A method and system for uploading data of intelligent connected vehicles and power batteries

Abstract

The present invention relates to the technical field of electronic digital data processing, and more particularly to a method and system for uploading data from an intelligent connected vehicle and a power battery. The method obtains a current data sequence and a voltage data sequence of a power battery, and uses a simulated annealing algorithm to perform an interpolation process on the current data sequence. In the interpolation process, each time a new solution is output through interpolation, the acceptability of the new solution is analyzed. The preference of each new solution is determined based on the acceptability of the new solution and the voltage data sequence. An optimal solution is determined based on the preference of each new solution. A target current data sequence is determined based on the optimal solution and the current data sequence, and the data is uploaded. Introducing the acceptability and preference of the new solution helps improve the accuracy of the optimal solution used for interpolation and ensures the accuracy of the uploaded target current data sequence.

Description

Technical Field

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

[0002] With the rapid development of intelligent connected vehicles (ICVs), the automotive industry is moving towards intelligence, automation, and networking. As a key component in ICVs, power batteries' battery current and voltage data significantly impact vehicle safety, endurance, and user experience. Therefore, uploading power battery data has become a crucial feature in intelligent automotive systems. Real-time monitoring and uploading of power battery data enables battery status analysis, fault diagnosis, and lifecycle management, thereby improving battery efficiency and extending its service life.

[0003] In the actual data collection process, due to interference in signal transmission, sensor failure, device loss, or environmental factors, smart connected vehicles may encounter loss or omission of power battery current data, which may lead to inaccurate data analysis results, thus affecting the performance and reliability of the entire system. Currently, in order to fill the missing data, the simulated annealing algorithm is commonly used. During each optimal solution output iteration, the simulated annealing algorithm continuously compares the objective function value of the current solution with the new solution to determine whether to accept the new solution. Finally, after completing the iteration, the optimal solution is obtained. 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. The optimal solution obtained in this way may not be consistent with the variation 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. There may be certain errors when restoring the original data, which reduces the accuracy of interpolation. Summary of the Invention

[0004] In order to solve the above technical problems, the purpose of the present invention is to provide a method and system for uploading data of intelligent connected vehicles and power batteries. The technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a method for uploading power battery data, comprising:

[0006] Obtaining a current data sequence and a voltage data sequence of a power battery;

[0007] performing an interpolation process on the current data sequence using a simulated annealing algorithm, wherein each time a new solution is outputted through interpolation, analyzing the acceptability of the new solution; the acceptability representing the difference between the missing current data corresponding to the new solution and adjacent current data;

[0008] Determining the preference level of each new solution based on the acceptability of the new solution and the voltage data sequence; the preference level represents the error level after the new solution is inserted into the corresponding missing current data position;

[0009] An optimal solution is determined according to the degree of preference of each of the new solutions, and a target current data sequence is determined and uploaded according to the optimal solution and the current data sequence.

[0010] In one embodiment, in the interpolation process, each time the interpolation process outputs a new solution, analyzing the acceptability of the new solution includes:

[0011] In the interpolation process, each time the interpolation process outputs a new solution, determining the value of the new solution;

[0012] Simulating the corresponding simulated current data sequences after the values ​​of the new solutions are inserted into the missing current data positions of the current data sequence, and determining the corresponding change characteristics of the simulated current data sequences;

[0013] The acceptability of the new solution is determined according to the change characteristics.

[0014] In one embodiment, determining the change characteristics corresponding to the analog current data sequence includes:

[0015] Determining the current data mean within a preset neighborhood of the missing current data position in each of the simulated current data sequences, and determining the relative offset of each of the new solutions based on the value of the new solution and the corresponding current data mean;

[0016] Determining, in each of the simulated current data sequences, a first change between the value of the new solution and the current data preceding the location of the missing current data, and a second change between two adjacent current data within a preset proximity range of the location of the missing current data;

[0017] respectively determining a first ratio of the first variation to the corresponding maximum second variation, and obtaining a degree of variation smoothness corresponding to each of the new solutions;

[0018] The change characteristics corresponding to the simulated current data sequence include the relative offset of each new solution and the corresponding change smoothness.

[0019] In one embodiment, determining the acceptability of the new solution based on the change characteristics includes:

[0020] Determining calculation results according to the inverse of the relative offset of each of the new solutions and the natural exponential function;

[0021] The acceptance of each new solution is obtained according to the product of the calculation result and the stability of the change of each new solution.

