CN113485302B - Vehicle operation process fault diagnosis method and system based on multivariate time sequence data - Google Patents
Vehicle operation process fault diagnosis method and system based on multivariate time sequence data Download PDFInfo
- Publication number
- CN113485302B CN113485302B CN202110819532.8A CN202110819532A CN113485302B CN 113485302 B CN113485302 B CN 113485302B CN 202110819532 A CN202110819532 A CN 202110819532A CN 113485302 B CN113485302 B CN 113485302B
- Authority
- CN
- China
- Prior art keywords
- time sequence
- fault
- data
- sequence data
- multivariate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The utility model discloses a vehicle operation process fault diagnosis method and system based on multivariate time series data, including: acquiring running state information in the running process of a vehicle; time sequence division is carried out on each running state information to obtain multivariate time sequence data; extracting correlation characteristics of the multivariate time sequence data from the multivariate time sequence data; extracting time dependency characteristics from the dependency characteristics of the multivariate time series data; and inputting the multivariate time sequence data and the time dependency characteristics into a trained fault detection and diagnosis model to obtain a fault detection and diagnosis result. The fault detection and diagnosis of the vehicle running process are realized.
Description
Technical Field
The invention relates to the technical field of vehicle operation process fault detection, in particular to a vehicle operation process fault diagnosis method and system based on multivariate time sequence data.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The vehicle operation process fault detection and diagnosis is an important tool for reminding a vehicle owner of whether a vehicle has a fault or not and giving diagnosis information when the fault occurs. When the vehicle runs, the multivariate time sequence data sent back by the component sensor has some fault changes, and if the vehicle owner does not timely acquire the relevant information of the vehicle fault, partial loss of the vehicle or the whole running stagnation can be caused. Therefore, the vehicle fault detection device can accurately detect the fault of the vehicle in the running process of the vehicle and timely remind a vehicle owner, and can avoid larger loss. Meanwhile, the vehicle operation system is complex, and if fault related diagnosis information can be given while fault is found, important factors causing the fault can be found out, and very powerful help can be provided for a vehicle owner to check the fault and recover the normal operation of the vehicle as soon as possible.
The current methods for detecting and diagnosing faults in the running process of the vehicle are deficient. The time sequence data generated during the running of the vehicle has randomness, characteristic rules are difficult to obtain, complex incidence relation exists among the time sequence data, the problem of unbalance of positive and negative samples exists, in addition, the running fault types of the vehicle are various, the generation of the faults can be the result of single component action or the combined action of a plurality of components, and the fault reason is difficult to locate. The traditional mode based on manual work and a fault alarm device has the problems of low efficiency, weak accuracy and difficulty in positioning fault reasons. Some fault detection based on the traditional machine learning algorithm needs data to meet a certain characteristic rule, and the commonly used fault detection algorithm based on classification is difficult to obtain higher precision under the condition of imbalance of positive and negative samples. Most of fault detection algorithms based on deep learning only consider the time dependency characteristics of single time sequence data, and ignore the mutual influence among multiple time sequence data. In addition, the existing algorithm judges data faults more and analyzes important factors influencing the fault generation less. Therefore, the existing method cannot effectively detect and diagnose the faults in the running process of the vehicle.
Disclosure of Invention
In order to solve the problems, the invention provides a vehicle operation process fault diagnosis method and system based on multivariate time sequence data, and fault detection and diagnosis in a vehicle operation process are realized.
In order to achieve the purpose, the following technical scheme is adopted in the disclosure:
in a first aspect, a vehicle operation process fault diagnosis method based on multivariate time series data is provided, which comprises the following steps:
acquiring running state information in the running process of a vehicle;
time sequence division is carried out on each running state information to obtain multivariate time sequence data;
extracting the correlation characteristics of the multivariate time sequence data from the multivariate time sequence data;
extracting time dependency characteristics from the dependency characteristics of the multivariate time series data;
and inputting the multivariate time sequence data and the time dependency characteristics into a trained fault detection and diagnosis model to obtain a fault detection and diagnosis result.
