CN110927606B - Battery state monitoring method and device - Google Patents

Abstract

Embodiments of the present application provide a battery state monitoring method, apparatus, computer-readable medium, and electronic device. The monitoring method includes: acquiring a first characteristic parameter of a battery; determining a second characteristic parameter of the battery according to the first characteristic parameter of the battery; inputting the first characteristic parameter and/or the second characteristic parameter of the battery The battery state monitoring model trained in advance outputs battery state parameters; based on the battery state parameters, the battery state is monitored. The technical solutions of the embodiments of the present application can enhance the portability of monitoring the battery state in different situations.

Description

Battery state monitoring method and device

technical field

The present application relates to the technical field of power supply monitoring, and in particular, to a battery state monitoring method and device.

Background technique

In a battery status monitoring scenario, such as a UPS battery health monitoring scenario, a special person usually conducts a discharge test on the battery on a regular basis to detect the battery capacity, and the ratio of the actual capacity to the rated capacity is used as a representation of the battery health status, or Online automatic monitoring of battery status, that is, based on a large number of experiments (especially charge and discharge experiments) data, establish corresponding mathematical models or intelligent algorithms, and collect battery data through automatic systems such as battery inspection instruments to evaluate battery health. However, how to enhance the portability of battery state monitoring in different situations is an urgent technical problem to be solved.

SUMMARY OF THE INVENTION

Embodiments of the present application provide a battery state monitoring method, apparatus, computer-readable medium, and electronic device, thereby enhancing the portability of battery state monitoring in different situations at least to a certain extent.

Other features and advantages of the present application will become apparent from the following detailed description, or be learned in part by practice of the present application.

According to an aspect of the embodiments of the present application, a battery state monitoring method is provided, comprising: acquiring a first characteristic parameter of a battery; determining a second characteristic parameter of the battery according to the first characteristic parameter of the battery; The first characteristic parameter and/or the second characteristic parameter of the battery is input into a battery state monitoring model trained in advance, and the battery state parameter is output; based on the battery state parameter, the state of the battery is monitored.

According to an aspect of the embodiments of the present application, a battery state monitoring device is provided, including: an acquisition unit, used for acquiring a first characteristic parameter of the battery; and a determining unit, used for, according to the first characteristic parameter of the battery, determining the second characteristic parameter of the battery; an output unit, used for inputting the first characteristic parameter and/or the second characteristic parameter of the battery into the battery state monitoring model trained in advance, to output the battery state parameter; the monitoring unit, is used to monitor the state of the battery based on the battery state parameter.

In some embodiments of the present application, based on the foregoing solution, the obtaining unit is configured to: obtain the first characteristic parameter of the battery at each moment in history and the decay time interval of the battery in history; the determining unit is configured to: : according to the first characteristic parameter, determine the second characteristic parameter of the battery at each time in history, and determine the battery state of the battery at each time in history according to the decline time interval of the battery in the history; The battery state monitoring device further includes: a model training unit, which is used to train and generate the battery based on the first characteristic parameter and/or the second characteristic parameter of the battery at various times in history and the battery state at various times in history. The battery state monitoring model.

In some embodiments of the present application, based on the foregoing solution, the acquisition unit is configured to: collect initial characteristic parameters of the battery at various moments in history; detect whether the initial characteristic parameters are abnormal; acquire the non-existing abnormality The initial feature parameters of are used as the first feature parameters.

In some embodiments of the present application, based on the foregoing solution, the acquisition unit is configured to: acquire current value and/or voltage value and/or internal resistance value and/or temperature value of the battery at various moments in history.

In some embodiments of the present application, based on the foregoing solution, the first characteristic parameters of the battery at various moments in history include current values of the battery at various moments in history, and the obtaining unit is configured to: The first characteristic parameter, before determining the second characteristic parameter of the battery at each time in history, to detect whether the current value of the battery at each time in history is greater than a predetermined threshold; filtering the time corresponding to the time when the current value is greater than the predetermined threshold the first characteristic parameter of .

In some embodiments of the present application, based on the foregoing solution, the first characteristic parameter of the battery at each time in history includes the voltage value and/or the internal resistance value of the battery at each time in history, and the determining unit configures To: determine the relative voltage value and/or the relative internal resistance value and/or the voltage change value and/or the relative voltage value and/or the relative internal resistance value and/or the voltage change value of the battery at each historical moment according to the voltage value and/or the internal resistance value of the battery at each historical moment Internal resistance change value and/or voltage gradient value and/or internal resistance gradient value and/or voltage-to-resistance ratio.

In some embodiments of the present application, based on the foregoing solution, the obtaining unit is configured to: determine a first moment when the battery meets a fault replacement condition and a second moment when the battery is replaced; determine that the battery enters a fault The performance degradation time experienced before the state; according to the first moment and the second moment, and the performance degradation time experienced before the battery enters the fault state, determine the historical degradation time interval of the battery.

In some embodiments of the present application, based on the foregoing solution, the determining unit is configured to: determine the battery state at each moment in the decay time interval as an early warning state; The state of the battery at each moment in the system is determined as the healthy state.

In some embodiments of the present application, based on the foregoing solution, the determining unit is configured to: determine sub-decay time intervals within the decay time interval, and the battery has different degradation degrees in different sub-decay time intervals; The degradation degree of the battery in different sub-decay time intervals is determined, and the warning state level of the battery in the different sub-decay time intervals is determined.

