CN115186502A

CN115186502A - Vehicle abnormal data identification method and device, electronic device and storage medium

Info

Publication number: CN115186502A
Application number: CN202210891134.1A
Authority: CN
Inventors: 王欢; 王玉坤; 张珂; 牛尚冰; 邓紫威; 张瑞天; 孙哲; 牛亚琪
Original assignee: Zhejiang Geely Holding Group Co Ltd; Weirui Electric Automobile Technology Ningbo Co Ltd; Zhejiang Zeekr Intelligent Technology Co Ltd
Current assignee: Zhejiang Geely Holding Group Co Ltd; Weirui Electric Automobile Technology Ningbo Co Ltd; Zhejiang Zeekr Intelligent Technology Co Ltd
Priority date: 2022-07-27
Filing date: 2022-07-27
Publication date: 2022-10-14

Abstract

The application discloses a method and a device for identifying abnormal data of a vehicle, an electronic device and a storage medium, wherein the method for identifying the abnormal data of the vehicle comprises the following steps: acquiring at least one group of arrays to be identified corresponding to a preset time period to be identified; comparing the arrays to be identified, and determining the array difference degree corresponding to each array to be identified; and if a target array with array difference exceeding a preset difference threshold value is detected in each array to be identified, determining the data in the target array as abnormal data. The method and the device solve the technical problem that in the prior art, the identification accuracy of the abnormal data is low.

Description

Vehicle abnormal data identification method and device, electronic device and storage medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method and an apparatus for identifying abnormal data of a vehicle, an electronic device, and a storage medium.

Background

With the increasing popularization of new energy vehicles, countries and vehicle enterprises also put higher requirements on the supervision of new energy vehicle operation data, and the accurate identification of abnormal data from massive operation data is one of the keys for improving the safety early warning capability of new energy vehicles.

At present, for time series data such as the temperature in a battery pack and the voltage of a cell, difference values between data detected by different detection cells corresponding to the same time are mainly calculated, and abnormal data identification is performed according to whether the difference values exceed a preset difference threshold value, however, the identification accuracy of the abnormal data identification method is low due to the large numerical fluctuation range of the abnormal data, if the difference threshold value is set to be large, abnormal data which abnormally fluctuate within a small numerical range can be missed, and potential safety hazards exist, and if the difference threshold value is set to be small, a large amount of non-abnormal deviations can be mistakenly reported as abnormal data, so that user experience is affected.

Disclosure of Invention

The application mainly aims to provide a vehicle abnormal data identification method, a vehicle abnormal data identification device, an electronic device and a storage medium, and aims to solve the technical problem that in the prior art, abnormal data identification accuracy is low.

In order to achieve the above object, the present application provides an abnormal data recognition method for a vehicle, the abnormal data recognition method comprising:

acquiring at least one group of arrays to be identified corresponding to a preset time period to be identified;

comparing the arrays to be identified, and determining the array difference degree corresponding to each array to be identified;

and if a target array with array difference exceeding a preset difference threshold value is detected in each array to be identified, determining the data in the target array as abnormal data.

Optionally, the array difference includes a change rate difference, the comparing the arrays to be identified, and the determining the array difference corresponding to each array to be identified includes:

determining the change rate array corresponding to each array to be identified;

comparing the change rate arrays among the groups to determine the Euclidean distance among the change rate arrays;

and determining the change rate difference degree corresponding to each array to be identified according to each Euclidean distance.

Optionally, the step of determining, according to each euclidean distance, a change rate difference degree corresponding to each of the to-be-identified arrays includes:

calculating a first average value of Euclidean distances corresponding to each change rate array and a second average value of each first average value;

and determining the difference value between the first average value and the second average value corresponding to each change rate array as the change rate difference degree corresponding to each change rate array.

Optionally, the step of determining the change rate array corresponding to each array to be identified includes:

acquiring a previous frame subdata and a next frame subdata of two adjacent frames in each array to be identified and a time difference between the next frame subdata and the previous frame subdata;

and calculating the ratio of the difference between the next frame of subdata and the previous frame of subdata to the time difference to obtain change rate subdata, wherein the change rate array consists of at least one change rate subdata.

Optionally, before the step of obtaining at least one group of arrays to be identified corresponding to the preset time period to be identified, the method further includes:

obtaining at least one current operating data of the vehicle;

detecting whether suspected abnormal data exceeding the range of the corresponding preset first threshold exists in each current operation data or not;

if suspected abnormal data exceeding the range of the corresponding preset first threshold value is detected in each current operation data, determining a preset time period to be identified according to the suspicious time point corresponding to the suspected abnormal data.

Optionally, if suspected abnormal data exceeding the respective corresponding preset first threshold range is detected in each current operating data, the step of determining the preset time period to be identified according to the suspicious time point corresponding to the suspected abnormal data includes:

if suspected abnormal data exceeding the range of the corresponding preset first threshold value is detected in each current operation data, judging whether the suspected abnormal data exceeds the range of a preset second threshold value;

if the suspected abnormal data exceeds a preset second threshold range, determining the suspected abnormal data as abnormal data;

and if the suspected abnormal data does not exceed the preset second threshold range, determining a preset time range from the suspicious time point corresponding to the suspected abnormal data as a preset time period to be identified.

Optionally, the abnormal data identification method for a vehicle further includes:

and when the abnormal data is detected, generating and outputting alarm information corresponding to the abnormal data.