In a second aspect, a vehicle operation process fault diagnosis system based on multivariate time series data is provided, which comprises:
the data acquisition module is used for acquiring running state information in the running process of the vehicle;
the time sequence dividing module is used for carrying out time sequence division on each running state information to obtain multivariate time sequence data;
the correlation characteristic extraction module is used for extracting correlation characteristics of the multivariate time sequence data from the multivariate time sequence data;
the time dependency characteristic extraction module is used for extracting time dependency characteristics from the correlation characteristics of the multi-element time sequence data;
and the fault detection and diagnosis module is used for inputting the multivariate time sequence data and the time dependency characteristics into the trained fault detection and diagnosis model to obtain a fault detection and diagnosis result.
In a third aspect, an electronic device is provided, which includes a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of the method for diagnosing faults in a vehicle operation process based on multivariate time series data.
In a fourth aspect, a computer-readable storage medium is provided for storing computer instructions, which when executed by a processor, perform the steps of the method for diagnosing vehicle operation process faults based on multivariate time series data.
Compared with the prior art, the beneficial effect of this disclosure is:
1. the method and the device can be used for analyzing the multivariate time sequence data acquired by each sensor on the vehicle, and further realizing the diagnosis of the fault on the basis of detecting the fault in the running process of the vehicle.
2. When fault detection and diagnosis are carried out on the vehicle running process, firstly, the correlation characteristics of the multi-element time sequence data are extracted from the multi-element time sequence data, then, the time dependency characteristics are obtained from the correlation characteristics of the multi-element time sequence data, the time dependency characteristics not only comprise the time dependency characteristics of single time sequence data, but also comprise the correlation characteristics among the multi-element time sequence data, and the fault detection and diagnosis are carried out on the vehicle running process through the time dependency characteristics, so that the accuracy of the fault detection and diagnosis is improved.
Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the application and, together with the description, serve to explain the application and are not intended to limit the application.
FIG. 1 is a flow chart of a method disclosed in example 1 of the present disclosure;
FIG. 2 is a diagram of a model framework disclosed in example 1 of the present disclosure;
FIG. 3 is a graph of correlation characteristic extraction of multivariate timing data disclosed in embodiment 1 of the present disclosure;
FIG. 4 is a graph of time-dependent feature extraction disclosed in example 1 of the present disclosure;
fig. 5 is a schematic diagram of fault detection and diagnosis disclosed in embodiment 1 of the present disclosure.
The specific implementation mode is as follows:
the present disclosure is further described with reference to the following drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
In the present disclosure, terms such as "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "side", "bottom", and the like indicate orientations or positional relationships based on orientations or positional relationships shown in the drawings, are only terms of relationships determined for convenience in describing structural relationships of the components or elements of the present disclosure, do not refer to any components or elements of the present disclosure, and are not to be construed as limiting the present disclosure.
In the present disclosure, terms such as "fixedly connected", "connected", and the like are to be understood in a broad sense, and mean either a fixed connection or an integrally connected or detachable connection; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present disclosure can be determined on a case-by-case basis by a person skilled in the art and should not be construed as limiting the present disclosure.
Example 1
In order to realize the detection and diagnosis of the vehicle operation process fault, the embodiment discloses a vehicle operation process fault diagnosis method based on multivariate time series data, which comprises the following steps:
acquiring running state information in the running process of a vehicle;
time sequence division is carried out on each running state information to obtain multivariate time sequence data;
extracting correlation characteristics of the multivariate time sequence data from the multivariate time sequence data;
extracting time dependency characteristics from the dependency characteristics of the multivariate time series data;
and inputting the multivariate time sequence data and the time dependency characteristics into a trained fault detection and diagnosis model to obtain a fault detection and diagnosis result.
Further, the running state information includes an engine coolant temperature, an engine speed, atmospheric pressure, an engine voltage, an engine torque, an accelerator pedal opening, a vehicle speed, and a fuel consumption rate.
Furthermore, before time sequence division is carried out on each operation state information, normalization is carried out on each operation state information.
