CN113022378A

CN113022378A - Temperature consistency prediction method, temperature consistency prediction device, prediction equipment and storage medium

Info

Publication number: CN113022378A
Application number: CN202110227426.0A
Authority: CN
Inventors: 付振; 梁小明; 王明月; 彭凯; 刘相超; 王文彬
Original assignee: FAW Group Corp
Current assignee: FAW Group Corp
Priority date: 2021-03-01
Filing date: 2021-03-01
Publication date: 2021-06-25
Anticipated expiration: 2041-03-01
Also published as: WO2022183817A1; CN113022378B

Abstract

The invention discloses a temperature consistency prediction method, a temperature consistency prediction device, prediction equipment and a storage medium. The method comprises the following steps: collecting vehicle state data, wherein the vehicle state data comprise temperature data and time sequence information which are collected by a shared temperature sensor between each group of module monomers; and predicting the temperature consistency among the groups of modules according to the vehicle state data through a prediction model. Through above-mentioned technical scheme, from the temperature uniformity between the dimension prediction module of time dimension and different batteries, be convenient for in time discover the phenomenon of temperature imbalance, improve power battery's security, realize fault isolation to a certain extent.

Description

Temperature consistency prediction method, temperature consistency prediction device, prediction equipment and storage medium

Technical Field

The embodiment of the invention relates to the technical field of vehicle monitoring, in particular to a temperature consistency prediction method, a temperature consistency prediction device, temperature consistency prediction equipment and a storage medium.

Background

Nowadays, the internet of vehicles and new energy vehicles develop rapidly, many kinds of faults of the new energy vehicles are caused by thermal runaway of power batteries, and the reason for the thermal runaway is attributed to temperature abnormity, so that the temperature monitoring of the power batteries is particularly important. The power battery comprises a plurality of single batteries, the temperature consistency among different single batteries is an important index for ensuring the safety of the power battery, and the temperature consistency indirectly reflects whether the power battery is in a normal working state or not. When the temperature difference between different monomers is monitored to be large, an alarm is given or the voltage, the current and the like are adjusted too late, so that the occurrence of faults cannot be avoided, and great potential safety hazards exist.

Disclosure of Invention

The invention provides a temperature consistency prediction method, a temperature consistency prediction device, prediction equipment and a storage medium, which are used for predicting the temperature consistency among modules, are convenient for finding out the phenomenon of temperature imbalance in time, improve the safety of a power battery and realize fault isolation.

In a first aspect, an embodiment of the present invention provides a temperature consistency prediction method, including:

collecting vehicle state data, wherein the vehicle state data comprise temperature data and time sequence information which are collected by a shared temperature sensor between each group of module monomers;

and predicting the temperature consistency among the groups of modules according to the vehicle state data through a prediction model.

Further, the method also comprises the following steps:

acquiring historical temperature data and historical time sequence information;

and constructing a prediction model according to the historical temperature data and the historical time sequence information.

Further, predicting temperature consistency among the groups of modules according to the vehicle state data through a prediction model, wherein the predicting comprises the following steps:

sequentially calculating the difference value between the highest temperature and the lowest temperature of each group of modules at each moment according to the time sequence information through a prediction model;

for each moment, if the difference value is greater than or equal to a first threshold value, adding 1 to the count value of the counter on the basis of the count value of the previous moment, and if the difference value is less than the first threshold value, clearing the count value of the counter;

and if the count value of the counter reaches a second threshold value, judging that the temperature between the modules in each group does not accord with consistency.

extracting the characteristics of the temperature data by adopting a set sliding window through the prediction model according to the time sequence information, wherein the characteristics of the temperature data comprise the temperature of each group of modules at different moments;

and predicting the temperature consistency among the groups of modules according to the characteristics of the temperature data.

Further, predicting the temperature consistency among the groups of modules according to the characteristics of the temperature data comprises the following steps:

and classifying the characteristics of the temperature data based on an enhanced learning AdaBoost algorithm to predict the temperature consistency among the groups of modules.

Further, the vehicle state data further includes at least one of: vehicle code, cell temperature, cell voltage, cell current, charge and discharge state, charge and discharge current, charge and discharge voltage, vehicle operating state, cell voltage extreme value, cell current extreme value, cell temperature extreme value, Battery Management System (BMS) alarm information.