The present application also provides an abnormal data identification apparatus, including:

the acquisition module is used for acquiring at least one group of arrays to be identified corresponding to a preset time period to be identified;

the difference determining module is used for comparing the arrays of the arrays to be identified and determining the array difference corresponding to the arrays to be identified;

and the abnormal data determining module is used for determining the data in the target array as abnormal data if the target array with the array difference degree exceeding a preset difference degree threshold value is detected in each array to be identified.

The present application further provides an electronic device, the electronic device is an entity device, the electronic device includes: the vehicle abnormal data identification method comprises a memory, a processor and a program of the vehicle abnormal data identification method stored on the memory and capable of running on the processor, wherein the program of the vehicle abnormal data identification method can realize the steps of the vehicle abnormal data identification method when being executed by the processor.

The present application also provides a storage medium which is a computer-readable storage medium having stored thereon a program for implementing the abnormal data identifying method of a vehicle, which when executed by a processor, implements the steps of the abnormal data identifying method of a vehicle as described above.

The present application also provides a computer program product comprising a computer program which, when executed by a processor, implements the steps of the method for identifying abnormal data of a vehicle as described above.

The application provides a method, a device, an electronic device and a storage medium for identifying abnormal data of a vehicle, wherein the method comprises the steps of obtaining at least one group of arrays to be identified corresponding to a preset time period to be identified, comparing the arrays to be identified, determining the array difference degree corresponding to each array to be identified, comparing the array difference degrees, determining data in the target array to be abnormal data if the array difference degree exceeds a target array with a preset difference degree threshold value in each array to be identified, identifying the abnormal data based on the array difference degree, comparing the difference degree between the arrays with the difference value between single data corresponding to a single moment, wherein the array difference degree not only comprises the difference of the data sizes between the arrays, but also can reflect the difference of the data change conditions of different arrays, further judging the abnormal data from the two aspects of the data sizes and the data change conditions, and combining the abnormal condition fluctuation of the data, so that the technical problem of low data identification accuracy in the prior art is solved.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and, together with the description, serve to explain the principles of the application.

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art to obtain other drawings without inventive exercise.

FIG. 1 is a schematic diagram of a time-varying curve of data to be identified provided herein;

FIG. 2 is a schematic representation of another time-dependent profile of data to be identified provided herein;

FIG. 3 is a schematic flow chart diagram illustrating one embodiment of anomalous data identification for a vehicle according to the present application;

fig. 4 is a schematic view of an abnormal data identification scenario provided in this embodiment;

FIG. 5 is a schematic flow chart diagram illustrating another embodiment of the vehicle anomaly data identification of the present application;

FIG. 6 is a schematic diagram of an array to be identified in one possible embodiment provided herein;

FIG. 7 is a schematic diagram of a change rate array corresponding to an array to be identified in an exemplary embodiment of the present disclosure;

FIG. 8 is a schematic diagram of an array to be identified in another possible implementation provided herein;

FIG. 9 is a schematic diagram illustrating a change rate array corresponding to an array to be identified in another embodiment of the present disclosure;

FIG. 10 is a diagram illustrating Euclidean distances corresponding to an array to be identified in an exemplary embodiment of the present disclosure;

FIG. 11 is a schematic diagram illustrating Euclidean distances corresponding to an array to be identified in another possible embodiment provided by the present application;

fig. 12 is a schematic device configuration diagram of a hardware operating environment related to the abnormal data identification method for the vehicle in the embodiment of the present application.

The implementation of the objectives, functional features, and advantages of the present application will be further described with reference to the accompanying drawings.

Detailed Description

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in detail below. It is to be understood that the described embodiments are merely exemplary of the invention, and not restrictive of the full scope of the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

At present, for time series data such as the temperature in a battery pack, the cell voltage of a battery cell and the like, difference values between data detected by different detection cells corresponding to the same time are mainly calculated, and abnormal data identification is performed according to whether the difference values exceed a preset difference threshold value. However, the states of the detection cells (for example, cell electric cores, temperature probes, etc.) in the vehicle are not completely the same, so that the magnitude of the monitored data may deviate, but the variation trend difference of the data should be smaller under the condition that the overall operation state of the vehicle is the same, for example, a battery pack of a new energy vehicle may include one or more battery modules, each battery module includes one or more cell electric cores, the temperature probes are usually disposed at different positions of the battery pack, the distance between each position and a heat source may be the same or different, and the temperature fields distributed unevenly in the battery pack may cause the temperature detected by each temperature probe at the same time to differ; in another example, the SOC (state of charge) of each cell in the new energy vehicle battery pack may be the same or different, and the difference in SOC may also cause a difference in the voltages of the cells detected at the same time. However, if the difference threshold is set to be small, a large amount of non-abnormal deviations are falsely reported as abnormal data, which affects user experience. For example, fig. 1 is a schematic diagram of a time-varying curve of data to be identified provided by the present application, as shown in fig. 1, fig. 1 includes a curve of temperature variation with time corresponding to 28 temperature probes numbered T1 to T28, where the abscissa is time and the ordinate is temperature, in a region indicated by a box, among temperatures detected by respective temperature probes corresponding to the same time, a difference between a highest temperature and a lowest temperature exceeds 10 ℃, and if abnormality identification is performed according to whether single data at a single time exceeds a threshold, it is very easy to determine as abnormal data, however, it can be known from an overall variation trend of respective temperature curves of fig. 1 that a temperature difference in fig. 1 is possibly caused by uneven distribution of a temperature field, a temperature probe closer to a high-temperature region is higher in temperature, and a temperature probe farther from the high-temperature region is lower in temperature, that is, data detected in a region indicated by a box in fig. 1 is not abnormal data. In the prior art, a difference comparison method for single data corresponding to a single moment identifies non-abnormal deviation of an area similar to a square frame in fig. 1 as abnormal data, which causes a large amount of false alarms and affects user experience.

