CN116030550B - Abnormality recognition and processing method, device and medium for vehicle state data - Google Patents
Abnormality recognition and processing method, device and medium for vehicle state data Download PDFInfo
- Publication number
- CN116030550B CN116030550B CN202310293015.0A CN202310293015A CN116030550B CN 116030550 B CN116030550 B CN 116030550B CN 202310293015 A CN202310293015 A CN 202310293015A CN 116030550 B CN116030550 B CN 116030550B
- Authority
- CN
- China
- Prior art keywords
- abnormal
- field
- data
- time frame
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Landscapes
- Emergency Alarm Devices (AREA)
Abstract
The invention relates to the technical field of data processing, and discloses a method, equipment and medium for identifying and processing abnormality of vehicle state data. The method comprises the following steps: analyzing the acquired current vehicle state data to obtain physical data of each time frame to be detected, further detecting whether field values are abnormal values or invalid values, are missing items or redundant items, exceed a preset value range and other abnormal fields, determining whether timeliness conditions are met or not, detecting the normalization, the integrity, the accuracy, the consistency and the timeliness of the data, detecting various abnormal types of data, solving the problem that various abnormal data cannot be identified, further determining the abnormal grade corresponding to each time frame to be detected, obtaining an abnormal reference value according to the time frame ratio under each abnormal grade, realizing different processing modes of the data with different abnormal degrees through the abnormal reference value, and improving the prediction accuracy of a safety early warning model.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, and a medium for identifying and processing anomalies in vehicle state data.
Background
In recent years, with the rapid increase of the keeping amount of new energy automobiles, the safety accidents of the new energy automobiles are increasing, and the health sustainable development of the new energy automobiles industry faces challenges. At present, the new energy automobile industry has established a three-level data monitoring system of national platform-enterprise platform-monitored vehicle, and plays an important role in preventing the new energy automobile safety accident by playing the efficacy of the enterprise platform and early warning the faults in advance. The new energy automobile monitoring platform aims at: according to the vehicle running state data acquired by the vehicle-mounted T-box, statistical analysis processing is carried out on the data, so that the state condition of the new energy vehicle is effectively monitored, and the healthy development of the new energy vehicle industry is ensured.
However, the data quality of the new energy automobile real-time monitoring data uploaded by the vehicles acquired by enterprises has decisive influence on the effective implementation of vehicle fault warning and safety early warning. At present, an anomaly identification method for uploading data of a new energy automobile is generally established based on a national standard 32960, only abnormal data which does not accord with 32960 protocol specifications can be detected, various anomaly types of data can not be identified, most of data anomalies are regarded as normal by a system and are further applied to a safety early warning model, so that false alarm of the safety early warning model on the new energy automobile is caused.
In view of this, the present invention has been made.
Disclosure of Invention
In order to solve the technical problems, the invention provides a method, equipment and medium for identifying and processing the abnormality of vehicle state data, which can identify various types of abnormal data and further ensure the accuracy of safety pre-warning of new energy automobiles.
The embodiment of the invention provides an anomaly identification and processing method of vehicle state data, which comprises the following steps:
acquiring current vehicle state data to be identified, wherein the current vehicle state data comprises state data of each original time frame;
analyzing the state data of each original time frame in the current vehicle state data to obtain physical data of each time frame to be inspected, wherein the analysis is successful;
for each physical data of the time frame to be detected, detecting whether an abnormal field with an abnormal value or an invalid value, an abnormal field with a missing item or a redundant item, an abnormal field exceeding a preset value range, an abnormal field with abnormal change trend, an abnormal field with wrong format, an abnormal field with a value not conforming to a preset logic condition with an associated field and an abnormal field with unreasonable change value exist in the field, and determining whether the physical data meets a timeliness condition;
Determining an abnormality level corresponding to each time frame to be detected according to an abnormality field in physical data of the time frame to be detected and whether the physical data meets an timeliness condition or not;
determining the time frame duty ratio under each abnormal level according to the abnormal level corresponding to each time frame to be detected, and determining an abnormal reference value corresponding to the current vehicle state data based on the time frame duty ratio under each abnormal level;
and carrying out abnormal recognition on all state data of the vehicle type corresponding to the current vehicle state data according to the abnormal reference value, or generating alarm information or prompt information corresponding to the current vehicle state data.
The embodiment of the invention provides electronic equipment, which comprises:
a processor and a memory;
the processor is configured to execute the steps of the method for identifying and processing the abnormality of the vehicle state data according to any of the embodiments by calling a program or instructions stored in the memory.
An embodiment of the present invention provides a computer-readable storage medium storing a program or instructions that cause a computer to execute the steps of the abnormality identification and processing method of vehicle state data according to any of the embodiments.
The embodiment of the invention has the following technical effects:
the method comprises the steps of obtaining current vehicle state data to be identified, analyzing the state data of each original time frame to obtain physical data of each time frame to be detected, further detecting whether field values are abnormal values or invalid values, are abnormal fields which are missing items or redundant items and exceed a preset value range, change trend is abnormal and the like according to the physical data of each time frame to be detected, determining whether the physical data meets timeliness conditions or not, detecting the normalization, integrity, accuracy, consistency and timeliness of the data, detecting various abnormal types of data, solving the problem that the prior art cannot identify various abnormal data, avoiding that the abnormal data cannot be identified to be input into a safety pre-warning model, determining the corresponding abnormal level according to the abnormal fields in the physical data of each time frame to be detected, determining the time frame occupation ratio under each abnormal level according to the abnormal level corresponding to all the time frames to be detected, determining whether all the states are subjected to the abnormal conditions or not, generating the same or not according to the abnormal level, and then realizing the safety pre-warning model, and further realizing the accurate pre-warning of the data, and further realizing the safety pre-warning model.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for anomaly identification and processing of vehicle status data provided by an embodiment of the present invention;
fig. 2 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the invention, are within the scope of the invention.