Further, the multivariate time sequence data is input into the trained CNN network model, and the correlation characteristics of the multivariate time sequence data are obtained.
Further, a Transformer Encoder module is used for extracting time-dependent characteristics from the correlation characteristics of the multivariate time series data.
Further, the fault detection and diagnosis model employs a generative countermeasure network.
Further, the generation of the countermeasure network comprises a generator and a discriminator; inputting the multivariate time sequence data and the time-dependent characteristics into a generator to obtain a reconstruction sequence and a reconstruction error; inputting the reconstructed sequence and the multivariate time sequence data into a discriminator to obtain a discrimination score; obtaining a fault score by using the discrimination score and the reconstruction error; judging whether the multivariate time sequence is fault data or not according to the fault score; and diagnosing the fault according to the change before and after the reconstruction of each operation state information in the multi-element time sequence data of the data judged to be the fault.
The method for detecting the vehicle operation process fault based on the multivariate time series data disclosed in the embodiment is described in detail with reference to fig. 1-5.
The method for detecting the vehicle running process fault based on the multivariate time sequence data realizes the detection and diagnosis of the vehicle running process fault by analyzing the obtained multivariate time sequence data, as shown in fig. 1 and 2, and mainly comprises the following steps: acquiring multivariate time sequence data, extracting correlation characteristics of the multivariate time sequence data, extracting time dependence characteristics and detecting and diagnosing faults.
The acquisition process of the multivariate time sequence data comprises the following steps:
the method comprises the steps of obtaining running state information in the running process of the vehicle, wherein the running state information is detected by various sensors in the vehicle, comprises the temperature of engine coolant, the rotating speed of an engine, the atmospheric pressure, the voltage of the engine, the torque of the engine, the opening degree of an accelerator pedal, the speed of the vehicle, the consumption rate of fuel and the like, and is time sequence data.
In specific implementation, the operation state information can be changed in an increasing and decreasing mode according to actual requirements of fault detection and diagnosis.
Because the dimensions of the numerical values obtained by the sensors of different parts are different, the running state information obtained by the different sensors in the running process of the vehicle is normalized, so that the information obtained by all the sensors has the same scale.
For a certain sequence of vehicle operating state information { x1,x2,…,xNThe formula for normalizing the running state information is as follows:
the method comprises the following steps of performing time sequence division on running state information by utilizing a sliding window to obtain multivariate time sequence data, and specifically comprises the following steps:
the operating state information transmitted back by the various component sensors during operation of the vehicle contains successive observations that are typically collected at equidistant time stamps.
Defining the multivariate timing data as:
X＝{x1，x2，…，xN}
where N is the length of x and from 1 to N each represents a time instant.
Defining the observed values at time t as:
xtis an M-dimensional vector, each dimension of the vector representing a component sensor, where t is less than or equal to N, and x is equal to RN×M。
The sliding window selects time sequence data for a specified unit length, the time sequence data is compared with a graduated scale, the sliding window is equivalent to a sliding block with a fixed length and slides on the graduated scale, and the data in the sliding block is selected when the sliding window slides one unit. Using xt-T：t(∈R(T+1)×M) The observed value of the sliding window defining the unit from time T-T to time T, i.e. T +1, is:
{xt-T，xt-T+1，…，xt}
the time sequence matrix is obtained by expanding the time sequence matrix, and can be represented as:
the extraction process of the correlation characteristics of the multivariate time series data comprises the following steps: and extracting the correlation characteristics of the multivariate time sequence data from the multivariate time sequence data by using the CNN network.
Adopting a CNN network, and checking the collection of local information by means of convolution in the CNN to extract the correlation characteristics of the multivariate time series data, as shown in FIG. 3. The vehicle running process data has complex correlation among the running state information, for example, the opening of an accelerator pedal influences the vehicle speed, and the speed has correlation with the engine speed, the fuel injection quantity, the fuel consumption rate and the like, so that the correlation characteristics among the running state information need to be extracted, namely, the correlation characteristics among the dimensions of the multivariate time sequence data X are extracted.