While the value of common abnormal data usually fluctuates frequently within a certain time range, fig. 2 is a schematic diagram of another time-varying curve of data to be identified provided by the present application, as shown in fig. 2, fig. 2 includes a curve of temperature variation with time corresponding to 28 temperature probes numbered from T1 to T28, where the abscissa is time and the ordinate is temperature, where the temperature probe numbered as T18 detects abnormal data, and as can be seen from fig. 2, the abnormal data has a characteristic that the value fluctuates frequently.

In view of the above, the present application provides a method, an apparatus, an electronic device, and a storage medium for identifying abnormal data of a vehicle, in which at least one group of arrays to be identified corresponding to a preset time period to be identified is obtained, the arrays are compared, an array difference corresponding to each array to be identified is determined, the difference between the arrays is compared, and then, if a target array in which the array difference exceeds a preset difference threshold is detected in each array to be identified, data in the target array is determined as abnormal data, so that identification of the abnormal data based on the difference between the arrays is achieved. Compared with the difference value between the single data corresponding to a single moment, the difference degree between the data groups not only comprises the difference of the numerical values between the data groups, but also can reflect the difference of the data change conditions of different data groups, and further can judge abnormal data from two aspects of the numerical values and the data change conditions, the abnormal fluctuation condition of the data can be accurately identified by combining the data change conditions no matter whether the fluctuation numerical value range of the abnormal data is large or small, and the technical problem of lower identification accuracy of the abnormal data in the prior art is solved.

In a first embodiment of the method for identifying abnormal data of a vehicle according to the present application, referring to fig. 3, the method for identifying abnormal data of a vehicle includes:

step S10, acquiring at least one group of arrays to be recognized corresponding to a preset time period to be recognized;

in this embodiment, it should be noted that the abnormal data identification method for the vehicle may be applied to a vehicle monitoring platform, where the vehicle monitoring platform is a platform for collecting, monitoring, storing and the like vehicle operation data, and includes an automobile enterprise monitoring platform or a national monitoring platform, and the abnormal data identification method for the vehicle may also be applied to a vehicle-mounted terminal. For convenience of reading and understanding, the vehicle monitoring platform is taken as an execution main body of the abnormal data identification method for the vehicle in the present application to specifically explain the present embodiment, and referring to fig. 4, fig. 4 is a schematic view of an abnormal data identification scene provided in the present embodiment, and the vehicle monitoring platform receives the operation data uploaded by the vehicle and performs abnormal data identification on the operation data.

In an implementable manner, the abnormal data identification method of the vehicle is used for performing abnormal data identification on time series data in operation data of a new energy automobile, wherein the time series data are time series data, are data collected at different times and are used for the condition that the described phenomenon changes along with time, and the time series data in the operation data of the new energy automobile comprise the temperature in a battery pack, the cell voltage, the tire pressure and the like. In order to ensure the safety of the new energy automobile, for example, the use safety of a battery, the safety of a vehicle in the driving process and the like, a plurality of detection units for detecting the vehicle operation data are arranged on the new energy automobile, for example, a plurality of temperature probes arranged at different positions in a battery pack, the detection unit for detecting the voltage of each single battery cell and the like are arranged, the vehicle-mounted terminal can regularly acquire the operation data detected by each detection unit and upload the operation data to a vehicle monitoring platform so as to analyze the data, monitor the fault and the like of the vehicle monitoring platform.

Specifically, at least one group of arrays to be identified corresponding to a preset time period to be identified is obtained from a vehicle-mounted terminal of the vehicle, where the arrays to be identified are formed by arranging single data of a single moment detected by a detection unit in the vehicle-mounted terminal according to a time sequence, and each array to be identified corresponds to a different detection unit, that is, subdata in each group of arrays to be identified is data detected by the same detection unit, for example, if three temperature probes A1, A2, and A3 exist, and each temperature probe detects 5 temperature values in t1 to t2 minutes, an array to be identified A1 corresponding to the temperature probe A1, an array to be identified A2 corresponding to the temperature probe A2, and an array to be identified A3 corresponding to the temperature probe A3 can be obtained, where the array to be identified A1 is formed by detecting 5 temperature values in t1 to t2 minutes by the temperature probe A1, and the array to be identified A3 is formed by detecting 5 temperature values in t1 to t2 minutes by the temperature probe A2, and the array to be identified A3 is formed by detecting 5 temperature values in t1 to t2 minutes.

