degree between each fault and the first fault from the second fault until the fault of which the clustering degree is greater than a preset value is obtained; the historical fault data includes a time of occurrence of each fault;
taking the fault with the clustering degree between the first fault and the preset value as a first target fault, and adding the first target fault and the first fault into a first fault group;
sequentially acquiring the clustering degrees between the faults after the first target fault and the faults in the first fault group until the faults with the clustering degrees larger than the preset value are acquired, and adding the faults with the clustering degrees larger than the preset value in the first fault group as the first target faults into the first fault group;
repeating the previous step until the last fault in the historical fault data;
as for the fault which is not added with the first fault group in the historical fault data, fault grouping is carried out according to the steps, the historical fault data corresponding to the obtained fault group is used as the training data, and the fault group comprises the first fault group;
training the fault trend analysis model using the training data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111570496.2A CN114239734B (en) | 2021-12-21 | 2021-12-21 | Distributed vehicle-mounted health management system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111570496.2A CN114239734B (en) | 2021-12-21 | 2021-12-21 | Distributed vehicle-mounted health management system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114239734A true CN114239734A (en) | 2022-03-25 |
| CN114239734B CN114239734B (en) | 2023-09-12 |
Family
ID=80760147
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111570496.2A Active CN114239734B (en) | 2021-12-21 | 2021-12-21 | Distributed vehicle-mounted health management system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114239734B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115203001A (en) * | 2022-09-09 | 2022-10-18 | 中国电子科技集团公司第十五研究所 | Equipment health management method and system |
| CN115214700A (en) * | 2022-05-26 | 2022-10-21 | 广州汽车集团股份有限公司 | Vehicle health management method and system |
| CN117671818A (en) * | 2024-02-01 | 2024-03-08 | 新汽有限公司 | Management system for vehicle data |
| CN117671818B (en) * | 2024-02-01 | 2024-04-16 | 新汽有限公司 | Management system for vehicle data |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110172874A1 (en) * | 2010-01-13 | 2011-07-14 | Gm Global Technology Operations, Inv. | Fault prediction framework using temporal data mining |
| US20140244552A1 (en) * | 2013-02-28 | 2014-08-28 | University Of Southern California | Global model for failure prediction for artificial lift systems |
| CN105548764A (en) * | 2015-12-29 | 2016-05-04 | 山东鲁能软件技术有限公司 | Electric power equipment fault diagnosis method |
| CN107579846A (en) * | 2017-08-23 | 2018-01-12 | 昆明理工大学 | A kind of cloud computing fault data detection method and system |
| CN109421466A (en) * | 2017-09-04 | 2019-03-05 | 武汉德朗高科汽车电气有限公司 | Air-conditioning health monitoring systems and monitoring method for electric motor coach |
| EP3489912A1 (en) * | 2017-11-28 | 2019-05-29 | The Boeing Company | Apparatus and method for vehicle maintenance scheduling and fault monitoring |
| CN109902153A (en) * | 2019-04-02 | 2019-06-18 | 杭州安脉盛智能技术有限公司 | Equipment fault diagnosis method and system based on natural language processing and reasoning by cases |
| CN111240300A (en) * | 2020-01-07 | 2020-06-05 | 国电南瑞科技股份有限公司 | Vehicle health state evaluation model construction method based on big data |
| CN113379390A (en) * | 2021-06-23 | 2021-09-10 | 沈阳顺义科技有限公司 | War chariot team health management device |
| CN113704075A (en) * | 2021-09-23 | 2021-11-26 | 中国人民解放军国防科技大学 | Fault log-based high-performance computing system fault prediction method |
-
2021
- 2021-12-21 CN CN202111570496.2A patent/CN114239734B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110172874A1 (en) * | 2010-01-13 | 2011-07-14 | Gm Global Technology Operations, Inv. | Fault prediction framework using temporal data mining |
| US20140244552A1 (en) * | 2013-02-28 | 2014-08-28 | University Of Southern California | Global model for failure prediction for artificial lift systems |
| CN105548764A (en) * | 2015-12-29 | 2016-05-04 | 山东鲁能软件技术有限公司 | Electric power equipment fault diagnosis method |
| CN107579846A (en) * | 2017-08-23 | 2018-01-12 | 昆明理工大学 | A kind of cloud computing fault data detection method and system |