The method for identifying and processing the abnormality of the vehicle state data is mainly suitable for identifying the abnormality of the vehicle state data uploaded to the platform by each vehicle and processing the vehicle state data according to the identified abnormality reference value describing the abnormality degree of the data. The abnormality recognition and processing method for the vehicle state data provided by the embodiment of the invention can be executed by electronic equipment such as a computer.
Fig. 1 is a flowchart of a method for identifying and processing anomalies in vehicle state data according to an embodiment of the present invention. Referring to fig. 1, the abnormality identification and processing method for vehicle state data specifically includes:
s110, acquiring current vehicle state data to be identified, wherein the current vehicle state data comprise state data of each original time frame.
The current vehicle state data may be data uploaded to the platform by the vehicle through a T-BOX (telecommunications device), among others. Specifically, the current vehicle state number may be data describing a vehicle running state of the new energy vehicle, such as a vehicle state, a state of charge, an operation mode, a vehicle speed, an accumulated mileage, a total voltage, a battery state of charge, a battery current, a cell voltage, an insulation resistance, a longitude and latitude, or the like.
In the embodiment of the invention, each vehicle can upload the vehicle state data in real time, and the platform can perform abnormal recognition on the vehicle state data sent by one vehicle in a set time period after receiving the vehicle state data uploaded at each time point, namely, the vehicle state data related to the vehicle to be recognized in the set time period is taken as the current vehicle state data.
S120, analyzing the state data of each original time frame in the current vehicle state data to obtain the physical data of each time frame to be inspected, which is successfully analyzed.
In the embodiment of the invention, since the current vehicle state data may be composed of the vehicle state data at each time point within the set period, each time point in the current vehicle state data may be determined as each original time frame.
Specifically, the platform may parse the state data of each original time frame in the current vehicle state data according to the national standard 32960 specification to convert the state data of each original time frame into physical data. If the state data of the original time frame is correct, the state data can be successfully analyzed to obtain physical data.
After the platform analyzes the state data of all the original time frames, the original time frames successfully analyzed can be used as the time frames to be detected, and the physical data of the time frames to be detected can be obtained.
S130, detecting whether an abnormal field with an abnormal value or an invalid value, an abnormal field with a missing item or a redundant item, an abnormal field exceeding a preset value range, an abnormal field with abnormal change trend, an abnormal field with wrong format, an abnormal field with a value which does not meet a preset logic condition with an associated field and an abnormal field with unreasonable change value exist in each physical data of the time frame to be detected, and determining whether the physical data meets a timeliness condition.
Specifically, for the physical data of each time frame to be detected, abnormality identification can be performed on the physical data from the standardability, integrity, accuracy, consistency and timeliness of the data.
The platform can detect whether the analyzed physical data has an abnormal value or an invalid value field for each physical data of the time frame to be detected so as to detect the normalization of the physical data. Specifically, if a field with a field value of "FE" exists in the physical data, it may be determined that the field value of the field is an abnormal value, and the field is an abnormal field; if a field with a field value of "FF" exists in the physical data, the field value of the field can be determined to be an invalid value, and the field is an abnormal field.
For the physical data of each time frame to be detected, the platform can also detect whether the fields of the missing items or the redundant items exist in the parsed physical data so as to detect the integrity of the physical data, namely, whether the field data quantity in the physical data meets the digital requirement or not according to the national standard 32960 specification.
Wherein detecting whether an exception field exists that is a missing item or a redundant item may include: (1) A field identifying whether there is a missing item in the physical data; (2) Identifying whether redundancy items exist in the monomer voltage and the probe temperature in the physical data, specifically extracting the preset monomer voltage number and the temperature probe number, calculating the battery monomer voltage number and the probe temperature number in the physical data, and comparing the battery monomer voltage number and the probe temperature number with preset values so as to identify whether the redundancy reserved monomer voltage and the redundancy reserved probe temperature exist; (3) When the physical data is identified, analyzed and stored and then recalled, whether redundant field items exist or not is identified, namely whether two or more data exist in a single data requirement or not is identified.
For the physical data of each time frame to be detected, the platform can also detect whether an abnormal field exceeding a preset value range, an abnormal field with abnormal change trend and an abnormal field with wrong format exist in the analyzed physical data so as to detect the accuracy of the physical data.
Each field can be provided with a corresponding preset value range, and the preset value range describes the value condition of the corresponding field in the national standard range.
Exemplary, the preset value ranges corresponding to the fields are as follows:
1) Vehicle state: 1 (vehicle start state), 2 (vehicle off state), 3 (other state); 2) State of charge: 1 (parking charge), 2 (travel charge), 3 (uncharged), 4 (charge completed); 3) Operation mode: 1 (pure electric mode), 2 (hybrid mode), 3 (fuel oil)A mode); 4) Vehicle speed: 0-220 km/h; 5) Accumulated mileage: national standard range: 0-999999.9 km, recommended range: 0-999990 km; 6) Total voltage: national standard range: 0-1000V, recommended range: determining according to the condition of the vehicle; 7) Total current: national standard range: -1000 a, recommended range: determining according to the condition of the vehicle; 8) State of charge: the national standard range is 0-100; 9) Insulation resistance: national standard range: 0 to 60000k 
Suggested range: determining according to the condition of the vehicle; 10 Longitude): suggested range: 0-180; 11 Latitude): suggested range: 0-90; 12 Highest voltage battery subsystem number: national standard range: 1-250; 13 Highest voltage cell code: national standard range: 1-250; 14 Highest value of cell voltage): national standard range: 0-15V, and the recommended range is 2-5V; 15 Lowest voltage battery subsystem number: national standard range: 1-250; 16 Lowest voltage cell code: national standard range: 1-250; 17 Cell voltage minimum value): national standard range 0-15V, recommended range: 2-5V; 18 Highest temperature subsystem number: 1-250; 19 Highest temperature probe monomer code: 1-250; 20 Highest temperature value): national standard range: -40-210 ℃, recommended range: -30-120 ℃;21 Total number of cells): national standard range: 1-65531, recommended range: determining according to the condition of the vehicle; 22 Total number of single batteries in the present frame): national standard range: 1-200 parts; 23 Cell voltage): suggested range: 2-5V; 24 Number of chargeable stored energy temperature probes): national standard range 1-65531, recommended range: determining according to the condition of the vehicle; 25 Temperature values detected by each temperature probe: national standard range-40-210 ℃, recommended range: -30-120 ℃.