It should be noted that the preset time period to be identified may be determined based on actual needs or test results, which is not limited in this embodiment, for example, the preset time period to be identified may be used as a time interval for acquiring the array to be identified each time, the array to be identified is acquired once every preset time period to be identified to identify the abnormal data, or a certain time range corresponding to the suspected abnormal data may be determined as the preset time period to be identified based on the suspected abnormal data identified in advance.

step A10, acquiring at least one current operation data of the vehicle;

in the present embodiment, the current operation data detected by each detection cell in the vehicle is obtained in real time from the vehicle-mounted terminal of the vehicle, and illustratively, at least one current operation data of the vehicle may be obtained by consuming real-time stream data of Kafka (an open source stream processing platform), flume (a log collection system), or the like.

Step A20, detecting whether suspected abnormal data exceeding a respective corresponding preset first threshold range exists in each current operation data;

in this embodiment, it should be noted that the operation data that can be detected at a time includes a plurality of types, such as a temperature in a battery pack, a cell voltage, a tire pressure, and the like, each type of operation data may have a corresponding threshold range, and a preset first threshold range corresponding to each type of operation data may be determined according to big data, an actual test result, and the like, may be a fixed numerical range, and may also dynamically change according to a specific numerical value of each current operation data.

Specifically, each of the current operation data is compared with a preset first threshold range, whether each of the current operation data exceeds the preset first threshold range is respectively determined, if target operation data exceeding the preset first threshold range is detected in each of the current operation data, the target operation data is used as suspected abnormal data, and if target operation data exceeding the preset first threshold range is not detected in each of the current operation data, it may be determined that suspected abnormal data does not exist in each of the current operation data, or it may also be determined that abnormal data does not exist in each of the current operation data.

In an implementation manner, after the step of detecting whether there is any suspected abnormal data that exceeds the corresponding preset first threshold range in each current operation data, the method further includes: if suspected abnormal data exceeding the range of the corresponding preset first threshold value is detected in each current operation data, determining a target detection single body corresponding to the suspected abnormal data, and taking the data detected by the target detection single body after the current time as the suspected abnormal data until the suspected abnormal data is determined to be normal data, namely determining that the suspected abnormal data is not abnormal data. The abnormal data is usually caused by faults, if the faults are not solved after the faults occur, the detection single body can continuously detect the abnormal data, if the suspected abnormal data is abnormal numerical control, the faults are found, the subsequent continuous detection process is an unnecessary repeated detection process, and unnecessary time and calculation resources are occupied, so that the data detected by the target detection single body after the suspected data are detected are all used as the suspected abnormal data, the suspected abnormal data can be stored for analysis, and when the suspected abnormal data are determined not to be abnormal data, the abnormal data identification of the data detected by the detection single body can be recovered, and further the whole load pressure of the vehicle monitoring platform can be effectively reduced.

Step a30, if suspected abnormal data exceeding the respective corresponding preset first threshold range is detected in each current operation data, determining a preset time period to be identified according to the suspicious time point corresponding to the suspected abnormal data.

In this embodiment, specifically, if suspected abnormal data exceeding a preset first threshold range corresponding to each of the current operation data is detected in each of the current operation data, a suspicious time point corresponding to the suspected abnormal data is determined, a preset time range to which the suspicious time point belongs is determined as a preset time period to be identified, and if suspected abnormal data exceeding the preset first threshold range corresponding to each of the current operation data is not detected in each of the current operation data, it is determined that abnormal data does not exist in each of the current operation data, where the preset time range may be determined according to big data, an actual test result, and the like, a time length of the preset time range may be determined by combining timeliness and a calculation amount, for example, 7 minutes, 10 minutes, 12 minutes, and the like, this embodiment is not limited, and exemplarily, the suspicious time point and a period before the suspicious time point may be determined as a preset time period to be identified, and a period after the suspicious time point and a certain time before the suspicious time point may also be determined as a preset time period to be identified.

Optionally, if suspected abnormal data exceeding the respective corresponding preset first threshold range is detected in each of the current operating data, the step of determining a preset time period to be identified according to the suspicious time point corresponding to the suspected abnormal data includes:

step A31, if suspected abnormal data exceeding a respective corresponding preset first threshold range is detected in each current operation data, judging whether the suspected abnormal data exceeds a preset second threshold range;

in this embodiment, specifically, if suspected abnormal data exceeding a preset first threshold range is detected in each of the current operation data, the suspected abnormal data is compared with a preset second threshold range, and it is determined whether the suspected abnormal data exceeds a preset second threshold range, where the preset second threshold range is greater than the preset first threshold range, the preset second threshold range may be determined according to big data, an actual test result, and the like, may be a fixed numerical range, and may also dynamically change according to a specific numerical value of each of the current operation data, which is not limited in this embodiment.

Step A32, if the suspected abnormal data exceeds a preset second threshold range, determining that the suspected abnormal data is abnormal data;

in this embodiment, specifically, if the suspected abnormal data exceeds the preset second threshold range, the suspected abnormal data is determined to be abnormal data, and for data whose numerical value exceeds the reasonable range by a long distance and is basically not misjudged, the data can be directly determined to be abnormal data without performing the difference determination between the arrays, and the resource and time consumed by the difference determination between the arrays can be effectively reduced under the condition of ensuring the accuracy.

Step a33, if the suspected abnormal data does not exceed the preset second threshold range, determining a preset time range from the suspected abnormal data to the suspicious time point corresponding to the suspected abnormal data as a preset time period to be identified.

In this embodiment, specifically, if the suspected abnormal data does not exceed the preset second threshold range, the suspicious time point corresponding to the suspected abnormal data is determined, and the preset time range to which the suspicious time point belongs is determined as the preset time period to be identified.

