CN117892161A

CN117892161A - Vehicle fault processing method, processing device and vehicle fault management system

Info

Publication number: CN117892161A
Application number: CN202410060895.1A
Authority: CN
Inventors: 李俊佼; 杨金鹏; 鹿文慧; 江楠
Original assignee: Weichai Power Co Ltd
Current assignee: Weichai Power Co Ltd
Priority date: 2024-01-15
Filing date: 2024-01-15
Publication date: 2024-04-16

Abstract

The application provides a vehicle fault processing method, a processing device and a vehicle fault management system, wherein the method comprises the following steps: under the condition that the unreliable faults exist in the differential pressure sensor, acquiring a plurality of groups of first working condition sample data of the vehicle, and carrying out cluster analysis on the plurality of groups of first working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of first cluster data; respectively obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to upstream temperature values and downstream temperature values in a plurality of groups of first cluster data in sequence, and fitting according to the correlation between the deviation value and the sample waste gas volume flow to obtain a plurality of correlation curves; in the event that the deviation value of any one of the correlation curves from the standard correlation curve is greater than a first difference threshold, it is determined that the DPF is in an overload state and the regeneration operation is controlled to be performed. The method solves the problem that in the prior art, the pressure difference and the waste gas volume flow of the pressure difference sensor are utilized for analysis, and the pressure difference is ignored and is not credible, so that misdiagnosis is caused.

Description

Vehicle fault processing method, processing device and vehicle fault management system

Technical Field

The present invention relates to the field of vehicle overload faults, and in particular, to a vehicle fault processing method, a processing device, a computer readable storage medium, and a vehicle fault management system.

Background

Particulate matter is one of the main pollutants in diesel exhaust emissions, and the most effective aftertreatment device currently used to reduce diesel particulate emissions is a wall-flow particulate trap (DPF). The soot level (clogging degree) of the DPF needs to be monitored when the DPF traps particulate matter. In the monitoring process, the signals of the differential pressure sensor and the volume flow rate signals are generally utilized for analysis, but in the actual running process of the vehicle, the differential pressure sensor is affected by the environment and the working condition of the whole vehicle, the signal value of the differential pressure sensor is unreliable, and the differential pressure model tends to have larger deviation, so that overload diagnosis becomes more difficult, and auxiliary identification is needed through a certain algorithm or cloud big data analysis.

Disclosure of Invention

The application aims to provide a vehicle fault processing method, a processing device, a computer readable storage medium and a vehicle fault management system, which are used for at least solving the problem that in the prior art, a differential pressure signal and an exhaust gas volume flow signal are utilized for analysis and neglect the differential pressure signal to be unreliable, so that misdiagnosis is caused.

In order to achieve the above object, according to one aspect of the present application, there is provided a method of handling a vehicle failure, a differential pressure sensor for measuring differential pressure across the DPF being provided on a surface of a DPF of the vehicle, the method comprising: under the condition that the unreliable fault exists in the differential pressure sensor, acquiring a plurality of groups of first working condition sample data of the vehicle, and carrying out cluster analysis on the plurality of groups of first working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of first cluster data, wherein the first working condition sample data comprises sample waste gas volume flow, an upstream temperature value of the DPF and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to inaccurate measurement; respectively obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to the upstream temperature values and the downstream temperature values in a plurality of groups of first clustering data in sequence, and fitting according to the correlation between a deviation value and the sample waste gas volume flow to obtain a plurality of correlation curves, wherein the deviation value is the time interval between the peak value of the upstream temperature change rate curve and the peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one group of first clustering data; and under the condition that the deviation value of any one of the correlation curves and the standard correlation curve is larger than a first difference threshold, determining that the DPF is in an overload state and controlling to execute regeneration operation, wherein the overload state is a state that excessive particulate matters are accumulated in the DPF and cannot work normally, and the deviation value is the deviation value between each correlation curve and the standard correlation curve.

Optionally, before acquiring the plurality of sets of first operating condition sample data of the vehicle in the case that it is determined that the differential pressure sensor has an unreliable fault, the method further includes: acquiring a plurality of groups of second working condition sample data of the vehicle, wherein the second working condition sample data comprise sample waste gas volume flow and sample differential pressure values measured by the differential pressure sensor; performing the cluster analysis on a plurality of groups of second working condition sample data by adopting the spectral clustering algorithm to obtain a plurality of groups of second aggregate data, wherein each group of second aggregate data comprises a plurality of groups of second working condition sample data; judging whether the differential pressure value measured by the differential pressure sensor is credible or not according to a plurality of groups of second aggregate data in sequence to obtain a plurality of judging results, wherein one judging result corresponds to one group of second aggregate data, and the judging results comprise the unreliable faults and the faults; and under the condition that any one of the judging results is the unreliable fault, determining that the unreliable fault exists in the differential pressure sensor.

Optionally, performing the clustering analysis on the plurality of groups of second working condition sample data by using the spectral clustering algorithm to obtain a plurality of groups of second aggregate data, including: obtaining a data matrix according to the second working condition sample data, wherein the rows of the data matrix represent sample data of each sample, the columns of the data matrix represent sample characteristics, the sample data comprise one sample differential pressure value and one sample waste gas volume flow, and the sample characteristics comprise the sample differential pressure value and the sample waste gas volume flow; calculating weight values among all the samples according to the data matrix to obtain an adjacent matrix, and calculating to obtain a Laplacian matrix according to the adjacent matrix, wherein the adjacent matrix is a matrix formed by the weight values among any of the samples; calculating a feature vector corresponding to the minimum feature value of the Laplace matrix, and calculating a feature matrix according to the feature vector, wherein the feature matrix is formed by normalizing a matrix formed by the feature vectors; and calculating the characteristic matrix and the set clustering number by adopting a K-means clustering algorithm to obtain a plurality of groups of second clustering data.

Optionally, determining whether the differential pressure value measured by the differential pressure sensor is reliable according to the plurality of groups of second aggregate data in sequence, to obtain a plurality of determination results, including: according to the fitting analysis of a plurality of groups of second aggregate data and a plurality of preset standard data, a pressure difference-volume flow diagram is obtained, wherein the pressure difference-volume flow diagram is a two-dimensional coordinate diagram, the abscissa of the two-dimensional coordinate diagram is the volume flow, and the ordinate of the two-dimensional coordinate diagram is the differential pressure value; generating a corresponding carbon deposition level curve according to a plurality of sample pressure difference values and a plurality of sample waste gas volume flows in a plurality of groups of second polymer data, wherein the carbon deposition level curve is a relation curve between the sample pressure difference values and the sample waste gas volume flows, and one group of second polymer data corresponds to one carbon deposition level curve; generating a standard carbon deposition level curve according to a plurality of preset standard data, wherein the standard carbon deposition level curve is a relation curve between a standard pressure difference value and a standard waste gas volume flow in the preset standard data; determining that the judging result of the current carbon deposition level curve is the fault-free value under the condition that the offset value is smaller than or equal to a second difference value threshold, wherein the offset value is the offset between each carbon deposition level curve and the standard carbon deposition level curve; and under the condition that the offset value is larger than the second difference value threshold value, determining that the judgment result of the current carbon deposition level curve is the unreliable fault.

Optionally, after determining that the determination result of the current carbon deposition level curve is the fault-free, the method further includes: determining that the DPF is not in an overload state if the offset value is less than or equal to a third difference threshold, the third difference threshold being less than the second difference threshold; in the event that the offset value is greater than the third difference threshold, determining that the DPF is in the overload condition and controlling the regeneration operation.