Specifically, if the field value of a field in the physical data exceeds the preset value range corresponding to the field, the field can be determined to be an abnormal field.
The abnormal change trend may be that the change trend of the field in a period of time does not conform to the preset change trend, or the change trend of the field in a period of time does not conform to the change trend of the associated field. For example, if the detection field is constant over a period of time, for example, if a certain cell voltage is constant to be a fixed value over a certain period of time, but the current is large and fluctuates severely, then the cell voltage or current may be determined to be an abnormal field.
The format error may refer to that the field value of the field does not conform to the preset format corresponding to the field, such as a data type error, a data length error, or a data precision error. For example, if a numeric field appears as a string-type field in the physical data, the field may be determined to be an abnormal field.
In the embodiment of the invention, the consistency of the physical data can also be detected by detecting whether the physical data of each time frame to be detected has an abnormal field with a field value which does not accord with a preset logic condition with the value of the associated field and whether the physical data has an abnormal field with an unreasonable change value of the field value.
The preset logic condition may be a preset logic condition of a value between associated fields. If the value of the field 1 is greater than 0, the value of the field 2 cannot be less than 0; when the value change trend of the field 1 is monotonically increasing, the value change trend of the field 2 is also monotonically increasing; the sum of the value of field 1 and the value of field 2 cannot exceed the value of field 3.
The unreasonable change value may mean that the value change value of the field does not conform to a preset change condition, for example, the change value is too large, the change value is too small, or the change trend does not conform to a preset trend.
In a specific embodiment, detecting whether an abnormal field whose value does not meet a preset logic condition is present, including:
if the field value of the vehicle state field indicates the flameout state and the field value of the vehicle speed field is not zero, determining that the vehicle state field and the vehicle speed field do not accord with the preset logic condition, and determining the vehicle state field or the vehicle speed field as an abnormal field; if the field value of the total voltage field is larger than the sum of the field values of the battery cell voltage fields, determining that the total voltage field and each battery cell voltage field do not accord with a preset logic condition, and determining the total voltage field or each battery cell voltage field as an abnormal field;
Detecting whether an abnormal field with unreasonable field value change value exists comprises the following steps: if the field value of the accumulated mileage field does not monotonically increase with time, determining that the field value change value of the accumulated mileage field is unreasonable, and determining the accumulated mileage field as an abnormal field; if the change value of the accumulated mileage field in the adjacent time frame exceeds a preset first change threshold value, determining the accumulated mileage field as an abnormal field; if the field value of the vehicle state field indicates the charging state and the change value of the total voltage field in the adjacent time frame is greater than the preset second change threshold value, determining the total voltage field as an abnormal field.
That is, the vehicle status field and the vehicle speed field may be associated with each other, and the preset logic condition may include that the value of the vehicle speed field needs to be zero when the value of the vehicle status field is in the flameout state. The total voltage field and the battery cell voltage field may be related fields, and the preset logic condition may include that the value of the total voltage field does not exceed the sum of the values of the battery cell voltage fields.
In addition to the above-mentioned related fields, the temperature-maximum field and the probe temperature field may be related fields, and the cell voltage-maximum field and the cell voltage field may be related fields, which are only exemplary and not limited in this embodiment.
For the accumulated mileage field, the change trend of the field value should be monotonously increasing with time, if the change trend does not monotonously increase with time, the change value can be determined to be unreasonable, and the change trend is an abnormal field. And for the accumulated mileage field, the change value in the adjacent time frame to be detected cannot exceed the preset first change threshold value, and if so, the change value can be determined to be unreasonable and is an abnormal field. The preset first change threshold may be a product of a preset vehicle speed threshold and a time interval of an adjacent time frame to be detected.
For the total voltage field, the change trend of the field value should not be greater than the preset second change threshold when the vehicle state field is in the charging state, if the change trend is greater than the preset second change threshold, the change value can be determined to be unreasonable, and the change trend is an abnormal field. The preset second variation threshold may be a product of a preset variation threshold and a time interval of an adjacent time frame to be detected.
By the embodiment, the physical data of each time frame to be detected can be detected, whether the abnormal fields with the field values which are not in accordance with the preset logic conditions and the abnormal fields with the unreasonable field value change values exist or not are detected, and further the consistency of the physical data is accurately detected, and further each data with abnormal consistency can be identified, and the data with abnormal consistency is prevented from being used as normal data to carry out subsequent safety precaution.
It should be noted that, when detecting an abnormal field in the physical data of each time frame to be detected, the platform may record the abnormal field and record the time frame to be detected in which the abnormal field exists.
In addition to detecting the various anomaly fields in the physical data of each time frame under test, the platform may also detect whether the physical data of each time frame under test satisfies a timeliness condition. Wherein the timeliness condition may include at least one of: the time frames to be detected and other adjacent time frames to be detected meet the time sequence, no frame loss condition exists between the time frames to be detected and other adjacent time frames to be detected, other time frames to be detected which are the same as the time frames to be detected do not exist, or the time frames to be detected meet the preset time system.
In a specific embodiment, determining whether the physical data satisfies the timeliness condition comprises: judging whether the time sequence between the time frame to be detected corresponding to the physical data and other adjacent time frames is met; if yes, judging whether a frame loss condition exists between the to-be-detected time frame corresponding to the physical data and other adjacent to-be-detected time frames; if not, judging whether other time frames to be detected exist, which are the same as the time frames to be detected corresponding to the physical data; if not, judging whether the time frame to be detected corresponding to the physical data meets a preset time system; if yes, determining that the physical data meets the timeliness condition.