Each convolution layer in the CNN consists of a plurality of convolution units, and the parameters of each convolution unit are obtained by optimization of a back propagation algorithm. By providing a plurality of filters, different convolution units are used as different weight matrixes to perform convolution operation on data (the corresponding elements of the tensors with the same specification are multiplied and then added to obtain a new tensor). The convolution operation aims at capturing local and detail information, extracting correlation characteristics among different dimensions of input data by using different weight matrixes, and finally combining and outputting a new characteristic matrix zcThe feature matrix zcThe correlation characteristics of the obtained multivariate time series data are obtained.
The CNN network adopts a one-dimensional convolution layer and takes a Linear rectification function (ReLU) as an activation function, the result of the convolution layer is subjected to nonlinear mapping, and compared with the traditional sigmoid activation function, the ReLU can effectively relieve the problem of gradient disappearance. The ReLU function is a very simple function, with the output being zero when the input is less than zero, otherwise the output is equal to the input. ReLU function expression:
the specific process of extracting the time dependency characteristics from the relevance characteristics of the multivariate time series data is as follows: and extracting time-dependent characteristics from the correlation characteristics of the multivariate time series data through a Transformer Encoder module.
The running state information acquired in the running process of the vehicle is data sampled according to a time sequence, and a plurality of hidden information of the data is contained in a time dimension. If at a certain moment a certain operating state information is changed, for example the driver suddenly increases the opening of the accelerator pedal, at a later moment other operating state information related to the opening of the accelerator pedal, such as speed, engine speed, specific fuel consumption etc. will be changed. Therefore, the change information of each operation state information can be obtained by extracting the time dependency characteristics of each operation state information. The time dependency feature extraction of the time sequence data is realized by selecting multiple layers of transform encoders, wherein the specific structure of the transform encoders is shown in fig. 4. The specific process is as follows:
correlation feature matrix z for multi-element time sequence data extracted from multi-element time sequence datacPosition coding is carried out to obtain a coded feature matrix znThe feature matrix z after encodingnAs an input of the Encoder, the position of each vector in the sequence and the distance between different vectors can be determined, and meanwhile, the parameters of the model needing to be learned are less, and the model training is faster.
Coded feature matrix z to be added with position-coded informationnThe output is directly used as the input of the next Encoder to be calculated and continuously carried out until the output of the last Encoder is the final output, thereby realizing the characteristic of time dependencyThe extraction of (1). The Encoder is mainly composed of two parts: the first part is the Self-Attention mechanism (Self-Attention) and the second part is the feedforward neural network. Residual connections are designed among sub-layers inside the unit, and the connections can ensure that information of the previous layer is completely transmitted to the next layer. The self-attention mechanism is the most important component in the Transformer Encoder. The self-attention mechanism is improved by the attention mechanism, dependence on external information can be reduced, and internal correlation characteristics of captured data are enhanced. The self-attention mechanism can ensure that each position vector in the sequence can fuse the related information of the position vectors before and after the position vector.
Firstly, three weight matrixes W are constructedq,Wk,WvThe three matrices are obtained by model training, from which are calculated:
Q＝znWq
K＝znWk
V＝znWv
and (3) calculating according to the obtained Q, K and V matrixes:
wherein d iskThe final output of the self-attention mechanism is obtained for the dimension of K, and therefore the extraction of the time-dependent features is achieved.
And inputting the multivariate time sequence data and the time dependency characteristics into a trained fault detection and diagnosis model to obtain a fault detection and diagnosis result.
In particular implementations, the fault detection and diagnosis model employs a generator countermeasure network (GAN), and the GNA includes a generator and an arbiter.
The generation countermeasure network comprises a generator (G) and a discriminator (D); inputting the multivariate time sequence data and the time-dependent characteristics into a generator to obtain a reconstruction sequence and a reconstruction error; inputting the reconstructed sequence and the multivariate time sequence data into a discriminator to obtain a discrimination score; obtaining a fault score by using the discrimination score and the reconstruction error; judging whether the multivariate time sequence is fault data or not according to the fault score; and diagnosing the fault according to the change before and after the reconstruction of each operation state information in the multivariate time sequence of the fault data. As shown in fig. 5, the specific process is as follows:
(1) the reconstruction error is obtained using a GAN generator.
