Underwater glider battery pack performance evaluation method and system, electronic equipment and storage medium

Abstract

The invention discloses a method for evaluating the performance of a battery pack of an underwater glider. The method comprises the following steps: acquiring energy consumption parameters of the battery pack in all postures; determining the current variance of the battery pack according to the maximum current value variance and the minimum current value variance of the battery pack in all postures; and determining the basic performance grade of the battery pack according to the battery pack current variance. According to the method, the battery performance of the underwater glider can be evaluated, whether the battery pack can continue to be used or not can be judged in an auxiliary mode, data support is provided for reliability and safety evaluation of battery pack use, the cost for directly replacing the battery pack is reduced, and the reliability and safety evaluation accuracy of battery pack use are improved. The invention further discloses a system for implementing the method, electronic equipment and a computer readable storage medium.

Description

Technical Field

[0001] The present invention relates to the technical field of underwater gliders, and in particular to a method, system, electronic device and storage medium for evaluating the performance of an underwater glider battery pack. Background Art

[0002] Underwater Glider is a new type of autonomous underwater vehicle (AUV) that uses net buoyancy and attitude angle adjustment to obtain propulsion. It has an endurance of up to several months and can reach a range of thousands of kilometers.

[0003] At present, the energy of underwater gliders mainly comes from various types of battery packs. As the position and posture of the battery pack change, the posture of the underwater glider in the water will also change. These changes affect the stability of the battery and thus affect the working performance of the glider. There is no method for evaluating the performance of underwater glider battery packs in the prior art. Summary of the invention

[0004] In order to solve the above problems existing in the prior art, the present invention provides a method, system, electronic device and storage medium for evaluating the performance of an underwater glider battery pack. The technical problem to be solved by the present invention is achieved through the following technical solutions:

[0005] A first aspect of an embodiment of the present invention provides a method for evaluating the performance of an underwater glider battery pack, comprising the following steps:

[0006] Obtaining energy consumption parameters of the battery pack in all postures; wherein the energy consumption parameters include: maximum current value and minimum current value;

[0007] Determining a battery pack current variance according to a maximum current value variance and a minimum current value variance in all postures of the battery pack;

[0008] A basic performance level of the battery pack is determined according to the battery pack current variance.

[0009] In one embodiment of the present invention, the calculation formula of the maximum current value variance is:

[0010]

[0011] Wherein, S1 represents the maximum current value variance, m is the sequence number of the posture of the battery pack, n is the number of tests for each posture, m and n are both positive integers, and X ij represents the maximum current value of the jth test under the i-th posture, is the average value of n maximum current values ​​in the i-th posture;

[0012] The calculation formula of the minimum current value variance is:

[0013]

[0014] Wherein, S2 represents the minimum current value variance, m is the sequence number of the posture of the battery pack, n is the number of tests for each posture, m and n are both positive integers, and Y ij represents the minimum current value of the jth test in the i-th posture, is the average value of n minimum current values ​​under the i-th posture;

[0015] The calculation formula of the battery pack current variance is:

[0016]

[0017] Where S represents the battery pack current variance.

[0018] In one embodiment of the present invention, the energy consumption parameters also include: the posture of the battery pack, the communication status of the device, the movement speed of the underwater glider and the power parameters;

[0019] The method further comprises:

[0020] The comprehensive performance level of the battery pack is determined according to the posture of the battery pack, the corresponding communication status of the device, and the corresponding movement speed and power parameters of the underwater glider.

[0021] In one embodiment of the present invention, determining the comprehensive performance level of the battery pack according to the posture of the battery pack, the corresponding communication state of the device, and the corresponding movement speed and power parameters of the underwater glider includes:

[0022] Determining the conditional entropy of the electric energy parameter under the posture of all the battery packs, the corresponding communication state of the device and the corresponding movement speed of the underwater glider;

[0023] According to the conditional entropy, a comprehensive performance level of the battery pack is determined.

[0024] In one embodiment of the present invention, the calculation formula of the conditional entropy is:

[0025] H(D|X)=-Σ x∈X Σ d∈D p(x,d)[logp(x)+logp(d|x=(x1,x2,x3))];

[0026] Among them, H(D|X) represents conditional entropy, which is used to evaluate the stability of the battery pack; d represents the electric energy parameter, which includes the current value and the corresponding voltage value; x1 represents the posture of the battery pack, x2 represents the communication status of the device, and x3 represents the movement speed of the underwater glider.