Optionally, an upstream temperature change rate curve and a downstream temperature change rate curve are obtained according to the upstream temperature values and the downstream temperature values in the multiple groups of first cluster data in sequence, and fitting is performed according to the correlation between the deviation value and the sample exhaust gas volume flow to obtain multiple correlation curves, including: a first calculation step of respectively generating an upstream temperature change rate curve and a downstream temperature change rate curve according to the change condition of the upstream temperature value and time and the change condition of the downstream temperature value and time; a second calculation step of obtaining the deviation values corresponding to a plurality of first peaks and a plurality of second peaks according to the upstream temperature change rate curve and the downstream temperature change rate curve, wherein the first peaks are peaks on the upstream temperature change rate curve, the second peaks are peaks on the downstream temperature change rate curve, and the first peaks and the second peaks are in one-to-one correspondence; a third calculation step of generating a group of correlation curves corresponding to the first cluster data according to a plurality of deviation values and a plurality of sample waste gas volume flows, wherein the deviation values are in one-to-one correspondence with the sample waste gas volume flows; and sequentially repeating the first calculation step, the second calculation step and the third calculation step at least once until all the correlation curves are obtained.

Optionally, after fitting a plurality of correlation curves from the correlation between the deviation value and the sample exhaust gas volumetric flow, the method further comprises: determining that the DPF is not in the overload state if all of the deviation values of the correlation curves from the standard correlation curve are less than or equal to the first difference threshold; determining that the DPF is free of an overload risk if the DPF is not in the overload state and the deviation value of any one of the correlation curves from the standard correlation curve is less than or equal to a fourth difference threshold, the fourth difference threshold being less than the first difference threshold; in the event that the DPF is not in the overload state and the deviation value of any one of the correlation curves from the standard correlation curve is greater than the fourth difference threshold, determining that the DPF is at risk of overload and controlling the regeneration operation.

According to another aspect of the present application, there is provided a device for handling a failure of a vehicle, a differential pressure sensor being provided on a surface of a DPF of the vehicle, the differential pressure sensor being for measuring a differential pressure value across the DPF, the device comprising: the first acquisition unit is used for acquiring a plurality of groups of first working condition sample data of the vehicle under the condition that the differential pressure sensor is determined to have an unreliable fault, and carrying out cluster analysis on the plurality of groups of first working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of first cluster data, wherein the first working condition sample data comprises sample waste gas volume flow, an upstream temperature value of the DPF and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to inaccurate measurement; the calculating unit is used for respectively obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to the upstream temperature values and the downstream temperature values in the plurality of groups of first clustering data in sequence, fitting according to the correlation between the deviation value and the sample waste gas volume flow to obtain a plurality of correlation curves, wherein the deviation value is the time interval between the peak value of the upstream temperature change rate curve and the peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one group of first clustering data; and the control unit is used for determining that the DPF is in an overload state and controlling the regeneration operation to be executed under the condition that the deviation value of any one of the correlation curves and the standard correlation curve is larger than a first difference threshold, wherein the overload state is a state that too much particulate matters are accumulated in the DPF and cannot normally work, and the deviation value is the deviation value between each correlation curve and the standard correlation curve.

According to still another aspect of the present application, there is provided a computer readable storage medium including a stored program, wherein the program when run controls a device in which the computer readable storage medium is located to perform any one of the methods.

According to still another aspect of the present application, there is provided a vehicle fault management system including: one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods.

In the technical scheme of the application, in the vehicle fault processing method, firstly, under the condition that the existence of an unreliable fault of a differential pressure sensor is determined, a plurality of groups of first working condition sample data of a vehicle are obtained, and a spectral clustering algorithm is adopted to perform clustering analysis on the plurality of groups of first working condition sample data to obtain a plurality of groups of first clustering data, wherein the first working condition sample data comprises a sample waste gas volume flow, an upstream temperature value of a DPF and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to inaccurate measurement; then, respectively obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to upstream temperature values and downstream temperature values in a plurality of groups of first clustering data in sequence, fitting according to the correlation between the deviation value and the sample waste gas volume flow to obtain a plurality of correlation curves, wherein the deviation value is the time interval between the peak value of the upstream temperature change rate curve and the peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one group of first clustering data; and finally, under the condition that the deviation value of any one correlation curve and the standard correlation curve is larger than a first difference threshold, determining that the DPF is in an overload state and controlling to execute regeneration operation, wherein the overload state is a state that excessive particulate matters are accumulated in the DPF and cannot work normally, and the deviation value is the deviation value between each correlation curve and the standard correlation curve. According to the application, under the condition that an unreliable fault exists in the dpf differential pressure sensor of the current vehicle, namely, under the condition that the differential pressure value measured by the dpf differential pressure sensor is inaccurate, the upstream temperature and the downstream temperature of the dpf are measured through the temperature sensor to replace the differential pressure value measured by the differential pressure sensor, so that overload state identification can still be carried out under the unreliable state of the differential pressure sensor, after cluster analysis is carried out on working condition data, whether the dpf is overloaded is judged according to the deviation value between the working condition data generation correlation curve and the standard correlation curve generated by the preset standard data, and under the condition that the deviation value is larger than the differential value threshold, the dpf is determined to be in an overload state and regeneration operation is controlled to be executed. The application solves the problem of misdiagnosis caused by the fact that the pressure difference signal is not credible when the pressure difference signal is ignored in the prior art by utilizing the pressure difference signal of the pressure difference sensor and the waste gas volume flow signal for analysis.

Drawings

Fig. 1 is a block diagram showing a hardware configuration of a mobile terminal for performing a processing method of a vehicle fault according to an embodiment of the present application;

Fig. 2 is a schematic flow chart of a method for handling a vehicle fault according to an embodiment of the present application;

FIG. 3 is a schematic flow chart of a spectral clustering algorithm cluster analysis according to an embodiment of the present application;

FIG. 4 shows a schematic flow diagram of a vehicle fault handling provided in accordance with an embodiment of the present application;

FIG. 5 is a flow chart illustrating a specific method for handling a vehicle fault according to an embodiment of the present application;

Fig. 6 shows a block diagram of a vehicle fault handling apparatus according to an embodiment of the present application.

Wherein the above figures include the following reference numerals:

102. a processor; 104. a memory; 106. a transmission device; 108. and an input/output device.

Detailed Description

It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

In order that those skilled in the art will better understand the present application, a technical solution in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present application without making any inventive effort, shall fall within the scope of the present application.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the application herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

For convenience of description, the following will describe some terms or terminology involved in the embodiments of the present application:

Spectral clustering algorithm: a clustering method based on graph theory regards data as nodes on a graph, constructs the graph by calculating the similarity between the nodes, then cuts the graph, cuts the graph into a plurality of sub-graphs, and each sub-graph corresponds to one cluster.

As described in the background art, in the prior art, DPF overload is generally judged at the ECU end through the magnitude or slope of the differential pressure, and in order to solve the problem of misdiagnosis caused by unreliable differential pressure signals, the embodiment of the application provides a vehicle fault processing method, a processing device, a computer readable storage medium and a vehicle fault management system.

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

The method embodiments provided in the embodiments of the present application may be performed in a mobile terminal, a computer terminal or similar computing device. Taking the mobile terminal as an example, fig. 1 is a block diagram of a hardware structure of the mobile terminal according to an embodiment of the present application. As shown in fig. 1, a mobile terminal may include one or more (only one is shown in fig. 1) processors 102 (the processor 102 may include, but is not limited to, a microprocessor MCU or a processing device such as a programmable logic device FPGA) and a memory 104 for storing data, wherein the mobile terminal may also include a transmission device 106 for communication functions and an input-output device 108. It will be appreciated by those skilled in the art that the structure shown in fig. 1 is merely illustrative and not limiting of the structure of the mobile terminal described above. For example, the mobile terminal may also include more or fewer components than shown in fig. 1, or have a different configuration than shown in fig. 1.