The generator aims to generate a true sample x by learning the feature distribution of the true datat-T∶tThe reconstruction sequence g (z) is as similar as possible, so that the discriminator cannot distinguish between real and reconstructed samples.
Extracting a time dependency characteristic matrix of the multivariate time sequence data:
input to the generator, output reconstruction sequence g (z):
calculating a reconstruction error dGThe process comprises the following steps:
squaring each element in the matrix obtained by x-G (z) to obtain a matrix N:
then, taking the matrix N as a unit, adding all elements and then averaging to obtain:
Nt-T∶t＝[n1，n2，…，nM]
finally, to matrix Nt-T∶tAdding each element and averaging to obtain a reconstruction error dG。
(2) And obtaining a discrimination score by using a GAN discriminator.
The object of the discriminator is to discriminate the multivariate timing data x in which the input data is truet-T∶tOr the reconstructed sequence g (z) of the generator. In an ideal case, the output of D is 1 if the input data is multivariate time series data, and 0 if the input data is the reconstructed sequence g (z) of the generator. Directly outputting the discriminator to obtain a discrimination score dDAs output of the discriminator, dDLarger values indicate that the data is more likely to be real data, dDSmaller values indicate that the data is more likely to be reconstructed data.
(3) And obtaining a fault score by using the reconstruction error and the discrimination score, and judging the sequence exceeding a threshold value as normal data, otherwise, judging the sequence as fault data.
Output value d of the discriminatorDReconstruction error d of and generatorGIs taken as a fault score dscore：
dscore＝dD-dG
Failure score calculated by selecting training stage
Is the threshold th, then in the test phase, a determination is made as to whether the data is fault data:
where 0 represents fault data and 1 represents normal data.
(4) And diagnosing the fault by comparing the change values of all dimensions before and after data reconstruction of the multivariate time sequence data which is judged as fault data, wherein the change value of all dimensions is the change value of all running state information.
By calculating a fault score dscoreA basis for fault detection may be provided. If fault data is input in the test stage, a larger reconstruction error d is obtainedGThe fault is generated by each component sensorI.e. the individual operating state information influences together. Thus, the N obtained during the calculation of the reconstruction error can be usedt-T∶tAnd the matrix can obtain the change of each running state information before and after reconstruction, and if the change of the running state information before and after reconstruction is large, the running state information has a large influence on the fault. Based on the above, the change of each running state information before and after reconstruction is used as the basis of fault diagnosis, and the dimension of the change exceeding the set value before and after reconstruction is used as an important factor influencing fault generation, so that the fault is diagnosed.
According to the fault diagnosis method disclosed by the embodiment, the detection and diagnosis of the fault in the vehicle running process are realized by analyzing the multivariate time sequence data acquired by each sensor on the vehicle, and when the fault detection and diagnosis are performed in the vehicle running process, firstly, the correlation characteristics of the multivariate time sequence data are extracted from the multivariate time sequence data, and then, the time dependency characteristics are acquired from the correlation characteristics of the multivariate time sequence data, wherein the time dependency characteristics not only comprise the time dependency characteristics of single time sequence data, but also comprise the correlation characteristics among the multivariate time sequence data, and the fault detection and diagnosis in the vehicle running process are performed through the time dependency characteristics, so that the accuracy of the fault detection and diagnosis is improved.
Example 2
In this embodiment, a vehicle operation process fault diagnosis system based on multivariate time series data is disclosed, comprising:
the data acquisition module is used for acquiring running state information in the running process of the vehicle;
the time sequence dividing module is used for carrying out time sequence division on each running state information to obtain multivariate time sequence data;
the correlation characteristic extraction module is used for extracting correlation characteristics of the multi-element time sequence data from the multi-element time sequence data;
the time dependency characteristic extraction module is used for extracting time dependency characteristics from the correlation characteristics of the multi-element time sequence data;
and the fault detection and diagnosis module is used for inputting the multivariate time sequence data and the time dependency characteristics into the trained fault detection and diagnosis model to obtain a fault detection and diagnosis result.