Further, the method also comprises the following steps: preprocessing the vehicle state data; the pre-treatment comprises at least one of: data deduplication; processing unavailable values; processing abnormal data; alarm correction; current correction; correcting voltage; and (6) correcting the temperature.

In a second aspect, an embodiment of the present invention provides a temperature consistency prediction apparatus, including:

the system comprises an acquisition module, a storage module and a control module, wherein the acquisition module is used for acquiring vehicle state data, and the vehicle state data comprises temperature data and time sequence information acquired by a shared temperature sensor between each group of module monomers;

and the prediction module is used for predicting the temperature consistency among the groups of modules according to the vehicle state data through a prediction model.

In a third aspect, an embodiment of the present invention provides a prediction apparatus, including:

one or more processors;

a memory for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the temperature consistency prediction method of the first aspect.

In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the temperature consistency prediction method according to the first aspect.

The embodiment of the invention provides a temperature consistency prediction method, a temperature consistency prediction device, prediction equipment and a storage medium, wherein the method comprises the following steps: collecting vehicle state data, wherein the vehicle state data comprise temperature data and time sequence information which are collected by a shared temperature sensor between each group of module monomers; and predicting the temperature consistency among the groups of modules according to the vehicle state data through a prediction model. Through above-mentioned technical scheme, from the temperature uniformity between the dimension prediction module of time dimension and different batteries, be convenient for in time discover the phenomenon of temperature imbalance, improve power battery's security, realize fault isolation to a certain extent.

Drawings

Fig. 1 is a flowchart of a temperature consistency prediction method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram illustrating a temperature sensor deployment according to an embodiment of the present invention;

FIG. 3 is a flowchart of a temperature consistency prediction method according to a second embodiment of the present invention;

fig. 4 is a flowchart of a temperature consistency prediction method according to a third embodiment of the present invention;

fig. 5 is a schematic diagram illustrating an implementation of a temperature consistency prediction process according to a second embodiment of the present invention;

fig. 6 is a schematic structural diagram of a temperature uniformity prediction apparatus according to a fourth embodiment of the present invention;

fig. 7 is a schematic hardware structure diagram of a prediction apparatus according to a fifth embodiment of the present invention.

Detailed Description

The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. In addition, the embodiments and features of the embodiments in the present invention may be combined with each other without conflict. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.

Before discussing exemplary embodiments in more detail, it should be noted that some exemplary embodiments are described as processes or methods depicted as flowcharts. Although a flowchart may describe the steps as a sequential process, many of the steps can be performed in parallel, concurrently or simultaneously. In addition, the order of the steps may be rearranged. The process may be terminated when its operations are completed, but may have additional steps not included in the figure. The processes may correspond to methods, functions, procedures, subroutines, and the like.

It should be noted that the terms "first", "second", and the like in the embodiments of the present invention are only used for distinguishing different apparatuses, modules, units, or other objects, and are not used for limiting the order or interdependence relationship of the functions performed by these apparatuses, modules, units, or other objects.

Example one

Fig. 1 is a flowchart of a temperature consistency prediction method according to an embodiment of the present invention, which is applicable to predicting the temperature consistency of a power battery module. Specifically, the temperature consistency prediction method may be executed by a temperature consistency prediction apparatus, which may be implemented by software and/or hardware and integrated in the prediction device. Further, the prediction device includes, but is not limited to: desktop computer, driving computer, smart mobile phone, car networking server and high in the clouds server etc. electronic equipment.

As shown in fig. 1, the method specifically includes the following steps:

s110, collecting vehicle state data, wherein the vehicle state data comprise temperature data and time sequence information collected through a shared temperature sensor between each group of module units.

Specifically, power battery mainly refers to the battery that provides power for electric automobile, includes a plurality of battery cells usually for provide automobile-used high voltage, wherein, a plurality of battery cell can constitute a set of module, based on the power supply mode of module, makes power battery modularization and standardization, can improve the radiating efficiency, reduces the risk of thermal runaway. In this embodiment, a corresponding temperature sensor is respectively deployed for each group of modules, and is used to collect temperature data of the corresponding module, for example, 1 time per minute, where the collected temperature data is associated with timing information, including the time of each collection, the frequency of collecting the data, and the like. It should be noted that, a set of modules includes at least two single batteries, and in general, the temperature difference between the single batteries in a set of modules is small and can be regarded as approximately equal, so that the single batteries in each set of modules can share the same temperature sensor, and the temperature data is collected by taking the module as a unit.