In the embodiment, the comparison process of the numerical values is preposed, the current operation data is preliminarily screened, compared with the difference comparison process between the arrays, the calculation amount of the comparison process of the numerical values of the data is smaller, the speed is higher, the current operation data can be obtained in real time and detected in real time, the time efficiency is higher, suspected abnormal data possibly having abnormality can be screened out in time, the time period to be identified is determined according to the suspected abnormal data, the difference comparison between the arrays to be identified corresponding to the time period to be identified is carried out on the arrays to be identified, and the difference comparison is carried out on the suspected abnormal data subsequently, so that the threshold range setting of the comparison process of the numerical values can be set to be larger, the safety is ensured as much as possible, and the condition of possible false alarm can be avoided through the subsequent difference comparison between the arrays, and the accuracy of the identification of the whole abnormal data can be improved.

S20, comparing the arrays to be identified, and determining the array difference degree corresponding to each array to be identified;

in this embodiment, specifically, the difference between the sets of data to be identified is compared, and the difference between the sets of data to be identified is determined, where the difference between the sets of data includes a numerical difference in a numerical dimension and/or a rate difference in a rate of change in a numerical dimension.

For example, the comparison manner of the difference between the arrays may be to compare the numerical values of the subdata corresponding to the same time in each array to be identified, and determine the numerical difference; calculating and determining the change rate of each subdata in each array to be identified, comparing the change rates of the subdata corresponding to the same moment in each array to be identified, and determining the difference degree of the change rates; and jointly determining the numerical value difference degree and the numerical value change rate difference degree as the difference degree among the groups.

Step S30, if a target array with an array difference exceeding a preset difference threshold is detected in each array to be identified, determining data in the target array as abnormal data.

In this embodiment, specifically, each array difference is compared with a preset difference threshold, whether each array difference exceeds the preset difference threshold is detected, if a target array with the array difference exceeding the preset difference threshold is detected in each array to be identified, data in the target array is determined as abnormal data, and if a target array with the array difference exceeding the preset difference threshold is not detected in each array to be identified, it is determined that abnormal data does not exist in each array to be identified.

In an implementation manner, if the array difference is more than one, each array difference corresponds to a difference threshold, if a target array in which the array difference exceeds a preset difference threshold is detected in each array to be identified, the data in the target array is determined as anomalous data, for example, if the array difference includes a numerical difference and a change rate difference, the numerical difference corresponds to the numerical difference threshold, the change rate difference corresponds to the change rate difference threshold, and if the numerical difference exceeds the preset numerical difference threshold and the change rate difference exceeds the target array in which the change rate difference threshold is detected in each array to be identified, the target array is determined as anomalous data.

and when abnormal data are detected, generating and outputting alarm information corresponding to the abnormal data.

In this embodiment, specifically, when abnormal data is detected at any stage in the abnormal data identification method for a vehicle, abnormal data information corresponding to the abnormal data is determined, corresponding alarm information is generated based on the abnormal data information, and the alarm information is output to an electronic device of a user or a related monitoring person, where the alarm information includes the abnormal data information, the abnormal data information includes a specific value of the abnormal data, time information corresponding to the abnormal data, a number of a detection unit corresponding to the abnormal data, position information of the detection unit corresponding to the abnormal data, and/or vehicle information corresponding to the abnormal data, and the output form of the alarm information may be a short message, a telephone call, an indicator light, a prompt message, an alarm sound, and the like.

In the embodiment, at least one group of arrays to be recognized corresponding to a preset time period to be recognized is obtained, the arrays to be recognized are compared, the array difference degree corresponding to each array to be recognized is determined, the comparison of the difference degree between the arrays is realized, and then if a target array with the array difference degree exceeding a preset difference degree threshold value is detected in each array to be recognized, the data in the target array is determined to be abnormal data, the identification of abnormal data based on the difference degree between the arrays is realized.

Further, referring to fig. 5, based on the above embodiment of the present application, in another embodiment of the present application, the same or similar contents to those of the above embodiment may refer to the above description, and are not repeated herein. On this basis, the array difference comprises a change rate difference, the step of comparing the arrays to be identified and determining the array difference corresponding to each array to be identified comprises the following steps:

s21, determining the change rate array corresponding to each array to be identified;

in this embodiment, it should be noted that the array difference includes a change rate difference, where the change rate difference is a difference between a data change rate of data in an array and a data change rate of data in another array, the change rate array is composed of a change rate corresponding to each subdata in the array, and the change rate corresponding to each subdata in the array may be determined by a preset change rate algorithm or a first derivative manner.

Specifically, the change rate corresponding to each subdata in each array to be identified is determined, and one or more change rates corresponding to the same array to be identified are combined into a change rate array to obtain a change rate array corresponding to each array to be identified.

step S211, acquiring a previous frame subdata and a next frame subdata of two adjacent frames in each array to be identified, and a time difference between the next frame subdata and the previous frame subdata;

step S212, calculating the ratio of the difference between the next frame of subdata and the previous frame of subdata to the time difference to obtain change rate subdata, wherein the change rate array is composed of at least one change rate subdata.