Example 3
In this embodiment, an electronic device is disclosed, which comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of the method for diagnosing faults in a vehicle operation process based on multivariate time series data disclosed in embodiment 1.
Example 4
In this embodiment, a computer readable storage medium is disclosed for storing computer instructions which, when executed by a processor, perform the steps of the multivariate time series data based vehicle operation process fault diagnosis method disclosed in embodiment 1.
The above description is only a preferred embodiment of the present application and is not intended to limit the present application, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the present application shall be included in the protection scope of the present application.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting the same, and although the present invention is described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications and equivalents may be made to the embodiments of the invention without departing from the spirit and scope of the invention, which is to be covered by the claims.
Claims (6)
1. The vehicle operation process fault diagnosis method based on the multivariate time series data is characterized by comprising the following steps of:
acquiring running state information in the running process of a vehicle;
time sequence division is carried out on each running state information to obtain multivariate time sequence data;
inputting the multivariate time sequence data into a trained CNN network model to obtain the correlation characteristics of the multivariate time sequence data;
extracting time dependency characteristics from the correlation characteristics of the multivariate time sequence data by using a Transformer Encoder module;
inputting the multivariate time sequence data and the time dependency characteristics into a trained fault detection and diagnosis model to obtain a fault detection and diagnosis result;
wherein, the fault detection and diagnosis model adopts a generation countermeasure network; the generation countermeasure network comprises a generator and an arbiter; inputting the multivariate time sequence data and the time-dependent characteristics into a generator to obtain a reconstruction sequence and a reconstruction error; inputting the reconstructed sequence and the multivariate time sequence data into a discriminator to obtain a discrimination score; obtaining a fault score by using the discrimination score and the reconstruction error; judging whether the multivariate time sequence is fault data or not according to the fault score; and diagnosing the fault according to the change before and after the reconstruction of each operation state information in the multi-element time sequence data of the fault data.
2. The method of claim 1, wherein the operating condition information includes an engine coolant temperature, an engine speed, a barometric pressure, an engine voltage, an engine torque, an accelerator pedal opening, a vehicle speed, and a fuel consumption rate.
3. The multivariate time series data-based vehicle operational process fault diagnosis method as defined in claim 1, wherein the operational state information is normalized before time-series division of the operational state information.
4. Vehicle operation process fault diagnosis system based on many units time series data, its characterized in that includes:
the data acquisition module is used for acquiring running state information in the running process of the vehicle;
the time sequence dividing module is used for carrying out time sequence division on each running state information to obtain multivariate time sequence data;
the correlation characteristic extraction module is used for inputting the multivariate time sequence data into the trained CNN network model to obtain the correlation characteristics of the multivariate time sequence data;
the time dependency characteristic extraction module is used for extracting time dependency characteristics from the correlation characteristics of the multivariate time sequence data by using the Transformer Encoder module; wherein, the fault detection and diagnosis model adopts a generation countermeasure network; the generation countermeasure network comprises a generator and an arbiter; inputting the multivariate time sequence data and the time-dependent characteristics into a generator to obtain a reconstruction sequence and a reconstruction error; inputting the reconstructed sequence and the multivariate time sequence data into a discriminator to obtain a discrimination score; obtaining a fault score by using the discrimination score and the reconstruction error; judging whether the multivariate time sequence is fault data or not according to the fault score; diagnosing the fault according to the change before and after the reconstruction of each operation state information in the multi-element time sequence data which is judged as fault data;
and the fault detection and diagnosis module is used for inputting the multivariate time sequence data and the time dependency characteristics into the trained fault detection and diagnosis model to obtain a fault detection and diagnosis result.
5. An electronic device comprising a memory and a processor and computer instructions stored in the memory and executed on the processor, wherein the computer instructions, when executed by the processor, perform the steps of the multivariate time series data based vehicle operation process fault diagnosis method as claimed in any one of claims 1-3.