The memory 104 may be used to store a computer program, for example, a software program of application software and a module, such as a computer program corresponding to a display method of device information in an embodiment of the present invention, and the processor 102 executes the computer program stored in the memory 104 to perform various functional applications and data processing, that is, to implement the above-described method. Memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include memory remotely located relative to the processor 102, which may be connected to the mobile terminal via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or transmit data via a network. Specific examples of the network described above may include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, simply referred to as a NIC) that can connect to other network devices through a base station to communicate with the internet. In one example, the transmission device 106 may be a Radio Frequency (RF) module, which is configured to communicate with the internet wirelessly.

In the present embodiment, a method of handling a vehicle failure running on a mobile terminal, a computer terminal, or a similar computing device is provided, it being noted that the steps shown in the flowcharts of the drawings may be performed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that here.

Fig. 2 is a flowchart of a method of handling a vehicle fault according to an embodiment of the application. As shown in fig. 2, the method comprises the steps of:

Step S201, under the condition that the unreliable fault exists in the differential pressure sensor, acquiring a plurality of groups of first working condition sample data of the vehicle, and performing cluster analysis on the plurality of groups of first working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of first cluster data, wherein the first working condition sample data comprises a sample waste gas volume flow, an upstream temperature value of the DPF and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to inaccurate measurement.

Specifically, when the signal of the differential pressure sensor is not reliable, the signals of the temperature sensors arranged at the upstream and downstream of the DPF are adopted to carry out overload judgment, the upstream temperature sensor, the downstream temperature sensor and the exhaust gas volume flow of the DPF are utilized to carry out cluster analysis,

Step S202, an upstream temperature change rate curve and a downstream temperature change rate curve are obtained according to the upstream temperature values and the downstream temperature values in the plurality of groups of first clustering data in sequence, a plurality of correlation curves are obtained by fitting according to the correlation between the deviation value and the sample waste gas volume flow, the deviation value is the time interval between the peak value of the upstream temperature change rate curve and the peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one group of first clustering data.

Specifically, in each group of first cluster data, an upstream temperature change rate curve and a downstream temperature change rate curve are obtained respectively according to the condition that an upstream temperature value changes with time and the condition that a downstream temperature value changes with time, a certain correlation exists between the size of the exhaust gas volume flow and the distance between peaks of the upstream temperature change rate and the downstream temperature change rate, the distance between the peaks is the time interval, and therefore the correlation between the time interval between the peaks of the upstream temperature change rate curve and the peak of the downstream temperature change rate curve and the sample exhaust gas volume flow is subjected to fitting analysis, and a plurality of correlation curves are obtained. Through the correlation analysis of the upstream and downstream temperature change rate of the DPF and the volume flow of the waste gas, whether the DPF is in an overload state or not is timely judged, so that the regeneration operation can be timely controlled and executed, the phenomenon that the DPF cannot work normally due to excessive accumulated particulate matters is avoided, and the emission performance and the working stability of a vehicle are ensured.

In step S203, when the deviation value of any one of the correlation curves and the standard correlation curve is greater than the first difference threshold, it is determined that the DPF is in an overload state and the regeneration operation is controlled to be performed, where the overload state is a state in which too much particulate matter is accumulated in the DPF and cannot normally work, and the deviation value is the deviation value between each of the correlation curves and the standard correlation curve.

Specifically, as the exhaust gas volume flow increases, the longer the time required for the downstream temperature to rise or drop to the upstream temperature value, the deviation value between the time interval of one or more correlation curves and the time interval of the standard correlation curve in the same exhaust gas volume flow exceeds the preset range, so that the DPF can be determined to be in an overload state and the ECU is controlled to perform a regeneration operation, and the specific regeneration operation can be to remind the service station to perform the ash removal operation through the APP or the intelligent diagnostic terminal and then perform service regeneration; for a vehicle configured with one-key regeneration, the APP pushing regeneration reminding can be used for guiding a user to perform one-key parking regeneration to perform carbon elimination.

In the embodiment, firstly, under the condition that the existence of an unreliable fault of a differential pressure sensor is determined, acquiring a plurality of groups of first working condition sample data of a vehicle, and carrying out cluster analysis on the plurality of groups of first working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of first cluster data, wherein the first working condition sample data comprises a sample waste gas volume flow, an upstream temperature value of a DPF and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to inaccurate measurement; then, respectively obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to upstream temperature values and downstream temperature values in a plurality of groups of first clustering data in sequence, fitting according to the correlation between the deviation value and the sample waste gas volume flow to obtain a plurality of correlation curves, wherein the deviation value is the time interval between the peak value of the upstream temperature change rate curve and the peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one group of first clustering data; and finally, under the condition that the deviation value of any one correlation curve and the standard correlation curve is larger than a first difference threshold, determining that the DPF is in an overload state and controlling to execute regeneration operation, wherein the overload state is a state that excessive particulate matters are accumulated in the DPF and cannot work normally, and the deviation value is the deviation value between each correlation curve and the standard correlation curve. According to the application, under the condition that an unreliable fault exists in the dpf differential pressure sensor of the current vehicle, namely, under the condition that the differential pressure value measured by the dpf differential pressure sensor is inaccurate, the upstream temperature and the downstream temperature of the dpf are measured through the temperature sensor to replace the differential pressure value measured by the differential pressure sensor, so that overload state identification can still be carried out under the unreliable state of the differential pressure sensor, after cluster analysis is carried out on working condition data, whether the dpf is overloaded is judged according to the deviation value between the working condition data generation correlation curve and the standard correlation curve generated by the preset standard data, and under the condition that the deviation value is larger than the differential value threshold, the dpf is determined to be in an overload state and regeneration operation is controlled to be executed. The application solves the problem of misdiagnosis caused by the fact that the pressure difference signal is not credible when the pressure difference signal is ignored in the prior art by utilizing the pressure difference signal of the pressure difference sensor and the waste gas volume flow signal for analysis.

In order to enable those skilled in the art to more clearly understand the technical solution of the present application, the implementation procedure of the vehicle fault handling method of the present application will be described in detail below with reference to specific embodiments.

In order to find the measurement deviation of the differential pressure sensor in time, in an alternative embodiment, before the step S201, the method further includes:

Step S301, a plurality of sets of second working condition sample data of the vehicle are obtained, where the second working condition sample data includes a sample exhaust gas volume flow and a sample differential pressure value measured by a differential pressure sensor.

Specifically, it is necessary to monitor the soot level (clogging degree) of the DPF when the DPF traps particulate matter. In the monitoring process, the differential pressure sensor signal and the exhaust gas volume flow signal are generally utilized for analysis, so that the differential pressure sensor signal and the exhaust gas volume flow signal, namely second working condition sample data, are firstly obtained, and the sample differential pressure value and the sample exhaust gas volume flow are obtained.

Step S302, performing cluster analysis on multiple groups of second working condition sample data by adopting a spectral clustering algorithm to obtain multiple groups of second aggregate data, wherein each second aggregate data comprises multiple groups of second working condition sample data.