[0022] In one embodiment, determining the preference of each new solution based on the acceptance of the new solution and the voltage data sequence includes:

[0023] Determine, in each of the simulated current data sequences, a first current data subsequence within a preset proximity range of the missing current data location, and remove the new solution from the first current data subsequence to obtain a corresponding second current data subsequence;

[0024] determining, from the voltage data sequence, a first voltage data subsequence corresponding to the same time period based on the first current data subsequence, and removing the voltage data corresponding to the new solution from the first voltage data subsequence to obtain a corresponding second voltage data subsequence;

[0025] respectively determining a first Pearson correlation coefficient between each of the first current data subsequences and the corresponding first voltage data subsequence, and determining a second Pearson correlation coefficient between each of the second current data subsequences and the corresponding second voltage data subsequence;

[0026] The preference level of each new solution is determined according to the first Pearson correlation coefficient, the second Pearson correlation coefficient, and the acceptance level of the new solution.

[0027] In one embodiment, determining the preference of each new solution based on the first Pearson correlation coefficient, the second Pearson correlation coefficient, and the acceptability of the new solution includes:

[0028] respectively determining a difference between the first Pearson correlation coefficient and the second Pearson correlation coefficient, and obtaining a corresponding normalization result according to the difference and a normalization function;

[0029] The preference degree of each new solution is obtained according to the product of the acceptance degree of the new solution and the normalization result.

[0030] In one embodiment, determining the optimal solution according to the preference level of each new solution includes:

[0031] Determining the likelihood of each of the new solutions being the optimal solution based on the degree of preference of each of the new solutions and a preset objective function;

[0032] Iterate the new solution based on the possibilities to determine the optimal solution;

[0033] Among them, in the interpolation processing flow, each time a new solution is outputted in an iteration, the possibility of the current new solution is compared with the possibility of the output new solution, and the new solution with a greater possibility is used as the new current new solution to participate in the next new solution iteration.

[0034] In one embodiment, determining the likelihood of each new solution being the optimal solution based on the preference level of each new solution and a preset objective function includes:

[0035] Determining an objective function value for each of the new solutions based on a preset objective function, and respectively determining a second ratio of a preference level of each of the new solutions to the objective function value of the corresponding new solution;

[0036] The possibility of each of the new solutions being the optimal solution is obtained according to the second ratio and the normalization function.

[0037] In a second aspect, an embodiment of the present application provides a power battery data uploading system, comprising:

[0038] An acquisition module, used to acquire a current data sequence and a voltage data sequence of a power battery;

[0039] an analysis module configured to perform an interpolation process on the current data sequence using a simulated annealing algorithm, wherein each time a new solution is outputted through interpolation, the acceptance of the new solution is analyzed; the acceptance representing the difference between the missing current data corresponding to the new solution and adjacent current data;

[0040] a determination module, configured to determine a preference level of each of the new solutions based on the acceptability of the new solutions and the voltage data sequence; the preference level represents a degree of error after the new solution is inserted into the corresponding missing current data position;

[0041] The uploading module is used to determine the optimal solution according to the preference degree of each new solution, and to determine the target current data sequence according to the optimal solution and the current data sequence and upload the target current data sequence.

[0042] In a third aspect, an embodiment of the present application provides an intelligent connected vehicle, comprising: a processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the method in any one of the above-mentioned embodiments.

[0043] The present invention has the following beneficial effects:

[0044] By obtaining the current data sequence and voltage data sequence of the power battery, the simulated annealing algorithm is used to perform an interpolation processing flow on the current data sequence. In the interpolation processing flow, each time the interpolation processing outputs a new solution, the acceptance of the new solution is analyzed, and the preference of each new solution is determined according to the acceptance of the new solution and the voltage data sequence. According to the preference of each new solution, the optimal solution is determined, and according to the optimal solution and the current data sequence, the target current data sequence is determined and uploaded. The acceptance represents the difference between the missing current data corresponding to the new solution and the adjacent current data, and the preference represents the error degree after the new solution is inserted into the corresponding missing current data position. Therefore, introducing the acceptance and preference of the new solution is conducive to improving the accuracy of the optimal solution used for interpolation, thereby ensuring the accuracy of the uploaded target current data sequence. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 A schematic flow chart of the steps of a method for uploading power battery data provided by one embodiment of the present invention;

[0047] Figure 2 This is a structural block diagram of a power battery data uploading system provided by one embodiment of the present invention;

[0048] Figure 3 A structural block diagram of an intelligent connected vehicle provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0049] To further illustrate the technical means and effectiveness of the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, describes in detail the specific implementation, structure, features, and effectiveness of a method and system for uploading data from a connected vehicle and power battery according to the present invention. In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0050] 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 invention belongs.