That is, it may be determined whether the time of the time frame to be detected is after the time of the last time frame to be detected and before the time of the next time frame to be detected, if not, it may be determined that the physical data of the time frame to be detected does not satisfy the timeliness condition, and the time frame to be detected is recorded.
If yes, further judging whether the time interval between the time frame to be detected and the last time frame to be detected accords with the preset interval and whether the time interval between the time frame to be detected and the next time frame to be detected accords with the preset interval, if not, indicating that a frame loss condition exists, determining that the physical data of the time frame to be detected does not meet the timeliness condition, and recording the time frame to be detected.
If yes, further judging whether other time frames to be detected which are the same as the time frames to be detected exist, namely whether the time frames to be detected are repeated, if yes, determining that the physical data of the time frames to be detected do not meet the timeliness condition, and recording the time frames to be detected.
If not, further judging whether the time frame to be detected meets the preset time system, namely whether the time frame to be detected meets the actual system, if not, determining that the physical data of the time frame to be detected does not meet the timeliness condition, and recording the time frame to be detected.
By the embodiment, whether the physical data of each time frame to be detected meet timeliness or not is accurately detected, so that each data with timeliness abnormality can be identified, and the data with timeliness abnormality is prevented from being used as normal data for subsequent safety precaution. The step of determining the timeliness is only an example, and the order is not limited, for example, whether to lose a frame first may be determined, and whether to satisfy the chronological order may be determined.
S140, for each time frame to be detected, determining an abnormality level corresponding to the time frame to be detected according to an abnormality field in physical data of the time frame to be detected and whether the physical data meets timeliness conditions.
Specifically, for each time frame to be detected, an anomaly level corresponding to the time frame to be detected can be determined according to an anomaly field in the physical data and whether the physical data meets a timeliness condition. Wherein the anomaly level may be used to describe the degree of anomaly of the physical data of the time frame under inspection.
In a specific embodiment, for each time frame to be detected, determining, according to an anomaly field in physical data of the time frame to be detected and whether the physical data meets a timeliness condition, an anomaly level corresponding to the time frame to be detected includes: for each time frame to be detected, if the abnormal field of the physical data of the time frame to be detected is a key field, and the field value of the abnormal field is missing in a preset first time range, the value of the abnormal field does not accord with a preset logic condition, the change value is unreasonable, the abnormal value is an abnormal value or is an invalid value, determining that the abnormal level corresponding to the time frame to be detected is a first preset level; or, for each time frame to be detected, if the abnormal field of the physical data of the time frame to be detected is a non-key field and the field value of the abnormal field is missing in all the time frames, determining the abnormal level corresponding to the time frame to be detected as a first preset level.
That is, if the abnormal field in the physical data of the time frame to be detected is a key field, and the specific abnormal type of the abnormal field is that the field value is missing in the preset first time range, the value of the abnormal field does not conform to the preset logic condition, the change value is unreasonable, or is an abnormal value or an invalid value, it may be determined that the abnormal level corresponding to the time frame to be detected is the first preset level. In other words, when the field value of the key field is long term line missing, long term abnormal, long term consistency poor, long term accuracy poor or invalid, it can be regarded as the first preset level.
Or if the abnormal field in the physical data of the time frame to be detected is a non-critical field and the specific abnormal type of the abnormal field is that the field value is missing in all time frames, the abnormal level corresponding to the time frame to be detected can be determined to be a first preset level, in other words, when the non-critical field has a complete and definite situation, the abnormal level can be regarded as the first preset level.
The key fields may be fields such as vehicle state, state of charge, operating mode, vehicle speed, accumulated mileage, total voltage, total current, etc. The first preset level may be a level at which the degree of abnormality is highest.
By the method, whether each time frame to be detected is the highest abnormal degree can be judged, so that the abnormal level of each time frame to be detected is conveniently determined, the abnormal level of all the time frames to be detected is conveniently and subsequently integrated to determine the abnormal reference value corresponding to the whole current vehicle state data, the accuracy of the abnormal reference value is ensured, and the data can be accurately processed based on the abnormal reference value.
Optionally, for each time frame to be detected, determining, according to the exception field in the physical data of the time frame to be detected and whether the physical data meets the timeliness condition, an exception level corresponding to the time frame to be detected, and further including: for each time frame to be detected, if the abnormal field of the physical data of the time frame to be detected is a key field, and the field value of the abnormal field is missing in a preset second time range, is an invalid value, is an abnormal value, and does not accord with a preset logic condition with the value of the associated field, the change value is unreasonable, exceeds the preset value range, the change trend is abnormal or the format is wrong, determining that the abnormal level corresponding to the time frame to be detected is a second preset level; or, for each time frame to be detected, if the physical data of the time frame to be detected does not meet the timeliness condition, determining the abnormal level corresponding to the time frame to be detected as a second preset level; the preset second time range is smaller than the preset first time range.
That is, if the abnormal field in the physical data of the time frame to be detected is a key field, and the specific abnormal type of the abnormal field is that the field value is missing in the preset second time range, is an invalid value, is an abnormal value, and does not accord with the preset logic condition with the value of the associated field, the change value is unreasonable, exceeds the preset value range, the change trend is abnormal or the format is wrong, determining that the abnormal level corresponding to the time frame to be detected is a second preset level.
The preset second time range is smaller than the preset first time range, the preset first time range represents a long time range, and the preset second time range represents a short time range. For example, the first time range is preset to be greater than 3 minutes, and the second time range is preset to be less than 3 minutes.
In other words, if the field value of the key field in the physical data of the time frame to be detected is short-time line missing, short-time abnormal invalid, short-time consistency poor, short-time accuracy poor or redundancy, the time frame to be detected can be regarded as the second preset level.