According to an aspect of the embodiments of the present application, a computer-readable medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, implements the battery state monitoring method described in the foregoing embodiments.

According to an aspect of the embodiments of the present application, an electronic device is provided, including: one or more processors; and a storage device for storing one or more programs, when the one or more programs are stored by the one or more programs When executed by multiple processors, the one or more processors are made to implement the battery state monitoring method as described in the above embodiments.

In the technical solutions provided by some embodiments of the present application, the first characteristic parameter of the battery and the second characteristic parameter determined by the first characteristic parameter are used as input data, and the battery state monitoring model is output through the pre-training The battery state parameter, and the battery state is further monitored by the battery state parameter. Because the technical solution of the present application does not need to establish a fixed evaluation model in advance, but obtains the battery state monitoring model through battery historical data training, it is not limited to a specific battery model or usage scenario, so the present application The portability of the technical solution is strong. In addition, the technical solution of the present application realizes the automation of the whole process of battery state monitoring, online monitoring and processing of data, without the need to manually establish a fixed mathematical model, which greatly saves the labor cost of on-site and technical investment.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not limiting of the present application.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description serve to explain the principles of the application. Obviously, the drawings in the following description are only some embodiments of the present application, and for those of ordinary skill in the art, other drawings can also be obtained from these drawings without creative effort. In the attached image:

FIG. 1 shows a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of the present application can be applied;

FIG. 2 shows a flowchart of a battery state monitoring method according to an embodiment of the present application;

FIG. 3 shows a detailed flow chart of obtaining the battery state monitoring model according to an embodiment of the present application;

FIG. 4 shows a flowchart of acquiring the first characteristic parameters of the battery at various moments in history according to an embodiment of the present application;

FIG. 5 shows a detailed flowchart of acquiring the first characteristic parameters of the battery at various moments in history according to an embodiment of the present application;

FIG. 6 shows a flow chart of the method before determining the second characteristic parameter of the battery at various moments in history according to an embodiment of the present application;

FIG. 7 shows a detailed flow chart of obtaining the historical decay time interval of a battery according to an embodiment of the present application;

FIG. 8 shows a detailed flow chart of determining the battery state of the battery at various moments in history according to an embodiment of the present application;

FIG. 9 shows a detailed flowchart of determining the battery state at each moment in the decay time interval as an early warning state according to an embodiment of the present application;

FIG. 10 shows a schematic diagram of a supervised learning method according to an embodiment of the present application;

FIG. 11 shows a schematic diagram of a scenario of a battery state monitoring method according to an embodiment of the present application;

FIG. 12 shows a block diagram of a battery state monitoring device according to an embodiment of the present application;

FIG. 13 shows a schematic structural diagram of a computer system suitable for implementing the electronic device according to the embodiment of the present application.

Detailed ways

Example embodiments will now be described more fully with reference to the accompanying drawings. Example embodiments, however, can be embodied in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be thorough and complete, and will fully convey the concept of example embodiments to those skilled in the art.

Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided in order to give a thorough understanding of the embodiments of the present application. However, those skilled in the art will appreciate that the technical solutions of the present application may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be employed. In other instances, well-known methods, devices, implementations, or operations have not been shown or described in detail to avoid obscuring aspects of the present application.

The block diagrams shown in the figures are merely functional entities and do not necessarily necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices entity.

The flowcharts shown in the figures are only exemplary illustrations and do not necessarily include all contents and operations/steps, nor do they have to be performed in the order described. For example, some operations/steps can be decomposed, and some operations/steps can be combined or partially combined, so the actual execution order may be changed according to the actual situation.

FIG. 1 shows a schematic diagram of an exemplary system architecture to which the technical solutions of the embodiments of the present application can be applied.

As shown in FIG. 1, the system architecture may include terminal devices (one or more of a smartphone 101, a tablet computer 102, and a portable computer 103 as shown in FIG. 1, and of course it can also be a desktop computer, etc.) or devices, Network 104 and Server 105. The network 104 is the medium used to provide the communication link between the terminal device and the server 105 . The network 104 may include various connection types, such as wired communication links, wireless communication links, and the like.

It should be understood that the numbers of terminal devices, networks and servers in FIG. 1 are merely illustrative. There can be any number of terminal devices, networks and servers according to implementation needs. For example, the server 105 may be a server cluster composed of multiple servers, or the like.

In one embodiment of the present application, the battery status can be monitored remotely. For example, the battery installed in the server 105 may be remotely monitored through a terminal device such as a smartphone 101 as shown in FIG. 1 . Specifically, the first characteristic data of the battery in the server 105 may be acquired by the data acquisition device in the server 105 , the first characteristic data of the battery in the server 105 may be acquired by the smartphone 101 , and the second characteristic data may be determined according to the first characteristic data. , and further, input the first characteristic parameter and/or the second characteristic parameter of the battery into the battery state monitoring model set in the smart phone 101, and then output the battery state parameter capable of monitoring the battery state.

In an embodiment of the present application, the battery state may also be monitored locally. For example, the battery installed in the device may be locally monitored by a monitoring device provided in the device, and the monitoring device is provided with a battery state monitoring model.

It should be noted that the battery state monitoring method provided by the embodiment of the present application is generally executed by the server 105 , and accordingly, the battery state monitoring device is generally set in the server 105 . However, in other embodiments of the present application, the terminal device may also have similar functions to the server, so as to execute the battery state monitoring solution provided by the embodiments of the present application.