[0051] It should be noted that the term “exemplary” in the embodiments of the present application refers to examples listed for the convenience of explanation, and other embodiments are not limited to the examples listed.

[0052] The following describes in detail a method and system for uploading data of an intelligent connected vehicle and power battery provided by the present invention with reference to the accompanying drawings.

[0053] See also Figure 1 , which shows a schematic flow chart of the steps of a power battery data uploading method provided by one embodiment of the present invention. The power battery data uploading method may include at least steps S100-S400:

[0054] S100: Acquire a current data sequence and a voltage data sequence of a power battery.

[0055] S200 , performing an interpolation process on the current data sequence by using a simulated annealing algorithm. In the interpolation process, each time a new solution is outputted by the interpolation process, the acceptability of the new solution is analyzed.

[0056] Optionally, the acceptance represents the difference between the missing current data corresponding to the new solution and the adjacent current data.

[0057] S300 : Determine the preference of each new solution according to the acceptance of the new solution and the voltage data sequence.

[0058] Optionally, the preference level represents the error level after the new solution is inserted into the corresponding missing current data position.

[0059] S400 , determining an optimal solution based on the degree of preference of each new solution, and determining a target current data sequence based on the optimal solution and the current data sequence, and uploading the target current data sequence.

[0060] The technical solution of the embodiment of the present application is to obtain the current data sequence and voltage data sequence of the power battery, and use the simulated annealing algorithm to perform an interpolation processing flow on the current data sequence. In the interpolation processing flow, each time the interpolation processing outputs a new solution, the acceptance of the new solution is analyzed, and the preference of each new solution is determined according to the acceptance of the new solution and the voltage data sequence. The optimal solution is determined according to the preference of each new solution, and the target current data sequence is determined and uploaded according to the optimal solution and the current data sequence. The acceptance represents the difference between the missing current data corresponding to the new solution and the adjacent current data, and the preference represents the error degree after the new solution is inserted into the corresponding missing current data position. Therefore, introducing the acceptance and preference of the new solution is conducive to improving the accuracy of the optimal solution used for interpolation, thereby ensuring the accuracy of the uploaded target current data sequence.

[0061] In one embodiment, in step S100, the battery management system of an intelligent connected vehicle (hereinafter referred to as the vehicle) is equipped with a current sensor and a voltage sensor to collect current and voltage data from the power battery during driving. The frequency and duration of the collection can be set based on actual needs, for example, once per second for a total of two hours. This allows the collection of current and voltage data corresponding to multiple sampling moments, forming a current data sequence and a voltage data sequence for the power battery, respectively. It should be understood that each current data point is arranged in the current data sequence in chronological order of the sampling moments, corresponding to a corresponding current data point in the current data sequence. The same applies to the voltage data sequence.

[0062] Optionally, in the embodiment of the present application, the initial temperature value of the 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 (that is, the value of the first current solution at the first interpolation, set to the empirical value of 10A), and the disturbance range size of the new solution outputted by each interpolation process is preset to the current data setting value at the last iteration in the simulated annealing process. A.

[0063] Among them, construct the objective function:

[0064]

[0065] Where, Represents the objective function value corresponding to the current data of any power battery, and Respectively represent the weights of the two factors affecting the objective function value ( , ); Represents the current data of any power battery. When applied to a power battery with the same temperature as the current power battery, the temperature change rate per unit time. This value can be obtained from historical data using big data technology. The larger the value, the stronger the impact of this current data on the vehicle's driving process, and the smaller the corresponding objective function value; It represents the current data of any power battery. When applied to a power battery with the same power battery temperature, its energy consumption in one unit time. The larger the value, the more energy this battery current data consumes during driving, and the larger the corresponding objective function value. It can also be obtained based on historical data analysis and can be calculated based on existing methods, so it will not be repeated here.