Or if the physical data of the time frame to be detected does not meet the timeliness condition, namely that the timeliness is poor, the time frame to be detected can be determined to be of a second preset level. Wherein the degree of abnormality of the second preset level is lower than the degree of abnormality of the first preset level.
By the method, whether each time frame to be detected is of moderate degree of abnormality can be judged, and therefore abnormality levels of each time frame to be detected can be conveniently determined.
Optionally, for each time frame to be detected, determining, according to the exception field in the physical data of the time frame to be detected and whether the physical data meets the timeliness condition, an exception level corresponding to the time frame to be detected, and further including: for each time frame to be detected, if the abnormal field of the physical data of the time frame to be detected is a non-key field and the abnormality corresponding to the abnormal field is different from the abnormality corresponding to the first preset level and the second preset level, determining that the abnormality level corresponding to the time frame to be detected is a third preset level.
That is, if the anomaly field in the physical data of the time frame to be detected is a non-critical field and the specific anomaly type of the anomaly field is different from the anomalies corresponding to the first preset level and the second preset level, it may be determined that the anomaly level corresponding to the time frame to be detected is a third preset level. Wherein the degree of abnormality of the third preset level is lower than the degree of abnormality of the second preset level.
By the method, whether each time frame to be detected is the lowest abnormal degree can be judged, and the abnormal level of each time frame to be detected is conveniently determined.
It should be noted that if a plurality of abnormal fields occur in a time frame to be detected, an abnormal level may be determined for each abnormal field, and then the abnormal level with the greatest abnormal level is used as the final abnormal level corresponding to the time frame to be detected.
S150, determining the time frame duty ratio under each abnormal level according to the abnormal level corresponding to each time frame to be detected, and determining the abnormal reference value corresponding to the current vehicle state data based on the time frame duty ratio under each abnormal level.
Specifically, after obtaining the anomaly levels corresponding to all the time frames to be detected, the number of the time frames to be detected under each anomaly level may be counted, so as to obtain the time frame duty ratio under each anomaly level, for example, the ratio of the number of the time frames to be detected under the anomaly level to the number of the original time frames in the current vehicle state data.
In the embodiment of the invention, the abnormal level of the analysis failure data and the abnormal level of the complementary data can be determined, and the time frame duty ratio under each abnormal level is determined by combining the analysis failure data and the complementary data.
In a specific embodiment, after parsing the state data of each original time frame in the current vehicle state data, the method further includes: determining each state data with failed analysis as first recognition abnormal data, and acquiring reissue data corresponding to the current vehicle state data; determining an abnormality grade corresponding to the first recognition abnormality data and the reissue data; correspondingly, determining the time frame duty ratio under each abnormal level according to the abnormal level corresponding to each time frame to be detected comprises the following steps: and determining the time frame duty ratio under each abnormal level according to the abnormal level corresponding to each time frame to be detected, the abnormal level corresponding to the first recognition abnormal data, the number of the time frames in the first recognition abnormal data, the abnormal level corresponding to the concurrent data and the number of the time frames in the concurrent data.
That is, the state data of each original time frame that fails in analysis may be used as first-time identification anomaly data, further, for the first-time identification anomaly data, the corresponding original time frame may be recorded, and the anomaly level corresponding to the recorded original time frame may be determined to be a first preset level, and for the reissue data corresponding to the current vehicle state data, the corresponding time frame may be recorded, and the anomaly level corresponding to the recorded time frame may be determined to be the first preset level.
Furthermore, the time frame duty ratio under each abnormal level can be counted together according to the abnormal levels corresponding to all the time frames to be detected, all the first recognition abnormal data and all the reissue data. According to the embodiment, the analysis failure data and the reissue data are considered in the time frame duty ratio under the statistics of different abnormal grades, so that the comprehensiveness of abnormal statistics is ensured, and the accuracy of the subsequently determined abnormal reference value is further ensured.
In the embodiment of the invention, considering that data which does not accord with 32960 protocol specifications may exist in the current vehicle state data before the current vehicle state data is analyzed, the data which does not accord with 32960 protocol specifications can be identified before the current vehicle state data is analyzed.
Optionally, before parsing the state data of each original time frame in the current vehicle state data, the method further includes: for the state data of each original time frame, determining the state data which does not meet the login and logout requirements of the vehicle, does not meet the preset data packet structure or does not meet the preset data unit length as first identification abnormal data, and removing the first identification abnormal data from the current vehicle state data; and determining the state data with abnormal vehicle identification codes in the current vehicle state data as first-time abnormal identification data, and eliminating the first-time abnormal identification data from the current vehicle state data.
That is, after the platform acquires the current vehicle state data, it may first detect whether the state data of each original time frame in the current vehicle state data meets the 32960 protocol specification. The method comprises the following steps: if any one of the conditions exists, the state data of the original time frame can be determined to be the first abnormal data identification, the state data of the original time frame is further removed from the current vehicle state data, and the original time frame is recorded.
Further, whether the vehicle identification code in the state data of each original time frame is the vehicle identification code in the platform can be detected, if not, the state data of the original time frame can be determined to be the first abnormal identification data, the state data of the original time frame is further removed from the current vehicle state data, and the original time frame is recorded.
For example, for the original time frame corresponding to the recorded first identified abnormal data, the corresponding abnormal level may be a first preset level.
Further, the first recognition abnormal data before analysis, the first recognition abnormal data after analysis and the abnormal fields in each time frame to be detected after analysis can be integrated, and the time frame duty ratio under each abnormal level is counted. By the method, the data which do not accord with 32960 protocol specifications and the data of the vehicle which do not belong to the platform can be identified, the comprehensiveness of anomaly statistics is further ensured, and the accuracy of the subsequently determined anomaly reference value is further ensured.
After the time frame duty ratio under each abnormal grade is obtained, the time frame duty ratio can be used as a weight value corresponding to the abnormal grade, and an abnormal reference value corresponding to the current vehicle state data can be determined by combining the abnormal parameters corresponding to the abnormal grade.