6. A computer readable storage medium storing computer instructions which, when executed by a processor, perform the steps of the multivariate sequential data based vehicle operation process fault diagnosis method as claimed in any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110819532.8A CN113485302B (en) | 2021-07-20 | 2021-07-20 | Vehicle operation process fault diagnosis method and system based on multivariate time sequence data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110819532.8A CN113485302B (en) | 2021-07-20 | 2021-07-20 | Vehicle operation process fault diagnosis method and system based on multivariate time sequence data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113485302A CN113485302A (en) | 2021-10-08 |
| CN113485302B true CN113485302B (en) | 2022-06-21 |
Family
ID=77942507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110819532.8A Active CN113485302B (en) | 2021-07-20 | 2021-07-20 | Vehicle operation process fault diagnosis method and system based on multivariate time sequence data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113485302B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114264315B (en) * | 2021-11-24 | 2024-05-24 | 青岛迈金智能科技股份有限公司 | Parking judgment method based on barometer meter |
| CN114423035B (en) * | 2022-01-12 | 2023-09-19 | 北京宇卫科技有限公司 | Service function chain abnormality detection method in network slice scene |
| CN114611561B (en) * | 2022-03-29 | 2023-05-12 | 西门子交通技术(北京)有限公司 | Training method of fault prediction model, and train system fault prediction method and device |
| DE102022205885A1 (en) | 2022-06-09 | 2023-12-14 | Volkswagen Aktiengesellschaft | Method, computer program and device for processing time series data with an artificial neural network |
| CN115865751B (en) * | 2022-11-25 | 2024-05-14 | 南方电网数字平台科技(广东)有限公司 | Fault detection method and device based on polymorphic data |
| CN116110147A (en) * | 2023-04-12 | 2023-05-12 | 江西珉轩大数据有限公司 | Distributed time sequence data storage and aggregation analysis method |
| CN116361713B (en) * | 2023-04-19 | 2023-08-29 | 湖北交通职业技术学院 | Performance detection method and system for aircraft engine |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107703920A (en) * | 2017-10-25 | 2018-02-16 | 北京交通大学 | The fault detection method of train braking system based on multivariate time series |
| CN108491886A (en) * | 2018-03-29 | 2018-09-04 | 重庆大学 | A kind of sorting technique of the polynary time series data based on convolutional neural networks |
| CN110285976A (en) * | 2019-07-09 | 2019-09-27 | 哈尔滨工业大学（威海） | Multi-dimensional time sequence information based on DBN drives Fault Diagnosis of Aeroengines method |
| CN110674604A (en) * | 2019-09-20 | 2020-01-10 | 武汉大学 | Transformer DGA data prediction method based on multi-dimensional time sequence frame convolution LSTM |
| CN110702418A (en) * | 2019-10-10 | 2020-01-17 | 山东超越数控电子股份有限公司 | Aircraft engine fault prediction method |
| CN112461537A (en) * | 2020-10-16 | 2021-03-09 | 浙江工业大学 | Wind power gear box state monitoring method based on long-time neural network and automatic coding machine |
| CN112559598A (en) * | 2020-12-16 | 2021-03-26 | 南京航空航天大学 | Telemetry time series data abnormity detection method and system based on graph neural network |
| CN112712209A (en) * | 2020-12-31 | 2021-04-27 | 润联智慧科技(西安)有限公司 | Reservoir warehousing flow prediction method and device, computer equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018140337A1 (en) * | 2017-01-26 | 2018-08-02 | Siemens Aktiengesellschaft | A unifying semi-supervised approach for machine condition monitoring and fault diagnosis |
-
2021
- 2021-07-20 CN CN202110819532.8A patent/CN113485302B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107703920A (en) * | 2017-10-25 | 2018-02-16 | 北京交通大学 | The fault detection method of train braking system based on multivariate time series |
| CN108491886A (en) * | 2018-03-29 | 2018-09-04 | 重庆大学 | A kind of sorting technique of the polynary time series data based on convolutional neural networks |