[0066] 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 a missing current data position, and the missing current data is called missing current data. Current data usually has certain time series characteristics. The current of the battery is not only affected by the battery charge and discharge state, but also related to voltage factors. Therefore, missing data points often occur when the battery state suddenly changes, the sensor fails, or the data transmission error occurs. In step S200, the current data sequence is interpolated by the simulated annealing algorithm, that is, the current data sequence is processed by the simulated annealing algorithm. The purpose is to interpolate the missing current data position, fill in the missing data, and ensure that the interpolated data shows a reasonable trend in the time series. Therefore, after completing the initial parameter setting and the objective function design, the subsequent steps need to analyze the degree of preference of each new solution in the optimal solution output process during each interpolation process. Among them, after each new solution fills in the missing current data point, the smaller the difference in the numerical performance of the battery current data point and its surrounding data, the more the numerical value corresponding to the new solution conforms to the trend and change characteristics of the data sequence around the missing battery current data point processed by this interpolation, and the greater its corresponding acceptance will be.

[0067] In the embodiment of the present application, in step S200, in the interpolation process, each time the interpolation process outputs a new solution, the acceptability of the new solution is analyzed, including steps S201-S203:

[0068] S201 . In the interpolation process, each time the interpolation process outputs a new solution, determine the value of the new solution.

[0069] It should be noted that, in the interpolation process, the principle of the process of outputting a new solution each time by the simulated annealing algorithm can refer to the existing simulated annealing algorithm. In the embodiment of the present application, the focus is on further analysis of the acceptance and preference after outputting the new solution, so as to optimize the accuracy of the new solution. Specifically, each time the interpolation process outputs a new solution, the value of the new solution is determined. , Indicates the The output of the first interpolation process The value of a new solution.

[0070] S202 , respectively simulating the new solution values ​​to be inserted into the missing current data positions of the current data sequence, simulating the corresponding current data sequence, and determining the corresponding change characteristics of the simulated current data sequence.

[0071] Optionally, the numerical values ​​of the new solutions are respectively simulated and inserted into the missing current data positions of the current data sequence. For example, the new solution of the first interpolation process is simulated and inserted into the missing current data position. At this time, a corresponding simulated current data sequence can be obtained. Therefore, each time the new solution is inserted into the missing current data position, 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 corresponding change smoothness. The determination process specifically includes:

[0072] First, a preset proximity range can be set based on actual needs. For example, a 50-sampling time length can be set, i.e., 50 seconds. If it is less than 50 seconds, a 10-sampling time length can be set, i.e., 10 seconds. Taking 50 seconds as an example, the first 50 current data at the missing current data position in each simulated current data sequence are determined, and then the current data mean of the 50 current data is calculated to determine the current data mean within the preset proximity range of the missing current data position. , that is, The output of the first interpolation process Then, the relative offset of each new solution is determined based on the value of the new solution and the corresponding current data mean. .

[0073] Secondly, determine the first difference between the new solution value and the previous current data (i.e. the current data at the previous sampling moment) at the missing current data position in each simulated current data sequence. (i.e. The output of the first interpolation process The first variation corresponding to the simulated current data sequence corresponding to the new solution is obtained), and the second variation of the current data adjacent to each other within a preset proximity range of the missing current data position, that is, among the 50 current data, the absolute value of the difference between the adjacent two current data is calculated to obtain the second variation of the current data adjacent to each other.

[0074] Then, determine the first variation The second largest change corresponding to The first ratio of each new solution is obtained to obtain the stability of the change .

[0075] S203: Determine the acceptability of the new solution based on the change characteristics.

[0076] Optionally, the inverse of the relative offset of each new solution and the natural exponential function are used. , determine the calculation results , and then according to the calculation results and the stability of the change corresponding to each new solution The product of is used to obtain the acceptance of each new solution. The specific formula is:

[0077]

[0078] in, Indicates the The output of the first interpolation process The acceptance of a new solution, is a hyperparameter, , which exists to prevent The relative offset occurs when it is 0. The smaller the value, the more consistent the new solution value is with the changing trend and characteristics of the surrounding data sequence after filling in the missing current data position, and the greater the acceptance of the new solution. The smaller the value, the The output of the first interpolation process After a new solution fills the missing current data position, the more stable the change in the current data between the missing current data position and its immediately previous position, and the more consistent it is with the change trend and change characteristics of the surrounding data sequence, the greater the credibility will be, and the greater the acceptance of the corresponding new solution will be.