The implementation details of the technical solutions of the embodiments of the present application are described in detail below:

According to a first aspect of the present disclosure, a battery state monitoring method is provided.

Referring to FIG. 2 , a flowchart of a battery state monitoring method according to an embodiment of the present application is shown. The battery state monitoring method may be executed by a device with a computing processing function, such as the server 105 shown in FIG. 1 . to be executed, or executed by a terminal device as shown in FIG. 3 . As shown in FIG. 2 , the battery state monitoring method includes at least steps 310 to 370:

Step 310, acquiring the first characteristic parameter of the battery.

Step 330: Determine the second characteristic parameter of the battery according to the first characteristic parameter of the battery.

Step 350: Input the first characteristic parameter and/or the second characteristic parameter of the battery into the battery state monitoring model trained in advance, and output the battery state parameter.

Step 370 , monitor the state of the battery based on the battery state parameter.

The above implementation steps will be described in detail below:

In step 310, a first characteristic parameter of the battery is obtained.

It should be noted that the acquired first characteristic parameter of the battery is mainly used to monitor the state of the battery in real time, therefore, the acquired first characteristic parameter refers to the real-time first characteristic parameter.

In the present application, the battery may include a single battery, wherein a single battery corresponds to one or a set of first characteristic parameters, and the set of first characteristic parameters includes a plurality of first characteristic parameters.

In the present application, the battery may also comprise a group of single cells. It should be noted that a group of single cells includes multiple single cells, and it should be understood that multiple single cells should correspond to multiple or multiple sets of first characteristic parameters.

In an embodiment of the present application, the obtaining of the first characteristic parameter of the battery may be implemented in the following manner:

First, the initial characteristic parameters of the battery are collected by the collection device. Then, it is detected whether the initial feature parameter is abnormal. Finally, the initial characteristic parameter without abnormality is obtained as the first characteristic parameter.

In a specific implementation of an embodiment, the initial characteristic parameters of the collected battery may include at least one of the following:

The first is to collect the real-time current value of the battery.

The second is to collect the real-time voltage value of the battery.

The third is to collect the real-time internal resistance value of the battery.

Fourth, collect the real-time temperature value of the battery.

In an embodiment of the present application, the battery may refer to a UPS battery, and the collected initial battery characteristic parameters refer to a current value and/or a voltage value and/or an internal resistance value when the UPS battery is in a floating state and/or temperature values.

It should be explained that the battery floating charge refers to a supply (discharge) working method of the battery pack, that is, the system connects the battery and the power line to the load circuit in parallel, and its voltage is generally constant, only slightly Higher than the terminal voltage of the battery, a small amount of current supplied by the power supply line compensates for the loss of the local action of the battery, so that it can always be kept in a fully charged state without overcharging. Therefore, the battery can be charged and discharged as the power line voltage fluctuates up and down. When the load is light and the power line voltage is high, the battery is charged, and when the load is heavy or the power supply is interrupted unexpectedly, the battery is discharged to share some or all of the load. In this way, the battery acts as a voltage regulator and is on standby.

In an embodiment of the present application, the abnormality of the initial feature parameter may refer to a situation that the initial feature parameter is too large or too small, or may refer to a situation that the initial feature parameter is missing.

It should be noted that, in this application, if the initial characteristic parameters of the battery refer to a set of initial characteristic parameters, that is, including a plurality of initial characteristic parameters, then when an initial characteristic parameter in the set of initial characteristic parameters appears When abnormal, it is considered that the set of initial feature parameters is abnormal, therefore, the set of initial feature parameters will not be acquired.

For example, the initial characteristic parameters of the battery include current value, voltage value, internal resistance value and temperature value. If the current value is missing, even if the voltage value, internal resistance value and temperature value of the battery are normal, they will not be acquired as the first characteristic parameter.

Continuing to refer to FIG. 2 , in step 330 , the second characteristic parameter of the battery is determined according to the first characteristic parameter of the battery.

In an embodiment of the present application, the first characteristic parameter of the battery includes a current value, and before determining the second characteristic parameter of the battery according to the first characteristic parameter, the method further includes: detecting the Whether the current value of the battery is greater than a predetermined threshold value; filtering the corresponding first characteristic parameter whose current value is greater than the predetermined threshold value.

Specifically, for example, the first characteristic parameter of the battery includes a current value, a voltage value, an internal resistance value, and a temperature value. If the current value is greater than a predetermined threshold, the first characteristic parameters including the current value, voltage value, internal resistance value and temperature value will be filtered.

In an embodiment of the present application, the first characteristic parameter of the battery may include at least one of a battery voltage value and a battery internal resistance value, and the second characteristic parameter of the battery is determined according to the first characteristic parameter , including at least one of the following methods:

First, according to the voltage value of the battery, determine the relative voltage value of the battery.

Second, according to the voltage value of the battery, determine the voltage change value of the battery.

The third method is to determine the voltage gradient value of the battery according to the voltage value of the battery.

Fourth, the relative internal resistance value of the battery is determined according to the internal resistance value of the battery.

Fifth, according to the internal resistance value of the battery, determine the change value of the internal resistance of the battery.

Sixth, according to the internal resistance value of the battery, determine the internal resistance gradient value of the battery.