| CN110285976A (en) * | 2019-07-09 | 2019-09-27 | 哈尔滨工业大学（威海） | Multi-dimensional time sequence information based on DBN drives Fault Diagnosis of Aeroengines method |
| CN110674604A (en) * | 2019-09-20 | 2020-01-10 | 武汉大学 | Transformer DGA data prediction method based on multi-dimensional time sequence frame convolution LSTM |
| CN110702418A (en) * | 2019-10-10 | 2020-01-17 | 山东超越数控电子股份有限公司 | Aircraft engine fault prediction method |
| CN112461537A (en) * | 2020-10-16 | 2021-03-09 | 浙江工业大学 | Wind power gear box state monitoring method based on long-time neural network and automatic coding machine |
| CN112559598A (en) * | 2020-12-16 | 2021-03-26 | 南京航空航天大学 | Telemetry time series data abnormity detection method and system based on graph neural network |
| CN112712209A (en) * | 2020-12-31 | 2021-04-27 | 润联智慧科技(西安)有限公司 | Reservoir warehousing flow prediction method and device, computer equipment and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 层次分析法在电控发动机怠速不良故障诊断中的应用;韦皓，彭朝晖，刘存香;《小型内燃机与车辆技术》;20110625;第40卷(第3期);I136-957 * |
| 海事卫星天线控制器硬件综合测试软件的设计;薛亮;《中国优秀博硕士学位论文全文数据库(硕士)信息科技辑》;20110915(第09期);第83-87页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113485302A (en) | 2021-10-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113485302B (en) | Vehicle operation process fault diagnosis method and system based on multivariate time sequence data | |
| CN104712542B (en) | A kind of reciprocating compressor sensitive features based on Internet of Things are extracted and method for diagnosing faults | |
| CN109581871B (en) | Industrial control system intrusion detection method of immune countermeasure sample | |
| CN104596780B (en) | Diagnosis method for sensor faults of motor train unit braking system | |
| CN112766342A (en) | Abnormity detection method for electrical equipment | |
| CN102265227A (en) | Method and apparatus for creating state estimation models in machine condition monitoring | |
| CN111122162B (en) | Industrial system fault detection method based on Euclidean distance multi-scale fuzzy sample entropy | |
| CN111898644B (en) | Intelligent identification method for health state of aerospace liquid engine under fault-free sample | |
| CN112464990B (en) | Method and device for sensing vibration data based on current-voltage sensor | |
| CN111678699A (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| Son et al. | Deep learning-based anomaly detection to classify inaccurate data and damaged condition of a cable-stayed bridge | |
| CN116522265A (en) | Industrial Internet time sequence data anomaly detection method and device | |
| CN118427681A (en) | Cross-working condition open-set fault diagnosis method and equipment based on self-supervision contrast learning enhancement | |
| CN112880726A (en) | Sensor fault diagnosis method and device based on variational modal decomposition sample entropy | |
| CN117591860A (en) | Data anomaly detection method and device | |
| CN117113139A (en) | Training method and device for fault detection model, computer equipment and storage medium | |
| CN114818811B (en) | Aeroengine rolling bearing fault diagnosis method based on twin network metric learning | |
| CN116720149A (en) | Flight data anomaly detection and recovery method based on space-time correlation multiple regression | |
| CN116522237A (en) | Rolling bearing fault diagnosis method based on parallel convolution neural network | |
| CN115600143A (en) | Energy storage lithium battery fault diagnosis method and device | |
| JP2020107248A (en) | Abnormality determination device and abnormality determination method | |
| Lu et al. | Weak monotonicity with trend analysis for unsupervised feature evaluation | |
| CN117688496B (en) | Abnormality diagnosis method, system and equipment for satellite telemetry multidimensional time sequence data | |
| CN116150666B (en) | Energy storage system fault detection method and device and intelligent terminal | |
| Chen et al. | A Multivariate Time Series Anomaly Detection Method Based on Generative Model |
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 |