[0079] It's important to note that while the acceptability of a new solution has been preliminarily determined, in some cases, such as when the current data at a missing current point significantly changes compared to the surrounding data, simply quantifying the numerical representation of each new solution within the surrounding data sequence may not accurately determine the acceptability of the new solution. Therefore, restoring the true value of the missing current data is necessary. Based on scenario research, battery current data and battery voltage data are closely correlated. This is primarily because as battery voltage data increases, the vehicle's relative speed increases, leading to increased power consumption. The relationship between power and battery current is typically cubic, meaning that power increases significantly with increasing battery current data. Based on this principle, the preference of each new solution can be analyzed in conjunction with voltage data. The greater the correlation between the missing current data location and the corresponding battery voltage data at the same sampling time, the more accurately the new solution restores the true current data at the missing location, the less likely it is to have errors, and the higher its preference.

[0080] In one embodiment, step S300 includes steps S301-S304:

[0081] S301 , determining first current data subsequences within a preset proximity range of a missing current data position in each simulated current data sequence, and removing new solutions from the first current data subsequences to obtain corresponding second current data subsequences.

[0082] Optionally, the preset adjacent range is also taken as an example of a time length of 50 seconds. For example, a sequence of 50 current data of the first 50 seconds including the missing current data positions after the new solution is filled can be determined, and the new solution of the missing current data positions after the new solution is filled in the sequence is removed to obtain a sequence containing 50 current data, that is, the corresponding second current data subsequence.

[0083] S302 : Determine a first voltage data subsequence corresponding to the same time period from the voltage data sequence according to the first current data subsequence, and remove the voltage data corresponding to the new solution from the first voltage data subsequence to obtain a corresponding second voltage data subsequence.

[0084] Optionally, based on the sampling moment corresponding to the first current data subsequence, the first voltage data subsequence of the same time period is determined from the voltage data sequence. At this time, the first voltage data subsequence includes the newly solved moment and voltage data at 50 moments. The voltage data corresponding to the newly solved moment is removed to obtain a sequence containing 50 voltage data, that is, the corresponding second voltage data subsequence.

[0085] S303: Determine a first Pearson correlation coefficient between each first current data subsequence and the corresponding first voltage data subsequence. (No. The output of the first interpolation process a Pearson correlation coefficient between the first current data subsequence and the first voltage data subsequence corresponding to each new solution, and determining a second Pearson correlation coefficient between each second current data subsequence and the corresponding second voltage data subsequence (No. The output of the first interpolation process Pearson correlation coefficient between the second current data subsequence and the second voltage data subsequence corresponding to the new solution).

[0086] It should be noted that the calculation method of the Pearson correlation coefficient is based on the existing method and will not be repeated here.

[0087] S304 : Determine the preference level of each new solution based on the first Pearson correlation coefficient, the second Pearson correlation coefficient, and the acceptability of the new solution.

[0088] Optionally, determine the first Pearson correlation coefficient With the second Pearson correlation coefficient The difference value , and respectively according to the difference value and the normalization function , and get the corresponding normalized result , and then according to the acceptance of the new solution The product of the normalized result is the degree of preference of each new solution. , the specific formula is:

[0089]

[0090] Where, Indicates the The output of the first interpolation process The preference of a new solution and the acceptance of the new solution The larger the The output of the first interpolation process After a new solution fills the position of the missing current data, the more it conforms to the change trend and change characteristics of the surrounding data series, the greater the preference of this new solution; The larger the value, the The output of the first interpolation process After a new solution is filled into the missing current data position, the greater the correlation between the new solution of the missing current data position and the numerical performance of the voltage data corresponding to the same sampling moment, and the greater its contribution to the Pearson correlation coefficient value between the two data segments, the greater the degree of restoration of the true value of the missing current data position by this new solution, the smaller the possibility of error, and the greater its corresponding preference.

[0091] In one embodiment, determining the optimal solution according to the preference level of each new solution in step S400 includes steps S401-S402:

[0092] S401 : Determine the possibility of each new solution being the optimal solution based on the preference level of each new solution and a preset objective function.