Fig. 2 is a schematic diagram illustrating a deployed temperature sensor according to an embodiment of the present invention. As shown in fig. 2, two single batteries form a set of modules, and the two single batteries share one temperature sensor, so that the number of temperature sensors to be deployed can be reduced, and each temperature sensor is used for collecting temperature data of adjacent single batteries, thereby reducing the cost and improving the efficiency of data collection and temperature consistency prediction.

And S120, predicting the temperature consistency among the groups of modules according to the vehicle state data through a prediction model.

Specifically, the prediction model can be a machine learning model, the prediction model learns the rule of judging the temperature consistency of each group of modules through training of a large amount of sample data, and the prediction result can be efficiently and accurately output for the input temperature data and the time sequence information so as to predict the temperature consistency among the modules of each group and conveniently find abnormality in time. The rule for judging the temperature consistency of the modules in each group is, for example, that if the temperature difference (difference between the highest temperature and the lowest temperature) between the modules in each group at a certain moment is greater than a set threshold, the temperature between the modules in each group is judged to be inconsistent, which indicates that the power battery has a fault or a fault trend and needs to be alarmed; or the temperature difference between the groups of modules is continuously larger than a set threshold value in a set time period, or the temperature data acquired at a plurality of continuous moments indicate that the temperature difference between the groups of modules is larger than the set threshold value, and the temperature between the groups of modules is judged not to accord with the consistency; whether the temperature among the groups of modules accords with consistency can also be determined according to factors such as the jumping degree of the temperature of the groups of modules at adjacent time or between adjacent time periods, the standard deviation or variance of the temperature of the groups of modules and the like.

Optionally, the vehicle state data collected in real time may be collected through a Controller Area Network (CAN) bus, uploaded to the internet of vehicles platform by a Telematics BOX (T-BOX), and stored in a data storage system (data lake). And the prediction equipment of the Internet of vehicles platform predicts the temperature consistency aiming at the vehicle state data by using the prediction model. The prediction result may be temperature conformity or nonconformity between the groups of modules (for example, output "0" indicates that the conformity is satisfied, and output "1" indicates that the conformity is not satisfied), or may be a probability that the temperature between the groups of modules conforms to or does not conform to the temperature conformity (for example, output is a value belonging to the interval [0,1 ]). In some embodiments, the time when the temperature of each module is changed from consistency to inconsistency in a set period in the future can be predicted according to the change trend of the temperature of each module, so that Predictive Maintenance (PdM) is realized, advance decision making is facilitated, and risks are avoided.

In an embodiment, the vehicle state data may further comprise at least one of:

vehicle codes, such as a frame number, a vehicle identification, an identification number (ID), etc., for distinguishing different vehicles;

the cell temperature, i.e. the temperature of each cell in the module;

the cell voltage, i.e. the voltage of each cell in the module;

the cell current is the current of each cell in the module;

the charging and discharging state comprises a charging state or a discharging state of the power battery;

charging and discharging current comprising charging current or discharging current of the power battery;

the charging and discharging voltage comprises the charging voltage or the discharging voltage of the power battery;

the working state of the vehicle comprises a flameout state, a driving state, a reversing state, an idling state and the like;

the extreme value of the single voltage is the highest voltage and/or the lowest voltage of the single battery in the power battery or each group of modules;

the extreme value of the single current is the highest current and/or the lowest current of the single battery in the power battery or each group of modules;

the extreme temperature value of the single battery, namely the highest temperature and/or the lowest temperature of the single battery in the power battery or each group of modules;

BMS alarm information, for example, alarm information of energy imbalance between the unit batteries, alarm information of abnormality of the unit batteries or the module, and the like.

Based on above-mentioned vehicle state data, not only can the uniformity of prediction module temperature, the prevention trouble, but also real-time supervision power battery's working parameter when each module temperature is not conform to the uniformity, also can fix a position unusual position fast and analysis trouble reason, be convenient for in time get rid of the trouble to guarantee power battery's security. It should be noted that the voltage sensor, the current sensor, and the like may be respectively disposed for each single battery, which is convenient for accurately positioning the abnormal single battery, and ensures the safety and reliability of the power battery.

