Battery pack operating state determination method and system

Abstract

The application discloses a kind of battery pack operating state determination method and system, by obtaining the operating state parameter of battery pack, according to the state value corresponding to operating state parameter determines the operating state of battery pack, without needing to detect the operating state by artificial, can improve the detection efficiency of battery pack operating state, can avoid the error introduced by artificial detection. By determining the operating state of battery pack according to the state value related to the operating state of battery pack, the accuracy of the determined operating state of battery pack is guaranteed. The technical scheme of the present application can not only determine the current operating state, but also determine the operating state of the future prediction period. In the case where the current operating state is determined to be a fault state or a fault state will occur in the future prediction period, the battery pack is maintained in time, the service life of the battery pack is prolonged, and the maintenance efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of battery health state detection, and particularly relates to a method and system for determining the running state of a battery pack. BACKGROUND

[0002] A battery pack is a group of independent and reliable power supplies, and plays an especially important role in the normal operation of a substation due to its stability, low cost and excellent performance.

[0003] At present, discharge testing of the battery pack is mainly performed manually to detect the running state of the battery. However, this method has the problems of large operation amount and long time consumption. The current maintenance work lacks more convenient and advanced monitoring methods, which leads to the inability to more accurately monitor the real-time state of the battery and thus eliminates the safety hazards buried therein.

[0004] Therefore, how to improve the efficiency and accuracy of the running state detection of the battery pack becomes a problem to be solved. SUMMARY

[0005] The present application provides a method and system for determining the running state of a battery pack to improve the efficiency and accuracy of the running state detection of the battery pack, thereby maintaining the battery pack and prolonging the service life of the battery pack.

[0006] According to an aspect of the present application, a method for determining the running state of a battery pack is provided, comprising:

[0007] obtaining a running state parameter of the battery pack, the running state parameter comprising at least one of a current capacity, a current number of charge and discharge, an internal temperature, an internal gas content, and a deformation amount of the battery pack;

[0008] determining a corresponding state value according to the running state parameter and a determination rule corresponding to the running state parameter;

[0009] determining the running state of the battery pack according to the state value, the running state comprising a current running state and / or a running state in a future prediction period.

[0010] Optionally, determining the running state of the battery pack according to the state value comprises:

[0011] in a case where at least one state value exceeds a corresponding preset state value range, determining that the current running state is a fault state;

[0012] in a case where none of the state values exceeds the corresponding preset state value range, determining that the current running state is a normal state.

[0013] Optionally, determining the running state of the battery pack according to the state value comprises:

[0014] taking the state value and the corresponding current running state, and the state values and the corresponding historical running states of multiple time points in a preset historical period as samples;

[0015] training the neural network model on the multiple samples to obtain a state prediction model of the running state in a future prediction period;

[0016] predicting the running state in the future prediction period according to the state prediction model.

[0017] Optionally, the neural network model comprises an input layer, an output layer and one or at least two intermediate layers; the training of the neural network model on the multiple samples to obtain the state prediction model of the running state in the future prediction period comprises:

[0018] In the process of training the neural network model on the multiple samples, the number of neurons in the intermediate layer is adjusted to reduce the error, so as to obtain the state prediction model of the running state in the future prediction period.

[0019] Optionally, in the process of training the neural network model on the multiple samples, the number of neurons in the intermediate layer is adjusted to reduce the error, so as to obtain the state prediction model of the running state in the future prediction period, comprising:

[0020] In the process of training the neural network model on the multiple samples, the number of neurons in the intermediate layer is adjusted, and the number of neurons at the time of the minimum error is determined as the final corresponding number of neurons in the intermediate layer, so as to obtain the state prediction model of the running state in the future prediction period.

[0021] Optionally, in the process of training the neural network model on the multiple samples, the number of neurons in the intermediate layer is adjusted to reduce the error, so as to obtain the state prediction model of the running state in the future prediction period, comprising:

[0022] The number of neurons in the intermediate layer is adjusted according to the following formula:

[0023] y = (n + m) + k·b 1 / 2 ;

[0024] wherein y is the number of neurons in the intermediate layer, n and m are the numbers of neurons in the output layer and the input layer respectively, b is a constant value, and k is a variable weight.