Specifically, the pressure difference sensor is affected by the environment and the working condition of the whole vehicle in the actual running process of the vehicle, the signal value of the pressure difference sensor is unreliable, and the pressure difference model tends to deviate greatly, so that overload diagnosis is easy to become more difficult, auxiliary identification is needed through a certain algorithm or cloud big data analysis, and therefore, the sample pressure difference value and the sample waste gas volume flow are subjected to clustering analysis by adopting a spectral clustering algorithm, and the measurement deviation of the sensor is found in time.

Step S303, judging whether the differential pressure value measured by the differential pressure sensor is reliable or not according to a plurality of groups of second aggregate data in sequence, and obtaining a plurality of judging results, wherein one judging result corresponds to one group of second aggregate data, and the judging results comprise unreliable faults and non-faults.

Specifically, after a plurality of groups of second aggregate data are obtained, each group of second aggregate data is analyzed to judge whether the differential pressure value measured by the differential pressure sensor is credible or not, and a judgment result that the differential pressure sensor has an unreliable fault or has no fault is obtained, so that the problem of false alarm of DPF overload is avoided.

Step S304, determining that the differential pressure sensor has an unreliable fault under the condition that any judging result is an unreliable fault.

Specifically, one or more of all the judging results are unreliable faults, which means that the differential pressure value measured by the differential pressure sensor is inaccurate, and the differential pressure sensor has an unreliable fault.

In order to improve the data processing efficiency, in an alternative embodiment, as shown in fig. 3, step S302 includes:

In step S3021, according to the sample data under the second working condition, a data matrix is obtained, the rows of the data matrix represent the sample data of each sample, the columns of the data matrix represent a sample feature, the sample data includes a sample differential pressure value and a sample exhaust gas volume flow, and the sample feature includes a sample differential pressure value and a sample exhaust gas volume flow.

In particular, a spectral clustering algorithm is adopted, after sample data is acquired, the sample data is graphically converted into a data matrix,

In step S3022, a neighboring matrix is obtained by calculating the weight value between the samples according to the data matrix, and a laplace matrix is obtained by calculating the neighboring matrix, where the neighboring matrix is a matrix composed of the weight values between any samples.

Specifically, the data matrix may be obtained by a full connection method or other calculation methods, where the weight value is lower if the two samples are far apart and higher if the two samples are close. And obtaining a Laplace matrix according to the difference between the degree matrix and the adjacent matrix, wherein the Laplace matrix is a symmetrical positive definite matrix for describing the similarity and the difference between samples, and the degree matrix is a matrix formed by the degree of each sample point.

In step S3023, a feature vector corresponding to the minimum feature value of the laplace matrix is calculated, and a feature matrix is obtained according to the feature vector calculation, where the feature matrix is a matrix formed by normalizing a matrix formed by the feature vectors.

Specifically, feature vectors corresponding to a plurality of minimum feature values of the laplace matrix are calculated, the matrix formed by the feature vectors is normalized according to rows to form a feature matrix, and the feature vectors can be used for describing clustering relations among samples.

Step S3024, calculating the feature matrix and the set cluster number by using a K-means clustering algorithm to obtain a plurality of sets of second cluster data.

Specifically, each row in the feature matrix is used as one sample, and a K-means clustering algorithm is adopted to calculate all samples and set clustering numbers of all rows to obtain a plurality of groups of second clustering data. The K-means clustering algorithm may divide the samples into K clusters, and each sample belongs to the cluster closest to it. The clustering result can clearly show the similarity and the difference between the samples, discover the rules and the characteristics between the samples, and reduce the calculated amount of data processing.

In order to find out an unreliable problem of the differential pressure sensor in time, in an alternative embodiment, the step S303 includes:

Step S3031, a pressure difference-volume flow diagram is obtained according to fitting analysis of a plurality of groups of second polymer data and a plurality of preset standard data, wherein the pressure difference-volume flow diagram is a two-dimensional coordinate diagram, the abscissa of the two-dimensional coordinate diagram is the volume flow, and the ordinate of the two-dimensional coordinate diagram is the differential pressure value.

Specifically, a plurality of sets of second aggregate data and a plurality of preset standard data are fitted to obtain a pressure difference value-volume flow rate relation diagram, namely the pressure difference-volume flow rate diagram.

Step S3032, generating a corresponding carbon deposition level curve according to the plurality of sample pressure differences and the plurality of sample exhaust gas volume flows in the plurality of sets of second polymer data, where the carbon deposition level curve is a relation curve between the sample pressure differences and the sample exhaust gas volume flows, and one set of second polymer data corresponds to one carbon deposition level curve.

Specifically, for each set of second polymer data, a corresponding carbon deposition level curve is generated according to the variation of the sample pressure difference value in the second polymer data along with the sample exhaust gas volume flow.

Step S3033, a standard carbon deposition level curve is generated according to a plurality of preset standard data, wherein the standard carbon deposition level curve is a relation curve between a standard pressure difference value and a standard waste gas volume flow in the preset standard data.

Specifically, a standard carbon deposition level curve is generated for the stored preset standard data according to the condition that the standard pressure difference value in the preset standard data changes along with the standard waste gas volume flow in a fitting mode, so that the comparison analysis is facilitated.

Step S3034, determining that the judgment result of the current carbon deposition level curve is fault-free under the condition that the offset value is smaller than or equal to the second difference value threshold value, wherein the offset value is the offset between each carbon deposition level curve and the standard carbon deposition level curve.

Specifically, under the same volume flow of the waste gas, the offset of the differential pressure values of all the carbon deposition level curves and the differential pressure value of the standard carbon deposition level curve are in a reliable preset range, namely the second differential value threshold value indicates that the detected sample differential pressure value and the standard differential pressure value have smaller differences and belong to an allowable range, and at the moment, the differential pressure value measured by the differential pressure sensor is accurate, and the differential pressure sensor has no faults.

Step S3035, determining that the judgment result of the current carbon deposition level curve is an unreliable fault under the condition that the offset value is larger than the second difference value threshold.

Specifically, the offset of the differential pressure value of one or more carbon deposition level curves and the differential pressure value of the standard carbon deposition level curve under the same exhaust gas volume flow exceeds a trusted preset range, which indicates that the differential pressure sensor may generate zero drift problem at the moment, and the measured differential pressure value is inaccurate and has an unreliable fault.

In order to ensure the accuracy of the overload monitoring determination of the DPF, in an alternative embodiment, after the step S3034, the method further includes:

in step S401, it is determined that the DPF is not in the overload state if the offset value is less than or equal to the third difference threshold, which is less than the second difference threshold.

Specifically, as shown in fig. 4, when the differential pressure signal is reliable, the differential pressure and the volume flow are directly adopted to distinguish whether the DPF is in an overload state, and when the offset between each carbon deposition level curve and the standard carbon deposition level curve is smaller than or equal to a preset third differential value threshold, the difference between the different carbon deposition level curves and the standard carbon deposition level curve is small, and the DPF is not in the overload state.

Step S402, in the case where the offset value is greater than the third difference threshold, determines that the DPF is in an overload state and controls to perform a regeneration operation.

Specifically, when the deviation of the differential pressure value of one or more carbon deposition level curves and the differential pressure value of the standard carbon deposition level curve exceeds a preset range under the same exhaust gas volume flow, or when the deviation of the exhaust gas volume flow on one or more carbon deposition level curves and the exhaust gas volume flow on the standard carbon deposition level curve exceeds a preset range under the same differential pressure value, namely the third differential value threshold, it can be stated that the DPF is in an overload state at this time, the ECU is controlled to execute the regeneration operation.

To ensure overload condition identification in the unreliable state of the differential pressure sensor, in an alternative embodiment, step S202 includes:

in step S2021, in the first calculation step, an upstream temperature change rate curve and a downstream temperature change rate curve are generated according to the change condition of the upstream temperature value and the time and the change condition of the downstream temperature value and the time, respectively.