According to the temperature consistency prediction method provided by the embodiment of the invention, an Artificial Intelligence (AI) model is constructed, the temperature consistency among all groups of modules can be predicted according to the collected known data, and potential safety hazards caused by unbalanced temperature of the power battery monomer are eliminated to a certain extent. The method combines an artificial intelligence technology to realize fault Prediction and Health Management (PHM) of the power battery, can predict the time or probability of the fault of the power battery by using known information, can provide decision reference for preventive maintenance and repair of the vehicle, and reduces maintenance cost and fault probability. Through the temperature uniformity between the dimensionality prediction module from time dimension and different batteries, be convenient for in time discover the phenomenon of temperature imbalance, improve power battery's security, realize fault isolation to a certain extent.

Example two

Fig. 3 is a flowchart of a temperature consistency prediction method according to a second embodiment of the present invention, where the second embodiment is optimized based on the foregoing embodiments, and a temperature consistency prediction process is specifically described. It should be noted that technical details that are not described in detail in the present embodiment may be referred to any of the above embodiments.

Specifically, as shown in fig. 3, the method specifically includes the following steps:

and S210, collecting vehicle state data.

Specifically, the vehicle state data includes temperature data of each group of modules and time series information, for example, temperature data of each group of modules within 20 minutes, and every 1 minute corresponds to one group of temperature data. It should be noted that the vehicle state data may be collected in real time and predicted in real time, that is, temperature data is collected once at the current time, the prediction model may perform comprehensive prediction by combining the temperature data and the time sequence information at the current time according to the temperature data and the time sequence information collected in the previous 19 minutes, and the temperature data and the time sequence information in the previous 19 minutes may be downloaded from the cloud platform.

And S220, sequentially calculating the difference value between the highest temperature and the lowest temperature of each group of modules at each moment according to the time sequence information through the prediction model.

In this embodiment, the prediction model sequentially calculates the difference between the highest temperature and the lowest temperature in the temperatures of the modules at each time according to the time sequence information, that is, the sequence of temperature data acquisition, and if the difference is smaller, it indicates that the temperatures of the modules at each time are more balanced, and the temperature consistency is met; if the difference is large, the prediction result at the moment shows that the temperatures among the groups of modules are relatively unbalanced, the temperature consistency is not met, or the temperature is not consistent, so that the faults are easily caused by thermal runaway in the future.

S230, for each time instant, is the difference greater than or equal to a first threshold? If yes, go to S240; otherwise, S250 is performed.

S240, the count value of the counter is increased by 1 based on the count value of the previous time.

And S250, clearing the count value of the counter.

Specifically, the first threshold is used to determine whether the temperature of each group of modules at a certain time is consistent with the temperature consistency. In some embodiments, if the difference between the highest temperature and the lowest temperature of each group of modules reaches the first threshold at a certain time, the predicted result can be determined as that the temperatures of each group of modules do not conform. In this embodiment, in order to avoid erroneous determination caused by transient temperature instability and improve the reliability of prediction, the number of times when the temperature difference of each group of modules reaches the first threshold is recorded by the counter, and the prediction result is finally determined that the temperatures of each group of modules do not have consistency when the temperature difference of each group of modules continuously reaches the first threshold at a plurality of consecutive times (or in a set time).

S260, the count value of the counter reaches the second threshold? If yes, go to S290; otherwise, return to S230.

Specifically, if the difference between the highest temperature and the lowest temperature at a plurality of consecutive moments reaches a first threshold, counting a value of + 1; and if the difference value between the highest temperature and the lowest temperature at one moment is smaller than a first threshold value, clearing the count value until the count value reaches a second threshold value, and finally judging that the prediction result is that the temperatures of all groups of modules do not accord with consistency. By setting the second threshold, misjudgment caused by instable instantaneous temperature can be avoided, and the reliability of prediction is improved.

And S270, judging that the temperature between the modules in each group is inconsistent.

As another example, in the case of collecting vehicle state data in real time and predicting temperature consistency in real time, the implementation of the temperature consistency prediction process includes:

step1 two variables are defined: count (count value), and index [ ] (temperature difference time sequence index container), which are initialized to 0 and [ ], respectively;

step2, putting the temperature data acquired in real time and the corresponding time sequence information into a temperature difference time sequence index container;

step3, calculating the difference value between the highest temperature and the lowest temperature of each module temperature at the current moment, and counting +1 if the difference value is greater than or equal to a first threshold value; if the value is less than the first threshold value, the count is initialized to 0;

step4, judging whether the count reaches a second threshold value, if so, outputting a prediction result that the temperature between each group of modules does not accord with consistency; if not, then index [ ] +1, and the temperature data and the corresponding time sequence information collected at the next moment are continuously put into a temperature difference time sequence index container, and the Step3 is returned to be executed.

And on the basis that the prediction result at a certain moment is that the temperatures among the modules do not accord with each other, the difference value between the highest temperature and the lowest temperature of the temperatures of the modules at any subsequent moment is greater than or equal to a first threshold value, and the temperature is regarded as the temperature non-conformity among the modules.

In one embodiment, the vehicle state data further comprises at least one of: the system comprises a vehicle code, a monomer temperature, a monomer voltage, a monomer current, a charge-discharge state, a charge-discharge current, a charge-discharge voltage, a vehicle working state, a monomer voltage extreme value, a monomer current extreme value, a monomer temperature extreme value and battery management system alarm information.

In one embodiment, the method further comprises: preprocessing vehicle state data; the pre-treatment comprises at least one of: data deduplication; processing unavailable values; processing abnormal data; alarm correction; current correction; correcting voltage; and (6) correcting the temperature.

Specifically, a sensor in the vehicle collects vehicle state data and uploads the vehicle state data to a prediction device, and the prediction device conducts at least one of the following preprocessing on the vehicle state data before constructing a prediction model or predicting temperature consistency so as to improve data quality:

data deduplication, for example, deduplication of data at repeated times in vehicle state data, the time repetition possibly being caused by a time series information upload delay, and when one time corresponds to a plurality of repeated temperature data, only one of all the repeated temperature data is retained;

processing an unavailable value (NaN value), and deleting data at the moment containing the NaN value for all the cell voltage data and all the temperature measuring point data in the vehicle state data;

processing abnormal data, wherein a part of data of the vehicle state data in time sequence is abnormal, such as month is not within 1-12, time is not within 0:00-24:00, and the like, and the abnormal data can be deleted;

alarm correction, wherein an alarm (Mask) field in the vehicle state data is expressed in a decimal mode, but the alarm field set in the alarm field comparison table may be in a binary mode, for example, "0" represents that a single battery is normal, and "1" represents that a single battery is abnormal and triggers an alarm, so that the value of the alarm field in the vehicle state data can be converted into a binary value;

current correction, in which a maximum value of a single current and a minimum value of the single current at each time are recalculated to replace the maximum value of the single current uploaded to the prediction device, or the current at an intermediate time is re-estimated according to the currents at the previous and subsequent times within a set time period, for example, because the extreme values of the single current and the single current may deviate from the measured values due to instability, jump, system errors, and the like existing in the controller, parts, and the like of the vehicle during the working process and during the data transmission process;

correcting the voltage, wherein the extreme values of the cell voltage and the cell voltage may deviate from the measured values, so that the voltage is corrected, for example, the maximum value and the minimum value of the cell voltage at each moment are recalculated to replace the extreme value of the cell voltage uploaded to the prediction equipment, or the voltage at the middle moment is recalculated according to the voltages at the front moment and the rear moment in the set time period;

correcting the temperature, wherein deviation may occur between the monomer temperature and the extreme value of the monomer temperature and the measured value, so as to correct the temperature, for example, recalculating the maximum value and the minimum value of the monomer temperature at each moment to replace the extreme value of the monomer temperature uploaded to the prediction device, or re-estimating the temperature at the intermediate moment according to the temperatures at the front and rear moments in the set time period;

in addition, the preprocessing may also include data combining, disassembling, extracting, integrating, and the like. For example, the cell voltage and the cell temperature in the vehicle state data are stored in a list of listcell and listten and stored in a form of a character string in the list, but in the following actual use, the list may need to be expanded into a tabular data structure (DataFrame), so the listcell and listtemp need to be disassembled and extracted; for another example, data at a plurality of moments need to be combined together according to a specific time window, and operations such as averaging, variance and the like can also be performed; for another example, the processed vehicle state data can be integrated into a file in npy or pickle format, so that the occupied memory is small, the storing and reading speed is high, and the data processing efficiency can be improved.

In addition, preprocessing may also include edge calculations to reduce data transfer and storage pressure. And performing edge calculation on the data acquired by the vehicle end, namely encoding, packaging or compressing the data and the like. For example, under the condition of more alarm types, uploading one by one can cause greater pressure on storage, and cloud storage resources can be effectively saved by encoding alarm information into a binary form; and if the frequency of data acquisition at the vehicle end is high and the data acquisition is in the millisecond level, the low-frequency processing can be carried out on the original data, the data volume is reduced, and the data diversity is ensured.