[0093] Optionally, based on the above preset objective function , determine the objective function value of each new solution (i.e. The output of the first interpolation process The objective function value of the new solution, different new solutions can correspond to different and , thereby determining different objective function values), and determining the degree of preference for each new solution The objective function value of the corresponding new solution The second ratio ; Then, according to the second ratio and the normalization function , get the possibility of each new solution being the optimal solution :

[0094]

[0095] in, For the The output of the first interpolation process The possibility of a new solution being the optimal solution, the greater the preference degree of the new solution, the more consistent the value is with the trend and change characteristics of the data sequence around the missing current data position of this interpolation processing, the higher the degree of restoration of the real current data at the missing current data position, the smaller the possibility of error after filling, and the greater the possibility of it eventually becoming the optimal solution; and the smaller the objective function value of each new solution in the optimal solution output process during each interpolation processing, the more consistent the new solution is with the current data of the ideal battery in the current state, and the greater the possibility of it eventually becoming the optimal solution.

[0096] S402: Iterate the new solution according to the probability to determine the optimal solution.

[0097] It should be noted that in the interpolation processing flow, each time a new solution is output in an iteration, the probability of the current new solution is compared with the probability of the output new solution, and the new solution with a greater probability is used as the new current new solution to participate in the next new solution iteration. Based on this principle, the iteration of the new solution is realized in the interpolation processing flow until the entire interpolation processing flow (simulated annealing process) is completed to finally determine the optimal solution.

[0098] In one embodiment, in step S400, a target current data sequence is determined based on the optimal solution and the current data sequence and uploaded. Specifically, the determined optimal solution is inserted into the missing current data position of the current data sequence to obtain a filled, accurate, and complete target current data sequence, which is then uploaded.

[0099] In the embodiment of the present application, an in-depth analysis of the numerical performance of the current data and voltage data in the power battery data is conducted, the iterative process of the current simulated annealing algorithm is improved, the acceptability and preference of the new solution are carefully evaluated, and the optimal solution is finally determined. This helps to balance the objective function value and the changing characteristics of the data itself, so that the optimal solution finally output is more consistent with the trend and changes of the actual data, thereby improving the accuracy of the interpolation results, reducing large fluctuations, avoiding unreasonable interpolation points, ensuring that the missing data is supplemented more smoothly and accurately, and effectively reducing the errors caused by large jumps in the power battery current data sequence, and ultimately providing 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.

[0100] Reference Figure 2 , shows a structural block diagram of a power battery data uploading system according to an embodiment of the present application, which may include:

[0101] An acquisition module, used to acquire a current data sequence and a voltage data sequence of a power battery;

[0102] An analysis module is configured to perform an interpolation process on the current data sequence using a simulated annealing algorithm. During the interpolation process, each time a new solution is outputted by the interpolation process, the acceptance of the new solution is analyzed; the acceptance represents the difference between the missing current data corresponding to the new solution and the adjacent current data;

[0103] A determination module is used to determine the preference of each new solution based on the acceptance of the new solution and the voltage data sequence; the preference degree represents the error degree after the new solution is inserted into the corresponding missing current data position;

[0104] The uploading module is used to determine the optimal solution according to the preference degree of each new solution, and to determine the target current data sequence according to the optimal solution and the current data sequence, and to upload the target current data sequence to the database.

[0105] In the embodiment of the present application, the functions of each module in the system can be referred to the corresponding description in the above method and will not be repeated here.

[0106] In one embodiment, the present 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. The memory 310 stores instructions that can be run on the processor 320. The processor 320 loads and executes the instructions to implement the power battery data uploading 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.