[0027] In one embodiment of the present invention, determining the comprehensive performance level of the battery pack according to the posture of each battery pack, the corresponding communication state of the device, and the corresponding movement speed and power parameters of the underwater glider includes:

[0028] The posture of the battery pack, the corresponding communication status of the device, the corresponding movement speed of the underwater glider and the corresponding electric energy parameters are input into the trained machine learning model, and the comprehensive performance level result of the battery pack is output.

[0029] In one embodiment of the present invention, the method further comprises:

[0030] Input the training samples with comprehensive performance level labels into the initial machine learning model, and output the sample comprehensive performance level results of the battery pack;

[0031] According to the comprehensive performance level result of the sample and the corresponding comprehensive performance level label, a loss value is calculated using a preset cross entropy loss function;

[0032] Update the parameters of the initial machine learning model according to the loss value to obtain a trained machine learning model.

[0033] A second aspect of an embodiment of the present invention provides a system for evaluating the performance of an underwater glider battery pack, comprising:

[0034] An acquisition module, used to acquire energy consumption parameters of the battery pack in all postures; wherein the energy consumption parameters include: a maximum current value and a minimum current value;

[0035] A determination module, configured to determine a battery pack current variance according to a maximum current value variance and a minimum current value variance in all postures of the battery pack;

[0036] An evaluation module is used to determine a basic performance level of the battery pack according to the battery pack current variance.

[0037] A third aspect of an embodiment of the present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for evaluating the performance of an underwater glider battery pack provided by the first aspect of an embodiment of the present invention is implemented.

[0038] A fourth aspect of an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for evaluating the performance of an underwater glider battery pack provided by the first aspect of an embodiment of the present invention is implemented.

[0039] Beneficial effects of the present invention:

[0040] The present invention calculates the variance of the battery pack current by calculating the variance of the maximum current value and the variance of the minimum current value in all postures. The smaller the variance of the battery pack current, the more stable the battery pack performance, which can evaluate the battery pack performance of the underwater glider, and then assist in judging whether the battery pack can continue to be used, providing data support for the reliability and safety evaluation of the battery pack, reducing the cost of directly replacing the battery pack, and improving the reliability of the battery pack and the accuracy of the safety evaluation.

[0041] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0042] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0044] Figure 1 A schematic diagram of a flow chart of a method for evaluating the performance of an underwater glider battery pack provided by an embodiment of the present invention;

[0045] Figure 2 A block diagram of an underwater glider battery pack performance evaluation system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The present invention is further described in detail below with reference to specific embodiments, but the embodiments of the present invention are not limited thereto.

[0047] As the position and attitude of the battery pack changes, the attitude of the underwater glider in the water will also change, and these changes will affect the stability of the battery pack.

[0048] According to the law of conservation of energy, the battery pack can be analyzed as follows:

[0049] W=W G +W F +Wf

[0050] Where W is the work done by the roll motor and pitch motor to pull the battery pack, W G is the work done by the battery pack to overcome gravity, W F is the work done by the cable on the battery pack through traction, W f It is the work done by friction when the battery pack moves.

[0051] According to Ohm's law, W = I 2 Rt, analysis shows that the current I is proportional to W. The more work W the motor does, the more current I is needed to supply it.

[0052] In summary, ignoring the work done by friction, W G and W F The larger it is, the greater the work W done by the motor and the greater the current I required.

[0053] The force analysis of the battery pack in different postures shows that when the battery pack is in a flat state and performs extreme forward and backward motion, or rolls in an upright or inverted state, it does not need to overcome gravity to do work. G is 0, so the required current I is the smallest at this time; the battery pack needs to overcome gravity to do work when rolling in a flat state, while the battery pack does not need to overcome gravity to do work when rolling in an upright or inverted state. Therefore, the work done by the motor when the battery pack is lying flat is greater than the work done when it is rolling in an upright or inverted state, and the required current I is also greater; by the same token, the work done by the motor when the battery pack is lying flat and doing extreme forward and backward motion is less than the work done when it is upright or inverted, and the required current I is also smaller.