[0025] Optionally, the corresponding state value is determined according to the running state parameter and the determination rule corresponding to the running state parameter, comprising:

[0026] determining the first state value according to the ratio of the current capacity to the factory capacity of the battery pack, wherein the test temperatures of the current capacity and the factory capacity are the same;

[0027] The current charging and discharging times include a current charging cumulative times and a current discharging cumulative times; a second state value is determined according to a ratio of a sum of the current charging cumulative times and the current discharging cumulative times to the rated charging and discharging times;

[0028] A third state value is determined according to a ratio of a difference between a variation of the oxygen content and a variation of the hydrogen content in a first set time period before the current time and the variation of the oxygen content;

[0029] A fourth state value is determined according to a variation of the internal temperature in a second set time period before the current time;

[0030] A fifth state value is determined according to a ratio of a deformation of the battery pack at the current time and a factory size of the battery pack.

[0031] According to another aspect of the present application, a battery pack operation state determination system is provided, comprising: an operation state parameter acquisition module and a processing module;

[0032] The operation state parameter acquisition module is connected with the processing module, and is configured to acquire operation state parameters of the battery pack, the operation state parameters comprising at least one of a current capacity, a current charging and discharging times, an internal temperature, an internal gas content and a deformation of the battery pack;

[0033] The processing module is configured to determine corresponding state values according to the operation state parameters acquired from the operation state parameter acquisition module and determination rules corresponding to the operation state parameters; and determine an operation state of the battery pack according to the state values, the operation state comprising a current operation state and / or an operation state in a future prediction time period.

[0034] Optionally, the operation state parameter acquisition module comprises at least one of a current capacity acquisition unit, a charging and discharging times acquisition unit, a gas content acquisition unit, an internal temperature acquisition unit and a deformation acquisition unit; the current capacity acquisition unit, the charging and discharging times acquisition unit, the gas content acquisition unit, the internal temperature acquisition unit and the deformation acquisition unit are respectively connected with the processing module; the current capacity acquisition unit is configured to acquire the current capacity of the battery pack; the charging and discharging times acquisition unit is configured to acquire the current charging and discharging times of the battery pack; the gas content acquisition unit is configured to acquire the oxygen content and the hydrogen content in the battery pack; the internal temperature acquisition unit is configured to acquire the temperature in the battery pack; and the deformation acquisition unit is configured to acquire the current size of the battery pack.

[0035] Optionally, at least one of a communication module, an alarm module and an input module is further included; the communication module, the alarm module and the input module are connected with the processing module respectively, the processing module is used for sending a prompt information through the communication module or sending an alarm message through the alarm module when it is determined that the running state includes the fault state; the input module is used for receiving a preset state value range corresponding to the state value, and the processing module is used for determining that the current running state is the fault state when at least one state value exceeds the corresponding preset state value range; and the current running state is determined as the normal state when all the state values do not exceed the corresponding preset state value range.

[0036] The method and system for determining the running state of the battery pack provided by the embodiments of the present application can obtain the running state parameters of the battery pack, determine the corresponding state values according to the running state parameters and the determination rules corresponding to the running state parameters, and determine the running state of the battery pack according to the state values, wherein the running state includes the current running state and / or the running state in a future prediction period, so that the detection efficiency of the running state of the battery pack can be improved and the error caused by manual detection can be avoided. In addition, the running state of the battery pack is determined according to the state values related to the running state of the battery pack, so that the accuracy of the determined running state of the battery pack is ensured. Moreover, in the embodiments of the present application, not only the current running state can be determined, but also the running state in a future prediction period can be determined, so that the battery pack can be maintained in time in the case that the current running state is the fault state or the fault state will occur in the future prediction period, the service life of the battery pack is prolonged, and the maintenance efficiency is improved.