Exemplary, the abnormal reference value=w1+w2+q2+w3+q3, where Q1, Q2, Q3 are abnormal parameters corresponding to the first preset level, the second preset level, and the third preset level, respectively, and Q1> Q2> Q3; w1, W2 and W3 are the time frame duty ratios of the first preset level, the second preset level and the third preset level respectively.
In the embodiment of the present invention, the purpose of determining the abnormal reference value corresponding to the current vehicle state data is to: and determining the abnormality degree of the whole current vehicle state data by determining the abnormality reference value, so that the subsequent processing strategy of the current vehicle state data is determined conveniently according to the abnormality degree of the whole current vehicle state data. The greater the abnormality reference value, the higher the degree of abnormality representing the entire current vehicle state data.
S160, carrying out abnormal recognition on all state data of the vehicle type corresponding to the current vehicle state data according to the abnormal reference value, or generating alarm information or prompt information corresponding to the current vehicle state data.
Specifically, the processing strategy of the current vehicle state data includes performing abnormality recognition on all state data of a vehicle type corresponding to the current vehicle state data, generating alarm information or generating prompt information.
In the embodiment of the invention, a plurality of reference value intervals can be set, if the abnormal reference value corresponding to the current vehicle state data is located in the high reference value interval, alarm information can be immediately generated, the alarm information is sent to the terminal equipment of the responsible person, and the abnormal recognition is carried out on all the state data under the vehicle type corresponding to the current vehicle state data. Or, the vehicle corresponding to the current vehicle state data may be written into the key detection list to perform abnormality recognition on all vehicle state data sent subsequently by the vehicle, and if no abnormal reference value is located in the high reference value interval within a set time (for example, 2 months), the vehicle may be moved out of the key detection list.
If the abnormal reference value corresponding to the current vehicle state data is located in the middle reference value interval, prompt information can be generated, the prompt information is sent to terminal equipment of a responsible person, the vehicle corresponding to the current vehicle state data is written into a continuous detection list, so that abnormal recognition is carried out on the vehicle state data which is sent subsequently by the vehicle when the set time is reached, and if the abnormal reference value is not located in the high reference value interval within the set time (such as 2 months), the vehicle can be moved out of the continuous detection list.
If the abnormal reference value corresponding to the current vehicle state data is located in the lower reference value interval, the vehicle type of the vehicle corresponding to the current vehicle state data can be recorded, the vehicle state data of each vehicle under the vehicle type can be identified, if the ratio of the number of vehicles which are not located in the extremely low reference value interval exceeds a preset value (such as 30%), whether the ratio of the number of vehicles located in the middle reference value interval or the high reference value interval is larger than the preset value (such as 20%), if so, alarm information corresponding to the vehicle type can be generated, and the alarm information can be sent to terminal equipment of a responsible person.
If the abnormal reference value corresponding to the current vehicle state data is located in the extremely low reference value interval, the current vehicle state data may not be processed.
The invention has the following technical effects: the method comprises the steps of obtaining current vehicle state data to be identified, analyzing the state data of each original time frame to obtain physical data of each time frame to be detected, further detecting whether field values are abnormal values or invalid values, are abnormal fields which are missing items or redundant items and exceed a preset value range, change trend is abnormal and the like according to the physical data of each time frame to be detected, determining whether the physical data meets timeliness conditions or not, detecting the normalization, integrity, accuracy, consistency and timeliness of the data, detecting various abnormal types of data, solving the problem that the prior art cannot identify various abnormal data, avoiding that the abnormal data cannot be identified to be input into a safety pre-warning model, determining the corresponding abnormal level according to the abnormal fields in the physical data of each time frame to be detected, determining the time frame occupation ratio under each abnormal level according to the abnormal level corresponding to all the time frames to be detected, determining whether all the states are subjected to the abnormal conditions or not, generating the same or not according to the abnormal level, and then realizing the safety pre-warning model, and further realizing the accurate pre-warning of the data, and further realizing the safety pre-warning model.
Fig. 2 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 2, electronic device 400 includes one or more processors 401 and memory 402.
The processor 401 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities and may control other components in the electronic device 400 to perform desired functions.
In one example, the electronic device 400 may further include: an input device 403 and an output device 404, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown). The input device 403 may include, for example, a keyboard, a mouse, and the like. The output device 404 may output various information to the outside, including early warning prompt information, braking force, etc. The output device 404 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 400 that are relevant to the present invention are shown in fig. 2 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, electronic device 400 may include any other suitable components depending on the particular application.
In addition to the methods and apparatus described above, embodiments of the invention may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps of the anomaly identification and processing method of vehicle state data provided by any of the embodiments of the invention.
The computer program product may write program code for performing operations of embodiments of the present invention in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like 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 computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present invention may also be a computer-readable storage medium, on which computer program instructions are stored, which, when being executed by a processor, cause the processor to perform the steps of the anomaly identification and processing method of vehicle state data provided by any embodiment of the present invention.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application. As used in this specification, the terms "a," "an," "the," and/or "the" are not intended to be limiting, but rather are to be construed as covering the singular and the plural, unless the context clearly dictates otherwise. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, 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, 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 or apparatus comprising such elements.
It should also be noted that the positional or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the positional or positional relationship shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the apparatus or element in question must have a specific orientation, be constructed and operated in a specific orientation, and thus should not be construed as limiting the present invention. Unless specifically stated or limited otherwise, the terms "mounted," "connected," and the like are to be construed broadly and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.