[0107] It should be noted that the order of the embodiments of the present application described above is for illustrative purposes only and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0108] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A method for uploading power battery data, characterized in that: The method comprises: Obtaining a current data sequence and a voltage data sequence of a power battery; performing an interpolation process on the current data sequence using a simulated annealing algorithm, wherein each time a new solution is outputted through interpolation, analyzing the acceptability of the new solution; the acceptability representing the difference between the missing current data corresponding to the new solution and adjacent current data; Determining the preference level of each new solution based on the acceptability of the new solution and the voltage data sequence; the preference level represents the error level after the new solution is inserted into the corresponding missing current data position; Determining an optimal solution based on the degree of preference of each of the new solutions, and determining a target current data sequence based on the optimal solution and the current data sequence and uploading the target current data sequence; Determining the preference of each new solution according to the acceptance of the new solution and the voltage data sequence includes: Determining, in each of the simulated current data sequences, a first current data subsequence within a preset proximity of the missing current data location, and removing the new solution from each of the first current data subsequences to obtain a corresponding second current data subsequence; wherein the corresponding simulated current data sequence is obtained by simulating the insertion of the new solution into the missing current data location of the current data sequence; determining, from the voltage data sequence, a first voltage data subsequence corresponding to the same time period based on the first current data subsequence, and removing the voltage data corresponding to the new solution from the first voltage data subsequence to obtain a corresponding second voltage data subsequence; respectively determining a first Pearson correlation coefficient between each of the first current data subsequences and the corresponding first voltage data subsequence, and determining a second Pearson correlation coefficient between each of the second current data subsequences and the corresponding second voltage data subsequence; Determining the preference of each new solution according to the first Pearson correlation coefficient, the second Pearson correlation coefficient, and the acceptability of the new solution, including: respectively determining a difference between the first Pearson correlation coefficient and the second Pearson correlation coefficient, and obtaining a corresponding normalization result according to the difference and a normalization function; Obtaining the degree of preference of each new solution according to the product of the acceptance degree of the new solution and the normalization result; Determining the optimal solution according to the preference level of each new solution includes: Determining an objective function value for each of the new solutions based on a preset objective function, and respectively determining a second ratio of a preference level of each of the new solutions to the objective function value of the corresponding new solution; Obtaining, based on the second ratio and the normalization function, a probability of each of the new solutions being an optimal solution; Iterate the new solution based on the possibilities to determine the optimal solution; Among them, in the interpolation processing flow, each time a new solution is outputted in an iteration, the possibility of the current new solution is compared with the possibility of the output new solution, and the new solution with a greater possibility is used as the new current new solution to participate in the next new solution iteration.

2. The method for uploading power battery data according to claim 1, characterized in that: In the interpolation process, each time the interpolation process outputs a new solution, analyzing the acceptability of the new solution includes: In the interpolation process, each time the interpolation process outputs a new solution, determining the value of the new solution; After respectively simulating the values ​​of the new solutions to be inserted into the missing current data positions of the current data sequence, determining the corresponding change characteristics of the simulated current data sequence; The acceptability of the new solution is determined according to the change characteristics.

3. The method for uploading power battery data according to claim 2, characterized in that: Determining the change characteristics corresponding to the analog current data sequence includes: Determining the current data mean within a preset neighborhood of the missing current data position in each of the simulated current data sequences, and determining the relative offset of each of the new solutions based on the value of the new solution and the corresponding current data mean; Determining, in each of the simulated current data sequences, a first change between the value of the new solution and the current data preceding the location of the missing current data, and a second change between two adjacent current data within a preset proximity range of the location of the missing current data; respectively determining a first ratio of the first variation to the corresponding maximum second variation, and obtaining a degree of variation smoothness corresponding to each of the new solutions; The change characteristics corresponding to the simulated current data sequence include the relative offset of each new solution and the corresponding change smoothness.

4. The method for uploading power battery data according to claim 3, characterized in that: Determining the acceptability of the new solution according to the change characteristics includes: Determining calculation results according to the inverse of the relative offset of each of the new solutions and the natural exponential function; The acceptance of each new solution is obtained according to the product of the calculation result and the stability of the change of each new solution.

5. A power battery data uploading system, characterized in that: To implement the power battery data uploading method according to any one of claims 1 to 4, the system includes: An acquisition module, used to acquire a current data sequence and a voltage data sequence of a power battery; an analysis module configured to perform an interpolation process on the current data sequence using a simulated annealing algorithm, wherein each time a new solution is outputted through interpolation, the acceptance of the new solution is analyzed; the acceptance representing the difference between the missing current data corresponding to the new solution and adjacent current data; a determination module, configured to determine a preference level of each of the new solutions based on the acceptability of the new solutions and the voltage data sequence; the preference level represents a degree of error after the new solution is inserted into the corresponding missing current data position; The uploading module is used to determine the optimal solution according to the preference degree of each new solution, and to determine the target current data sequence according to the optimal solution and the current data sequence and upload the target current data sequence.

6. An intelligent connected vehicle, characterized in that: include: A processor and a memory, wherein the memory stores instructions, and the instructions are loaded and executed by the processor to implement the power battery data uploading method according to any one of claims 1 to 4.

Images