[0037] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0039] Figure 1 is a flow chart of a method for determining the running state of a battery pack provided by the embodiments of the present application;

[0040] Figure 2 is a structural schematic diagram of a system for determining the running state of a battery pack provided by the embodiments of the present application;

[0041] Figure 3is a flow chart of another battery pack operation state determination method provided by an embodiment of the present application;

[0042] Figure 4 is a schematic diagram of a neural network structure;

[0043] Figure 5 is a structural schematic diagram of another battery pack operation state determination system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0044] In order to enable persons skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by persons skilled in the art without creative labor should fall within the protection scope of the present application.

[0045] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to the process, method, product or device.

[0046] Figure 1 is a flow chart of a battery pack operation state determination method provided by an embodiment of the present application, which is applied to a battery pack operation state determination system, wherein the battery pack can be applied in a substation. Figure 2 is a structural schematic diagram of a battery pack operation state determination system provided by an embodiment of the present application, referring to Figure 2 , the battery pack operation state determination system comprises an operation state parameter acquisition module 10 and a processing module 20, the operation state parameter acquisition module 10 is connected with the processing module 20, the operation state parameter acquisition module 10 can acquire the operation state parameters of the battery pack, and the processing module 20 can be used for executing the battery pack operation state determination method of any embodiment of the present application. Referring to Figure 1 , the battery pack operation state determination method comprises:

[0047] S110, acquire the operation state parameter of the battery pack, the operation state parameter including at least one of the current capacity, the current charge-discharge times, the internal temperature, the internal gas content and the deformation amount of the battery pack.

[0048] Specifically, the processing module 20 can acquire the operation state parameter of the battery pack from the operation state parameter acquisition module 10. The operation state acquisition module can include an acquisition unit for operation state parameter acquisition. Considering that the operation state of the battery pack is related to factors such as the charge-discharge characteristics, capacity characteristics, internal temperature variation characteristics and internal gas content variation characteristics of the battery pack, the operation state parameter acquisition module 10 is provided to include at least one of a current capacity acquisition unit, a charge-discharge times acquisition unit, a gas content acquisition unit, an internal temperature acquisition unit and a deformation acquisition unit; the current capacity acquisition unit, the charge-discharge times acquisition unit, the gas content acquisition unit, the internal temperature acquisition unit and the deformation acquisition unit are respectively connected with the processing module 20; the current capacity acquisition unit is used to acquire the current capacity of the battery pack; the charge-discharge times acquisition unit is used to acquire the current charge-discharge times of the battery pack; the gas content acquisition unit is used to acquire the oxygen content and the hydrogen content inside the battery pack; the internal temperature acquisition unit is used to acquire the temperature inside the battery pack; the deformation acquisition unit is used to acquire the current size of the battery pack; and the processing module 20 is used to determine the deformation amount according to the current size and the factory size of the battery.

[0049] S120, determine the corresponding state value according to the operation state parameter and the determination rule corresponding to the operation state parameter.

[0050] In this step, the state value corresponding to different operation state parameters can be calculated by different determination rules. The determination rule of the state value corresponding to the operation state parameter can be pre-stored and set, which can be a calculation formula, a corresponding relationship lookup table of the operation state parameter and the state value, or other forms of determination rules, which are not specifically limited in the present embodiment. For example, the first state value corresponding to the current capacity of the battery pack is determined according to the current capacity of the battery pack and the first determination rule; the second state value is determined according to the current charge-discharge times and the second determination rule; the third state value is determined according to the internal temperature and the third determination rule; the fourth state value is determined according to the internal gas content and the fourth determination rule; and the fifth state value is determined according to the deformation amount and the fifth determination rule. The first determination rule, the second determination rule, the third determination rule, the fourth determination rule and the fifth determination rule can be pre-stored and set in the processing module 20, and the processing module 20 can determine the corresponding state value according to the operation state parameter and the corresponding determination rule after acquiring the operation state parameter. In this step, the corresponding state value is determined according to the operation state parameter related to the operation state of the battery pack, which serves as a quantitative index for determining the operation state of the battery pack.