Claims (7)
1. An abnormality recognition and processing method of vehicle state data, characterized by comprising:
acquiring current vehicle state data to be identified, wherein the current vehicle state data comprises state data of each original time frame;
analyzing the state data of each original time frame in the current vehicle state data to obtain physical data of each time frame to be detected, and carrying out anomaly identification on the physical data of each time frame to be detected from the standardability, integrity, accuracy, consistency and timeliness of the data;
for each physical data of the time frame to be detected, detecting whether an abnormal field with an abnormal value or an invalid value, an abnormal field with a missing item or a redundant item, an abnormal field exceeding a preset value range, an abnormal field with abnormal change trend, an abnormal field with wrong format, an abnormal field with a value not conforming to a preset logic condition with an associated field and an abnormal field with unreasonable change value exist in the field, and determining whether the physical data meets a timeliness condition;
Determining an abnormality level corresponding to the time frame to be detected according to an abnormality field in the physical data of the time frame to be detected and whether the physical data meets timeliness conditions or not, wherein the abnormality level is used for describing the abnormality degree of the physical data of the time frame to be detected, when the field value of a related field is long-time line missing, long-time abnormality, long-time consistency difference, long-time accuracy difference or invalidity, the abnormality is regarded as a first preset level, when the non-critical field is in the condition of whole column missing, the abnormality is regarded as the first preset level, when the field value of the related field is short-time line missing, short-time abnormality is invalid, short-time consistency difference, short-time accuracy difference or redundancy, the abnormality level is regarded as a second preset level, when the physical data does not meet timeliness conditions, the abnormality level is regarded as a non-critical field, the specific abnormality type of the abnormality field is different from the first preset level and the abnormality corresponding to the second preset level, the abnormality level is regarded as a third preset level, and if the abnormality level is the largest for each of the abnormality levels is determined for the abnormality levels respectively;
Determining a time frame duty ratio under each abnormal level according to the abnormal level corresponding to each time frame to be detected, and determining an abnormal reference value corresponding to the current vehicle state data based on the time frame duty ratio under each abnormal level, wherein the time frame duty ratio is a ratio of the number of the time frames to be detected under the abnormal level to the number of original time frames in the current vehicle state data, the time frame duty ratio is used as a weight value corresponding to the abnormal level, and the abnormal reference value corresponding to the current vehicle state data is determined by combining with an abnormal parameter corresponding to the abnormal level;
and carrying out abnormal recognition on all state data of the vehicle type corresponding to the current vehicle state data according to the abnormal reference value, or generating alarm information or prompt information corresponding to the current vehicle state data, wherein the abnormal reference value is used for determining a subsequent processing strategy of the current vehicle state data.
2. The method of claim 1, further comprising, after said parsing the state data of each of said original time frames in said current vehicle state data:
determining each state data with failed analysis as first recognition abnormal data, and acquiring reissue data corresponding to the current vehicle state data;
Determining the first recognition abnormal data and the abnormal grade corresponding to the reissue data;
correspondingly, the determining the time frame duty ratio under each abnormal level according to the abnormal level corresponding to each time frame to be detected comprises the following steps:
and determining the time frame duty ratio under each abnormal level according to the abnormal level corresponding to each time frame to be detected, the abnormal level corresponding to the first abnormal data identification, the number of time frames in the first abnormal data identification, the abnormal level corresponding to the reissue data and the number of time frames in the reissue data.
3. The method of claim 2, further comprising, prior to said parsing the state data of each of said original time frames in said current vehicle state data:
for the state data of each original time frame, determining the state data which does not meet the login and logout requirements of the vehicle, does not meet the preset data packet structure or does not meet the preset data unit length as first identification abnormal data, and removing the first identification abnormal data from the current vehicle state data;
and determining the state data with abnormal vehicle identification codes in the current vehicle state data as first-time identification abnormal data, and eliminating the first-time identification abnormal data from the current vehicle state data.
4. The method of claim 1, wherein the determining whether the physical data satisfies a timeliness condition comprises:
judging whether the time sequence is satisfied between the time frame to be detected corresponding to the physical data and other adjacent time frames;
if yes, judging whether a frame loss condition exists between the to-be-detected time frame corresponding to the physical data and other adjacent to-be-detected time frames;
if not, judging whether other to-be-detected time frames which are the same as the to-be-detected time frames corresponding to the physical data exist or not;
if not, judging whether the time frame to be detected corresponding to the physical data meets a preset time system or not;
if yes, determining that the physical data meets the timeliness condition.
5. The method of claim 1, wherein detecting whether an exception field exists for which the field value and the associated field value do not meet a preset logic condition comprises:
if the field value of the vehicle state field indicates a flameout state and the field value of the vehicle speed field is not zero, determining that the vehicle state field and the vehicle speed field do not accord with preset logic conditions, and determining the vehicle state field or the vehicle speed field as an abnormal field;
If the field value of the total voltage field is larger than the sum of the field values of the battery cell voltage fields, determining that the total voltage field and each battery cell voltage field do not accord with a preset logic condition, and determining the total voltage field or each battery cell voltage field as an abnormal field;
detecting whether an abnormal field with unreasonable field value change value exists comprises the following steps:
if the field value of the accumulated mileage field does not monotonically increase with time, determining that the field value change value of the accumulated mileage field is unreasonable, and determining the accumulated mileage field as an abnormal field;
if the change value of the accumulated mileage field in the adjacent time frame exceeds a preset first change threshold value, determining the accumulated mileage field as an abnormal field;
and if the field value of the vehicle state field represents the charging state and the change value of the total voltage field in the adjacent time frame is greater than a preset second change threshold value, determining the total voltage field as an abnormal field.
6. An electronic device, the electronic device comprising:
a processor and a memory;
the processor is configured to execute the steps of the abnormality recognition and processing method of the vehicle state data according to any one of claims 1 to 5 by calling a program or instructions stored in the memory.