Seventh, according to the voltage value and the internal resistance value of the battery, determine the voltage and internal resistance ratio of the battery.

As described above, it can be understood that the manner of determining the second characteristic parameter of the battery according to the first characteristic parameter may be arbitrary, and is not limited to those shown above.

Continuing to refer to FIG. 2 , in step 350 , the first characteristic parameter and/or the second characteristic parameter of the battery is input into the battery state monitoring model trained in advance, and the battery state parameter is output.

In an embodiment of the present application, the battery state monitoring model can be obtained by the method shown in FIG. 3 .

Referring to FIG. 3, a detailed flowchart of the method for obtaining the battery state monitoring model according to an embodiment of the present application is shown, which may specifically include steps 3530 to 3570:

Step 3530: Acquire first characteristic parameters of the battery at various times in history, so as to determine second characteristic parameters of the battery at various times in history according to the first characteristic parameters.

In a specific implementation of an embodiment, the acquiring the first characteristic parameter of the battery at each moment in history may be implemented through the steps shown in FIG. 4 .

Referring to FIG. 4 , a detailed flowchart of obtaining the battery state monitoring model according to an embodiment of the present application is shown, which may specifically include steps 3531 to 3533:

Step 3531: Collect initial characteristic parameters of the battery at various moments in history.

It should be noted that the initial feature parameter may be an initial feature parameter, or may be a set of initial feature parameters, wherein a set of initial feature parameters may include multiple initial feature parameters.

In the present application, before training the battery state monitoring model, the initial characteristic parameters of the battery cells can be collected in real time through sensors and the data can be saved. For those skilled in the art, it should be understood that the collection of the initial characteristic parameters needs to be performed for a long enough time and continuously, so that the initial characteristic parameters of the battery at various moments in history can be collected. It should also be understood that the time interval between each adjacent moment in the history may be arbitrary, for example, it may be 1 second or 1 minute. If the time interval between each adjacent time in the history is 1 second, then within 1 hour, 60×60 or 60×60 groups of initial characteristic parameters of the batteries should be collected.

In this application, the battery may be a battery, that is, a single battery, or a group of batteries, that is, a plurality of single batteries. For example, the battery includes multiple single cells, and at each moment, multiple or multiple sets of initial characteristic parameters should be collected. For example, if the battery includes 10 single cells, and the time interval between each adjacent moment in the history is 1 second, then within 1 hour, 10×60×60 or 10×60 cells should be collected. The initial characteristic parameters of the 60×60 group of the batteries.

Specifically, the initial characteristic parameters of the collection battery at each moment in history may include at least one of the following:

The first method is to collect the current value of the battery at each moment in history.

The second is to collect the voltage values of the battery at various moments in history.

The third method is to collect the internal resistance value of the battery at each moment in history.

Fourth, collect the temperature values of the battery at various moments in history.

Step 3532: Detect whether the initial feature parameter is abnormal.

Step 3533: Obtain the initial characteristic parameter without abnormality as the first characteristic parameter.

In a specific implementation of an embodiment, the collected initial characteristic parameters of the battery at various moments in history include a set of initial characteristic parameters including the current value, voltage value, internal resistance value, and temperature value of the battery. The detecting whether there is an abnormality in the initial characteristic parameter, and acquiring the initial characteristic parameter without the abnormality as the first characteristic parameter, may be implemented through the process shown in FIG. 5 .

Referring to FIG. 5 , it shows a detailed flow chart of acquiring the first characteristic parameters of the battery at various moments in history according to an embodiment of the present application, and the specific contents are as follows:

First, input a set of initial characteristic parameters including the current value, voltage value, internal resistance value and temperature value of the battery. Secondly, check whether the voltage value, current value, internal resistance value and temperature value of the battery are abnormal or missing in turn. If there is one, discard this group of initial characteristic parameters, and if none of them exist, output this group of initial characteristic parameters as the first characteristic parameter.

In the present application, it is more preferable that the acquired data samples of the first characteristic parameter of the battery may be sufficient.

The advantage of the specific implementation in the above embodiment is that because the data collected on site is usually not completely reliable, abnormal sensor readings often occur. When a characteristic parameter (such as a voltage value) of a single battery exceeds a set threshold at a certain time, it is determined that the value is "abnormal". In addition, there is also a certain packet loss rate in the data transmission process, resulting in missing data, that is, the stored value of a certain characteristic parameter (such as a voltage value) at a certain moment is a null value. Therefore, by detecting the initial feature parameters to clean the data, it can be ensured that the sample data used for model training is reasonable.

In a specific implementation of an embodiment, the first characteristic parameter of the battery at each time in history includes the current value of the battery at each time in the history, and according to the first characteristic parameter, it is determined that the battery is in the history Before the second characteristic parameter at each moment, the method steps shown in FIG. 6 may also be implemented.

Referring to FIG. 6 , it shows a flowchart of the method before determining the second characteristic parameter of the battery at various moments in history according to an embodiment of the present application, which may specifically include steps 3511 to 3512:

Step 3511: Detect whether the current value of the battery at each moment in history is greater than a predetermined threshold.

Step 3512: Filter the first characteristic parameter corresponding to the moment when the current value is greater than a predetermined threshold.

Specifically, the predetermined threshold value of the current value can be set according to the actual situation, for example, it can be set to 2A (ampere) or 3A (ampere).