[0051] S130, determining the operation state of the battery pack according to the state value, the operation state including a current operation state and / or an operation state in a future prediction period.

[0052] Since the state value is determined according to the operation state parameter, the operation state parameter is related to the operation state of the battery pack. In this step, the operation state of the battery pack can be determined according to the state value, which can be a current operation state, i.e., an operation state at the current time; or an operation state in a future prediction period. The current operation state includes a normal operation state and a fault state, and the operation state in the future prediction period also includes a normal operation state and a fault state. In this step, not only the current operation state of the battery pack can be determined according to the state value, but also the operation state of the battery pack in the future prediction period can be predicted. In the case of predicting the operation state of the battery pack in the future prediction period, a corresponding prediction model can be obtained by using a machine learning algorithm in combination with the state values at multiple time points in a set period of time before the state value at the current time, and then the operation state in the future set period can be predicted according to the prediction model.

[0053] The battery pack operation state determination method of the embodiment of the application determines the operation state of the battery pack by obtaining the operation state parameter of the battery pack, determining the corresponding state value according to the operation state parameter and the determination rule corresponding to the operation state parameter, and determining the operation state of the battery pack according to the state value. The operation state includes a current operation state and / or an operation state in a future prediction period. The detection of the operation state by artificial means can be avoided, the detection efficiency of the operation state of the battery pack can be improved, and the error introduced by artificial detection can be avoided. In addition, in this embodiment, the operation state of the battery pack is determined according to the state value related to the operation state of the battery pack, so that the accuracy of the determined operation state of the battery pack is ensured. In this embodiment, not only the current operation state can be determined, but also the operation state in the future prediction period can be determined, so that the battery pack can be maintained in time in the case of determining that the current operation state is a fault state or the operation state in the future prediction period will be a fault state, the service life of the battery pack is prolonged, and the maintenance efficiency is improved.

[0054] In some optional embodiments of the application, S130 includes: in the case that at least one state value exceeds the corresponding preset state value range, determining that the current operation state is a fault state; and in the case that none of the state values exceeds the corresponding preset state value range, determining that the current operation state is a normal state.

[0055] Before S110, a preset state value range corresponding to each state value can be set in advance, wherein the preset state value range is a state value range of the battery pack in a normal working state. In a case where at least one state value exceeds the corresponding preset state value range, it indicates that the battery pack currently has an abnormality, and the current running state is determined as a fault state, and then the battery pack is maintained in time.

[0056] In some optional embodiments, S120 comprises: determining the first state value according to a ratio of the current capacity and a factory capacity of the battery pack, wherein the current capacity and the factory capacity are tested at the same test temperature.

[0057] In order to better guarantee the output performance of the battery pack, the life of the battery pack needs to be understood in time, and the capacity change is one of the verification factors, and therefore the ratio of the current capacity of the battery to the initial health state capacity (i.e. the factory capacity) is determined as the first state value as a running state evaluation quantitative index. The first state value ΔS is calculated according to the following formula:

[0058]

[0059] Wherein, S(T, I, K) is the capacity released from full charge and discharge to the termination voltage at a load current I under a certain health state K and temperature T of the battery; S(T, I) represents the factory capacity, i.e. the capacity released from full charge and discharge to the termination voltage at a load current I at the temperature T of the battery at the time of production.

[0060] In some optional embodiments, the current charge and discharge times include a current charge cumulative number and a current discharge cumulative number; S120 comprises: determining the second state value according to a ratio of a sum of the current charge cumulative number and the current discharge cumulative number to a rated charge and discharge number.

[0061] Specifically, the battery pack has a rated charge and discharge number, and therefore the number of charge and discharge times is also one of the factors affecting the health state of the battery pack. The second state value ΔP is calculated according to the following formula:

[0062]

[0063] Wherein, C is the current charge cumulative number; D is the current discharge cumulative number; H is the rated charge and discharge number of the battery pack.