7. A computer-readable storage medium storing a program or instructions that cause a computer to execute the steps of the abnormality recognition and processing method of vehicle state data according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310293015.0A CN116030550B (en) | 2023-03-24 | 2023-03-24 | Abnormality recognition and processing method, device and medium for vehicle state data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310293015.0A CN116030550B (en) | 2023-03-24 | 2023-03-24 | Abnormality recognition and processing method, device and medium for vehicle state data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116030550A CN116030550A (en) | 2023-04-28 |
| CN116030550B true CN116030550B (en) | 2023-06-23 |
Family
ID=86079761
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310293015.0A Active CN116030550B (en) | 2023-03-24 | 2023-03-24 | Abnormality recognition and processing method, device and medium for vehicle state data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116030550B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110006672A (en) * | 2019-04-09 | 2019-07-12 | 唐山百川智能机器股份有限公司 | Rail vehicle fault monitoring method based on acoustic imaging technology |
| CN111914661A (en) * | 2020-07-06 | 2020-11-10 | 广东技术师范大学 | Abnormal behavior recognition method, target abnormal recognition method, device, and medium |
| CN114137421A (en) * | 2021-11-30 | 2022-03-04 | 蜂巢能源(上海)有限公司 | Battery abnormality detection method, apparatus, device and storage medium |
| CN114494994A (en) * | 2021-12-30 | 2022-05-13 | 深圳云天励飞技术股份有限公司 | Vehicle abnormal aggregation monitoring method and device, computer equipment and storage medium |
Family Cites Families (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090030753A1 (en) * | 2007-07-27 | 2009-01-29 | General Electric Company | Anomaly Aggregation method |
| AT10073U9 (en) * | 2008-01-14 | 2009-02-15 | Avl List Gmbh | METHOD AND DEVICE FOR ANALYZING AND EVALUATING MEASUREMENT DATA OF A MEASURING SYSTEM |
| WO2019116973A1 (en) * | 2017-12-15 | 2019-06-20 | パナソニック インテレクチュアル プロパティ コーポレーション オブ アメリカ | Fraud detection device, in-vehicle network system, and fraud detection method |
| CN109017630B (en) * | 2018-06-26 | 2020-06-12 | 上海西井信息科技有限公司 | Fault monitoring method and device for truck, electronic equipment and storage medium |
| US10936461B2 (en) * | 2018-12-21 | 2021-03-02 | Upstream Security, Ltd. | System and method for sequence-based anomaly detection and security enforcement for connected vehicles |
| CN110351295A (en) * | 2019-07-22 | 2019-10-18 | 百度在线网络技术（北京）有限公司 | Message detecting method and device, electronic equipment, computer-readable medium |
| CN114323143A (en) * | 2021-12-30 | 2022-04-12 | 上海商汤临港智能科技有限公司 | Vehicle data detection method and device, computer equipment and storage medium |
| CN114839556A (en) * | 2022-05-10 | 2022-08-02 | 中国第一汽车股份有限公司 | Power battery abnormality detection method, power battery abnormality detection device, storage medium, and electronic device |
| CN115186502A (en) * | 2022-07-27 | 2022-10-14 | 浙江极氪智能科技有限公司 | Vehicle abnormal data identification method and device, electronic device and storage medium |
-
2023
- 2023-03-24 CN CN202310293015.0A patent/CN116030550B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110006672A (en) * | 2019-04-09 | 2019-07-12 | 唐山百川智能机器股份有限公司 | Rail vehicle fault monitoring method based on acoustic imaging technology |
| CN111914661A (en) * | 2020-07-06 | 2020-11-10 | 广东技术师范大学 | Abnormal behavior recognition method, target abnormal recognition method, device, and medium |
| CN114137421A (en) * | 2021-11-30 | 2022-03-04 | 蜂巢能源(上海)有限公司 | Battery abnormality detection method, apparatus, device and storage medium |
| CN114494994A (en) * | 2021-12-30 | 2022-05-13 | 深圳云天励飞技术股份有限公司 | Vehicle abnormal aggregation monitoring method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116030550A (en) | 2023-04-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113415165B (en) | Fault diagnosis method and device, electronic equipment and storage medium | |
| CN107153914B (en) | System and method for evaluating automobile operation risk | |
| CN111204363B (en) | Fault diagnosis early warning and state evaluation method, device and system for traction system | |
| CN111241154A (en) | Storage battery fault early warning method and system based on big data | |
| CN105334843B (en) | Remote monitoring data method for uploading and device for vehicle | |
| CN114148216B (en) | Method, system, equipment and storage medium for detecting battery self-discharge rate abnormality | |
| CN110749829B (en) | Power supply equipment abnormality detection method and device | |
| CN111241120A (en) | Vehicle energy filling point analysis method and device, vehicle-mounted equipment and storage medium | |
| CN110674009A (en) | Application server performance monitoring method and device, storage medium and electronic equipment | |
| CN111966084A (en) | TBOX detection device and method | |
| CN115796708B (en) | Big data intelligent quality inspection method, system and medium for engineering construction | |
| CN111832974A (en) | Vehicle fault early warning method and storage medium | |
| CN212694288U (en) | TBOX detection device | |
| CN111506048A (en) | Vehicle fault early warning method and related equipment | |
| CN115384311A (en) | Method, system, vehicle and storage medium for diagnosing insulation fault of power battery | |
| CN115268417A (en) | Self-adaptive ECU fault diagnosis control method | |
| CN114779085A (en) | Real-time battery thermal runaway detection method, system, device and medium | |
| CN115219903A (en) | Battery self-discharge rate abnormity judgment method and device based on Internet of vehicles data analysis | |
| CN116030550B (en) | Abnormality recognition and processing method, device and medium for vehicle state data | |
| CN117491813A (en) | Insulation abnormality detection method for power battery system of new energy automobile | |
| CN116008820B (en) | Method, device and medium for detecting inconsistency of vehicle battery cells | |
| CN115480944A (en) | Black screen fault analysis method and device of vehicle-mounted entertainment terminal, vehicle and medium | |
| CN115204260A (en) | Prediction model training method, prediction device, electronic equipment and storage medium | |
| CN111381165A (en) | Vehicle power battery monitoring method, device and platform | |
| CN114839554A (en) | Battery alarm method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |