Intelligent networked automobile and power battery data uploading method and system

Abstract

The invention relates to the technical field of electronic digital data processing, in particular to an intelligent networked automobile and power battery data uploading method and system.The method comprises the steps that a current data sequence and a voltage data sequence of a power battery are obtained, an interpolation processing flow is executed on the current data sequence through a simulated annealing algorithm, and in the interpolation processing flow, the current data sequence and the voltage data sequence are processed; when new solutions are output during interpolation processing each time, the acceptance of the new solutions is analyzed, the optimal degree of each new solution is determined according to the acceptance of the new solutions and the voltage data sequence, the optimal solution is determined according to the optimal degree of each new solution, and a target current data sequence is determined and uploaded according to the optimal solution and the current data sequence. And the acceptance and the optimization degree of the new solution are introduced, so that the accuracy of the optimal solution for interpolation is improved, and the accuracy of the uploaded target current data sequence is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular to an intelligent connected vehicle and a method and system for uploading power battery data. Background Art

[0002] With the rapid development of intelligent connected vehicles, the automotive industry is constantly moving towards the direction of intelligence, automation, and networking. Among them, as a key component in intelligent connected vehicles, the battery current data and battery voltage data of the power battery have an important impact on the safety, endurance, and user experience of the vehicle. Therefore, the upload of power battery data of intelligent connected vehicles has become an important function in the vehicle intelligent system. By real-time monitoring and uploading the power battery data, it is possible to achieve state analysis, fault diagnosis, and life cycle management of the battery, thereby improving the battery usage efficiency and extending its service life.

[0003] In the actual data collection process, due to the interference of signal transmission, sensor failures, device loss, or environmental factors, intelligent connected vehicles may encounter the situation of loss or missing of the current data of the power battery, which may lead to inaccurate data analysis results, and further affect the performance and reliability of the entire system. Currently, in order to fill in the missing data, the simulated annealing algorithm is usually used. In each iteration process of outputting the optimal solution, the simulated annealing algorithm continuously compares the objective function values of the current solution and the new solution to determine whether to accept the new solution. Finally, the optimal solution is obtained after the iteration is completed. However, the optimal solution obtained based on the objective function value is the current data of an ideal battery that conforms to the current state. Such an optimal solution may not conform well to the change characteristics of the data around the missing point. That is, inserting the optimal solution as the filling value into the current data sequence will cause a large numerical jump in the power battery current data sequence, and there may be a certain error when restoring the original data, resulting in a decrease in interpolation accuracy. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide an intelligent connected vehicle and a method and system for uploading power battery data. The specific technical solutions adopted are as follows: In the first aspect, an embodiment of the present application provides a method for uploading power battery data, including: Obtain the current data sequence and voltage data sequence of the power battery; Perform an interpolation processing process on the current data sequence through the simulated annealing algorithm. In the interpolation processing process, when a new solution is output in each interpolation process, analyze the acceptance degree of the new solution; the acceptance degree characterizes the difference between the missing current data corresponding to the new solution and the adjacent current data; Determine the preference degree of each new solution according to the acceptance degree of the new solution and the voltage data sequence respectively; the preference degree characterizes the error degree after the new solution is inserted into the corresponding missing current data position. Determine the optimal solution according to the preference degree of each new solution, and determine the target current data sequence and upload it according to the optimal solution and the current data sequence.

[0005] In one implementation, in the interpolation processing flow, when each interpolation processing outputs a new solution, analyzing the acceptance degree of the new solution includes: In the interpolation processing flow, when each interpolation processing outputs a new solution, determine the value of the new solution. Respectively simulate the corresponding simulated current data sequences after inserting the values of the new solutions into the missing current data positions of the current data sequence, and determine the change characteristics of the simulated current data sequences. Respectively determine the acceptance degree of the new solution according to the change characteristics.

[0006] In one implementation, determining the change characteristics corresponding to the simulated current data sequence includes: Respectively determine the average value of the current data within the preset proximity range of the missing current data position in each simulated current data sequence, and respectively determine the relative offset of each new solution according to the value of the new solution and the corresponding average value of the current data. Respectively determine the first change amount between the value of the new solution and the previous current data at the missing current data position in each simulated current data sequence, and the second change amount between two adjacent current data within the preset proximity range of the missing current data position. Respectively determine the first ratio of the first change amount to the largest second change amount to obtain the change amount smoothness corresponding to each new solution. Wherein, the change characteristics corresponding to the simulated current data sequence include the relative offset of each new solution and the corresponding change amount smoothness.

[0007] In one implementation, respectively determining the acceptance degree of the new solution according to the change characteristics includes: Respectively determine the calculation results according to the opposite number of the relative offset of each new solution and the natural exponential function. Respectively obtain the acceptance degree of each new solution according to the product of the calculation results and the change amount smoothness of each new solution.

[0008] In one implementation, respectively determining the preference degree of each new solution according to the acceptance degree of the new solution and the voltage data sequence includes: For each of the simulated current data sequences, determine a first current data subsequence within a preset proximity range of the missing current data position, and respectively remove the new solution from the first current data subsequence to obtain a corresponding second current data subsequence; According to the first current data subsequence, determine a first voltage data subsequence corresponding to the same time period from the voltage data sequence, and respectively remove the voltage data corresponding to the new solution from the first voltage data subsequence to obtain a corresponding second voltage data subsequence; Respectively determine a first Pearson correlation coefficient between each first current data subsequence and the corresponding first voltage data subsequence, and determine a second Pearson correlation coefficient between each second current data subsequence and the corresponding second voltage data subsequence; Respectively determine the preference level of each new solution according to the first Pearson correlation coefficient, the second Pearson correlation coefficient, and the acceptance of the new solution.

[0009] In one implementation, the step of respectively determining the preference level of each new solution according to the first Pearson correlation coefficient, the second Pearson correlation coefficient, and the acceptance of the new solution includes: Respectively determine the difference value between the first Pearson correlation coefficient and the second Pearson correlation coefficient, and respectively obtain corresponding normalization results according to the difference value and a normalization function; Respectively obtain the preference level of each new solution according to the product of the acceptance of the new solution and the normalization result.

[0010] In one implementation, the step of determining the optimal solution according to the preference level of each new solution includes: Respectively determine the possibility of each new solution being the optimal solution according to the preference level of each new solution and a preset objective function; Perform iteration of new solutions according to the possibility to determine the optimal solution; Among them, in the interpolation processing flow, each time a new solution is output during iteration, compare the possibility of the current new solution with the possibility of the output new solution, and use the new solution with a greater possibility as the new current new solution to participate in the next iteration of new solutions.

[0011] In one implementation, the step of respectively determining the possibility of each new solution being the optimal solution according to the preference level of each new solution and a preset objective function includes: Based on the preset objective function, determine the objective function value of each new solution, and respectively determine a second ratio of the preference level of each new solution to the corresponding objective function value of the new solution; According to the second ratio and the normalization function respectively, obtain the possibility of each of the new solutions being the optimal solution.

[0012] In a second aspect, an embodiment of the present application provides a power battery data uploading system, including: An acquisition module, configured to acquire a current data sequence and a voltage data sequence of a power battery; An analysis module, configured to perform an interpolation processing flow on the current data sequence through a simulated annealing algorithm. In the interpolation processing flow, when a new solution is output for each interpolation processing, analyze the acceptance degree of the new solution; the acceptance degree characterizes the difference between the missing current data corresponding to the new solution and the adjacent current data; A determination module, configured to determine the preference degree of each new solution respectively according to the acceptance degree of the new solution and the voltage data sequence; the preference degree characterizes the error degree after the new solution is inserted into the corresponding missing current data position; An upload module, configured to determine an optimal solution according to the preference degree of each new solution, and determine a target current data sequence and upload it according to the optimal solution and the current data sequence.

[0013] In a third aspect, an embodiment of the present application provides an intelligent connected vehicle, including: a processor and a memory. Instructions are stored in the memory, and the instructions are loaded and executed by the processor to implement the method in any one of the above aspects.

[0014] The present invention has the following beneficial effects: By acquiring the current data sequence and the voltage data sequence of the power battery, performing an interpolation processing flow on the current data sequence by using a simulated annealing algorithm. In the interpolation processing flow, when a new solution is output for each interpolation processing, analyze the acceptance degree of the new solution, determine the preference degree of each new solution respectively according to the acceptance degree of the new solution and the voltage data sequence, determine the optimal solution according to the preference degree of each new solution, and determine a target current data sequence and upload it according to the optimal solution and the current data sequence, where the acceptance degree characterizes the difference between the missing current data corresponding to the new solution and the adjacent current data, and the preference degree characterizes the error degree after the new solution is inserted into the corresponding missing current data position. Therefore, introducing the acceptance degree and the preference degree of the new solution is beneficial to improving the accuracy of the optimal solution for interpolation, thereby ensuring the accuracy of the uploaded target current data sequence. Description of the Drawings

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0016] Figure 1 Schematic diagram of the step flow of a power battery data upload method provided by an embodiment of the present invention; Figure 2 Block diagram of the structure of a power battery data upload system provided by an embodiment of the present invention; Figure 3 Block diagram of the structure of an intelligent connected vehicle provided by an embodiment of the present invention. Detailed implementation manners

[0017] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in combination with the accompanying drawings and preferred embodiments, details the specific implementation manners, structures, features, and effects of an intelligent connected vehicle, a power battery data upload method, and a system according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0019] It should be noted that the "exemplary" in the embodiments of the present application refers to examples listed for convenience of description, and other embodiments are not limited to the examples listed.

[0020] The following specifically describes the specific solutions of an intelligent connected vehicle, a power battery data upload method, and a system provided by the present invention in combination with the accompanying drawings.

[0021] Please refer to Figure 1 , which shows a schematic diagram of the step flow of a power battery data upload method provided by an embodiment of the present invention. The power battery data upload method may at least include steps S100 - S400: S100. Obtain the current data sequence and voltage data sequence of the power battery.

[0022] S200. Perform an interpolation processing flow on the current data sequence through the simulated annealing algorithm. In the interpolation processing flow, when a new solution is output for each interpolation processing, analyze the acceptance degree of the new solution.

[0023] Optionally, the acceptance characterizes the difference between the missing current data corresponding to the new solution and the adjacent current data.

[0024] S300. Determine the preference level of each new solution respectively according to the acceptance of the new solution and the voltage data sequence.

[0025] Optionally, the preference level characterizes the error degree after the new solution is inserted into the corresponding missing current data position.

[0026] S400. Determine the optimal solution according to the preference level of each new solution, and determine the target current data sequence according to the optimal solution and the current data sequence and upload it.

[0027] In the technical solution of the embodiment of the present application, by acquiring the current data sequence and voltage data sequence of the power battery, and using the simulated annealing algorithm to perform the interpolation processing flow on the current data sequence. In the interpolation processing flow, each time a new solution is output during the interpolation processing, analyze the acceptance of the new solution, and determine the preference level of each new solution respectively according to the acceptance of the new solution and the voltage data sequence. According to the preference level of each new solution, determine the optimal solution, and determine the target current data sequence according to the optimal solution and the current data sequence and upload it, where the acceptance characterizes the difference between the missing current data corresponding to the new solution and the adjacent current data, and the preference level characterizes the error degree after the new solution is inserted into the corresponding missing current data position. Therefore, introducing the acceptance and preference level of the new solution is beneficial to improving the accuracy of the optimal solution for interpolation, thereby ensuring the accuracy of the uploaded target current data sequence.

[0028] In one implementation manner, in step S100, the battery management system of the intelligent connected vehicle (hereinafter referred to as the vehicle) is provided with a current sensor and a voltage sensor, and can collect the current data and voltage data of the power battery during the vehicle's driving process. Among them, the acquisition frequency and acquisition time can be set based on actual needs. For example, once per second, and the acquisition time is 2 hours in total. Therefore, current data and voltage data corresponding to multiple sampling moments can be collected, respectively forming the current data sequence and voltage data sequence of the power battery. It can be understood that each current data is arranged in the current data sequence in the time order of the sampling moment, equivalent to a current data point, and has its corresponding arranged current data position in the current data sequence. The same applies to the voltage data sequence.

[0029] Optionally, in the embodiments of the present application, the initial temperature value of the set simulated annealing algorithm is set to 200 °C, the temperature threshold is preset to 60 °C, the cooling coefficient is set to 0.95, the initial solution of the current data of the power battery (i.e., the value of the first current solution at the first interpolation, set to the empirical value of 10 A), and the perturbation range size of the new solution output by each interpolation process is preset to be A.

[0030] Among them, the objective function is constructed: In the formula, represents the objective function value corresponding to the current data of any power battery. and respectively represent the weights of the two influencing factors of the objective function value ( , ); represents the temperature change rate of any power battery current data within a unit time when applied to a power battery with the same temperature as the power battery at the current moment. This value can be obtained from historical data using big data technology. The larger this value, the stronger the influence of this current data on the vehicle during driving, and the smaller its corresponding objective function value; represents the energy consumption of any power battery current data within a unit time when applied to a power battery with the same temperature as the power battery. The larger this value, the more energy the battery current data consumes during vehicle driving, and the larger its corresponding objective function value. Similarly, it can be obtained based on historical data analysis and can be calculated based on existing methods, which will not be elaborated here.

[0031] It should be noted that since the current data at a certain moment may be missing, that is, there is no current data at a certain current data position, this position can also be called the missing current data position, and the missing current data is called the missing current data. And the current data usually has certain time series characteristics. The current of the battery is not only affected by the charge and discharge state of the battery, but also related to the voltage factor. Therefore, the missing data points often occur when the battery state changes suddenly, the sensor fails, or there is a data transmission error. In step S200, an interpolation processing flow is performed on the current data sequence through the simulated annealing algorithm, that is, the simulated annealing algorithm is used to process the current data sequence, and the purpose is to interpolate at the missing current data position to fill in the missing data and ensure that the interpolated data shows a reasonable trend in the time series. Therefore, after the initial parameter settings and the objective function design are completed, in the subsequent steps, it is necessary to analyze the preference degree of each new solution during the optimal solution output for each interpolation process. Among them, after each new solution is filled into the current data point with missing data, the smaller the numerical performance difference between the battery current data point and its surrounding data, the more it can be explained that the value corresponding to the new solution conforms to the trend and change characteristics of the surrounding data sequence of the missing battery current data point for this interpolation process, and the greater its corresponding acceptance degree will be.

[0032] In the embodiment of the present application, in step S200, during the interpolation processing flow, when a new solution is output for each interpolation process, analyzing the acceptance degree of the new solution includes steps S201 - S203: S201. During the interpolation processing flow, when a new solution is output for each interpolation process, determine the value of the new solution.

[0033] It should be noted that during the interpolation processing flow, the process principle of the simulated annealing algorithm for outputting a new solution each time can refer to the existing simulated annealing algorithm. In the embodiment of the present application, the focus is on further analyzing the acceptance degree, preference degree, etc. after the new solution is output, so as to optimize the accuracy of the new solution. Specifically, when a new solution is output for each interpolation process, determine the value of the new solution , denotes the value of the th new solution output during the

[0034] S202. After respectively simulating the corresponding simulated current data sequence when the value of the new solution is inserted into the missing current data position of the current data sequence, and determine the change characteristics corresponding to the simulated current data sequence.

[0035] Optionally, the numerical values of the new solutions are respectively inserted into the positions of the missing current data in the current data sequence. For example, when simulating the insertion of the new solution obtained from the first interpolation process into the position of the missing current data, one corresponding simulated current data sequence can be obtained. Therefore, each time a new solution is inserted into the position of the missing current data, a corresponding simulated current data sequence can be obtained. Then, the change characteristics corresponding to each simulated current data sequence are determined. The change characteristics corresponding to the simulated current data sequence include the relative offset of each new solution and the smoothness of the corresponding change amount. The specific determination process is as follows: First, a preset proximity range can be set based on actual needs. For example, a length of 50 sampling instants, that is, 50 seconds, can be set. If it is insufficient, a length of 10 sampling instants, that is, 10 seconds, can be set. Taking 50 seconds as an example, for each simulated current data sequence, the first 50 current data at the position of the missing current data are respectively determined, and then the mean value of these 50 current data is calculated, so as to determine the mean value of the current data within the preset proximity range of the position of the missing current data , that is, the mean value of the current data corresponding to the simulated current data sequence corresponding to the th new solution output during the th interpolation process. Then, based on the numerical value of the new solution and the corresponding mean value of the current data, the relative offset of each new solution is determined .

[0036] Secondly, for each simulated current data sequence, the first change amount between the numerical value of the new solution and the previous current data (i.e., the current data at the previous sampling instant) at the position of the missing current data (i.e., the first change amount corresponding to the simulated current data sequence corresponding to the th new solution output during the th interpolation process) is respectively determined, and the second change amount between two adjacent current data within the preset proximity range of the position of the missing current data is determined. That is, among the 50 current data, the absolute value of the difference is calculated for each pair of adjacent current data to obtain the second change amount of the two adjacent current data.

[0037] Then, the first ratio between the first change amount and the corresponding maximum second change amount is respectively determined to obtain the smoothness of the change amount corresponding to each new solution .

[0038] S203. Determine the acceptance degree of the new solution according to the change characteristics respectively.

[0039] Optionally, according to the opposite number of the relative offset of each new solution and the natural exponential function , the calculation result , and then, according to the calculation results and the change smoothness corresponding to each new solution The product of, obtain the acceptance degree of each new solution, and the specific formula is: Among them, Indicates the acceptance degree of the th interpolation process for the th new solution output, Is a hyperparameter, , and its existence is to prevent From being 0; the smaller the relative offset , it indicates that after the value corresponding to this new solution is filled into the missing current data position, it is more in line with the change trend and change characteristics of the surrounding data sequence, and the acceptance degree corresponding to this new solution will be greater; the smaller the value of the change smoothness , it indicates that after the th interpolation process for the th new solution is filled into the missing current data position, the change between the missing current data position and the current data immediately before it is smoother, more in line with the change trend and change characteristics of the surrounding data sequence, the credibility will be greater, and the acceptance degree corresponding to this new solution will also be greater.

[0040] It should be noted that although the acceptance degree of the new solution is initially determined, in some cases, for example, when the current data at this missing current data point changes significantly compared with its surrounding data, the acceptance degree of the new solution obtained only by quantifying the numerical performance characteristics of each new solution in the surrounding data sequence of this missing current data cannot be accurate. Therefore, it is necessary to restore the true value of the missing current data. Based on the scenario research, there is a close correlation between the current data of the battery and the voltage data of the battery. The main reason is that when the battery voltage data increases, the relative speed of the vehicle increases, resulting in an increase in power consumption; then the relationship between power and battery current usually shows a cubic relationship, that is, the power increases significantly with the increase of the battery current data. Therefore, based on this principle, the preference degree of each new solution can be analyzed in combination with the voltage data. Among them, after each new solution is filled into the missing current data position, the greater the correlation between the numerical performance of this missing current data position and the battery voltage data corresponding to the same sampling moment, it indicates that the restoration degree of this new solution to the true current data at the missing current data position is greater, the possibility of error is smaller, and its corresponding preference degree will also be greater.

[0041] In one implementation manner, step S300 includes steps S301 - S304: S301. Determine, for each analog current data sequence, a first current data subsequence within a preset proximity range of the positions of the missing current data, and respectively remove the newly solved values from the first current data subsequence to obtain the corresponding second current data subsequence.

[0042] Optionally, taking 50 seconds as an example of the preset proximity range, for instance, a sequence of 50 current data including the 50 seconds before the position of the missing current data after filling the newly solved value can be determined, and the newly solved value at the position of the missing current data after filling in this sequence is removed to obtain a sequence of 50 current data, which is the corresponding second current data subsequence.

[0043] S302. Determine, according to the first current data subsequence, a first voltage data subsequence corresponding to the same time period from the voltage data sequence, and respectively remove the voltage data corresponding to the newly solved values from the first voltage data subsequence to obtain the corresponding second voltage data subsequence.

[0044] Optionally, based on the sampling moments corresponding to the first current data subsequence, determine a first voltage data subsequence corresponding to the same time period from the voltage data sequence. At this time, the first voltage data subsequence includes the moment of the newly solved value and the voltage data at 50 moments. Remove the voltage data corresponding to the moment of the newly solved value to obtain a sequence of 50 voltage data, which is the corresponding second voltage data subsequence.

[0045] S303. Determine the first Pearson correlation coefficient between each first current data subsequence and the corresponding first voltage data subsequence (the Pearson correlation coefficient between the first current data subsequence and the first voltage data subsequence corresponding to the th newly solved value output during the th interpolation process), and determine the second Pearson correlation coefficient between each second current data subsequence and the corresponding second voltage data subsequence (the Pearson correlation coefficient between the second current data subsequence and the second voltage data subsequence corresponding to the th newly solved value output during the th interpolation process).

[0046] It should be noted that the calculation method of the Pearson correlation coefficient is implemented based on existing methods and will not be elaborated here.

[0047] S304. Determine the preference degree of each newly solved value respectively according to the first Pearson correlation coefficient, the second Pearson correlation coefficient, and the acceptance degree of the newly solved value.

[0048] Optionally, determine the difference value between the first Pearson correlation coefficient and the second Pearson correlation coefficient respectively , and respectively according to the difference value and the normalization function , the corresponding normalization result is obtained , and then respectively according to the acceptance degree of the new solution The product of and the normalization result gives the preference degree of each new solution , and the specific formula is: In the formula, represents the preference degree of the th interpolation process output of the th new solution. The greater the acceptance degree of the new solution , it indicates that after the th interpolation process output of the th new solution fills into the missing current data position, the more it conforms to the change trend and characteristics of the surrounding data sequence, and the greater the preference degree of this new solution; The greater the value, it indicates that after the th interpolation process output of the

[0049] In one implementation, in step S400, according to the preference degree of each new solution, the optimal solution is determined, including steps S401 - S402: S401. Respectively according to the preference degree of each new solution and the preset objective function, determine the possibility of each new solution as the optimal solution.

[0050] Optionally, based on the above - mentioned preset objective function , determine the objective function value of each new solution (that is, the objective function value of the th interpolation process output of the th new solution. Different new solutions may correspond to different and , so as to determine different objective function values), and respectively determine the preference degree of each new solution and the objective function value of the corresponding new solution The second ratio ; then, respectively according to the second ratio and the normalization function , obtain the possibility of each new solution as the optimal solution : Among them, is the possibility that the th new solution output during the th interpolation process is used as the optimal solution. The greater the preference degree of the new solution, the more this value conforms to the trend and change characteristics of the data sequence around the missing current data position of this interpolation process, the higher its restoration degree for the true current data at the missing current data position, the smaller the possibility of error after its filling, and the greater the possibility of finally becoming the optimal solution; and the smaller the objective function value of each new solution during the output process of the optimal solution in each interpolation process, the more this new solution conforms to the current state of the current data of the ideal battery, and the greater the possibility of finally becoming the optimal solution.

[0051] S402. Iterate the new solutions according to the possibility to determine the optimal solution.

[0052] It should be noted that in the interpolation process, when outputting a new solution in each iteration, compare the possibility of the current new solution with the possibility of the output new solution, and use the new solution with a greater possibility as the new current new solution to participate in the next iteration of the new solution. Based on this principle, the iteration of the new solution is realized in the interpolation process until the entire interpolation process (simulated annealing process) is completed to finally determine the optimal solution.

[0053] In one implementation manner, in step S400, according to the optimal solution and the current data sequence, determine the target current data sequence and upload it. Specifically, insert the determined optimal solution into the missing current data position of the current data sequence, so as to obtain a filled, accurate, and complete target current data sequence, and then upload it.

[0054] In the embodiments of the present application, by deeply analyzing the numerical performance of the current data and voltage data in the power battery data, improving the iteration process of the current simulated annealing algorithm, and finely evaluating the acceptance degree and preference degree of the new solution, the optimal solution is finally determined, which helps to balance the objective function value and the change characteristics of the data itself, making the finally output optimal solution more in line with the trend and change of the actual data, thereby improving the accuracy of the interpolation result, being able to reduce large fluctuations, avoid unreasonable interpolation points, ensure that the supplement of the missing data is smoother, accurately and effectively reduce the error caused by large jumps in the power battery current data sequence, and finally provide more reliable support for restoring the original data, effectively improving the quality and application effect of data interpolation, and the accuracy of the filled target current data sequence is higher.

[0055] Referring to Figure 2 , a structural block diagram of a power battery data uploading system according to an embodiment of the present application is shown. The system may include: An acquisition module, configured to acquire a current data sequence and a voltage data sequence of a power battery; An analysis module, configured to perform an interpolation processing flow on the current data sequence through a simulated annealing algorithm. In the interpolation processing flow, when a new solution is output for each interpolation processing, analyze the acceptance degree of the new solution; the acceptance degree characterizes the difference between the missing current data corresponding to the new solution and the adjacent current data; A determination module, configured to determine the preference degree of each new solution respectively according to the acceptance degree of the new solution and the voltage data sequence; the preference degree characterizes the error degree after the new solution is inserted into the position of the corresponding missing current data; An upload module, configured to determine an optimal solution according to the preference degree of each new solution, and determine a target current data sequence according to the optimal solution and the current data sequence, and upload the target current data sequence to a database.

[0056] In the embodiments of this application, the functions of the modules in the system can refer to the corresponding descriptions in the above methods, and will not be elaborated here.

[0057] In one implementation manner, an embodiment of this application further provides an intelligent connected vehicle. Referring to Figure 3 , the intelligent connected vehicle includes: a memory 310, a processor 320, and a communication interface 330. Instructions that can run on the processor 320 are stored in the memory 310. The processor 320 loads and executes the instructions to implement the power battery data upload method in the above embodiment to obtain a target current data sequence, and finally uploads the target current data sequence through the communication interface 330.

[0058] It should be noted that the above sequence of the embodiments of this application is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some implementation manners, multi-task processing and parallel processing are also possible or may be advantageous.

[0059] Each embodiment in this specification is described in a progressive manner. The same or similar parts among the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for uploading power battery data, characterized in that, The method includes: Obtaining a current data sequence and a voltage data sequence of a power battery; Performing an interpolation processing flow on the current data sequence through a simulated annealing algorithm. In the interpolation processing flow, when a new solution is output for each interpolation processing, analyzing the acceptance degree of the new solution; the acceptance degree characterizes the difference between the missing current data corresponding to the new solution and the adjacent current data; Determining the preference degree of each new solution respectively according to the acceptance degree of the new solution and the voltage data sequence; the preference degree characterizes the error degree after the new solution is inserted into the position of the corresponding missing current data; Determining an optimal solution according to the preference degree of each new solution, and determining a target current data sequence based on the optimal solution and the current data sequence and uploading it.

2. The method for uploading power battery data according to claim 1, wherein: In the interpolation processing flow, when a new solution is output for each interpolation processing, analyzing the acceptance degree of the new solution includes: In the interpolation processing flow, when a new solution is output for each interpolation processing, determining the value of the new solution; Respectively simulating the corresponding simulated current data sequence after inserting the value of the new solution into the position of the missing current data in the current data sequence, and determining the change characteristics corresponding to the simulated current data sequence; Respectively determining the acceptance degree of the new solution according to the change characteristics.

3. The method for uploading power battery data according to claim 2, wherein: Determining the change characteristics corresponding to the simulated current data sequence includes: Respectively determining the current data mean value within a preset proximity range of the position of the missing current data in each simulated current data sequence, and respectively determining the relative offset of each new solution according to the value of the new solution and the corresponding current data mean value; Respectively determining the first change amount between the value of the new solution and the previous current data at the position of the missing current data, and the second change amount between two adjacent current data within a preset proximity range of the position of the missing current data in each simulated current data sequence; Respectively determining the first ratio of the first change amount to the maximum second change amount to obtain the change amount smoothness corresponding to each new solution; Wherein, the change characteristics corresponding to the simulated current data sequence include the relative offset of each new solution and the corresponding change amount smoothness.

4. The method for uploading power battery data according to claim 3, wherein: Respectively determining the acceptance degree of the new solution according to the change characteristics includes: Respectively determining the calculation result according to the opposite number of the relative offset of each new solution and the natural exponential function; Respectively obtaining the acceptance degree of each new solution according to the product of the calculation result and the change amount smoothness of each new solution.

5. The method for uploading power battery data according to any one of claims 2-4, characterized in that: Respectively determining the preference degree of each new solution according to the acceptance degree of the new solution and the voltage data sequence includes: Respectively determining the first current data subsequence within a preset proximity range of the position of the missing current data in each simulated current data sequence, and respectively removing the new solution from the first current data subsequence to obtain the corresponding second current data subsequence; According to the first current data subsequence, determine a first voltage data subsequence corresponding to the same time period from the voltage data sequence, and respectively remove the voltage data corresponding to the new solution in the first voltage data subsequence to obtain a corresponding second voltage data subsequence; Respectively determine the first Pearson correlation coefficient between each first current data subsequence and the corresponding first voltage data subsequence, and determine the second Pearson correlation coefficient between each second current data subsequence and the corresponding second voltage data subsequence; Respectively determine the preference degree of each new solution according to the first Pearson correlation coefficient, the second Pearson correlation coefficient, and the acceptance degree of the new solution.

6. The method for uploading power battery data according to claim 5, wherein: The step of respectively determining the preference degree of each new solution according to the first Pearson correlation coefficient, the second Pearson correlation coefficient, and the acceptance degree of the new solution includes: Respectively determine the difference value between the first Pearson correlation coefficient and the second Pearson correlation coefficient, and respectively obtain the corresponding normalization result according to the difference value and the normalization function; Respectively obtain the preference degree of each new solution according to the product of the acceptance degree of the new solution and the normalization result.

7. The method for uploading power battery data according to any one of claims 2-4, characterized in that: The step of determining the optimal solution according to the preference degree of each new solution includes: Respectively determine the possibility of each new solution as the optimal solution according to the preference degree of each new solution and a preset objective function; Perform iteration of new solutions according to the possibility to determine the optimal solution; Wherein, in the interpolation processing flow, each time a new solution is output during iteration, compare the possibility of the current new solution with the possibility of the output new solution, and use the new solution with a greater possibility as the new current new solution to participate in the next iteration of new solutions.

8. The method for uploading power battery data according to claim 7, wherein: The step of respectively determining the possibility of each new solution as the optimal solution according to the preference degree of each new solution and a preset objective function includes: Based on the preset objective function, determine the objective function value of each new solution, and respectively determine the second ratio of the preference degree of each new solution to the objective function value of the corresponding new solution; Respectively obtain the possibility of each new solution as the optimal solution according to the second ratio and the normalization function.

9. A power battery data upload system, characterized in that including: An acquisition module for acquiring a current data sequence and a voltage data sequence of a power battery; An analysis module for performing an interpolation processing flow on the current data sequence through a simulated annealing algorithm, and analyzing the acceptance degree of the new solution each time a new solution is output during the interpolation processing flow; the acceptance degree characterizes the difference between the missing current data corresponding to the new solution and the adjacent current data; A determination module for respectively determining the preference degree of each new solution according to the acceptance degree of the new solution and the voltage data sequence; the preference degree characterizes the error degree after the new solution is inserted into the position of the corresponding missing current data; An upload module for determining the optimal solution according to the preference degree of each new solution, and determining a target current data sequence and uploading it according to the optimal solution and the current data sequence.

10. An intelligent connected vehicle, characterized in that, including: A processor and a memory, wherein instructions are stored in the memory and loaded and executed by the processor to implement the power battery data uploading method according to any one of claims 1-8.

Images