[0054] According to the work calculation formula W F =F 牵 S, analysis shows that when the glider is doing rolling motion while doing forward and backward extreme motion, the required traction force is the largest and the work done is also the largest, so the current required to do the work is the largest.

[0055] like Figure 1 As shown, a first aspect of an embodiment of the present invention provides a method for evaluating the performance of an underwater glider battery pack, comprising the following steps:

[0056] Step 11, obtaining energy consumption parameters of the battery pack in all postures.

[0057] The energy consumption parameters include: maximum current value and minimum current value.

[0058] In this step, multiple tests are performed in each posture, and multiple current values ​​are collected each time for each posture, and a maximum current value and a minimum current value collected in each test are screened. Here, the posture of the battery pack includes fifteen postures, namely: lying flat front limit roll, lying flat rear limit roll, lying flat left limit front and rear limits, lying flat right limit front and rear limits, lying flat front and rear limit roll, inverted front limit roll, inverted left limit front and rear limits, inverted right limit front and rear limits, inverted front and rear limit roll, upright front limit roll, upright rear limit roll, upright left limit front and rear limits, upright right limit front and rear limits, upright front and rear limit roll.

[0059] Step 12, determining the battery pack current variance according to the maximum current value variance and the minimum current value variance in all postures of the battery pack.

[0060] In this step, multiple tests are performed in each posture, and a set of maximum current values ​​and a minimum current value are obtained in each test in each posture, that is, there are multiple sets of maximum current values ​​and minimum current values ​​corresponding to each posture. Therefore, the maximum current value variance and the minimum current value variance in all postures are calculated first, and then the maximum current value variance and the minimum current value variance are averaged to obtain the battery pack current variance.

[0061] Specifically, the maximum current value variance is calculated as:

[0062]

[0063] Wherein, S1 represents the maximum current value variance, m is the sequence number of the battery pack posture, the value range is 1-15, n is the number of tests for each posture, m and n are both positive integers, preferably, the value range of n is ≥5, X ij represents the maximum current value of the jth test under the i-th posture, is the average value of n maximum current values ​​in the i-th posture;

[0064] The calculation formula for the minimum current value variance is:

[0065]

[0066] Among them, S2 represents the minimum current value variance, m is the sequence number of the battery pack posture, the value range is 1-15, n is the number of tests for each posture, the value range of n is ≥5, m and n are both positive integers, Y ij represents the minimum current value of the jth test in the i-th posture, is the average value of the n minimum current values ​​under the i-th posture.

[0067] The calculation formula for the battery pack current variance is:

[0068]

[0069] Wherein, S represents the current variance of the battery pack, that is, the current variance of the battery pack in all postures.

[0070] Step 13: Determine the basic performance level of the battery pack according to the battery pack current variance.

[0071] In this step, the smaller the battery pack current variance is, the more stable this set of data is, that is, the more stable the battery pack is, the better the performance is. The larger the battery pack current variance is, the more unstable this set of data is, that is, the more unstable the battery pack is, the worse the performance is. The basic performance level of the battery pack can be divided into multiple levels based on historical data. Different levels correspond to different ranges of battery pack current variance. The current battery pack current variance is calculated and corresponds to the corresponding range of battery pack current variance, thereby determining the corresponding basic performance level.

[0072] In this embodiment, the variance of the battery pack current is calculated by calculating the variance of the maximum current value and the variance of the minimum current value in all postures. The smaller the variance of the battery pack current, the more stable the battery pack performance, which can evaluate the battery pack performance of the underwater glider, and then assist in determining whether the battery pack can continue to be used, providing data support for the reliability and safety evaluation of the battery pack, and reducing the cost of directly replacing the battery pack, and improving the reliability of the battery pack and the accuracy of the safety evaluation.

[0073] On the basis of the first aspect of the embodiment of the present invention, the second aspect of the embodiment of the present invention provides a method for evaluating the performance of an underwater glider battery pack, further comprising:

[0074] Energy consumption parameters also include: battery pack posture, device communication status, underwater glider movement speed and power parameters. Power parameters include current value and corresponding voltage value.

[0075] After evaluating the basic performance level of the battery pack, the comprehensive performance of the battery can be further evaluated. Specifically, the comprehensive performance level of the battery pack can be determined based on the posture of the battery pack, the corresponding device communication status, and the movement speed and power parameters of the corresponding underwater glider.

[0076] In the first aspect of the embodiment of the present invention, the basic performance of the battery pack can be preliminarily evaluated based on the current in different postures. In this embodiment, the comprehensive performance of the battery pack can be further evaluated in combination with more data related to battery use. Specifically, in various postures of the battery pack, whether the underwater glider is communicating and the movement speed of the underwater glider (indicating the power of the motor) can reflect the comprehensive power consumption of the underwater glider.

[0077] Specifically, it includes step 21 and step 22:

[0078] Step 21, determining the conditional entropy of the electric energy parameters under the postures of all battery packs, the corresponding device communication states and the corresponding movement speeds of the underwater glider.

[0079] The calculation formula of conditional entropy is:

[0080] H(D|X)=-Σ x∈X Σ d∈D p(x,d)[logp(x)+logp(d|x=(x1,x2,x3))];

[0081] Among them, H(D|X) represents conditional entropy, which is used to evaluate the stability of the battery pack; d represents the electric energy parameter, which includes the current value and the corresponding voltage value. d can also represent the current value or the voltage value; x1 represents the posture of the battery pack, x2 represents the communication status of the device, and x3 represents the movement speed of the underwater glider.

[0082] In this step, conditional entropy represents the uncertainty of D under the known condition X, that is, the uncertainty of the battery pack performance (i.e., current value and voltage value) under various postures, communication and various movement speeds, and the stability of the battery pack is evaluated based on this. X represents the set of all battery pack postures, communication and corresponding movement speeds under each posture, and D represents the set of current values ​​and voltage values ​​under all postures.

[0083] Among them, various probabilities in the conditional entropy can be calculated based on the currently collected data, or can be pre-calculated based on historical data.

[0084] Step 22, determining the comprehensive performance level of the battery pack based on the conditional entropy.

[0085] In this step, the smaller the entropy, the smaller the uncertainty, that is, the better the stability of the battery pack, the larger the entropy, the greater the uncertainty, and the worse the stability of the battery pack. Different ranges of conditional entropy values ​​can be corresponded to different comprehensive performance levels, and the current conditional entropy can be calculated and corresponded to the corresponding range value to determine the corresponding comprehensive performance level.

[0086] In this embodiment, the comprehensive performance level of the battery pack is further evaluated based on a variety of data, thereby improving the accuracy of the battery pack performance evaluation. The battery pack performance can be comprehensively evaluated based on the basic performance level and the comprehensive performance level, providing comprehensive data support for the underwater glider battery performance research.

[0087] On the basis of the first aspect of the embodiment of the present invention, the third aspect of the embodiment of the present invention provides a method for evaluating the performance of an underwater glider battery pack, further comprising:

[0088] The posture of the battery pack, the corresponding device communication status, the corresponding underwater glider's movement speed and the corresponding power parameters are input into the trained machine learning model to output the comprehensive performance level result.

[0089] In this embodiment, the input features of the model are:

[0090]

[0091] Among them, I represents current, V represents voltage, R represents posture, T represents whether to communicate, and Q represents movement speed.

[0092] The comprehensive performance level of the battery pack is evaluated through a trained machine learning model, and the comprehensive performance level results are more accurate, improving the evaluation efficiency.

[0093] In this embodiment, the training process of the machine learning model includes the following steps:

[0094] Step 31, input the training samples with comprehensive performance level labels into the initial machine learning model, and output the sample comprehensive performance level results of the battery pack. The current and voltage values ​​of the battery packs with different stability, whether they communicate in various postures, the movement speed (power consumption) of the equipment in various postures, etc. are input into the machine learning model for training.

[0095] Step 32: Based on the comprehensive performance level results of the samples And the corresponding comprehensive performance level label y, the loss value is calculated using the preset cross entropy loss function.

[0096] Here, the cross entropy loss function is used to calculate the loss value, and the cross entropy loss function is:

[0097]

[0098] That is, the loss value is calculated based on the true value and the predicted value output by the machine learning model.

[0099] Step 33, update the parameters of the initial machine learning model according to the loss value to obtain a trained machine learning model.

[0100] During the model training process, the training goal is to minimize the cross entropy loss function. After each training sample outputs the result, the loss value is calculated, and the parameters of the machine learning model are adjusted according to the loss value. The training, loss value calculation and model parameters are updated repeatedly until the loss function is minimized and the training is ended.

[0101] Here, the training samples can be divided into multiple batches for training, and the losses of a batch of training samples can be averaged or aggregated to obtain a training loss value representing a batch of training sets, and then the model parameters can be adjusted and updated.

[0102] In this embodiment, the comprehensive performance level of the battery pack is further evaluated based on a variety of data, thereby improving the accuracy of the battery pack performance evaluation. The battery pack performance can be comprehensively evaluated based on the basic performance level and the comprehensive performance level, providing comprehensive data support for the underwater glider battery performance research.

[0103] like Figure 2 As shown, a fourth aspect of an embodiment of the present invention provides a system for evaluating the performance of an underwater glider battery pack, comprising:

[0104] The acquisition module 41 is used to acquire energy consumption parameters of the battery pack in all postures; wherein the energy consumption parameters include: maximum current value and minimum current value;

[0105] A determination module 42, configured to determine a current variance of the battery pack according to a maximum current value variance and a minimum current value variance in all postures of the battery pack;

[0106] The evaluation module 43 is used to determine the basic performance level of the battery pack according to the battery pack current variance.

[0107] In one embodiment of the present invention, the maximum current value variance is calculated as follows:

[0108]

[0109] Among them, S1 represents the maximum current value variance, m is the sequence number of the battery pack posture, n is the number of tests for each posture, m and n are both positive integers, X ij represents the maximum current value of the jth test under the i-th posture, is the average value of n maximum current values ​​in the i-th posture;

[0110] The calculation formula for the minimum current value variance is:

[0111]

[0112] Among them, S2 represents the minimum current value variance, m is the sequence number of the battery pack posture, n is the number of tests for each posture, m and n are both positive integers, and Y ij represents the minimum current value of the jth test in the i-th posture, is the average value of n minimum current values ​​under the i-th posture;

[0113] The calculation formula for the battery pack current variance is:

[0114]

[0115] Where S represents the battery pack current variance.

[0116] In one embodiment of the present invention, the energy consumption parameters also include: the posture of the battery pack, the communication status of the device, the movement speed of the underwater glider and the power parameters;

[0117] The system also includes:

[0118] The comprehensive evaluation module is used to determine the comprehensive performance level of the battery pack according to the posture of the battery pack, the corresponding device communication status and the corresponding movement speed and power parameters of the underwater glider.

[0119] In one embodiment of the present invention, the comprehensive performance level of the battery pack is determined according to the posture of the battery pack, the corresponding device communication state, and the corresponding movement speed and power parameters of the underwater glider, including:

[0120] Determine the conditional entropy of the electric energy parameters under the posture of all battery packs, the corresponding device communication state and the corresponding underwater glider movement speed;

[0121] According to the conditional entropy, the comprehensive performance level of the battery pack is determined.

[0122] In one embodiment of the present invention, the calculation formula of conditional entropy is:

[0123] H(D|X)=-Σ x∈X Σ d∈D p(x,d)[logp(x)+logp(d|x=(x1,x2,x3))];

[0124] Among them, H(D|X) represents conditional entropy, which is used to evaluate the stability of the battery pack; d represents the electric energy parameter, which includes the current value and the corresponding voltage value; x1 represents the posture of the battery pack, x2 represents the communication status of the device, and x3 represents the movement speed of the underwater glider.

[0125] In one embodiment of the present invention, the comprehensive performance level of the battery pack is determined according to the posture of each battery pack, the corresponding device communication state, and the corresponding motion speed and power parameters of the underwater glider, including:

[0126] The posture of the battery pack, the corresponding device communication status, the corresponding movement speed of the underwater glider and the corresponding power parameters are input into the trained machine learning model to output the comprehensive performance level result of the battery pack.

[0127] In one embodiment of the present invention, training samples with comprehensive performance level labels are input into an initial machine learning model, and the sample comprehensive performance level results of the battery pack are output;

[0128] According to the sample comprehensive performance level results and the corresponding comprehensive performance level labels, the loss value is calculated using the preset cross entropy loss function;

[0129] Update the parameters of the initial machine learning model according to the loss value to obtain a trained machine learning model.

[0130] A fifth aspect of an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, a method for evaluating the performance of an underwater glider battery pack provided in the above embodiment of the present invention is implemented.