According to the temperature consistency prediction method provided by the second embodiment of the invention, the time when the difference value between the highest temperature and the lowest temperature of each module reaches the first threshold is recorded by the counter, so that misjudgment caused by instable instantaneous temperature can be avoided, and the reliability of prediction is improved; by preprocessing the original data, the data volume can be reduced, unnecessary calculation is avoided, the data quality is improved, the accuracy and the reliability of prediction are improved, the phenomenon of temperature imbalance can be found conveniently in time, the safety of the power battery is improved, and fault isolation is realized.

EXAMPLE III

Fig. 4 is a flowchart of a temperature consistency prediction method according to a third embodiment of the present invention, where the third embodiment is optimized based on the foregoing embodiments, and specifically describes a working principle of a prediction model. It should be noted that technical details that are not described in detail in the present embodiment may be referred to any of the above embodiments.

Specifically, as shown in fig. 4, the method specifically includes the following steps:

and S310, acquiring historical temperature data and historical time sequence information.

Specifically, the prediction results corresponding to the historical temperature data and the historical time series information are known, that is, the labels are known, and therefore, the prediction results can be used as sample data of the prediction model.

And S320, constructing a prediction model according to the historical temperature data and the historical time sequence information.

Specifically, historical temperature data and historical time sequence information are used as input, corresponding historical prediction results are used as output, and a prediction model is trained to learn a rule for predicting temperature consistency according to the temperature data and the time sequence information.

In one embodiment, the performance of the predictive model is also tested after the predictive model training is completed. For example, all sample data is expressed as 7: 3, dividing the ratio into a training data set and a testing data set, and testing the performance of the prediction model by using sample data in the testing data set, wherein the ratio of positive and negative sample (sample which does not accord with or accords with temperature consistency) data in the testing data set is 10: 1, the evaluation index of the test can be the accuracy, the recall rate, the precision and/or the Area (AUC) enclosed by a Receiver Operating Characteristic Curve (ROC) and a coordinate axis. In some embodiments, further real vehicle verification can be performed on real vehicle data under the condition that the test result is ideal, and the prediction model is put into practical application only if the real vehicle verification effect is ideal.

And S330, collecting vehicle state data.

And S340, extracting the characteristics of the temperature data by adopting a set sliding window according to the time sequence information through the prediction model.

Specifically, because single data is easy to fluctuate and has low stability, the embodiment adopts a sliding window to extract features in feature engineering. Illustratively, the size of the sliding window is M pieces of data, the time span is T, the frequency of data acquisition is different, the values of M and T can be flexibly set, and T is about 5 minutes. For example, if the sliding window starts from the 0 th to the (M-1) th data and the number of sliding steps is 1, the features of the temperature data are sequentially extracted from the 1 st to the M th data and from the 2 nd to the (M +1) th data, and so on, and the features of the temperature data are continuously extracted.

The M pieces of data are selected for smoothing, and compared with the method for extracting the characteristics of single data in time sequence, the method has higher reliability and can avoid accidental errors; moreover, the quantity of continuous negative sample data on the vehicle with the temperature difference is small, and about 50 continuous negative sample data can show obvious temperature difference jump, so that the negative sample data needs to be selected as much as possible in the sliding window, and the stability of the sample data is ensured. If the sliding window is too large, some negative samples can not be extracted, so that valuable features are lost; if the sliding window is too small, timing information may be incomplete.

And S350, classifying the characteristics of the temperature data based on an AdaBoost algorithm to predict the temperature consistency among the modules.

Specifically, the extracted features of the temperature data are classified, that is, whether the extracted features are positive samples or negative samples is determined, so that the temperature consistency is predicted. Considering the temperature jump condition and the nonlinear factor of the characteristic variable, the embodiment selects the nonlinear classification AdaBoost algorithm as the classification model to improve the prediction accuracy. The AdaBoost algorithm may learn serially from training data to derive a series of weak learners, and linearly combine these weak learners into one strong learner.