In this embodiment, specifically, a previous sub-data frame and a next sub-data frame of two adjacent frames in each to-be-identified array, and a time difference between the next sub-data frame and the previous sub-data frame are obtained, a difference between the next sub-data frame and the previous sub-data frame is calculated, a ratio of the difference to the time difference is used as change rate sub-data corresponding to the next sub-data frame, change rate sub-data corresponding to part or all of the sub-data in each to-be-identified array is calculated and determined, and the change rate sub-data corresponding to the same to-be-identified array are sequentially arranged to form a change rate array, so that the change rate array corresponding to each to-be-identified array can be obtained.

In an implementation manner, referring to fig. 6 and 7, fig. 6 is a schematic diagram of an array to be identified in an implementation manner provided in the present application, in fig. 6, T1, T2, T3, and T4 are numbers of temperature probes, respectively, T1, T2, T3, T4, and T5 are time points arranged in sequence, a time difference value between each time point and an adjacent time point is 1 time unit, where T1 is an earliest time point, and T5 is a latest time point, each of tables is listed as an array to be identified, each value is a temperature detected by the corresponding temperature probe at the corresponding time point, a difference value between a temperature corresponding to each time point and a temperature at the previous time point is divided by the time difference value to obtain a change rate corresponding to each time point, a change rate of the temperature in each of the array to be identified is calculated and determined as shown in fig. 7, fig. 7 is a schematic diagram of a change rate array corresponding to the array to be identified in one implementation manner, fig. 7 is a schematic diagram of a set of tables of T1, T2, T3, and T4, and a time point, and a change rate of the corresponding to the temperature probe at the previous time point, and a time point are listed as a time point, and a change rate is a time point, and a time point, respectively, and a change rate is a time point is listed as a time point.

In another implementation manner, referring to fig. 8 and 9, fig. 8 is a schematic diagram of an array to be identified in another implementation manner provided in this application, in fig. 8, V1, V2, V3, and V4 are numbers of individual cells, respectively, t1, t2, t3, t4, t5, t6, and t7 are time points arranged in sequence, a time difference between each time point and an adjacent time point is 1 time unit, where t1 is an earliest time point, t7 is a latest time point, each column in the table is a set of array to be identified, each value is a voltage of a corresponding individual cell, a change rate corresponding to each time point is obtained by dividing a difference between a voltage corresponding to each time point and a voltage of a previous time point by the time difference, a change rate corresponding to each time point is calculated and determined, the change rate of the voltage in each array to be identified is as shown in fig. 9, fig. 9 is a schematic diagram of an array corresponding to an array to the array to be identified in another implementation manner, where V1, V2, V3, t4, t7 are numbers of the corresponding to the voltage at the time points, t6, and t7 are times of the voltage change rates, and the time points are arranged in sequence, and the time points are the latest time points.

Step S22, comparing the change rate arrays among several groups to determine the Euclidean distance among the change rate arrays;

in this embodiment, specifically, the groups of the change rate arrays are compared, and the euclidean distance between the change rate arrays is calculated and determined, where a specific calculation method of the euclidean distance is similar to that in the prior art and is not described in detail herein.

In an implementable manner, the change rate array corresponding to each temperature probe in the table shown in fig. 7 and the change rate array corresponding to each temperature probe are subjected to euclidean distance calculation, so as to obtain a result shown in fig. 10, fig. 10 is a schematic diagram of euclidean distances corresponding to arrays to be identified in an implementable manner provided by the present application, in fig. 10, T1, T2, T3, and T4 are numbers of the temperature probes, respectively, and the euclidean distance between the change rate arrays corresponding to any two temperature probes is calculated and determined as shown in fig. 10.

In another practical manner, the change rate array corresponding to each single battery cell in the table shown in fig. 9 and the change rate array corresponding to each single battery cell are calculated to obtain a result shown in fig. 11, where fig. 11 is a schematic diagram of euclidean distances corresponding to arrays to be identified in another practical manner provided by this application, V1, V2, V3, and V4 in fig. 11 are numbers of single battery cells, respectively, and the euclidean distances between the change rate arrays corresponding to any two determined single battery cells are calculated and determined as shown in fig. 11.

And S23, determining the change rate difference degree corresponding to each array to be identified according to each Euclidean distance.

In this embodiment, specifically, according to each euclidean distance, the change rate difference degree corresponding to each array to be identified is determined.

For example, the array difference degree may be a difference degree between each array to be identified and an array to be identified other than itself, or may be a difference degree between each array to be identified and an average level of all arrays to be identified.

For example, the manner of determining the array difference degree corresponding to each array to be identified according to each euclidean distance may be to compare each euclidean distance with a preset standard euclidean distance, and use a difference value between each euclidean distance and a preset standard euclidean distance as the array difference degree corresponding to each array to be identified, where the standard euclidean distance may be determined according to big data, an actual test, or the like, or may be an average value of each euclidean distance, or the like.

step S231, calculating a first average value of euclidean distances corresponding to each of the change rate arrays, and a second average value of each of the first average values;

in this embodiment, specifically, a first average value of the euclidean distances corresponding to each of the change rate arrays is calculated, and an average value is obtained for each of the first average values, so as to obtain a second average value, where the second average value is an average euclidean distance of all the euclidean distances corresponding to the preset time period to be identified.