Specifically, after detecting in real time to obtain a plurality of upstream temperature values and a plurality of downstream temperature values, an upstream temperature change rate curve is generated according to the change condition of the upstream temperature values with time, and a downstream temperature change rate curve is generated according to the change condition of the downstream temperature values with time, wherein the two curves can be located in a coordinate system.

In step S2022, in the second calculation step, a deviation value corresponding to the two first peak values and the second peak values is obtained according to the upstream temperature change rate curve and the downstream temperature change rate curve, where the first peak value is a peak value on the upstream temperature change rate curve, and the second peak value is a peak value on the downstream temperature change rate curve, and the first peak value and the second peak value are in one-to-one correspondence.

Specifically, when the particulate matter in the DPF is blocked and not overloaded, the upstream temperature value and the upstream temperature value are slightly different, and the downstream temperature will gradually rise to the upstream temperature value along with the upstream temperature change, so that the deviation value between the first peak value and the second peak value, that is, the response time required for the downstream temperature to gradually rise or fall to the upstream temperature value, is calculated according to the first peak values on the upstream temperature change rate curve and the second peak values on the downstream temperature change rate curve, so as to obtain the corresponding deviation value between the two peak values.

In step S2023, in a third calculation step, a set of correlation curves corresponding to the first cluster data is generated according to the plurality of deviation values and the plurality of sample exhaust gas volume flows, where the deviation values are in one-to-one correspondence with the sample exhaust gas volume flows.

Specifically, there is a correlation between the magnitude of the exhaust gas volumetric flow rate and the peak intervals of the upstream temperature change rate curve and the downstream temperature change rate curve, in other words, the longer the downstream temperature increases or decreases to the upstream temperature value the greater the exhaust gas volumetric flow rate, the longer the time required to generate a correlation curve from the correlation therebetween.

Step S2024, repeating the first calculation step, the second calculation step, and the third calculation step at least once in sequence until all the correlation curves are obtained.

Specifically, all the first cluster data sequentially repeat the first calculation step, the second calculation step and the third calculation step to obtain the corresponding correlation curve.

In order to avoid that the DPF is in an overload state, in an alternative embodiment, after the step S202, the method further includes:

in step S501, it is determined that the DPF is not in the overload state if all the deviation values of the correlation curves from the standard correlation curve are smaller than or equal to the first difference threshold.

Specifically, as the exhaust gas volumetric flow increases, the longer the downstream temperature needs to be raised to the upstream temperature value, but the deviation value of the time intervals of all the correlation curves from the time intervals of the standard correlation curve at the same exhaust gas volumetric flow remains within a preset range, which means that the time at which the downstream temperature is raised or lowered to the upstream temperature remains within the preset range, overload is not caused, and it can be determined that the DPF is not in the overload state.

In step S502, when the DPF is not in the overload state and the deviation value of any one of the correlation curves from the standard correlation curve is smaller than or equal to a fourth difference threshold, it is determined that the DPF is free of the risk of overload, and the fourth difference threshold is smaller than the first difference threshold.

In particular, if the DPF is not in an overload state and the deviation values of the time intervals of all the correlation curves from the time intervals of the standard correlation curve at the same exhaust gas volume flow are not within the risk preset range of the overload state, i.e., the above-mentioned fourth difference threshold, it can be determined that the DPF is free from the risk of overload, without performing a regeneration operation.

In step S503, in the case that the DPF is not in an overload state and the deviation value of any one of the correlation curves from the standard correlation curve is greater than the fourth difference threshold, it is determined that the DPF is at risk of being overloaded and the control is performed to perform the regeneration operation.

Specifically, in order to avoid the DPF being in the overload state, a judgment is made in advance that the DPF is not currently in the overload state and the deviation value of the time intervals of all the correlation curves from the time intervals of the standard correlation curves under the same exhaust gas volume flow rate is not in the overload state, but the deviation value has exceeded the risk preset range of the overload state, it is determined that the DPF is at risk of overload, and the DPF will be in the overload state in view of the current accumulated particulate matter, so that the control ECU performs the regeneration operation in advance. In short, if the DPF is not currently overloaded, but there is a possibility of overload, the control ECU performs the regeneration operation in advance.

The embodiment relates to a specific vehicle fault processing method, as shown in fig. 5, including the following steps:

Step S1: presetting vehicle driving data in a normal state at a cloud end;

Step S2: after the vehicle runs for a certain time or before the service station performs maintenance to perform service regeneration, collecting the data of the current vehicle as sample data for fault identification;

step S3: the cloud builds a spectral cluster analysis algorithm, performs cluster analysis data processing and overload identification by combining preset normal data and sample data after uploading the data, and judges whether overload is possible after a diagnosis result is obtained;

Step S4: and the cloud returns the diagnosis result to the ECU to carry out regeneration triggering judgment, and the executor executes carbon elimination operation.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.

The embodiment of the application also provides a vehicle fault processing device, and the vehicle fault processing device can be used for executing the vehicle fault processing method. The device is used for realizing the above embodiments and preferred embodiments, and is not described in detail. As used below, the term "module" may be a combination of software and/or hardware that implements a predetermined function. While the means described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and contemplated.

The following describes a vehicle fault handling device provided by an embodiment of the present application.

Fig. 6 is a block diagram of a processing apparatus of a vehicle failure according to an embodiment of the present application. As shown in fig. 6, the apparatus includes:

The first acquisition unit is used for acquiring a plurality of groups of first working condition sample data of the vehicle under the condition that the unreliable fault exists in the differential pressure sensor, carrying out cluster analysis on the plurality of groups of first working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of first cluster data, wherein the first working condition sample data comprises a sample waste gas volume flow, an upstream temperature value of the DPF and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to inaccurate measurement.

The calculating unit 20 is configured to sequentially obtain an upstream temperature change rate curve and a downstream temperature change rate curve according to the upstream temperature values and the downstream temperature values in the multiple sets of first cluster data, and fit the upstream temperature change rate curve and the downstream temperature change rate curve according to the correlation between the deviation value and the sample exhaust gas volume flow to obtain multiple correlation curves, where the deviation value is a time interval between a peak value of the upstream temperature change rate curve and a peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one set of first cluster data.

And the control unit 30 is configured to determine that the DPF is in an overload state and control to perform a regeneration operation when a deviation value of any one of the correlation curves from the standard correlation curve is greater than a first difference threshold, where the overload state is a state in which too much particulate matter is accumulated in the DPF to normally operate, and the deviation value is an offset between each of the correlation curves and the standard correlation curve.

