Adaptive charging control system based on battery monitoring and diagnosis

Abstract

The present application relates to the field of charging control technology, and specifically to an adaptive charging control system based on battery monitoring and diagnosis. The system can implement the following steps through the cooperation between multiple modules: obtaining the historical temperature data and historical current data of the battery to be monitored in the historical time period, as well as the current temperature data at the current moment; determining the initial weight and target abnormality corresponding to each historical temperature data; correcting the initial weight corresponding to each historical temperature data; predicting the temperature prediction data at the current moment; and monitoring the charging of the battery to be monitored. If an abnormality is detected, the current at the current moment is controlled and adjusted. The present application utilizes historical temperature data, historical current data, and current temperature data to monitor the battery charging process and control the current during the battery charging process, effectively improving the accuracy of temperature prediction and the rationality of controlling and adjusting the charging process.

Description

Technical Field

[0001] The present application relates to the technical field of charging control, and in particular to an adaptive charging control system based on battery monitoring and diagnosis. Background Art

[0002] In order to facilitate the battery to provide a stable current output when needed, it is often necessary to charge the battery when idle. During the battery charging process, the battery charging state is judged by real-time monitoring of electrical parameters, and the charging is adaptively regulated based on the monitoring results. The battery charging process is accompanied by changes in battery temperature. If there is a temperature abnormality, it will often affect the service life of the battery and may cause safety hazards. Therefore, during the battery charging process, it is often necessary to detect and diagnose abnormal temperatures. When there is a temperature abnormality, it is often necessary to adaptively control and adjust the electrical parameters during the charging process. For example, the current can be adjusted to achieve charging control and regulation. When detecting abnormalities in data, it is possible to judge whether the data is abnormal by comparing the difference between the predicted normal data and the measured data. That is, if the difference between the predicted normal data and the measured data is large, it often indicates that there is an abnormality.

[0003] At present, the method usually adopted for predicting data is: assigning weights to historical data according to the time when the historical data was collected, and predicting the data through the weighted method, wherein the earlier the time when the historical data was collected, the smaller the weight assigned to the historical data is.

[0004] However, when weights are assigned to historical temperature data based on the time when the historical temperature data was collected and temperature data is predicted using the weighted method, the following technical problems often occur:

[0005] Due to the influence of various factors during the battery charging process, abnormal charging temperature data may exist in the historical temperature data involved in temperature data prediction. If the abnormal charging temperature data is collected late and a larger weight is given to the abnormal charging temperature data, the predicted temperature may be biased towards the temperature during abnormal charging, resulting in the final predicted temperature being difficult to characterize the temperature during normal charging of the battery, which often indicates that the accuracy of temperature prediction is poor, which in turn leads to poor accuracy in temperature abnormality detection, resulting in poor rationality in controlling and regulating the charging process. Summary of the invention

[0006] In order to solve the technical problem that the rationality of controlling and regulating the charging process is poor due to the poor accuracy of temperature prediction, the present application proposes an adaptive charging control system based on battery monitoring diagnosis.

[0007] The present application provides an adaptive charging control system based on battery monitoring diagnosis, the system comprising:

[0008] A data acquisition module is used to acquire the historical temperature data and historical current data of the battery to be monitored at each acquisition moment in the historical time period, as well as the current temperature data at the current moment;

[0009] An initial weight determination module, used to determine the initial weight corresponding to each historical temperature data according to the time interval between the collection time corresponding to each historical temperature data and the current time;

[0010] A change difference determination module, used to determine the change difference index corresponding to each historical temperature data according to the temperature change of each historical temperature data before and after its collection time, and the current change of the historical current data at the same collection time as each historical temperature data before and after its collection time;

[0011] An abnormality determination module, used to determine the target abnormality corresponding to each historical temperature data according to the change difference index and LOF value corresponding to each historical temperature data;

[0012] A target weight determination module is used to modify the initial weight corresponding to each historical temperature data according to the target abnormality corresponding to each historical temperature data to obtain the target weight corresponding to each historical temperature data;

[0013] A data prediction module, used to predict the temperature prediction data at the current moment according to all historical temperature data and their corresponding target weights;

[0014] The monitoring control and regulation module is used to monitor the charging of the battery to be monitored according to the difference between the current temperature data and the temperature prediction data, and if an abnormality is detected, control and regulate the current at the current moment.

[0015] Preferably, determining the change difference index corresponding to each historical temperature data according to the temperature change of each historical temperature data before and after its collection time, and the current change of the historical current data at the same collection time as each historical temperature data before and after its collection time, includes:

[0016] Determine any historical temperature data and its corresponding collection time as the marked temperature data and the marked time respectively; determine the historical current data whose collection time is the marked time as the matching current data corresponding to the marked temperature data;

[0017] Filter out a preset number of historical temperature data whose collection time is before the marking time and whose time interval between the collection time and the marking time is the shortest from all historical temperature data as upper temperature data, and obtain an upper temperature data sequence corresponding to the marked temperature data;

[0018] Based on the same acquisition method as the upper temperature data sequence, a lower temperature data sequence, an upper current data sequence and a lower current data sequence corresponding to the marked temperature data are acquired, wherein the acquisition moments corresponding to the elements in the lower temperature data sequence and the lower current data sequence are both after the marked moment, and the acquisition moments corresponding to the elements in the upper current data sequence are before the marked moment;

[0019] Determine the upper temperature change feature corresponding to the marked temperature data according to the similarity between the marked temperature data and the corresponding upper temperature data sequence and the upper current data sequence;

[0020] Determine the lower temperature change feature corresponding to the marked temperature data according to the similarity between the marked temperature data and the corresponding lower temperature data sequence and the lower current data sequence;

[0021] The change difference index corresponding to the marked temperature data is determined according to the upper temperature change characteristics and the lower temperature change characteristics corresponding to the marked temperature data.

[0022] Preferably, determining the upper temperature change feature corresponding to the marked temperature data according to the similarity between the marked temperature data and the corresponding upper temperature data sequence and the upper current data sequence includes:

[0023] ;

[0024] in, is the upper temperature change feature corresponding to the marked temperature data, is the normalization function, It is the mean of the absolute values ​​of the slopes of all historical temperature data in the upper temperature data sequence corresponding to the marked temperature data. It is the cumulative sum of the absolute values ​​of the differences between the historical temperature data and the marked temperature data in the upper temperature data sequence corresponding to the marked temperature data; is the mean of the absolute values ​​of the slopes of all historical current data in the upper current data sequence corresponding to the marked temperature data. It is the cumulative sum of the absolute values ​​of the differences between the historical current data and the matching current data in the upper current data sequence corresponding to the marked temperature data.

[0025] Preferably, determining the lower temperature change feature corresponding to the marked temperature data according to the similarity between the marked temperature data and the corresponding lower temperature data sequence and the lower current data sequence includes:

[0026] Calculate the mean of the absolute values ​​of the slopes of all historical temperature data in the temperature data sequence corresponding to the marked temperature data ;

[0027] Calculate the cumulative sum of the absolute values ​​of the differences between the historical temperature data and the marked temperature data in the upper temperature data sequence corresponding to the marked temperature data ;

[0028] Calculate the mean of the absolute values ​​of the slopes of all historical current data in the upper current data sequence corresponding to the marked temperature data ;

[0029] Calculate the cumulative sum of the absolute values ​​of the differences between the historical current data and the matching current data in the upper current data sequence corresponding to the marked temperature data ;

[0030] Use the upper temperature change feature corresponding to the marked temperature data The same calculation principle is used , , as well as , get the lower temperature change characteristics corresponding to the marked temperature data .

[0031] Preferably, determining the change difference index corresponding to the marked temperature data according to the upper temperature change characteristics and the lower temperature change characteristics corresponding to the marked temperature data includes:

[0032] One-half of the sum of the upper temperature change feature corresponding to the marked temperature data and the lower temperature change feature corresponding to the marked temperature data is used as a change difference index corresponding to the marked temperature data.

[0033] Preferably, determining the target abnormality corresponding to each historical temperature data according to the change difference index and LOF value corresponding to each historical temperature data includes:

[0034] All historical temperature data are combined into a historical temperature data sequence, and all historical current data are combined into a historical current data sequence;

[0035] Taking the extreme value in the historical temperature data sequence as a segmentation point, segmenting the historical temperature data sequence to obtain historical temperature data segments;

[0036] Taking the extreme value in the historical current data sequence as a segmentation point, segmenting the historical current data sequence to obtain historical current data segments;

[0037] Determine any historical temperature data and its corresponding collection time as the marked temperature data and the marked time respectively; determine the historical current data whose collection time is the marked time as the matching current data corresponding to the marked temperature data;

[0038] The target abnormality corresponding to the marked temperature data is determined based on the change difference index and LOF value corresponding to the marked temperature data, the average of the absolute values ​​of the slopes corresponding to all historical temperature data in the historical temperature data segment to which the marked temperature data belongs, and the average of the absolute values ​​of the slopes corresponding to all historical current data in the historical current data segment to which the matching current data corresponding to the marked temperature data belongs.

[0039] Preferably, the formula corresponding to the target abnormality corresponding to the historical temperature data is:

[0040] ;

[0041] ;

[0042] in, is the target abnormality corresponding to the i-th historical temperature data, i is the sequence number of the historical temperature data collected in the historical time period, is the normalization function, is the LOF value corresponding to the i-th historical temperature data, It is the ratio of the abnormal change factor of the i-th historical temperature data in the historical time period to the sum of the abnormal change factors of all historical temperature data;

[0043] is the abnormal change factor of the i-th historical temperature data in the historical time period, is the change difference index corresponding to the i-th historical temperature data, It is the absolute value function; is the mean of the absolute values ​​of the slopes corresponding to all historical temperature data in the historical temperature data segment to which the i-th historical temperature data belongs; It is the average of the absolute values ​​of the slopes corresponding to all historical current data in the historical current data segment to which the matching current data corresponding to the i-th historical temperature data belongs.

[0044] Preferably, the formula corresponding to the target weight corresponding to the historical temperature data is:

[0045] ;

[0046] in, is the target weight corresponding to the i-th historical temperature data; i is the sequence number of the historical temperature data collected in the historical time period; is the normalization function; is the target abnormality corresponding to the i-th historical temperature data, It is the cumulative result of the target abnormality corresponding to all historical temperature data; is the initial weight corresponding to the i-th historical temperature data.

[0047] Preferably, the charging monitoring of the battery to be monitored according to the difference between the current temperature data and the temperature prediction data includes:

[0048] When the absolute value of the difference between the current temperature data and the temperature prediction data is greater than a preset abnormality threshold, it is diagnosed that the battery to be monitored has a temperature abnormality at the current moment.

[0049] Preferably, if an abnormality is detected, the current at the current moment is controlled and adjusted, including:

[0050] If the battery to be monitored has a temperature abnormality at the current moment, and the temperature prediction data is greater than the current temperature data, the current at the current moment is increased;

[0051] If the battery to be monitored has a temperature abnormality at the current moment, and the temperature prediction data is less than the current temperature data, the current at the current moment is adjusted down.

[0052] This application has the following beneficial effects:

[0053] The adaptive charging control system based on battery monitoring and diagnosis of the present application can realize the monitoring of the battery charging process and the control of the current during the battery charging process by using historical temperature data, historical current data and current temperature data, and solves the technical problem that the rationality of controlling and adjusting the charging process is poor due to the poor accuracy of temperature prediction, and effectively improves the accuracy of temperature prediction and the rationality of controlling and adjusting the charging process. First, in the normal charging process, the temperature and current of the battery are often positively correlated. Therefore, in the normal charging process, the temperature change and current change of the battery often have certain similarities. Therefore, when the change difference index corresponding to the quantified historical temperature data is larger, it often indicates that the difference between the temperature change before and after the collection of the historical temperature data and the corresponding current change is larger, and it often indicates that the collection time corresponding to the historical temperature data is more likely to be an abnormal charging time, and it often indicates that the historical temperature data is more likely to represent the temperature during abnormal charging. Secondly, the larger the LOF value corresponding to the historical temperature data is, the more likely the historical temperature data is to be abnormal data. Therefore, when the target abnormality corresponding to the quantified historical temperature data is larger, it often indicates that the historical temperature data is more likely to represent the temperature during abnormal charging, and it often indicates that it is more necessary to give a smaller weight to the historical temperature data. Afterwards, compared to assigning weights to historical temperature data directly based on the collection moment of historical temperature data, this application modifies the initial weights corresponding to the historical temperature data based on the target abnormality, and the target weights corresponding to the quantified historical temperature data can often more accurately represent the real weights required when the historical temperature data participates in the prediction. Then, based on all historical temperature data and their corresponding target weights, the predicted temperature prediction data at the current moment can often represent the temperature during normal charging at the current moment. Finally, based on the difference between the current temperature data and the temperature prediction data, the battery to be monitored is charged and monitored. If an abnormality is detected, the current at the current moment is controlled and adjusted, thereby realizing charging monitoring and current control of the battery to be monitored. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0055] Figure 1 A schematic diagram of the structure of an adaptive charging control system based on battery monitoring and diagnosis provided in an embodiment of the present application;

[0056] Figure 2 This is a flowchart for implementing the change difference indicator provided in the embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the specific implementation methods, structures, features and effects of the technical solutions proposed by the present application are described in detail below in conjunction with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0058] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0059] refer to Figure 1 , shows a schematic diagram of the structure of an adaptive charging control system based on battery monitoring and diagnosis according to the present application. The adaptive charging control system based on battery monitoring and diagnosis includes:

[0060] The data acquisition module 101 is used to acquire the historical temperature data and the historical current data of the battery to be monitored at each collection moment in the historical time period, as well as the current temperature data at the current moment.

[0061] Among them, the battery to be monitored may be a battery to be monitored for charging. The historical time period may be a time period starting at the start time of charging of the battery to be monitored and before the current time. The collection time and the current time in the historical time period may both be moments in the same charging process of the battery to be monitored. The current time is also called the current time. The duration between adjacent collection times may be the same. The historical temperature data and the historical current data may be the temperature data and the current data collected in the historical time period. The current temperature data at the current time may be the temperature data collected at the current time.

[0062] It should be noted that during the battery charging process, if there is a temperature abnormality, it will often affect the battery's service life and may cause safety hazards. Therefore, obtaining temperature data can facilitate monitoring whether there is a temperature abnormality during the battery charging process. Since during the normal charging process, the battery's temperature and current are often positively correlated, that is, the battery's temperature change and current change often have a certain similarity, therefore, obtaining current data can facilitate the subsequent analysis of the temperature change and current change of the battery to be monitored, thereby facilitating monitoring whether there is a temperature abnormality during the battery charging process.

[0063] As an example, during the charging process of the battery to be monitored, if the current time is 13:21:06 on March 24, 2024, and the charging start time of the battery to be monitored is 13:15:00 on March 24, 2024, the temperature of the battery to be monitored can be collected every 1 second starting from 13:15:00 on March 24, 2024 through the temperature sensor as temperature data; the current data can be collected every 1 second starting from 13:15:00 on March 24, 2024 through the ammeter. The current of the battery to be monitored is used as the current data. At this time, the temperature data collected at 13:21:06 on March 24, 2024 can be the current temperature data, and the temperature data and current data collected before 13:21:06 on March 24, 2024 can be the historical temperature data and the historical current data, respectively; at this time, the start time of the historical time period can be 13:15:00 on March 24, 2024, and the end time can be 13:21:05 on March 24, 2024.

[0064] The initial weight determination module 102 is used to determine the initial weight corresponding to each historical temperature data according to the time interval between the collection time corresponding to each historical temperature data and the current time.

[0065] It should be noted that, generally speaking, the shorter the time interval between the collection time corresponding to the historical temperature data and the current time is, the greater the weight should be given to the historical temperature data.

[0066] As an example, the formula for determining the initial weight corresponding to the historical temperature data may be:

[0067] ;

[0068] in, is the initial weight corresponding to the i-th historical temperature data. i is the sequence number of the historical temperature data collected in the historical time period. It is an exponential function with a natural constant as its base. It is the time interval between the collection time corresponding to the i-th historical temperature data and the current time.

[0069] It should be noted that when The smaller the value, the more important the i-th historical temperature data is to the predicted data, and the more weight should be given to the i-th historical temperature data. The weight of the i-th historical temperature data can be roughly characterized.

[0070] The change difference determination module 103 is used to determine the change difference index corresponding to each historical temperature data according to the temperature change of each historical temperature data before and after its collection time, and the current change of the historical current data at the same collection time as each historical temperature data before and after its collection time.

[0071] It should be noted that during normal charging, the battery temperature and current are often positively correlated. Therefore, during normal charging, the battery temperature change and current change often have certain similarities. Therefore, the larger the change difference index corresponding to the quantified historical temperature data, the greater the difference between the temperature change before and after the historical temperature data is collected and the corresponding current change. This often indicates that the collection time corresponding to the historical temperature data is more likely to be an abnormal charging time, and the historical temperature data is more likely to represent the temperature during abnormal charging.

[0072] As an example, this step obtains the implementation flow chart of the change difference index corresponding to each historical temperature data, such as Figure 2 As shown, it includes steps 201 to 205:

[0073] 201 , determining marked temperature data and matching current data corresponding to the marked temperature data.

[0074] Any historical temperature data and its corresponding collection time are determined as marked temperature data and marked time, respectively. The historical current data whose collection time is the marked time is determined as matching current data corresponding to the marked temperature data.

[0075] For example, if a certain collection time is 13:15:25 on March 24, 2024, then the matching current data corresponding to the temperature data collected at 13:15:25 on March 24, 2024 may be: the current data collected at 13:15:25 on March 24, 2024.

[0076] 202, obtaining an upper temperature data sequence corresponding to the marked temperature data.

[0077] A preset number of historical temperature data with a collection time before the marking time and a shortest time interval between the collection time and the marking time are selected from all historical temperature data as upper temperature data, and an upper temperature data sequence corresponding to the marked temperature data is obtained.

[0078] The preset number may be a pre-set number. For example, the preset number may be 5. The upper temperature data sequence corresponding to the marked temperature data may include: a preset number of historical temperature data whose collection time is before the marking time and whose time interval between the collection time and the marking time is the shortest; if there are less than the preset number of historical temperature data before the marking time, all the historical temperature data before the marking time constitute the upper temperature data sequence corresponding to the marked temperature data.

[0079] For example, if the preset number is 5, and the 6 historical temperature data collected during the historical time period can be respectively: first temperature data, second temperature data, third temperature data, fourth temperature data, fifth temperature data and sixth temperature data, then the upper temperature data sequence corresponding to the sixth temperature data can be {first temperature data, second temperature data, third temperature data, fourth temperature data, fifth temperature data}; the upper temperature data sequence corresponding to the fifth temperature data can be {first temperature data, second temperature data, third temperature data, fourth temperature data}.

[0080] 203 , respectively obtain a lower temperature data sequence, an upper current data sequence, and a lower current data sequence corresponding to the marked temperature data.

[0081] According to the processing flow of step 202, a lower temperature data sequence, an upper current data sequence and a lower current data sequence corresponding to the marked temperature data are obtained.

[0082] The acquisition times corresponding to the elements in the lower temperature data sequence and the lower current data sequence are all after the marking time, and the acquisition times corresponding to the elements in the upper current data sequence are before the marking time.

[0083] For example, first, a preset number of historical temperature data whose corresponding collection time is after the above-mentioned marking time and whose time interval between the corresponding collection time and the above-mentioned marking time is the shortest can be selected from all historical temperature data as lower temperature data, and a lower temperature data sequence corresponding to the above-mentioned marked temperature data can be obtained. Next, a preset number of historical current data whose corresponding collection time is before the above-mentioned marking time and whose time interval between the corresponding collection time and the above-mentioned marking time is the shortest can be selected from all historical current data as upper current data, and an upper current data sequence corresponding to the above-mentioned marked temperature data can be obtained. Finally, a preset number of historical current data whose corresponding collection time is after the above-mentioned marking time and whose time interval between the corresponding collection time and the above-mentioned marking time is the shortest can be selected from all historical current data as lower current data, and a lower current data sequence corresponding to the above-mentioned marked temperature data can be obtained.

[0084] For example, if the preset number is 5, and the 6 historical temperature data collected in the historical time period can be: first temperature data, second temperature data, third temperature data, fourth temperature data, fifth temperature data and sixth temperature data, then the lower temperature data sequence corresponding to the first temperature data can be {second temperature data, third temperature data, fourth temperature data, fifth temperature data, sixth temperature data}; the lower temperature data sequence corresponding to the second temperature data can be {third temperature data, fourth temperature data, fifth temperature data, sixth temperature data}. Since the method for obtaining the upper current data sequence is the same as the method for obtaining the upper temperature data sequence, and the method for obtaining the lower current data sequence is the same as the method for obtaining the lower temperature data sequence, the methods for obtaining the upper current data sequence and the lower current data sequence are not repeated here.

[0085] It should be noted that the upper temperature data sequence and the upper current data sequence corresponding to the temperature data collected at the first collection moment in the charging process of the battery to be monitored are empty. The embodiment of the present application can correct the initial weights corresponding to the temperature data collected at all collection moments after the first collection moment in the charging process of the battery to be monitored, and the initial weights corresponding to the temperature data collected at the first collection moment may not be corrected. Therefore, the target abnormality degree corresponding to the temperature data collected at the first collection moment may not be calculated, and the target abnormality degree corresponding to the temperature data collected at the first collection moment may be directly set to 0, or the temperature data collected at the first collection moment may not participate in the subsequent data weighted prediction.

[0086] 204 , respectively determine the upper temperature change feature and the lower temperature change feature corresponding to the marked temperature data.

[0087] Among them, the upper temperature change feature corresponding to the marked temperature data represents whether the temperature change and the current change before the collection time corresponding to the marked temperature data have a relatively similar relationship; the lower temperature change feature corresponding to the marked temperature data can represent whether the temperature change and the current change after the collection time corresponding to the marked temperature data have a relatively similar relationship.

[0088] Specifically, taking the above temperature change characteristics as an example, the upper temperature change characteristics corresponding to the above marked temperature data can be determined based on the difference between the above marked temperature data and the historical temperature data in the corresponding upper temperature data sequence, and the difference between the historical current data in the upper current data sequence corresponding to the marked temperature data.

[0089] Among them, the absolute value of the slope corresponding to the historical temperature data is the absolute value of the slope corresponding to the historical temperature data. The method for obtaining the slope corresponding to the historical temperature data can be: using the collection time in the historical time period as the horizontal coordinate and the historical temperature data in the historical time period as the vertical coordinate to draw a temperature change curve in the historical time period; the slope of the coordinate point to which the historical temperature data belongs on the temperature change curve is the slope corresponding to the historical temperature data. The horizontal coordinate of the coordinate point to which the historical temperature data belongs can be the collection time corresponding to the historical temperature data, and the vertical coordinate of the coordinate point to which the historical temperature data belongs can be the historical temperature data.

[0090] The method for obtaining the slope corresponding to the historical current data can be: using the collection time in the historical time period as the horizontal coordinate and the historical current data in the historical time period as the vertical coordinate to draw a current change curve in the historical time period; the slope of the coordinate point to which the historical current data belongs on the current change curve is the slope corresponding to the historical current data. The horizontal coordinate of the coordinate point to which the historical current data belongs can be the collection time corresponding to the historical current data, and the vertical coordinate of the coordinate point to which the historical current data belongs can be the historical current data.

[0091] Furthermore, the calculation formula of the upper temperature change characteristic corresponding to the marked temperature data is:

[0092] ;

[0093] in, is the upper temperature change feature corresponding to the marked temperature data, is the normalization function, It is the mean of the absolute values ​​of the slopes of all historical temperature data in the upper temperature data sequence corresponding to the marked temperature data. It is the cumulative sum of the absolute values ​​of the differences between the historical temperature data and the marked temperature data in the upper temperature data sequence corresponding to the marked temperature data; is the mean of the absolute values ​​of the slopes of all historical current data in the upper current data sequence corresponding to the marked temperature data. It is the cumulative sum of the absolute values ​​of the differences between the historical current data and the matching current data in the upper current data sequence corresponding to the marked temperature data.

[0094] It should be noted that It can represent the difference between the marked temperature data and all the historical temperature data in the corresponding upper temperature data sequence. The larger the value, the greater the degree of temperature change before the marked temperature data. The larger the value is, the greater the fluctuation between the historical temperature data in the upper temperature data sequence corresponding to the marked temperature data is. It can represent the temperature change before marking the temperature data. The larger the value, the greater the temperature change before marking the temperature data. It can characterize the difference between the matching current data corresponding to the marked temperature data and all the historical current data in the corresponding upper current data sequence. The larger the value, the greater the degree of current change before the historical current data at the same collection time as the marked temperature data. The larger the value, the greater the fluctuation between the historical current data in the upper current data sequence corresponding to the marked temperature data. It can characterize the current change before the historical current data collected at the same time as the marked temperature data. The larger the value, the greater the degree of current change before the historical current data collected at the same time as the marked temperature data.

[0095] Generally speaking, during normal charging, the temperature change and current change of the battery are often similar. The smaller the value is, the closer the temperature change and current change are before the collection time corresponding to the marked temperature data, which often means that the charging process before the collection time corresponding to the marked temperature data is more likely to be a normal charging process, which often means that the marked temperature data is more likely to represent the temperature during a normal charging process.

[0096] Furthermore, the mean of the absolute values ​​of the slopes of all the historical temperature data in the lower temperature data sequence corresponding to the marked temperature data is obtained respectively. , the cumulative sum of the absolute values ​​of the differences between the historical temperature data and the marked temperature data in the upper temperature data sequence corresponding to the marked temperature data , and the mean of the absolute values ​​of the slopes of all historical current data in the current data sequence corresponding to the marked temperature data , the cumulative sum of the absolute values ​​of the difference between the historical current data and the matching current data in the current data sequence corresponding to the marked temperature data , according to The same calculation principle is used to obtain the temperature change characteristics corresponding to the marked temperature data. .

[0097] 205 , determining a change difference index corresponding to the marked temperature data according to the upper temperature change characteristics and the lower temperature change characteristics corresponding to the marked temperature data.

[0098] Specifically, according to the upper temperature change characteristics and the lower temperature change characteristics corresponding to the above-mentioned marked temperature data, the formula corresponding to the change difference index corresponding to the above-mentioned marked temperature data can be determined as follows:

[0099] ;

[0100] in, It is the change difference indicator corresponding to the marked temperature data. , They are the upper temperature change characteristics and the lower temperature change characteristics corresponding to the marked temperature data.

[0101] During normal charging, the temperature change and current change of the battery are often similar. The smaller the value, the closer the temperature change and current change are after the acquisition time corresponding to the marked temperature data, which often indicates that the charging process after the acquisition time corresponding to the marked temperature data is more likely to be a normal charging process, and the marked temperature data is more likely to represent the temperature during a normal charging process. The smaller the value, the closer the temperature change and current change before and after the collection time corresponding to the marked temperature data are, which often means that the charging process before and after the collection time corresponding to the marked temperature data is more likely to be a normal charging process, which often means that the marked temperature data is more likely to represent the temperature in the normal charging process. The larger the value is, the more likely the marked temperature data is to represent abnormal charging temperature.

[0102] The abnormality determination module 104 is used to determine the target abnormality degree corresponding to each historical temperature data according to the change difference index and the LOF value corresponding to each historical temperature data.

[0103] Among them, the method for obtaining the LOF (Local Outlier Factor) value corresponding to the historical temperature data can be: through the outlier factor detection algorithm, all historical temperature data are detected for anomalies to obtain the LOF value corresponding to each historical temperature data. In this embodiment, the number of neighboring points in the outlier factor detection algorithm is set to 5. The LOF algorithm is a commonly used technology in the field of data processing, and the specific process will not be repeated.

[0104] It should be noted that the larger the LOF value corresponding to the historical temperature data, the more likely the historical temperature data is abnormal data. Therefore, the larger the target abnormality corresponding to the quantified historical temperature data, the more likely the historical temperature data is to represent the temperature during abnormal charging, and the smaller the weight should be given to the historical temperature data.

[0105] As an example, this step may include the following steps:

[0106] In the first step, all historical temperature data are combined into a historical temperature data sequence, and all historical current data are combined into a historical current data sequence.

[0107] Among them, the historical temperature data sequence and the historical current data sequence are time series sequences.

[0108] In the second step, the extreme values ​​in the historical temperature data sequence are used as segmentation points to segment the historical temperature data sequence to obtain historical temperature data segments.

[0109] Among them, the extreme values ​​in the historical temperature data series are also the extreme values ​​in the temperature change curve.

[0110] For example, if the historical temperature data sequence is {first temperature data, second temperature data, third temperature data, fourth temperature data, fifth temperature data, sixth temperature data, seventh temperature data}, and the third temperature data and the fifth temperature data are extreme values, then three historical temperature data segments can be obtained, and these three historical temperature data segments can be respectively: {first temperature data, second temperature data}, {third temperature data, fourth temperature data} and {fifth temperature data, sixth temperature data, seventh temperature data}.

[0111] The third step is to segment the historical current data sequence using the extreme values ​​in the historical current data sequence as segmentation points to obtain historical current data segments.

[0112] Among them, the extreme value in the historical current data sequence is also the extreme value in the current change curve.

[0113] In the fourth step, any historical temperature data and its corresponding collection time are respectively determined as the marked temperature data and the marked time; and the historical current data whose collection time is the marked time is determined as the matching current data corresponding to the marked temperature data.

[0114] The fifth step is to determine the target abnormality corresponding to the above-mentioned marked temperature data based on the change difference index and LOF value corresponding to the above-mentioned marked temperature data, the average of the absolute values ​​of the slopes corresponding to all historical temperature data in the historical temperature data segment to which the above-mentioned marked temperature data belongs, and the average of the absolute values ​​of the slopes corresponding to all historical current data in the historical current data segment to which the matching current data corresponding to the above-mentioned marked temperature data belongs.

[0115] For example, the formula for determining the target abnormality corresponding to the historical temperature data may be:

[0116] ;

[0117] ;

[0118] in, is the target abnormality corresponding to the i-th historical temperature data. i is the sequence number of the historical temperature data collected in the historical time period. is a normalization function. is the LOF value corresponding to the i-th historical temperature data, It is the ratio of the abnormal change factor of the i-th historical temperature data in the historical time period to the sum of the abnormal change factors of all historical temperature data. It is the abnormal change factor of the i-th historical temperature data in the historical time period. It is the change difference index corresponding to the i-th historical temperature data. It is the absolute value function. It is the mean of the absolute values ​​of the slopes corresponding to all historical temperature data in the historical temperature data segment to which the i-th historical temperature data belongs. It is the average of the absolute values ​​of the slopes corresponding to all historical current data in the historical current data segment to which the matching current data corresponding to the i-th historical temperature data belongs.

[0119] It should be noted that when The larger the value is, the more likely the i-th historical temperature data is to be abnormal data. When the value is larger, it often indicates that the i-th historical temperature data is more likely to represent the temperature during abnormal charging. When the value is larger, it often indicates that the difference between the temperature change and the current change in the collection period of the i-th historical temperature data is larger, which often indicates that the i-th historical temperature data is more likely to represent the temperature during abnormal charging. The larger the value is, the more likely the i-th historical temperature data is to represent the temperature during abnormal charging. The larger the value is, the more likely the i-th historical temperature data is to represent the temperature during abnormal charging.

[0120] The target weight determination module 105 is used to modify the initial weight corresponding to each historical temperature data according to the target abnormality degree corresponding to each historical temperature data, so as to obtain the target weight corresponding to each historical temperature data.

[0121] It should be noted that compared to assigning weights to historical temperature data directly based on the time when the historical temperature data was collected, the present application corrects the initial weights corresponding to the historical temperature data based on the target abnormality. The target weights corresponding to the quantified historical temperature data can often more accurately represent the real weights required when the historical temperature data participates in prediction.

[0122] As an example, the formula for determining the target weight corresponding to the historical temperature data may be:

[0123] ;

[0124] in, is the target weight corresponding to the i-th historical temperature data. i is the sequence number of the historical temperature data collected in the historical time period. is a normalization function. is the target abnormality corresponding to the i-th historical temperature data, It is the cumulative result of the target abnormality corresponding to all historical temperature data. is the initial weight corresponding to the i-th historical temperature data.

[0125] It should be noted that when When the value is larger, it often indicates that the time interval between the collection time of the i-th historical temperature data and the current time is shorter, which often indicates that a larger weight should be given to the i-th historical temperature data. When the value is larger, it often means that the i-th historical temperature data is more likely to represent the temperature during abnormal charging, which often means that it is less necessary to give a larger weight to the i-th historical temperature data. The actual weight required for the i-th historical temperature data to participate in the prediction can be relatively accurately represented.

[0126] The data prediction module 106 is used to predict the temperature prediction data at the current moment according to all the historical temperature data and their corresponding target weights.

[0127] It should be noted that, based on all historical temperature data and their corresponding target weights, the predicted temperature data at the current moment can often represent the temperature during normal charging at the current moment.

[0128] As an example, the formula corresponding to the temperature prediction data at the current moment can be:

[0129] ;

[0130] Where Y is the temperature forecast data at the current moment. i is the serial number of the historical temperature data collected during the historical time period. N is the number of historical temperature data collected during the historical time period. is the target weight corresponding to the i-th historical temperature data. is the i-th historical temperature data.

[0131] It should be noted that the quantified Y can often represent the temperature during normal charging at the current moment.

[0132] The monitoring control and adjustment module 107 is used to monitor the charging of the monitored battery according to the difference between the current temperature data and the temperature prediction data, and control and adjust the current at the current moment if an abnormality is detected.

[0133] It should be noted that based on the difference between the current temperature data and the temperature prediction data, the monitored battery is charged and monitored. If an abnormality is detected, the current at the current moment is controlled and adjusted, thereby realizing charging monitoring and current control of the monitored battery.

[0134] As an example, this step may include the following steps:

[0135] In the first step, when the absolute value of the difference between the current temperature data and the predicted temperature data is greater than a preset abnormality threshold, it is determined that the battery to be monitored has a temperature abnormality at the current moment.

[0136] The preset abnormality threshold may be a preset threshold, for example, 5.

[0137] In the second step, if the battery to be monitored has abnormal temperature at the current moment, and the predicted temperature data is greater than the current temperature data, the current at the current moment is increased.

[0138] For example, if the battery to be monitored has a temperature anomaly at the current moment, and the temperature prediction data is greater than the current temperature data, the current can be appropriately increased. In this embodiment, the current adjustment value is set to 0.1 ampere each time. In other embodiments, the magnitude of the current adjustment value can be determined by the implementer, and this application does not impose any special restrictions on this. Among them, the adjusted current often cannot exceed the maximum current allowed. If the current at the current moment is already the maximum current allowed, it is often not necessary to increase the current.

[0139] In the third step, if the battery to be monitored has abnormal temperature at the current moment, and the predicted temperature data is less than the current temperature data, the current at the current moment is reduced.

[0140] For example, if the battery to be monitored has a temperature anomaly at the current moment, and the predicted temperature data is less than the current temperature data, the current may be appropriately reduced, for example, by 0.1 ampere.

[0141] It should be noted that if the battery to be monitored does not have a temperature abnormality at the current moment, there is no need to adjust the current at the current moment.

[0142] In summary, compared with assigning weights to historical temperature data directly based on the time when the historical temperature data was collected, the present application corrects the initial weights corresponding to the historical temperature data based on the target abnormality. The target weights corresponding to the quantified historical temperature data can often more accurately represent the real weights required when the historical temperature data participates in the prediction, thereby improving the accuracy of temperature prediction, and then improving the accuracy of temperature abnormality detection, thereby improving the rationality of controlling and regulating the charging process.

[0143] It should be noted that the above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

[0144] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. An adaptive charging control system based on battery monitoring and diagnosis, characterized in that: The system comprises: A data acquisition module is used to acquire the historical temperature data and historical current data of the battery to be monitored at each acquisition moment in the historical time period, as well as the current temperature data at the current moment; An initial weight determination module, used to determine the initial weight corresponding to each historical temperature data according to the time interval between the collection time corresponding to each historical temperature data and the current time; A change difference determination module, used to determine the change difference index corresponding to each historical temperature data according to the temperature change of each historical temperature data before and after its collection time, and the current change of the historical current data at the same collection time as each historical temperature data before and after its collection time; An abnormality determination module, used to determine the target abnormality corresponding to each historical temperature data according to the change difference index and LOF value corresponding to each historical temperature data; A target weight determination module is used to modify the initial weight corresponding to each historical temperature data according to the target abnormality corresponding to each historical temperature data to obtain the target weight corresponding to each historical temperature data; A data prediction module, used to predict the temperature prediction data at the current moment according to all historical temperature data and their corresponding target weights; A monitoring control and adjustment module, used for monitoring the charging of the battery to be monitored according to the difference between the current temperature data and the temperature prediction data, and controlling and adjusting the current at the current moment if an abnormality is detected; Determining the change difference index corresponding to each historical temperature data according to the temperature change of each historical temperature data before and after its collection time, and the current change of the historical current data at the same collection time as each historical temperature data before and after its collection time, includes: Determine any historical temperature data and its corresponding collection time as the marked temperature data and the marked time respectively; determine the historical current data whose collection time is the marked time as the matching current data corresponding to the marked temperature data; Filter out a preset number of historical temperature data whose collection time is before the marking time and whose time interval between the collection time and the marking time is the shortest from all historical temperature data as upper temperature data, and obtain an upper temperature data sequence corresponding to the marked temperature data; Based on the same acquisition method as the upper temperature data sequence, a lower temperature data sequence, an upper current data sequence and a lower current data sequence corresponding to the marked temperature data are acquired, wherein the acquisition moments corresponding to the elements in the lower temperature data sequence and the lower current data sequence are both after the marked moment, and the acquisition moments corresponding to the elements in the upper current data sequence are before the marked moment; Determine the upper temperature change feature corresponding to the marked temperature data according to the similarity between the marked temperature data and the corresponding upper temperature data sequence and the upper current data sequence; Determine the lower temperature change feature corresponding to the marked temperature data according to the similarity between the marked temperature data and the corresponding lower temperature data sequence and the lower current data sequence; The change difference index corresponding to the marked temperature data is determined according to the upper temperature change characteristics and the lower temperature change characteristics corresponding to the marked temperature data.

2. The adaptive charging control system based on battery monitoring diagnosis according to claim 1 is characterized in that: The determining of the upper temperature change feature corresponding to the marked temperature data according to the similarity between the marked temperature data and the corresponding upper temperature data sequence and the upper current data sequence includes: ； in, is the upper temperature change feature corresponding to the marked temperature data, is the normalization function, It is the mean of the absolute values ​​of the slopes of all historical temperature data in the upper temperature data sequence corresponding to the marked temperature data. It is the cumulative sum of the absolute values ​​of the differences between the historical temperature data and the marked temperature data in the upper temperature data sequence corresponding to the marked temperature data; is the mean of the absolute values ​​of the slopes of all historical current data in the upper current data sequence corresponding to the marked temperature data. It is the cumulative sum of the absolute values ​​of the differences between the historical current data and the matching current data in the upper current data sequence corresponding to the marked temperature data.

3. The adaptive charging control system based on battery monitoring diagnosis according to claim 1, characterized in that: The step of determining the lower temperature change feature corresponding to the marked temperature data according to the similarity between the marked temperature data and the corresponding lower temperature data sequence and the lower current data sequence includes: Calculate the mean of the absolute values ​​of the slopes of all historical temperature data in the temperature data sequence corresponding to the marked temperature data ; Calculate the cumulative sum of the absolute values ​​of the difference between the historical temperature data and the marked temperature data in the lower temperature data sequence corresponding to the marked temperature data ; Calculate the mean of the absolute values ​​of the slopes of all historical current data in the current data sequence corresponding to the marked temperature data ; Calculate the cumulative sum of the absolute values ​​of the differences between the historical current data and the matching current data in the lower current data sequence corresponding to the marked temperature data ; Use the upper temperature change feature corresponding to the marked temperature data The same calculation principle is used , , as well as , get the lower temperature change characteristics corresponding to the marked temperature data .

4. The adaptive charging control system based on battery monitoring and diagnosis according to claim 1, characterized in that: Determine the change difference index corresponding to the marked temperature data according to the upper temperature change characteristics and the lower temperature change characteristics corresponding to the marked temperature data, including: One-half of the sum of the upper temperature change feature corresponding to the marked temperature data and the lower temperature change feature corresponding to the marked temperature data is used as a change difference index corresponding to the marked temperature data.

5. The adaptive charging control system based on battery monitoring and diagnosis according to claim 1, characterized in that: Determining the target abnormality corresponding to each historical temperature data according to the change difference index and LOF value corresponding to each historical temperature data includes: All historical temperature data are combined into a historical temperature data sequence, and all historical current data are combined into a historical current data sequence; Taking the extreme value in the historical temperature data sequence as a segmentation point, segmenting the historical temperature data sequence to obtain historical temperature data segments; Taking the extreme value in the historical current data sequence as a segmentation point, segmenting the historical current data sequence to obtain historical current data segments; Determine any historical temperature data and its corresponding collection time as the marked temperature data and the marked time respectively; determine the historical current data whose collection time is the marked time as the matching current data corresponding to the marked temperature data; The target abnormality corresponding to the marked temperature data is determined based on the change difference index and LOF value corresponding to the marked temperature data, the average of the absolute values ​​of the slopes corresponding to all historical temperature data in the historical temperature data segment to which the marked temperature data belongs, and the average of the absolute values ​​of the slopes corresponding to all historical current data in the historical current data segment to which the matching current data corresponding to the marked temperature data belongs.

6. The adaptive charging control system based on battery monitoring diagnosis according to claim 5, characterized in that: The formula for the target abnormality corresponding to the historical temperature data is: ； ； in, is the target abnormality corresponding to the i-th historical temperature data, i is the sequence number of the historical temperature data collected in the historical time period, is the normalization function, is the LOF value corresponding to the i-th historical temperature data, It is the ratio of the abnormal change factor of the i-th historical temperature data in the historical time period to the sum of the abnormal change factors of all historical temperature data; is the abnormal change factor of the i-th historical temperature data in the historical time period, is the change difference index corresponding to the i-th historical temperature data, It is the absolute value function; is the mean of the absolute values ​​of the slopes corresponding to all historical temperature data in the historical temperature data segment to which the i-th historical temperature data belongs; It is the average of the absolute values ​​of the slopes corresponding to all historical current data in the historical current data segment to which the matching current data corresponding to the i-th historical temperature data belongs.

7. The adaptive charging control system based on battery monitoring diagnosis according to claim 1, characterized in that: The formula for the target weight corresponding to the historical temperature data is: ； in, is the target weight corresponding to the i-th historical temperature data; i is the sequence number of the historical temperature data collected in the historical time period; is the normalization function; is the target abnormality corresponding to the i-th historical temperature data, It is the cumulative result of the target abnormality corresponding to all historical temperature data; is the initial weight corresponding to the i-th historical temperature data.

8. The adaptive charging control system based on battery monitoring diagnosis according to claim 1, characterized in that: The step of performing charging monitoring on the battery to be monitored according to the difference between the current temperature data and the temperature prediction data comprises: When the absolute value of the difference between the current temperature data and the temperature prediction data is greater than a preset abnormality threshold, it is diagnosed that the battery to be monitored has a temperature abnormality at the current moment.

9. The adaptive charging control system based on battery monitoring diagnosis according to claim 8, characterized in that: If an abnormality is detected, the current at the current moment is controlled and adjusted, including: If the battery to be monitored has a temperature abnormality at the current moment, and the temperature prediction data is greater than the current temperature data, the current at the current moment is increased; If the battery to be monitored has a temperature abnormality at the current moment, and the temperature prediction data is less than the current temperature data, the current at the current moment is adjusted down.

Images