The advantage of the specific implementation in the above embodiment is that by detecting whether the current value of the battery at each time in history is greater than a predetermined threshold, it can be determined whether the battery corresponding to the time is in a floating state. In the present application, acquiring the first characteristic data of the battery in the floating state is conducive to training a more applicable battery state monitoring model.

In a specific implementation of an embodiment, the first characteristic parameter of the battery at each time in history includes at least the voltage value of the battery at each time in history and the internal resistance value of the battery at each time in history. One, determining the second characteristic parameter of the battery at each moment in history according to the first characteristic parameter, including at least one of the following methods:

The first is to determine the relative voltage value of the battery at each time in history according to the voltage value of the battery at each time in history.

Specifically, the relative voltage value of the battery at each moment in history can be obtained according to the following formula:

Wherein, RV _i ^t represents the relative voltage value of the ith single cell in the battery (battery pack) at time t in history, and V _i ^t represents the ith single cell in the battery (battery pack) at The voltage value at time t in history, G represents the number of single cells in the battery (battery pack).

Second, according to the voltage value of the battery at each time in history, determine the voltage change value of the battery at each time in history.

Specifically, the voltage change value of the battery at each moment in history can be obtained according to the following formula:

表示单体电池在历史上t时刻的电压值相对于t-T_change至t-T_change+interval时间区间内平均电压值的变化值；V_i ^t表示所述电池(电池组)中第i个单体电池在历史上的t时刻的电压值；interval表示在t-T_change至t-T_change+interval时间区间内时刻的个数。in,

Represents the change value of the voltage value of the single battery at time t in the history relative to the average voltage value in the time interval from tT _change to tT _change +interval; V _i ^t represents the i-th single battery in the battery (battery pack) at The voltage value at time t in history; interval represents the number of times in the time interval from tT _change to tT _change +interval.

The third method is to determine the voltage gradient value of the battery at each time in the history according to the voltage value of the battery at each time in the history.

Specifically, the voltage gradient values of the battery at various moments in history can be obtained according to the following calculation process:

用于表示单体电池在不同时刻的电压，

用于表示在不同时刻的时间轴，那么电压梯度

就是指在t-T_grad至t的时间区间内单体电池电压的最小二乘线性拟合的斜率。In this application, it is assumed that

Used to represent the voltage of a single battery at different times,

used to represent the time axis at different times, then the voltage gradient

It refers to the slope of the least squares linear fitting of the single cell voltage in the time interval from tT _grad to t.

Specifically, the least squares linear fitting refers to finding two real numbers a ₀ and a ₁ such that the following formula is minimized:

Among them, a ₁ is the voltage gradient at time t

Fourth, according to the internal resistance value of the battery at each time in history, determine the relative internal resistance value of the battery at each time in history.

Specifically, the relative internal resistance value of the battery at each moment in history can be obtained according to the following formula:

表示所述电池(电池组)中第i个单体电池在历史上的t时刻的相对内阻值、

表示所述电池(电池组)中第i个单体电池在历史上的t时刻的内阻值、G表示所述电池(电池组)中单体电池的数量。in,

Represents the relative internal resistance value of the i-th single cell in the battery (battery pack) at time t in history,

represents the internal resistance value of the i-th single cell in the battery (battery pack) at time t in history, and G represents the number of single cells in the battery (battery pack).

Fifth, according to the internal resistance value of the battery at each time in the history, determine the change value of the internal resistance of the battery at each time in the history.

Specifically, the change value of the internal resistance of the battery at each moment in history can be obtained according to the following formula:

表示单体电池在历史上t时刻的内阻值相对于t-T_change至t-T_change+interval时间区间内的平均内阻值的变化值；

表示所述电池(电池组)中第i个单体电池在历史上的t时刻的内阻值；interval表示在t-T_change至t-T_change+interval时间区间内时刻的个数。in,

Represents the change value of the internal resistance value of the single battery at time t in history relative to the average internal resistance value in the time interval from tT _change to tT _change +interval;

Represents the internal resistance value of the i-th single cell in the battery (battery pack) at time t in history; interval represents the number of times in the time interval from tT _change to tT _change +interval.

Sixth, according to the internal resistance value of the battery at each historical moment, determine the internal resistance gradient value of the battery at each historical moment.

Specifically, the internal resistance gradient values of the battery at various moments in history can be obtained according to the following calculation process:

用于表示单体电池在不同时刻的内阻，

用于表示在不同时刻的时间轴，那么内阻梯度

就是指在t-T_grad至t的时间区间内单体电池内阻的最小二乘线性拟合的斜率。In this application, it is assumed that

Used to represent the internal resistance of a single battery at different times,

Used to represent the time axis at different times, then the internal resistance gradient

It refers to the slope of the least squares linear fitting of the internal resistance of the single cell in the time interval from tT _grad to t.

Specifically, the least squares linear fitting refers to finding two real numbers a ₀ and a ₁ such that the following formula is minimized:

Among them, a ₁ is the internal resistance gradient at time t

Seventh, according to the voltage value and the internal resistance value of the battery at each time in the history, determine the voltage-to-internal resistance ratio of the battery at each time in the history.

Specifically, the voltage-to-internal resistance ratio refers to the ratio between the voltage value of the single cell and the internal resistance value of the single cell, that is:

As described above, it can be understood that the manner of determining the second characteristic parameter of the battery at each moment in history according to the first characteristic parameter may be arbitrary, and is not limited to those shown above.