In this embodiment, the first obtaining unit is configured to obtain multiple sets of first working condition sample data of the vehicle when it is determined that an unreliable fault exists in the differential pressure sensor, and perform cluster analysis on the multiple sets of first working condition sample data by using a spectral clustering algorithm to obtain multiple sets of first cluster data, where the first working condition sample data includes a sample exhaust gas volume flow, an upstream temperature value of the DPF, and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to measurement inaccuracy; the calculating unit is used for respectively obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to upstream temperature values and downstream temperature values in a plurality of groups of first clustering data in sequence, fitting according to the correlation between the deviation value and the sample waste gas volume flow to obtain a plurality of correlation curves, wherein the deviation value is the time interval between the peak value of the upstream temperature change rate curve and the peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one group of first clustering data; and the control unit is used for determining that the DPF is in an overload state and controlling the regeneration operation to be executed under the condition that the deviation value of any one correlation curve and the standard correlation curve is larger than a first difference threshold, wherein the overload state is a state that excessive particulate matters are accumulated in the DPF and cannot normally work, and the deviation value is the deviation value between each correlation curve and the standard correlation curve. According to the application, under the condition that the DPF differential pressure sensor of the current vehicle has an unreliable fault, namely, under the condition that the differential pressure value measured by the DPF differential pressure sensor is inaccurate, the upstream temperature and the downstream temperature of the DPF are measured by the temperature sensor to replace the differential pressure value measured by the differential pressure sensor, so that the overload state can still be identified under the unreliable state of the differential pressure sensor, the cluster analysis is carried out on the acquired working condition data, the DPF is judged whether to be overloaded according to the deviation value between the generated correlation curve of the working condition data and the standard correlation curve generated by the preset standard data, and under the condition that the deviation value is larger than the differential value threshold, the DPF is determined to be in the overload state and the regeneration operation is controlled to be executed. The application solves the problem of misdiagnosis caused by the fact that the pressure difference signal is not credible when the pressure difference signal is ignored in the prior art by utilizing the pressure difference signal of the pressure difference sensor and the waste gas volume flow signal for analysis.

In order to find the differential pressure sensor measurement deviation in time, in an alternative embodiment, the apparatus further comprises:

the second acquisition unit is used for acquiring a plurality of groups of second working condition sample data of the vehicle before acquiring a plurality of groups of first working condition sample data of the vehicle under the condition that the differential pressure sensor is determined to have an unreliable fault, wherein the second working condition sample data comprises a sample waste gas volume flow and a sample differential pressure value measured by the differential pressure sensor.

The analysis unit is used for carrying out cluster analysis on a plurality of groups of second working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of second aggregate data, and each group of second aggregate data comprises a plurality of groups of second working condition sample data.

The judging unit is used for judging whether the differential pressure value measured by the differential pressure sensor is reliable or not according to a plurality of groups of second aggregate data in sequence to obtain a plurality of judging results, one judging result corresponds to one group of second aggregate data, and the judging results comprise unreliable faults and non-faults.

And the first determining unit is used for determining that the differential pressure sensor has an unreliable fault under the condition that any judging result is an unreliable fault.

In order to improve the data processing efficiency, in an alternative embodiment, the analysis unit includes:

the first generation module obtains a data matrix according to the sample data of the second working condition, the rows of the data matrix represent the sample data of each sample, the columns of the data matrix represent sample characteristics, the sample data comprise a sample differential pressure value and a sample waste gas volume flow, and the sample characteristics comprise the sample differential pressure value and the sample waste gas volume flow.

And the second generation module is used for calculating weight values among all samples according to the data matrix to obtain an adjacent matrix, and calculating the Laplace matrix according to the adjacent matrix, wherein the adjacent matrix is a matrix formed by weight values among any samples.

The first calculation module calculates a feature vector corresponding to the minimum feature value of the Laplace matrix, calculates a feature matrix according to the feature vector, and the feature matrix is formed by normalizing a matrix formed by the feature vectors.

And the second calculation module is used for calculating the characteristic matrix and the set clustering number by adopting a K-means clustering algorithm to obtain a plurality of groups of second clustering data.

In order to find out an unreliable problem of the differential pressure sensor in time, in an alternative embodiment, the determining unit includes:

And the fitting module is used for obtaining a pressure difference-volume flow diagram according to the fitting analysis of the plurality of groups of second aggregate data and the plurality of preset standard data, wherein the pressure difference-volume flow diagram is a two-dimensional coordinate diagram, the abscissa of the two-dimensional coordinate diagram is the volume flow, and the ordinate of the two-dimensional coordinate diagram is the differential pressure value.

And the third generation module is used for generating a corresponding carbon deposition level curve according to the plurality of sample pressure difference values and the plurality of sample waste gas volume flows in the plurality of groups of second polymer data, wherein the carbon deposition level curve is a relation curve between the sample pressure difference values and the sample waste gas volume flows, and one group of second polymer data corresponds to one carbon deposition level curve.

And the fourth generation module is used for generating a standard carbon deposition level curve according to a plurality of preset standard data, wherein the standard carbon deposition level curve is a relation curve between a standard pressure difference value and a standard waste gas volume flow in the preset standard data.

And the first determining module is used for determining that the judging result of the current carbon deposition level curve is fault-free under the condition that the offset value is smaller than or equal to the second difference value threshold value, and the offset value is the offset between each carbon deposition level curve and the standard carbon deposition level curve.

And the second determining module is used for determining that the judgment result of the current carbon deposition level curve is an unreliable fault under the condition that the offset value is larger than a second difference value threshold value.

In order to ensure the accuracy of the overload monitoring judgment of the DPF, in an alternative embodiment, the device further comprises:

And the second determining unit is used for determining that the DPF is not in an overload state under the condition that the offset value is smaller than or equal to a third difference threshold value after determining that the judging result of the current carbon deposition level curve is fault-free, and the third difference threshold value is smaller than the second difference threshold value.

Specifically, when the differential pressure signal is reliable, the differential pressure and the volume flow are directly adopted to distinguish whether the DPF is in an overload state, and when the offset between each carbon deposition level curve and the standard carbon deposition level curve is smaller than or equal to a preset third differential value threshold value, the difference between different carbon deposition level curves and the standard carbon deposition level curve is small, and the DPF is not in the overload state.

And a third determining unit determining that the DPF is in an overload state and controlling to perform a regeneration operation in a case where the offset value is greater than a third difference threshold.

In order to ensure overload condition recognition in the unreliable state of the differential pressure sensor, in an alternative embodiment, the above-mentioned calculation unit comprises:

the first calculation module, the first calculation step, according to the change condition of the upstream temperature value and time and the change condition of the downstream temperature value and time, respectively generates an upstream temperature change rate curve and a downstream temperature change rate curve.

The second calculation module, the second calculation step, obtain the deviation value corresponding to the two of a plurality of first peak values and a plurality of second peak values according to the upstream temperature change rate curve and the downstream temperature change rate curve, the first peak value is the peak value on the upstream temperature change rate curve, the second peak value is the peak value on the downstream temperature change rate curve, the first peak value corresponds to the second peak value one by one.

And the third calculation module is used for generating a group of correlation curves corresponding to the first clustering data according to the plurality of deviation values and the plurality of sample waste gas volume flows, wherein the deviation values correspond to the sample waste gas volume flows one by one.

And the repeating module sequentially repeats the first calculating step, the second calculating step and the third calculating step at least once until all the correlation curves are obtained.

In order to avoid that the DPF is in an overload state, in an alternative embodiment, the apparatus further comprises:

And the fourth determining unit is used for determining that the DPF is not in an overload state under the condition that the deviation values of all the correlation curves and the standard correlation curve are smaller than or equal to a first difference threshold value after fitting according to the correlation between the deviation values and the sample exhaust gas volume flow to obtain a plurality of correlation curves.

And a fifth determining unit for determining that the DPF is free from the overload risk when the DPF is not in the overload state and the deviation value of any one of the correlation curves from the standard correlation curve is smaller than or equal to a fourth difference threshold, the fourth difference threshold being smaller than the first difference threshold.

And a sixth determining unit that determines that the DPF is at risk of being overloaded and controls to perform a regeneration operation in a case where the DPF is not in an overloaded state and a deviation value of any one of the correlation curves from the standard correlation curve is greater than a fourth difference threshold.