| CN109421466A (en) * | 2017-09-04 | 2019-03-05 | 武汉德朗高科汽车电气有限公司 | Air-conditioning health monitoring systems and monitoring method for electric motor coach |
| EP3489912A1 (en) * | 2017-11-28 | 2019-05-29 | The Boeing Company | Apparatus and method for vehicle maintenance scheduling and fault monitoring |
| CN109902153A (en) * | 2019-04-02 | 2019-06-18 | 杭州安脉盛智能技术有限公司 | Equipment fault diagnosis method and system based on natural language processing and reasoning by cases |
| CN111240300A (en) * | 2020-01-07 | 2020-06-05 | 国电南瑞科技股份有限公司 | Vehicle health state evaluation model construction method based on big data |
| CN113379390A (en) * | 2021-06-23 | 2021-09-10 | 沈阳顺义科技有限公司 | War chariot team health management device |
| CN113704075A (en) * | 2021-09-23 | 2021-11-26 | 中国人民解放军国防科技大学 | Fault log-based high-performance computing system fault prediction method |
Non-Patent Citations (3)
| Title |
|---|
| GUANG WANG、SHEN YIN: "Data-driven fault diagnosis for an automobile suspension system by using a clustering based method", 《JOURNAL OF THE FRANKLIN INSTITUTE》, pages 3231 - 3244 * |
| XIAOJIAN YI 等: "A Survey on Prognostic and Health Management for Special Vehicles", 《2018 PROGNOSTICS AND SYSTEM HEALTH MANAGEMENT CONFERENCE》, pages 201 - 208 * |
| 刘孔林、唐先兵: "矿用百吨级蓄电池铲板车研发", 《煤炭科学技术》, vol. 47, no. 2, pages 92 - 96 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115214700A (en) * | 2022-05-26 | 2022-10-21 | 广州汽车集团股份有限公司 | Vehicle health management method and system |
| CN115203001A (en) * | 2022-09-09 | 2022-10-18 | 中国电子科技集团公司第十五研究所 | Equipment health management method and system |
| CN117671818A (en) * | 2024-02-01 | 2024-03-08 | 新汽有限公司 | Management system for vehicle data |
| CN117671818B (en) * | 2024-02-01 | 2024-04-16 | 新汽有限公司 | Management system for vehicle data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114239734B (en) | 2023-09-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114239734B (en) | Distributed vehicle-mounted health management system | |
| CN113011530B (en) | Intelligent ammeter fault prediction method based on multi-classifier fusion | |
| JP2004531815A (en) | Diagnostic system and method for predictive condition monitoring | |
| CN112286771B (en) | Alarm method for monitoring global resources | |
| CN111143173A (en) | Server fault monitoring method and system based on neural network | |
| WO2011073613A1 (en) | A method, apparatus and computer program for diagnosing a mode of operation of a machine | |
| CN109809149B (en) | Fault early warning system and method for industrial production equipment | |
| EP3553044A1 (en) | System and method of remote object monitoring | |
| CN113762329A (en) | Method and system for constructing state prediction model of large rolling mill | |
| CN112906764B (en) | Communication safety equipment intelligent diagnosis method and system based on improved BP neural network | |
| CN110633905A (en) | Reliability calculation method for cloud platform of intelligent vehicle | |
| CN112083244A (en) | Integrated avionics equipment fault intelligent diagnosis system | |
| WO2019209146A1 (en) | Method and system for identifying and forecasting the development of faults in equipment | |
| CN113760670A (en) | Cable joint abnormity early warning method and device, electronic equipment and storage medium | |
| CN111506048A (en) | Vehicle fault early warning method and related equipment | |
| CN115037603A (en) | Diagnosis evaluation method, device and system of electricity consumption information acquisition equipment | |
| KR102516227B1 (en) | A system for predicting equipment failure in ship and a method of predicting thereof | |
| CN113919207A (en) | Top-level open type electrical intelligent health monitoring and management system | |
| CN113297033A (en) | Vehicle electric control system health assessment method and system based on cloud monitoring data | |
| CN111579001A (en) | Fault detection method and device for robot | |
| CN111965609A (en) | Radar reliability evaluation method and device, electronic equipment and readable storage medium | |
| CN109558258B (en) | Method and device for positioning root fault of distributed system | |
| CN115599077B (en) | Vehicle fault delimiting method and device, electronic equipment and storage medium | |
| CN115902485A (en) | Resident electricity utilization fault detection method and system | |
| WO2022133825A1 (en) | Method and device for evaluating remaining useful life of element, functional module and system, 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 |