[0131] A sixth aspect of an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of a method for evaluating the performance of an underwater glider battery pack provided in the above embodiment of the present invention are implemented.

[0132] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0133] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0134] The method provided in the embodiment of the present invention can be applied to electronic devices. Specifically, the electronic device can be: a desktop computer, a portable computer, an intelligent mobile terminal, a server, etc. This is not limited here, and any electronic device that can implement the present invention belongs to the protection scope of the present invention.

[0135] As for the system / electronic device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0136] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0137] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0138] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0139] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for evaluating the performance of an underwater glider battery pack, characterized in that: The following steps are involved: Obtaining energy consumption parameters of the battery pack in all postures; wherein the energy consumption parameters include: maximum current value and minimum current value; Determining a battery pack current variance according to a maximum current value variance and a minimum current value variance in all postures of the battery pack; A basic performance level of the battery pack is determined according to the battery pack current variance.

2. The method according to claim 1, characterized in that The calculation formula of the maximum current value variance is: Wherein, S1 represents the maximum current value variance, m is the sequence number of the posture of the battery pack, n is the number of tests for each posture, m and n are both positive integers, and X ij represents the maximum current value of the jth test under the i-th posture, is the average value of n maximum current values ​​in the i-th posture; The calculation formula of the minimum current value variance is: Wherein, S2 represents the minimum current value variance, m is the sequence number of the posture of the battery pack, n is the number of tests for each posture, m and n are both positive integers, and Y ij represents the minimum current value of the jth test in the i-th posture, is the average value of n minimum current values ​​under the i-th posture; The calculation formula of the battery pack current variance is: Where S represents the battery pack current variance.

3. The method according to claim 1, characterized in that The energy consumption parameters also include: the posture of the battery pack, the communication status of the device, the movement speed of the underwater glider and the power parameters; The method further comprises: The comprehensive performance level of the battery pack is determined according to the posture of the battery pack, the corresponding communication status of the device, and the corresponding movement speed and power parameters of the underwater glider.

4. The method according to claim 3, characterized in that Determining the comprehensive performance level of the battery pack according to the posture of the battery pack, the corresponding communication state of the device, and the corresponding movement speed and power parameters of the underwater glider includes: Determining the conditional entropy of the electric energy parameter under the posture of all the battery packs, the corresponding communication state of the device and the corresponding movement speed of the underwater glider; According to the conditional entropy, a comprehensive performance level of the battery pack is determined.

5. The method according to claim 1, characterized in that The calculation formula of the conditional entropy is: H(D|X)=-∑ x∈X ∑ d∈D p(x,d)[logp(x)+logp(d|x=(x1,x2,x3))]; Among them, H(D|X) represents conditional entropy, which is used to evaluate the stability of the battery pack; d represents the electric energy parameter, which includes the current value and the corresponding voltage value; x1 represents the posture of the battery pack, x2 represents the communication status of the device, and x3 represents the movement speed of the underwater glider.

6. The method according to claim 1, characterized in that Determining the comprehensive performance level of the battery pack according to the posture of each battery pack, the corresponding communication state of the device, and the corresponding movement speed and power parameters of the underwater glider includes: The posture of the battery pack, the corresponding communication status of the device, the corresponding movement speed of the underwater glider and the corresponding electric energy parameters are input into the trained machine learning model, and the comprehensive performance level result of the battery pack is output.

7. The method according to claim 6, characterized in that The method further comprises: Input the training samples with comprehensive performance level labels into the initial machine learning model, and output the sample comprehensive performance level results of the battery pack; According to the comprehensive performance level result of the sample and the corresponding comprehensive performance level label, a loss value is calculated using a preset cross entropy loss function; Update the parameters of the initial machine learning model according to the loss value to obtain a trained machine learning model.

8. An underwater glider battery pack performance evaluation system, characterized in that: include: An acquisition module, used to acquire energy consumption parameters of the battery pack in all postures; wherein the energy consumption parameters include: a maximum current value and a minimum current value; A determination module, configured to determine a current variance of the battery pack according to a maximum current value variance and a minimum current value variance in all postures of the battery pack; An evaluation module is used to determine a basic performance level of the battery pack according to the battery pack current variance.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the underwater glider battery pack performance evaluation method as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the underwater glider battery pack performance evaluation method according to any one of claims 1 to 7 is implemented.

Images