The processing device for the vehicle fault comprises a processor and a memory, wherein the first acquisition unit, the calculation unit and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions. The modules are all located in the same processor; or the above modules may be located in different processors in any combination.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The inner core can be provided with one or more than one, and the problem that the error diagnosis is caused by the fact that the pressure difference signal is not credible when the pressure difference signal and the waste gas volume flow signal are analyzed and ignored in the prior art is solved by adjusting the parameters of the inner core.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

The embodiment of the invention provides a computer readable storage medium, which comprises a stored program, wherein the program is used for controlling equipment where the computer readable storage medium is positioned to execute the method for processing the vehicle faults.

Specifically, the vehicle fault processing method includes:

Step S201, under the condition that the unreliable fault exists in the differential pressure sensor, acquiring a plurality of groups of first working condition sample data of the vehicle, and carrying out cluster analysis on the plurality of groups of first working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of first cluster data, wherein the first working condition sample data comprises sample waste gas volume flow, an upstream temperature value of the DPF and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to inaccurate measurement;

Step S202, respectively obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to upstream temperature values and downstream temperature values in a plurality of groups of first clustering data in sequence, fitting according to the correlation between the deviation value and the sample waste gas volume flow to obtain a plurality of correlation curves, wherein the deviation value is the time interval between the peak value of the upstream temperature change rate curve and the peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one group of first clustering data;

The embodiment of the invention provides a processor, which is used for running a program, wherein the program runs to execute the method for processing the vehicle faults.

Specifically, the vehicle fault processing method includes:

The embodiment of the invention provides a vehicle fault management system, which comprises a processor, a memory and a program which is stored in the memory and can run on the processor, wherein the processor realizes at least the following steps when executing the program:

The application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with at least the following method steps:

It will be appreciated by those skilled in the art that the modules or steps of the invention described above may be implemented in a general purpose computing device, they may be concentrated on a single computing device, or distributed across a network of computing devices, they may be implemented in program code executable by computing devices, so that they may be stored in a storage device for execution by computing devices, and in some cases, the steps shown or described may be performed in a different order than that shown or described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple modules or steps of them may be fabricated into a single integrated circuit module. Thus, the present invention is not limited to any specific combination of hardware and software.

It will be appreciated by those skilled in the art that 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 flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.

From the above description, it can be seen that the above embodiments of the present application achieve the following technical effects:

1) Firstly, under the condition that the unreliable fault exists in the differential pressure sensor, acquiring a plurality of groups of first working condition sample data of the vehicle, and carrying out cluster analysis on the plurality of groups of first working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of first cluster data, wherein the first working condition sample data comprises sample waste gas volume flow, an upstream temperature value of a DPF and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to inaccurate measurement; then, respectively obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to upstream temperature values and downstream temperature values in a plurality of groups of first clustering data in sequence, fitting according to the correlation between the deviation value and the sample waste gas volume flow to obtain a plurality of correlation curves, wherein the deviation value is the time interval between the peak value of the upstream temperature change rate curve and the peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one group of first clustering data; and finally, under the condition that the deviation value of any one correlation curve and the standard correlation curve is larger than a first difference threshold, determining that the DPF is in an overload state and controlling to execute regeneration operation, wherein the overload state is a state that excessive particulate matters are accumulated in the DPF and cannot work normally, and the deviation value is the deviation value between each correlation curve and the standard correlation curve. According to the application, under the condition that the DPF differential pressure sensor of the current vehicle has an unreliable fault, namely, under the condition that the differential pressure value measured by the DPF differential pressure sensor is inaccurate, the upstream temperature and the downstream temperature of the DPF are measured by the temperature sensor to replace the differential pressure value measured by the differential pressure sensor, so that the overload state can still be identified under the unreliable state of the differential pressure sensor, the cluster analysis is carried out on the acquired working condition data, the DPF is judged whether to be overloaded according to the deviation value between the generated correlation curve of the working condition data and the standard correlation curve generated by the preset standard data, and under the condition that the deviation value is larger than the differential value threshold, the DPF is determined to be in the overload state and the regeneration operation is controlled to be executed. The application solves the problem of misdiagnosis caused by the fact that the pressure difference signal is not credible when the pressure difference signal is ignored in the prior art by utilizing the pressure difference signal of the pressure difference sensor and the waste gas volume flow signal for analysis.

2) The device for processing the vehicle fault comprises a first acquisition unit, a second acquisition unit and a third acquisition unit, wherein the first acquisition unit is used for acquiring a plurality of groups of first working condition sample data of the vehicle under the condition that the differential pressure sensor is determined to have an unreliable fault, and performing cluster analysis on the plurality of groups of first working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of first cluster data, the first working condition sample data comprises a sample waste gas volume flow, an upstream temperature value of a DPF and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to inaccurate measurement; the calculating unit is used for respectively obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to upstream temperature values and downstream temperature values in a plurality of groups of first clustering data in sequence, fitting according to the correlation between the deviation value and the sample waste gas volume flow to obtain a plurality of correlation curves, wherein the deviation value is the time interval between the peak value of the upstream temperature change rate curve and the peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one group of first clustering data; and the control unit is used for determining that the DPF is in an overload state and controlling the regeneration operation to be executed under the condition that the deviation value of any one correlation curve and the standard correlation curve is larger than a first difference threshold, wherein the overload state is a state that excessive particulate matters are accumulated in the DPF and cannot normally work, and the deviation value is the deviation value between each correlation curve and the standard correlation curve. According to the application, under the condition that the DPF differential pressure sensor of the current vehicle has an unreliable fault, namely, under the condition that the differential pressure value measured by the DPF differential pressure sensor is inaccurate, the upstream temperature and the downstream temperature of the DPF are measured by the temperature sensor to replace the differential pressure value measured by the differential pressure sensor, so that the overload state can still be identified under the unreliable state of the differential pressure sensor, the cluster analysis is carried out on the acquired working condition data, the DPF is judged whether to be overloaded according to the deviation value between the generated correlation curve of the working condition data and the standard correlation curve generated by the preset standard data, and under the condition that the deviation value is larger than the differential value threshold, the DPF is determined to be in the overload state and the regeneration operation is controlled to be executed. The application solves the problem of misdiagnosis caused by the fact that the pressure difference signal is not credible when the pressure difference signal is ignored in the prior art by utilizing the pressure difference signal of the pressure difference sensor and the waste gas volume flow signal for analysis.

The above description is only of the preferred embodiments of the present application and is not intended to limit the present application, but various modifications and variations can be made to the present application by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for handling a vehicle failure, wherein a differential pressure sensor is disposed on a surface of a DPF of the vehicle, the differential pressure sensor being configured to measure differential pressure across the DPF, the method comprising:

Under the condition that the unreliable fault exists in the differential pressure sensor, acquiring a plurality of groups of first working condition sample data of the vehicle, and carrying out cluster analysis on the plurality of groups of first working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of first cluster data, wherein the first working condition sample data comprises sample waste gas volume flow, an upstream temperature value of the DPF and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to inaccurate measurement;

Respectively obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to the upstream temperature values and the downstream temperature values in a plurality of groups of first clustering data in sequence, and fitting according to the correlation between a deviation value and the sample waste gas volume flow to obtain a plurality of correlation curves, wherein the deviation value is the time interval between the peak value of the upstream temperature change rate curve and the peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one group of first clustering data;

And under the condition that the deviation value of any one of the correlation curves and the standard correlation curve is larger than a first difference threshold, determining that the DPF is in an overload state and controlling to execute regeneration operation, wherein the overload state is a state that excessive particulate matters are accumulated in the DPF and cannot work normally, and the deviation value is the deviation value between each correlation curve and the standard correlation curve.