[0064] In some optional embodiments, S120 comprises: determining the third state value according to a ratio of a difference between a change amount of the oxygen content and a change amount of the hydrogen content in a first set period of time before the current time to the change amount of the oxygen content.

[0065] Specifically, when the charging is about 90% complete, the negative electrode begins to produce hydrogen. There are two processes for the source of hydrogen production, (1) produced in the overcharging process, electrolytic water side reaction; (2) self-discharge reaction during open circuit storage. Therefore, the running condition of the battery pack can be determined by detecting the gas through the gas sensor. The third state value ΔQ is calculated according to the following formula:

[0066]

[0067] Q 氧气 represents the oxygen content change amount in the first set period, Q 氧气 represents the hydrogen content change amount in the first set period, and Δt represents the length of the first set period, wherein the first set period is continuous with the current time.

[0068] In some optional embodiments, S120 comprises: determining a fourth state value according to the change amount of the internal temperature in the second set period before the current time.

[0069] Specifically, the large internal temperature difference of the battery also has a certain impact on the service life of the battery pack, so the influence of the internal temperature of the battery pack is considered, and the optical fiber temperature sensor is used for measurement. The relationship between the optical fiber wavelength drift amount and the temperature change amount is as follows:

[0070] Δλ B = K T · ΔT;

[0071] wherein Δλ B is the drift amount of the optical fiber wavelength when only the temperature changes, K T is the FBG temperature sensitivity coefficient, and ΔT is the temperature change amount. According to the above formula, the change amount of the internal temperature of the battery pack in the second period can be determined as the fourth state value according to the drift amount of the optical fiber wavelength. The second set period is continuous with the current time, and in some optional embodiments of the present application, the second set period is the same as the first set period.

[0072] In some optional embodiments, S120 comprises: determining a fifth state value according to the ratio of the deformation amount of the battery pack at the current time to the factory size of the battery pack.

[0073] Specifically, after a period of operation, the battery pack may be deformed, such as surface deformation phenomenon such as bulging, therefore, the surface displacement change of the battery pack is detected by using the displacement sensor.

[0074]

[0075] Wherein, L2 is the size of the battery pack at t+1 moment; L is the size of the battery pack at t moment, L0 is the reference size (i.e. factory size) of the battery pack. Wherein, the size of the battery pack includes the length and / or width of the battery pack. The difference between t+1 and t is equal to the sampling interval time of the processing module 20 obtaining the running state parameter from the displacement sensor.

[0076] Figure 3 is the flow chart of another battery pack running state determination method provided by the embodiment of the application, referring to Figure 3 , optionally, the battery pack running state determination method comprises:

[0077] S210, obtaining the running state parameter of the battery pack, the running state parameter comprising at least one of the current capacity, the current charge-discharge times, the internal temperature, the internal gas content and the deformation amount of the battery pack.

[0078] S220, determining the corresponding state value according to the running state parameter and the determination rule corresponding to the running state parameter.

[0079] S230, taking the state value and the corresponding current running state, and the state value and the corresponding historical running state at multiple moments in the preset historical period as samples.

[0080] The data training sample set E is as follows:

[0081] E={(x1,y1),(x2,y2)……(xn,yn)}; n n

[0082] x i ∈R N ,y i ∈{0,1},i=1,2……n.

[0083] Wherein, x i is the sample (the data periodically obtained by the state parameter module of the processing module 20), yi is the category (such as 1 represents the normal state, 0 represents the fault state, and needs to be checked on site), R N is the N-dimensional high-dimensional feature space, and n is the sample number.

[0084] S240, training the multiple samples by using the neural network model to obtain the state prediction model of the running state in the future prediction period.

[0085] Figure 4 is the schematic diagram of the neural network structure, referring to Figure 4 ​​Wherein, the neural network structure has at least three layers, an input layer, one or more intermediate layers (hidden layers) and an output layer, the training process includes forward propagation of input data and backward propagation of error, and the process of neural network training and learning is a process of continuously correcting threshold and weight, so that the final output result is more consistent with the expectation.

[0086] Optionally, the S240 includes adjusting the number of neurons in the intermediate layer to reduce the error in the process of training the plurality of samples by using the neural network model, to obtain the state prediction model of the running state in the future prediction period.

[0087] Specifically, in the process of training the neural network model, the initial value of the number of neurons in the intermediate layer can be set first, and then the initial value is adjusted. The adjustment direction of the initial value can be the increasing direction or the decreasing direction, so as to reduce the error. In this way, the improved neural network model with variable number of neurons in the intermediate layer is used to train the samples to obtain the state prediction model, so as to ensure the accuracy of the determined state prediction model.

[0088] In some embodiments, in the process of training the plurality of samples by using the neural network model, the number of neurons in the intermediate layer is adjusted, and the number of neurons at the time when the error is the smallest is determined as the final number of neurons corresponding to the intermediate layer, to obtain the state prediction model of the running state in the future prediction period.

[0089] In other embodiments, the number of neurons in the intermediate layer is adjusted according to the following formula:

[0090] y = (n + m) 1 / 2 + k·b;

[0091] Wherein, y is the number of neurons in the intermediate layer, n and m are the number of neurons in the output layer and the input layer respectively, b is a constant value, and k is a variable weight. The number of neurons in the intermediate layer is adjusted by adjusting the size of the variable modulation k.

[0092] Optionally, the number of neurons in the intermediate layer can be first learned and trained with a smaller number of intermediate layer neurons, and then gradually increased until the number of intermediate layer neurons corresponding to the time when the error is the smallest is found. The training is as follows:

[0093] s t = Ux t + Wh t-1

[0094] h t = f((n + m) 1 / 2 + k·b)

[0095] o t = g(Vh t )

[0096] where x t is an n-dimensional vector, the input of the recurrent network will be an entire sequence, i.e., x = [x1,...,x t-1 , t , t+1 ,...x T ]; h t represents the hidden state at time t; o t represents the output at time t; U represents the weight from the input layer to the hidden layer; W represents the weight from the hidden layer to the hidden layer; and V represents the weight from the hidden layer to the output layer. n and m are respectively the number of neurons in the output layer and the input layer, b is a constant value, and k is a variable weight.

[0097] S250, predicting the running state of the future prediction period according to the state prediction model.

[0098] With reference back to Figure 2 , the embodiment of the present application also provides a battery pack running state determination system, which comprises a running state parameter acquisition module 10 and a processing module 20; the running state parameter acquisition module 10 is connected with the processing module 20, and is used to acquire the running state parameters of the battery pack; the running state parameters comprise at least one of the current capacity, the current charge-discharge times, the internal temperature, the internal gas content and the deformation amount of the battery pack; the processing module 20 is used to determine the corresponding state value according to the running state parameters acquired from the running state parameter acquisition module 10 and the determination rules corresponding to the running state parameters; and the running state of the battery pack is determined according to the state value, wherein the running state comprises the current running state and / or the running state of the future prediction period.

[0099] The battery pack running state determination system of the embodiment can automatically acquire the running state parameters of the battery pack through the running state parameter acquisition module 10, and does not need to detect the running state manually, so that the detection efficiency of the running state of the battery pack can be improved, and the error introduced by manual detection can be avoided. The processing module determines the running state of the battery pack according to the state value related to the running state of the battery pack, so that the accuracy of the determined running state of the battery pack is ensured. In the embodiment, not only the current running state can be determined, but also the running state of the future prediction period can be determined, so that the battery pack can be maintained in time in the case that the current running state is a fault state or the fault state will appear in the future prediction period, the service life of the battery pack is prolonged, and the maintenance efficiency is improved.

[0100] Figure 5 is a structural schematic diagram of another battery pack running state determination system provided by the embodiment of the present application, which is described with reference to Figure 5Optionally, the running state parameter acquisition module 10 comprises at least one of a current capacity acquisition unit 11, a charge-discharge frequency acquisition unit 12, a gas content acquisition unit 13, an internal temperature acquisition unit 14, and a deformation acquisition unit 15; the current capacity acquisition unit 11, the charge-discharge frequency acquisition unit 12, the gas content acquisition unit 13, the internal temperature acquisition unit 14, and the deformation acquisition unit 15 are connected with the processing module 20; the current capacity acquisition unit 11 is configured to acquire the current capacity of the battery pack; the charge-discharge frequency acquisition unit 12 is configured to acquire the current charge-discharge frequency of the battery pack; the gas content acquisition unit 13 is configured to acquire the oxygen content and the hydrogen content inside the battery pack; the internal temperature acquisition unit 14 is configured to acquire the temperature inside the battery pack; and the deformation acquisition unit 15 is configured to acquire the current size of the battery pack.

[0101] In some embodiments, the current capacity acquisition unit 11 can acquire the current capacity by receiving an external input, and the charge-discharge frequency acquisition unit 12 can acquire the charge-discharge frequency by receiving an external input.

[0102] With reference to the foregoing Figure 5 Optionally, the battery pack running state determination system further comprises at least one of a communication module 30, an alarm module 40, and an input module 50; the communication module 30, the alarm module 40, and the input module 50 are connected with the processing module 20; the processing module 20 is configured to send a prompt message through the communication module 30 or send an alarm message through the alarm module 40 when it is determined that the running state comprises a fault state; and the input module 50 is configured to receive a preset state value range corresponding to a state value, and the processing module 20 is configured to determine that the current running state is a fault state when at least one state value exceeds the corresponding preset state value range, and determine that the current running state is a normal state when none of the state values exceeds the corresponding preset state value range.

[0103] The communication module 30 can adopt a wired communication mode or a wireless communication mode. The alarm module 40 includes, but is not limited to, a buzzer, an indicator light, and the like. By arranging the storage battery operation state determination system to include the communication module 30 and / or the alarm module 40, the maintenance personnel can receive prompt information or alarm information in a timely manner when the storage battery is in a fault state, so that the storage battery can be maintained in a timely manner, which is conducive to prolonging the service life of the storage battery and improving the safety and reliability of the storage battery. The storage battery operation state system further includes an input module 50. The input module 50 can be a key or a touch panel, and the present embodiment does not make a specific limitation here.

[0104] It should be understood that the various forms of flow shown above can be reordered, added to, or deleted from. For example, the steps described in the present application can be executed in parallel, in sequence, or in a different order, as long as the desired results of the technical solutions of the present application can be achieved, and the present application does not make a limitation here.

[0105] The above specific embodiments do not constitute a limitation on the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modification, equivalent replacement, and improvement within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method of determining the operating state of a battery pack, characterized by, The method comprises the following steps: acquiring an operating state parameter of the battery pack, the operating state parameter comprising at least one of a current capacity, a current number of charge-discharge cycles, an internal temperature, an internal gas content, and a deformation amount of the battery pack; determining a corresponding state value according to the operating state parameter and a determination rule corresponding to the operating state parameter; determining an operating state of the battery pack according to the state value, the operating state comprising a current operating state and an operating state in a future prediction period; determining the operating state of the battery pack according to the state value comprises: taking the state value and the corresponding current operating state, and the state value and a corresponding historical operating state at multiple time points in a preset historical period as samples; training the samples by using a neural network model to obtain a state prediction model of the operating state in the future prediction period; predicting the operating state in the future prediction period according to the state prediction model.

2. The method of claim 1, wherein, determining the current operating state as a fault state in a case where at least one of the state values exceeds a corresponding preset state value range; determining the current operating state as a normal state in a case where none of the state values exceeds the corresponding preset state value range. The neural network model comprises an input layer, an output layer, and one or at least two intermediate layers; the training of the samples by using the neural network model to obtain the state prediction model of the operating state in the future prediction period comprises:

3. The method of claim 1, wherein, adjusting the number of neurons in the intermediate layer to reduce errors in the process of training the samples by using the neural network model to obtain the state prediction model of the operating state in the future prediction period. adjusting the number of neurons in the intermediate layer to reduce errors in the process of training the samples by using the neural network model to obtain the state prediction model of the operating state in the future prediction period comprises:

4. The method of claim 3, wherein, adjusting the number of neurons in the intermediate layer and determining the number of neurons at the time of the minimum error as the final corresponding number of neurons of the intermediate layer to obtain the state prediction model of the operating state in the future prediction period in the process of training the samples by using the neural network model. adjusting the number of neurons in the intermediate layer to reduce errors in the process of training the samples by using the neural network model to obtain the state prediction model of the operating state in the future prediction period comprises:

5. The method of claim 3, wherein, adjusting the number of neurons in the intermediate layer according to the following formula: wherein y is the number of neurons in the intermediate layer, n and m are the number of neurons in the output layer and the input layer respectively, b is a constant value, and k is a variable weight. ； determining the corresponding state value according to the operating state parameter and the determination rule corresponding to the operating state parameter comprises:

6. The method of claim 1, wherein, determining a first state value according to a ratio of the current capacity to a factory capacity of the battery pack, wherein the current capacity and the factory capacity are tested at the same temperature; ​ The current charge-discharge times include a current charge accumulation times and a current discharge accumulation times; a second state value is determined according to a ratio of a sum of the current charge accumulation times and the current discharge accumulation times to a rated charge-discharge times; A third state value is determined according to a ratio of a difference between a variation of an oxygen content and a variation of hydrogen within a first set time period before a current time and the variation of the oxygen content; A fourth state value is determined according to a variation of the internal temperature within a second set time period before the current time; A fifth state value is determined according to a ratio of a deformation of the battery pack at the current time to a factory size of the battery pack.

7. A battery operating state determination system characterized by comprising: Comprise: A running state parameter acquisition module and a processing module; The running state parameter acquisition module is connected with the processing module, and is used to acquire a running state parameter of the battery pack, the running state parameter comprising at least one of a current capacity, a current charge-discharge times, an internal temperature, an internal gas content, and a deformation of the battery pack; The processing module is used to determine a corresponding state value according to the running state parameter acquired from the running state parameter acquisition module and a determination rule corresponding to the running state parameter; The running state of the battery pack is determined according to the state value, the running state comprising a current running state and a running state of a future prediction time period; The running state of the battery pack is determined according to the state value, comprising: Taking the state value and the corresponding current running state, and the state value and a corresponding historical running state of a plurality of time points within a preset historical time period as samples; Training a plurality of the samples by using a neural network model to obtain a state prediction model of the running state of the future prediction time period; The running state of the future prediction time period is predicted according to the state prediction model.

8. The battery pack operating state determination system according to claim 7, characterized by The running state parameter acquisition module comprises at least one of a current capacity acquisition unit, a charge-discharge times acquisition unit, a gas content acquisition unit, an internal temperature acquisition unit, and a deformation acquisition unit; the current capacity acquisition unit, the charge-discharge times acquisition unit, the gas content acquisition unit, the internal temperature acquisition unit, and the deformation acquisition unit are respectively connected with the processing module; The current capacity acquisition unit is used to acquire the current capacity of the battery pack; The charge-discharge times acquisition unit is used to acquire the current charge-discharge times of the battery pack; The gas content acquisition unit is used to acquire the oxygen content and the hydrogen content inside the battery pack; The internal temperature acquisition unit is used to acquire the temperature inside the battery pack; The deformation acquisition unit is used to acquire the current size of the battery pack.

9. The battery pack operating state determination system according to claim 7, characterized by, Further comprise at least one of a communication module, an alarm module, and an input module; The communication module, the alarm module, and the input module are respectively connected with the processing module, and the processing module is used to send a prompt information through the communication module or send an alarm message through the alarm module when the running state is determined to be a fault state. The input module is configured to receive a preset state value range corresponding to the state value, and the processing module is configured to determine that the current running state is a fault state if at least one of the state values exceeds the corresponding preset state value range. In a case where none of the state values exceeds the corresponding preset state value range, the current running state is determined to be a normal state.

Images