In one practical aspect, referring to fig. 10, in fig. 10, the numerical value in the row corresponding to the divag is the first average value of the euclidean distances corresponding to the respective change rate arrays, the divag corresponding to T1 is the average value of the euclidean distances between the change rate array corresponding to T1 and the change rate arrays corresponding to T1, T2, T3, and T4, the divag corresponding to T2 is the average value of the euclidean distances between the change rate array corresponding to T2 and the change rate arrays corresponding to T1, T2, T3, and T4, the divag corresponding to T3 is the average value of the euclidean distances between the change rate array corresponding to T3 and the change rate arrays corresponding to T1, T2, T3, and T4, and the numerical value in the row corresponding to the divag is the second average value in fig. 10.

In another practical aspect, referring to fig. 11, in fig. 11, a numerical value in a row corresponding to the divag is a first average value of the euclidean distances corresponding to the respective change rate arrays, the divag corresponding to V1 is an average value of the euclidean distances between the change rate array corresponding to V1 and the change rate arrays corresponding to V1, V2, V3, and V4, the divag corresponding to V2 is an average value of the euclidean distances between the change rate array corresponding to V2 and the change rate arrays corresponding to V1, V2, V3, and V4, the divag corresponding to V3 is an average value of the euclidean distances between the change rate array corresponding to V3 and the change rate arrays corresponding to V1, V2, V3, and V4, the dig corresponding to V4 is an average value of the euclidean distances between the change rate array corresponding to V4 and the change rate arrays corresponding to V1, V2, V3, and V4, and the numerical value in a row corresponding to the Avg is a second average value in fig. 11.

Step S232, determining a difference between the first average value and the second average value corresponding to each of the change rate arrays as a change rate difference corresponding to each of the change rate arrays.

In this embodiment, specifically, a difference between the first average value and the second average value corresponding to each of the change rate arrays is determined by calculation, and the difference between the first average value and the second average value corresponding to each of the change rate arrays is determined as the change rate difference degree corresponding to each of the change rate arrays.

In one practical embodiment, referring to fig. 10, the difference between the divag and the Avg corresponding to T1, T2, T3, and T4 is calculated, so as to obtain the variation degree of the change rate corresponding to each of T1, T2, T3, and T4.

In another practical way, referring to fig. 11, the difference between the divavg and the Avg corresponding to V1, V2, V3, and V4 is calculated respectively, so as to obtain the variation degree of each of the change rates corresponding to V1, V2, V3, and V4.

In this embodiment, by detecting the difference of the change rate, false alarm of non-abnormal value deviation caused by the difference of the states of the detection monomers can be effectively avoided, and abnormal data with frequent fluctuation of the value can be accurately identified.

Further, an embodiment of the present application further provides an abnormal data identification apparatus, where the abnormal data identification apparatus is applied to an abnormal data identification device, and the abnormal data identification apparatus includes:

Optionally, the difference determining module is further configured to:

determining the change rate array corresponding to each array to be identified;

comparing the change rate arrays between groups to determine the Euclidean distance between the change rate arrays;

Optionally, the difference determining module is further configured to:

acquiring previous frame subdata and next frame subdata of two adjacent frames in each array to be identified, and a time difference between the next frame subdata and the previous frame subdata;

and calculating the ratio of the difference between the next frame of sub data and the previous frame of sub data to the time difference to obtain change rate sub data, wherein the change rate array is composed of at least one change rate sub data.

Optionally, the abnormal data identification apparatus further includes a to-be-identified time period determination module, where the to-be-identified time period determination module is configured to:

obtaining at least one current operating data of the vehicle;

Optionally, the to-be-identified time period determining module is further configured to:

Optionally, the abnormal data identification apparatus further includes an alarm module, and the to-be-identified time period determination module is configured to:

The abnormal data identification device provided by the invention adopts the abnormal data identification method of the vehicle in the embodiment, and solves the technical problem of low accuracy of abnormal data identification in the prior art. Compared with the prior art, the beneficial effects of the abnormal data identification device provided by the embodiment of the invention are the same as the beneficial effects of the abnormal data identification method for the vehicle provided by the embodiment, and other technical features of the abnormal data identification device are the same as those disclosed by the embodiment method, which are not repeated herein.

Further, an embodiment of the present invention provides an electronic device, where the electronic device includes: at least one processor; and a memory communicatively coupled to the at least one processor; the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the abnormal data identification method of the vehicle in the above embodiment.

Referring now to FIG. 12, shown is a block diagram of an electronic device suitable for use in implementing embodiments of the present disclosure. The electronic devices in the embodiments of the present disclosure may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., car navigation terminals), and the like, and fixed terminals such as digital TVs, desktop computers, and the like. The electronic device shown in fig. 12 is only an example, and should not bring any limitation to the functions and the scope of use of the embodiments of the present disclosure.

As shown in fig. 12, the electronic device may include a processing means (e.g., a central processing unit, a graphic processor, etc.) that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) or a program loaded from a storage means into a Random Access Memory (RAM). In the RAM, various programs and arrays required for the operation of the electronic device are also stored. The processing device, the ROM, and the RAM are connected to each other through a bus. An input/output (I/O) interface is also connected to the bus.

Generally, the following systems may be connected to the I/O interface: input devices including, for example, touch screens, touch pads, keyboards, mice, image sensors, microphones, accelerometers, gyroscopes, and the like; output devices including, for example, liquid Crystal Displays (LCDs), speakers, vibrators, and the like; storage devices including, for example, magnetic tape, hard disk, etc.; and a communication device. The communication means may allow the electronic device to communicate wirelessly or by wire with other devices to exchange arrays. While the figures illustrate an electronic device with various systems, it is understood that implementing or having all of the illustrated systems is not a requirement. More or fewer systems may alternatively be implemented or provided.