2. The method of claim 1, wherein prior to acquiring the plurality of sets of first operating condition sample data for the vehicle in the event that an unreliable fault is determined to exist with the differential pressure sensor, the method further comprises:

acquiring a plurality of groups of second working condition sample data of the vehicle, wherein the second working condition sample data comprise sample waste gas volume flow and sample differential pressure values measured by the differential pressure sensor;

Performing the cluster analysis on a plurality of groups of second working condition sample data by adopting the spectral clustering algorithm to obtain a plurality of groups of second aggregate data, wherein each group of second aggregate data comprises a plurality of groups of second working condition sample data;

Judging whether the differential pressure value measured by the differential pressure sensor is credible or not according to a plurality of groups of second aggregate data in sequence to obtain a plurality of judging results, wherein one judging result corresponds to one group of second aggregate data, and the judging results comprise the unreliable faults and the faults;

And under the condition that any one of the judging results is the unreliable fault, determining that the unreliable fault exists in the differential pressure sensor.

3. The method of claim 2, wherein performing the cluster analysis on the plurality of sets of second operating condition sample data using the spectral clustering algorithm to obtain a plurality of sets of second aggregate data, comprises:

Obtaining a data matrix according to the second working condition sample data, wherein the rows of the data matrix represent sample data of each sample, the columns of the data matrix represent sample characteristics, the sample data comprise one sample differential pressure value and one sample waste gas volume flow, and the sample characteristics comprise the sample differential pressure value and the sample waste gas volume flow;

Calculating weight values among all the samples according to the data matrix to obtain an adjacent matrix, and calculating to obtain a Laplacian matrix according to the adjacent matrix, wherein the adjacent matrix is a matrix formed by the weight values among any of the samples;

Calculating a feature vector corresponding to the minimum feature value of the Laplace matrix, and calculating a feature matrix according to the feature vector, wherein the feature matrix is formed by normalizing a matrix formed by the feature vectors;

and calculating the characteristic matrix and the set clustering number by adopting a K-means clustering algorithm to obtain a plurality of groups of second clustering data.

4. The method according to claim 2, wherein determining whether the differential pressure value measured by the differential pressure sensor is reliable sequentially according to the plurality of sets of the second aggregate data, to obtain a plurality of determination results, includes:

According to the fitting analysis of a plurality of groups of second aggregate data and a plurality of preset standard data, a pressure difference-volume flow diagram is obtained, wherein the pressure difference-volume flow diagram is a two-dimensional coordinate diagram, the abscissa of the two-dimensional coordinate diagram is the volume flow, and the ordinate of the two-dimensional coordinate diagram is the differential pressure value;

Generating a corresponding carbon deposition level curve according to a plurality of sample pressure difference values and a plurality of sample waste gas volume flows in a plurality of groups of second polymer data, wherein the carbon deposition level curve is a relation curve between the sample pressure difference values and the sample waste gas volume flows, and one group of second polymer data corresponds to one carbon deposition level curve;

generating a standard carbon deposition level curve according to a plurality of preset standard data, wherein the standard carbon deposition level curve is a relation curve between a standard pressure difference value and a standard waste gas volume flow in the preset standard data;

Determining that the judging result of the current carbon deposition level curve is the fault-free value under the condition that the offset value is smaller than or equal to a second difference value threshold, wherein the offset value is the offset between each carbon deposition level curve and the standard carbon deposition level curve;

And under the condition that the offset value is larger than the second difference value threshold value, determining that the judgment result of the current carbon deposition level curve is the unreliable fault.

5. The method of claim 4, wherein after determining that the determination of the current soot level curve is the fault-free, the method further comprises:

determining that the DPF is not in an overload state if the offset value is less than or equal to a third difference threshold, the third difference threshold being less than the second difference threshold;

In the event that the offset value is greater than the third difference threshold, determining that the DPF is in the overload condition and controlling the regeneration operation.

6. The method of claim 1, wherein sequentially obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to the upstream temperature values and the downstream temperature values in the plurality of sets of first cluster data, respectively, and fitting according to a correlation between a deviation value and the sample exhaust gas volume flow to obtain a plurality of correlation curves, comprises:

a first calculation step of respectively generating an upstream temperature change rate curve and a downstream temperature change rate curve according to the change condition of the upstream temperature value and time and the change condition of the downstream temperature value and time;

A second calculation step of obtaining the deviation values corresponding to a plurality of first peaks and a plurality of second peaks according to the upstream temperature change rate curve and the downstream temperature change rate curve, wherein the first peaks are peaks on the upstream temperature change rate curve, the second peaks are peaks on the downstream temperature change rate curve, and the first peaks and the second peaks are in one-to-one correspondence;

a third calculation step of generating a group of correlation curves corresponding to the first cluster data according to a plurality of deviation values and a plurality of sample waste gas volume flows, wherein the deviation values are in one-to-one correspondence with the sample waste gas volume flows;

And sequentially repeating the first calculation step, the second calculation step and the third calculation step at least once until all the correlation curves are obtained.

7. The method of claim 1, wherein after fitting a plurality of correlation curves from correlations between the deviation values and the sample exhaust gas volumetric flow rates, the method further comprises:

determining that the DPF is not in the overload state if all of the deviation values of the correlation curves from the standard correlation curve are less than or equal to the first difference threshold;

Determining that the DPF is free of an overload risk if the DPF is not in the overload state and the deviation value of any one of the correlation curves from the standard correlation curve is less than or equal to a fourth difference threshold, the fourth difference threshold being less than the first difference threshold;

in the event that the DPF is not in the overload state and the deviation value of any one of the correlation curves from the standard correlation curve is greater than the fourth difference threshold, determining that the DPF is at risk of overload and controlling the regeneration operation.

8. A device for handling a vehicle failure, wherein a differential pressure sensor is disposed on a surface of a DPF of the vehicle, the differential pressure sensor being configured to measure differential pressure across the DPF, the device comprising:

the first acquisition unit is used for acquiring a plurality of groups of first working condition sample data of the vehicle under the condition that the differential pressure sensor is determined to have an unreliable fault, and carrying out cluster analysis on the plurality of groups of first working condition sample data by adopting a spectral clustering algorithm to obtain a plurality of groups of first cluster data, wherein the first working condition sample data comprises sample waste gas volume flow, an upstream temperature value of the DPF and a downstream temperature value of the DPF, and the unreliable fault is a fault that the differential pressure value measured by the differential pressure sensor is not in a preset range and belongs to inaccurate measurement;

The calculating unit is used for respectively obtaining an upstream temperature change rate curve and a downstream temperature change rate curve according to the upstream temperature values and the downstream temperature values in the plurality of groups of first clustering data in sequence, fitting according to the correlation between the deviation value and the sample waste gas volume flow to obtain a plurality of correlation curves, wherein the deviation value is the time interval between the peak value of the upstream temperature change rate curve and the peak value of the downstream temperature change rate curve, and one correlation curve corresponds to one group of first clustering data;

and the control unit is used for determining that the DPF is in an overload state and controlling the regeneration operation to be executed under the condition that the deviation value of any one of the correlation curves and the standard correlation curve is larger than a first difference threshold, wherein the overload state is a state that too much particulate matters are accumulated in the DPF and cannot normally work, and the deviation value is the deviation value between each correlation curve and the standard correlation curve.

9. A computer readable storage medium, characterized in that the computer readable storage medium comprises a stored program, wherein the program, when run, controls a device in which the computer readable storage medium is located to perform the method of any one of claims 1 to 7.

10. A vehicle fault management system, comprising: one or more processors, memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing the method of any of claims 1-7.