Fig. 5 is a schematic diagram illustrating an implementation of a temperature consistency prediction process according to a second embodiment of the present invention. As shown in fig. 5, on line, the collected vehicle state data is input to the prediction model after being subjected to calculation and data preprocessing, and the prediction model can automatically output a prediction result; on line, the downloaded historical data is used as sample data to train a prediction model, the condition that the temperatures of all modules are consistent can be processed without any treatment, under the condition that the temperatures of all modules are inconsistent, the data need to be further extracted for preprocessing and input into a classification model, the classification model fully learns the prediction rule according to the temperature and time sequence characteristics of the data, model parameters are continuously optimized, the constructed prediction model can be tested by using a part of test data, and if the prediction result is inaccurate, problem backtracking can be carried out, and the model is adjusted. The trained predictive model can be directly applied to on-line real-time prediction. It should be noted that the data acquired in real time is also changed into historical data after being uploaded and stored to the cloud, and can be used for training or updating the prediction model. The process completes the off-line construction of the temperature inconsistency model, and predicts the real-time vehicle state data on line, and the prediction result can be stored or called in an interface mode. The temperature consistency prediction is realized through the data driving of the Internet of vehicles, the monitoring and the management of service ends such as product research and development, quality assurance after sale and the like on the vehicle can be driven through a real-time data stream interface calling mode, and a client is more transparent to the vehicle state, so that the use experience is improved.

According to the temperature consistency prediction method provided by the third embodiment of the invention, optimization is carried out on the basis of the third embodiment, and the reliability of the prediction model is ensured by testing and real vehicle verification on the prediction model; the characteristics of the temperature data are extracted by adopting a set sliding window, so that the comprehensiveness and stability of the characteristics are improved; the AdaBoost algorithm of nonlinear classification is used as a classification model, so that the accuracy of prediction is improved, the phenomenon of temperature imbalance is convenient to find in time, the safety of the power battery is further improved, and fault isolation is realized.

Example four

Fig. 6 is a schematic structural diagram of a temperature consistency prediction apparatus according to a fourth embodiment of the present invention. The temperature consistency prediction apparatus provided in this embodiment includes:

the acquisition module 410 is used for acquiring vehicle state data, wherein the vehicle state data comprises temperature data and time sequence information acquired by a shared temperature sensor between each group of module units;

and the prediction module 420 is used for predicting the temperature consistency among the groups of modules according to the vehicle state data through a prediction model.

According to the temperature consistency prediction device provided by the fourth embodiment of the invention, the temperature consistency between the modules is predicted from the time dimension and the dimensions of different batteries, so that the phenomenon of temperature imbalance can be conveniently found in time, the safety of the power battery is improved, and fault isolation is realized to a certain extent.

On the basis of the above embodiment, the method further includes:

the historical data acquisition module is used for acquiring historical temperature data and historical time sequence information;

and the construction module is used for constructing a prediction model according to the historical temperature data and the historical time sequence information.

Further, the prediction module 420 includes:

the calculation unit is used for sequentially calculating the difference value between the highest temperature and the lowest temperature of each group of modules at each moment according to the time sequence information through a prediction model;

the counting unit is used for adding 1 to the count value of the counter on the basis of the count value of the previous moment if the difference value is larger than or equal to a first threshold value for each moment, and clearing the count value of the counter if the difference value is smaller than the first threshold value;

and the judging unit is used for judging that the temperature between the groups of modules is inconsistent if the count value of the counter reaches a second threshold value.

Further, the prediction module 420 includes:

the characteristic extraction unit is used for extracting the characteristics of the temperature data by adopting a set sliding window according to the time sequence information through the prediction model, and the characteristics of the temperature data comprise the temperature of each group of modules at different moments;

and the prediction unit is used for predicting the temperature consistency among the groups of modules according to the characteristics of the temperature data.

Further, the prediction unit is specifically configured to:

the features of the temperature data are classified based on an AdaBoost algorithm to predict temperature consistency between groups of modules.

Further, the vehicle state data further includes at least one of: the system comprises a vehicle code, a monomer temperature, a monomer voltage, a monomer current, a charge-discharge state, a charge-discharge current, a charge-discharge voltage, a vehicle working state, a monomer voltage extreme value, a monomer current extreme value, a monomer temperature extreme value and battery management system alarm information.

Further, the method also comprises the following steps:

the preprocessing module is used for preprocessing the vehicle state data; the pre-treatment comprises at least one of: data deduplication; processing unavailable values; processing abnormal data; alarm correction; current correction; correcting voltage; and (6) correcting the temperature.

The temperature consistency prediction device provided by the fourth embodiment of the invention can be used for executing the temperature consistency prediction method provided by any of the above embodiments, and has corresponding functions and beneficial effects.