In particular, according to an embodiment of the present disclosure, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method illustrated in the flow chart. In such an embodiment, the computer program may be downloaded and installed from a network via the communication means, or installed from a storage means, or installed from a ROM. The computer program, when executed by a processing device, performs the above-described functions defined in the methods of the embodiments of the present disclosure.

The electronic device provided by the invention adopts the vehicle abnormal data identification method in the embodiment, and solves the technical problem of low accuracy of abnormal data identification in the prior art. Compared with the prior art, the beneficial effects of the electronic device provided by the embodiment of the invention are the same as the beneficial effects of the vehicle abnormal data identification method provided by the embodiment, and other technical features of the electronic device are the same as those disclosed by the embodiment method, which are not repeated herein.

It should be understood that portions of the present disclosure may be implemented in hardware, software, firmware, or a combination thereof. In the foregoing description of embodiments, the particular features, structures, materials, or characteristics may be combined in any suitable manner in any one or more embodiments or examples.

The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Further, the present embodiment provides a computer-readable storage medium having stored thereon computer-readable program instructions for executing the abnormal data identifying method of a vehicle in the above-described embodiments.

The computer readable storage medium provided by the embodiments of the present invention may be, for example, a USB flash disk, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, or device, or any combination thereof. More specific examples of the computer readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present embodiment, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, or device. Program code embodied on a computer readable storage medium may be transmitted using any appropriate medium, including but not limited to: electrical wires, optical cables, RF (radio frequency), etc., or any suitable combination of the foregoing.

The computer-readable storage medium may be embodied in an electronic device; or may be present alone without being incorporated into the electronic device.

The computer readable storage medium carries one or more programs which, when executed by the electronic device, cause the electronic device to: acquiring at least one group of arrays to be identified corresponding to a preset time period to be identified; comparing the arrays to be identified, and determining the array difference degree corresponding to each array to be identified; and if a target array with array difference exceeding a preset difference threshold value is detected in each array to be identified, determining the data in the target array as abnormal data.

Computer program code for carrying out operations for aspects of the present disclosure may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C + +, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).

The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The modules described in the embodiments of the present disclosure may be implemented by software or hardware. Wherein the names of the modules do not in some cases constitute a limitation of the unit itself.

The computer-readable storage medium provided by the invention stores the computer-readable program instructions for executing the abnormal data identification method of the vehicle, and solves the technical problem of low accuracy of abnormal data identification in the prior art. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the embodiment of the invention are the same as the beneficial effects of the vehicle abnormal data identification method provided by the embodiment, and are not repeated herein.

Further, the present application also provides a computer program product comprising a computer program which, when being executed by a processor, realizes the steps of the abnormal data identification method for a vehicle as described above.

The computer program product provided by the application solves the technical problem of low accuracy of abnormal data identification in the prior art. Compared with the prior art, the beneficial effects of the computer program product provided by the embodiment of the invention are the same as the beneficial effects of the vehicle abnormal data identification method provided by the embodiment, and are not repeated herein.

The above description is only a preferred embodiment of the present application, and not intended to limit the scope of the present application, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the specification and the drawings, or which are directly or indirectly applied to other related technical fields, are included in the scope of the present application.

Claims

1. An abnormal data recognition method for a vehicle, characterized by comprising the steps of:

comparing the arrays of the arrays to be identified to determine the array difference degree corresponding to each array to be identified;

and if a target array with the array difference degree exceeding a preset difference degree threshold value is detected in each array to be identified, determining data in the target array as abnormal data.

2. The abnormal data recognition method for vehicles according to claim 1, wherein the array difference degree includes a change rate difference degree, and the step of comparing the arrays to be recognized to determine the array difference degree corresponding to each array to be recognized comprises:

determining the change rate array corresponding to each array to be identified;

3. The abnormal data identification method for vehicles according to claim 2, wherein the step of determining the degree of difference in the change rate corresponding to each of the arrays to be identified based on each of the euclidean distances comprises:

4. The abnormal data identification method for vehicles according to claim 2, wherein the step of determining the change rate array corresponding to each array to be identified comprises:

5. The method for recognizing the abnormal data of the vehicle according to claim 1, wherein before the step of obtaining at least one group of arrays to be recognized corresponding to a preset time period to be recognized, the method further comprises:

obtaining at least one current operating data of the vehicle;

6. The method according to claim 5, wherein if the suspected abnormal data exceeding the corresponding preset first threshold range is detected in each of the current operation data, the step of determining the preset time period to be identified according to the suspected abnormal data corresponding to the suspicious time point comprises:

7. The abnormal data recognition method of a vehicle according to any one of claims 1 to 6, characterized by further comprising:

8. An abnormal data recognition apparatus, characterized in that the abnormal data recognition apparatus comprises:

9. An electronic device, characterized in that the electronic device comprises:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein, the first and the second end of the pipe are connected with each other,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the steps of the method of abnormality data identification of a vehicle of any one of claims 1 to 7.

10. A storage medium, characterized in that the storage medium is a computer-readable storage medium having stored thereon a program that implements an abnormal data identifying method of a vehicle, the program being executed by a processor to implement the steps of the abnormal data identifying method of a vehicle according to any one of claims 1 to 7.