Step 3550: Acquire the historical decay time interval of the battery, so as to determine the battery state of the battery at each historical moment in the history according to the historical decay time interval of the battery.

In a specific implementation of an embodiment, the acquisition of the historical decay time interval of the battery may be implemented through the steps shown in FIG. 7 .

Referring to FIG. 7 , it shows a detailed flow chart of acquiring the historical decay time interval of a battery according to an embodiment of the present application, which may specifically include steps 3551 to 3553:

Step 3551: Determine the first moment when the battery meets the fault replacement condition and the second moment when the battery is replaced.

Step 3552: Determine the performance degradation time experienced by the battery before the battery enters the fault state.

Step 3553 determines the historical decay time interval of the battery according to the first time and the second time, and the performance degradation time experienced before the battery enters the fault state.

In the present application, the battery generally goes through a period from normal operation to failure, from failure to replacement, and from replacement to normal operation. Therefore, in the specific implementation of the above embodiment, a period of time before the first moment when the battery satisfies the fault replacement condition and the time interval between the first moment and the second moment when the battery is replaced can be regarded as decay. time interval.

In a specific implementation of an embodiment, the determination of the battery state of the battery at each historical moment according to the historical decay time interval of the battery may be achieved through the steps shown in FIG. 8 .

Referring to FIG. 8 , it shows a detailed flowchart of determining the battery state of the battery at various moments in history according to an embodiment of the present application, which may specifically include steps 3554 to 3555:

Step 3554: Determine the battery state at each moment in the decay time interval as an early warning state.

Step 3555: Determine the battery state at each moment in the time interval other than the decay time interval as the healthy state.

Specifically, in the specific implementation of this embodiment, the state of the battery at different times can be marked in the form of labels, and the specific labeling rules can be:

First, according to the acquired data, determine the first time t ₁ when the battery meets the fault replacement condition, the second time t ₂ when the battery is replaced, and the time t ₃ when the battery data is stable after the replacement. Then, each time point of the battery in the time interval from t ₁ -T _decay to t ₂ is marked as a "warning" state label. Finally, the time interval of the battery before time t ₁ -T _decay -1 and the time interval of the battery after time t ₃ are marked as "healthy" state labels.

It should be noted that the T _decay in the above can be used to describe the performance decay time experienced by the battery before entering the fault state, which can be determined according to the experience of on-site experts.

In a specific implementation of an embodiment, determining the battery state at each moment in the decay time interval as an early warning state may be implemented through the steps shown in FIG. 9 .

Referring to FIG. 9, it shows a detailed flowchart of determining the battery state at each moment in the decay time interval as an early warning state according to an embodiment of the present application, which may specifically include steps 35541 to 35542:

Step 35541: Determine sub-decay time intervals within the decay time interval, and the battery has different degradation degrees in different sub-decay time intervals.

Step 35542: Determine the warning state level of the battery in different sub-decay time intervals according to the degradation degrees of the battery in different sub-decay time intervals.

It can be understood that, in the specific implementation of this embodiment, the warning state of the battery in the decay time interval can be measured in more detail through the warning state level. In the present application, it can be considered that the higher the warning state level, the higher the probability that the battery is unhealthy, that is, the more urgent the warning state is. Specifically, for example, the warning state can be divided into four levels of "1, 2, 3, and 4", and the decay time interval can be divided into four sub-intervals, wherein, for the distance from the second moment when the battery is replaced In the sub-interval that is closer to t ₂ , the probability that the battery is considered to be in an unhealthy state in this sub-interval is higher, that is, the higher the warning state level is.

Step 3570: Train and generate the battery state monitoring model based on the first characteristic parameter and/or the second characteristic parameter of the battery at each time in history and the battery state at each time in history.

In order to facilitate training to generate the battery state monitoring model, in the specific implementation of the above embodiment, different parameters may be assigned to different states of the battery, wherein the parameters may be used to represent the unhealthy state of the battery. Expected probability value. For example, the "health" state label of the battery may be assigned an expected probability value of less than 50%, the "warning" state label of the battery may be assigned an expected probability value greater than 50% and less than 100%, and further, the expected probability value may be assigned to The "level 1 warning" status label of the battery is assigned an expected probability value greater than 50% and less than 70%, and the "level 4 warning" status label of the battery can be assigned an expected probability value greater than 90% and less than 100%. In an embodiment of the present application, a supervised learning model may be used as an initial model to train and generate the battery state monitoring model.

Referring to FIG. 10, a schematic diagram of a supervised learning method according to an embodiment of the present application is shown.

As shown in Figure 10, supervised learning is a common method in machine learning, where each training sample consists of an "input vector" and a corresponding "expected output". Based on these "input-output pairs" and with the help of certain algorithms, a pattern (function) that maps inputs to outputs can be built, and new instances can be inferred from this pattern.

使得损失函数

最小化，其中X＝(x₁,x₂,……)是输入空间，Y＝(y₁,y₂,……)是输入空间对应的真实输出，

是函数g的输出空间。有监督学习方法循环地执行优化算法，更新模型参数以更改函数g的表示，使得损失函数

不断减小，直到达到某个事先指定的条件。In a formal language, the training set consisting of N samples is {(x ₁ , y ₁ ), ..., (x _N , y _N )}, where x _i is the "feature" of the ith sample. vector" (i.e. input vector), _yi is the "label" (i.e. expected output value, ) of the ith sample. Supervised learning methods try to find a function g:

make the loss function

Minimize, where X=(x ₁ , x ₂ ,...) is the input space, Y=(y ₁ , y ₂ ,...) is the real output corresponding to the input space,

is the output space of function g. Supervised learning methods iteratively execute the optimization algorithm, updating the model parameters to change the representation of the function g such that the loss function

It keeps decreasing until some pre-specified condition is reached.

In an embodiment of the present application, the input of the model is the first characteristic parameter and/or the second characteristic parameter, and the output is the predicted probability value of the training sample state being "warning". During the training process, the model continuously updates the parameters through a certain optimization algorithm to reduce the error between the predicted probability value and the expected probability value, until a certain set condition is met, the training is completed, and the battery state monitoring model is generated .

In other embodiments of the present application, the initial model used to train the battery state monitoring model may also be a support vector machine-based model such as SVM, or a linear regression-based model such as LR, or logistic regression, or Naive Bayesian model, or LDA and other linear discriminant analysis-based models, or GBDT and other decision tree-based models, or ANN and other neural network-based models, or KNN and other distance metric-based models, or Hybrid or improved versions of the above models.

Finally, in step 350, the first characteristic parameter and/or the second characteristic parameter of the battery are input into the battery state monitoring model generated by the above-mentioned process training in advance, and the battery state parameter, that is, the predicted probability value that meets the error requirement, is output. .

Continuing to refer to FIG. 2, in step 370, the state of the battery is monitored based on the battery state parameter.

Specifically, the state of the battery can be monitored according to the output battery state parameter. For example, in the aforementioned embodiment, if the output battery state parameter (predicted probability value) is greater than 90% and less than 100% of the predicted probability value, it means that the battery is in a "level 4 warning" state.

It should be noted that the meaning of the expected probability value/predicted probability value as described above is to measure the possibility of the battery being in an unhealthy state. When the probability value exceeds a threshold, that is, when the possibility of the battery being in an unhealthy state exceeds a certain degree, it can be considered that the battery enters a "warning" state and needs to be warned, for example, when the expected probability value of the battery is greater than When 90% is less than 100%, the battery needs to be alerted by level 4.

In order to make those skilled in the art better understand the present invention, the technical solutions of the present application will be described below with specific scene embodiments:

FIG. 11 is a schematic diagram of a scenario of a battery state monitoring method according to an embodiment of the present application.

As shown in the figure, first, the control center in the scene collects the initial characteristic data of the UPS battery installed in the database through the acquisition module, and the processing module and the extraction module are used to process and extract the initial characteristic parameters to obtain the first characteristic parameter. On the one hand, the first feature parameter in history can be further processed to obtain the 10-dimensional feature parameter of the battery and the state label corresponding to the 10-dimensional feature parameter, which is used to train the supervised learning model and obtain the battery state monitoring set in the detection module. Model. On the other hand, the real-time first characteristic parameter is further processed to obtain the real-time 10-dimensional characteristic parameter of the battery, and the real-time 10-dimensional characteristic parameter of the battery is input into the battery state monitoring model set in the detection module, then Real-time battery status parameters can be obtained, thereby realizing real-time monitoring of the battery,

The advantages of this scenario embodiment are:

economical. The invention realizes the automation of the whole process, online monitoring and processing of data, does not need to manually establish a mathematical model, and greatly saves the labor cost invested in the field and technology.

practicality. The invention only uses the voltage, internal resistance and temperature of the battery in the floating state to evaluate the health degree, which is in line with the actual situation that the on-site charging and discharging time accounts for a small proportion and the data acquisition dimension is low, and is suitable for most batteries including UPS batteries. Usage scenarios of energy storage batteries

portability. The present invention does not establish an evaluation model in advance, but learns from the collected battery historical data, and is not limited to a specific battery model or usage scenario.

reliability. The invention adopts a supervised learning method to perform data mining, and labels the training set according to expert experience, thereby ensuring the accuracy of the final model.

Convenience. The present invention does not require additional installation of other equipment, the on-site battery inspection instrument is used as the acquisition module, and other modules are implemented in the computer of the control center.

In the technical solutions provided by some embodiments of the present application, the first characteristic parameter of the battery and the second characteristic parameter determined by the first characteristic parameter are used as input data, and the battery state monitoring model is output through the pre-training The battery state parameter, and the battery state is further monitored by the battery state parameter. Because the technical solution of the present application does not need to establish a fixed evaluation model in advance, but obtains the battery state monitoring model through battery historical data training, it is not limited to a specific battery model or usage scenario, so the present application The portability of the technical solution is strong. In addition, the technical solution of the present application realizes the automation of the whole process of battery state monitoring, online monitoring and processing of data, without the need to manually establish a fixed mathematical model, which greatly saves the labor cost of on-site and technical investment.

The following describes the device embodiments of the present application, which can be used to execute the battery state monitoring method in the above-mentioned embodiments of the present application. For details not disclosed in the device embodiments of the present application, please refer to the above-mentioned embodiments of the battery state monitoring method of the present application.

FIG. 12 shows a block diagram of a battery state monitoring apparatus according to an embodiment of the present application.

Referring to FIG. 12 , a battery state monitoring device 1200 according to an embodiment of the present application includes an acquisition unit 1201 , a determination unit 1202 , an output unit 1203 and a monitoring unit 1204 .