EXAMPLE five

Fig. 7 is a schematic hardware structure diagram of a prediction apparatus according to a fifth embodiment of the present invention. The prediction device includes, but is not limited to: desktop computer, driving computer, smart mobile phone, car networking server and high in the clouds server etc. electronic equipment. As shown in fig. 7, the prediction apparatus provided in the present application includes a memory 42, a processor 41, and a computer program stored on the memory and executable on the processor, and when the processor 41 executes the computer program, the temperature consistency prediction method described above is implemented.

The prediction device may also include a memory 42; the number of the processors 41 in the prediction device may be one or more, and one processor 41 is taken as an example in fig. 7; the memory 42 is used to store one or more programs; the one or more programs are executed by the one or more processors 41, causing the one or more processors 41 to implement a temperature consistency prediction method as described in embodiments of the present application.

The prediction apparatus further includes: a communication device 43, an input device 44 and an output device 45.

The processor 41, the memory 42, the communication means 43, the input means 44 and the output means 45 in the prediction device may be connected by a bus or other means, and fig. 7 illustrates the connection by a bus as an example.

The input device 44 may be used to receive entered numeric or character information and to generate key signal inputs relating to user settings and function control of the predictive device. The output device 45 may include a display device such as a display screen.

The communication means 43 may comprise a receiver and a transmitter. The communication device 43 is configured to perform information transmission and reception communication in accordance with control of the processor 41.

The memory 42, as a computer-readable storage medium, may be configured to store software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the temperature consistency prediction method according to the embodiment of the present application (for example, the acquisition module 410 and the prediction module 320 in the temperature consistency prediction apparatus). The memory 42 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created according to the use of the prediction apparatus, and the like. Further, the memory 42 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 42 may further include memory located remotely from processor 41, which may be connected to the predictive device over a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

On the basis of the above-described embodiments, the present embodiment also provides a computer-readable storage medium having stored thereon a computer program that, when executed by a temperature consistency prediction apparatus, implements a temperature consistency prediction method in any of the above-described embodiments of the present invention, the method including: collecting vehicle state data, wherein the vehicle state data comprise temperature data and time sequence information which are collected by a shared temperature sensor between each group of module monomers; and predicting the temperature consistency among the groups of modules according to the vehicle state data through a prediction model.

Embodiments of the present invention provide a storage medium including computer-executable instructions, which may take any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer-readable storage medium may be, for example, but is not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: 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), a flash Memory, an optical fiber, a portable CD-ROM, an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. 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, apparatus, or device.

A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take a variety of forms, including, but not limited to: an electromagnetic signal, an optical signal, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, Radio Frequency (RF), etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations for aspects of the present application 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 case of a remote computer, 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).

From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes several instructions for enabling a computer device (which may be a personal computer, a server, or a network device) to execute the temperature consistency prediction method according to the embodiments of the present invention.

It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for predicting temperature uniformity, comprising:

2. The method of claim 1, further comprising:

acquiring historical temperature data and historical time sequence information;

3. The method of claim 1, wherein predicting temperature consistency between groups of modules from the vehicle state data via a predictive model comprises:

calculating the difference value between the highest temperature and the lowest temperature of each group of modules at each moment in sequence according to the time sequence information through the prediction model;

4. The method of claim 1, wherein predicting temperature consistency between groups of modules from the vehicle state data via a predictive model comprises:

5. The method of claim 4, wherein predicting temperature consistency between groups of modules based on characteristics of the temperature data comprises:

6. The method of claim 1, wherein the vehicle state data further comprises at least one of: the system comprises a vehicle code, a monomer temperature, a monomer voltage, a monomer current, a charge-discharge state, a charge-discharge current, a charge-discharge voltage, a vehicle working state, a monomer voltage extreme value, a monomer current extreme value, a monomer temperature extreme value and battery management system alarm information.

7. The method of claim 1, further comprising: preprocessing the vehicle state data; the pre-treatment comprises at least one of: data deduplication; processing unavailable values; processing abnormal data; alarm correction; current correction; correcting voltage; and (6) correcting the temperature.

8. A temperature uniformity prediction apparatus, comprising:

9. A prediction apparatus, characterized by comprising:

one or more processors;

a memory for storing one or more programs;

when executed by the one or more processors, cause the one or more processors to implement the temperature consistency prediction method as recited in any one of claims 1-7.

10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out a method for temperature consistency prediction as defined in any one of claims 1 to 7.