The acquiring unit 1201 is used to acquire the first characteristic parameter of the battery; the determining unit 1202 is used to determine the second characteristic parameter of the battery according to the first characteristic parameter of the battery; and the output unit 1203 is used to determine the second characteristic parameter of the battery for inputting the first characteristic parameter and/or the second characteristic parameter of the battery into the battery state monitoring model trained in advance to output the battery state parameter; the monitoring unit 1204 is used for monitoring the battery based on the battery state parameter status.

In some embodiments of the present application, based on the foregoing solution, the obtaining unit 1201 is configured to: obtain the first characteristic parameter of the battery at each moment in history and the decay time interval of the battery in the history; the determining unit 1202 is configured to: determine the second characteristic parameter of the battery at each moment in history according to the first characteristic parameter, and determine the battery of the battery at each moment in history according to the decay time interval of the battery in the history state; the battery state monitoring device further includes: a model training unit, which is used for, based on the first characteristic parameter and/or the second characteristic parameter of the battery at various moments in history, and the battery state at various moments in history, Train and generate the battery state monitoring model.

In some embodiments of the present application, based on the foregoing solution, the acquisition unit 1201 is configured to: collect initial characteristic parameters of the battery at various moments in history; detect whether the initial characteristic parameters are abnormal; acquire the non-existence The abnormal initial feature parameter is used as the first feature parameter.

In some embodiments of the present application, based on the foregoing solution, the acquiring unit 1201 is configured to: acquire the current value and/or the voltage value and/or the internal resistance value and/or the temperature value of the battery at various moments in history.

In some embodiments of the present application, based on the foregoing solution, the first characteristic parameter of the battery at each time in history includes the current value of the battery at each time in history, and the obtaining unit 1201 is configured to: the first characteristic parameter, before determining the second characteristic parameter of the battery at each time in history, detecting whether the current value of the battery at each time in history is greater than a predetermined threshold; filtering the time when the current value is greater than the predetermined threshold The corresponding first characteristic parameter.

In some embodiments of the present application, based on the foregoing solution, the first characteristic parameter of the battery at each time in history includes the voltage value and/or the internal resistance value of the battery at each time in history, and the determining unit 1202 be configured to: determine the relative voltage value and/or the relative internal resistance value and/or the voltage change value and/or the relative voltage value and/or the relative internal resistance value and/or the voltage change value of the battery at each historical moment according to the voltage value and/or the internal resistance value of the battery at each historical moment Or internal resistance change value and/or voltage gradient value and/or internal resistance gradient value and/or voltage internal resistance ratio.

In some embodiments of the present application, based on the foregoing solution, the obtaining unit 1201 is configured to: determine a first moment when the battery satisfies the fault replacement condition and a second moment when the battery is replaced; determine that the battery enters the The performance degradation time experienced before the failure state; the historical degradation time interval of the battery is determined according to the first time and the second time, and the performance degradation time experienced before the battery enters the failure state.

In some embodiments of the present application, based on the foregoing solution, the determining unit 1202 is configured to: determine the battery state at each moment in the decay time interval as an early warning state; The battery state at each moment in the interval is determined as the healthy state.

In some embodiments of the present application, based on the foregoing solution, the determining unit 1202 is configured to: determine sub-decay time intervals within the decay time interval, and the battery has different degradation degrees in different sub-decay time intervals; The degradation degree of the battery in different sub-decay time intervals determines the warning state level of the battery in different sub-decay time intervals.

FIG. 13 shows a schematic structural diagram of a computer system suitable for implementing the electronic device according to the embodiment of the present application.

It should be noted that the computer system 1300 of the electronic device shown in FIG. 13 is only an example, and should not impose any limitations on the functions and scope of use of the embodiments of the present application.

As shown in FIG. 13 , the computer system 1300 includes a central processing unit (Central Processing Unit, CPU) 1301, which can be loaded into a random device according to a program stored in a read-only memory (Read-Only Memory, ROM) 1302 or from a storage part 1308 A program in a random access memory (RAM) 1303 is accessed to perform various appropriate actions and processes, for example, the methods described in the above embodiments are performed. In the RAM 1303, various programs and data necessary for system operation are also stored. The CPU 1301 , the ROM 1302 , and the RAM 1303 are connected to each other through a bus 1304 . An Input/Output (I/O) interface 1305 is also connected to the bus 1304 .

The following components are connected to the I/O interface 1305: an input section 1306 including a keyboard, a mouse, etc.; an output section 1307 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc. ; a storage section 1308 including a hard disk and the like; and a communication section 1309 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication section 1309 performs communication processing via a network such as the Internet. Drivers 1310 are also connected to I/O interface 1305 as needed. A removable medium 1311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 1310 as needed so that a computer program read therefrom is installed into the storage section 1308 as needed.

In particular, according to embodiments of the present application, the processes described above with reference to the flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method illustrated in the flowchart. In such an embodiment, the computer program may be downloaded and installed from the network via the communication portion 1309, and/or installed from the removable medium 1311. When the computer program is executed by the central processing unit (CPU) 1301, various functions defined in the system of the present application are executed.

It should be noted that the computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples of computer readable storage media may include, but are not limited to, electrical connections with one or more wires, portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), erasable Erasable Programmable Read Only Memory (EPROM), flash memory, optical fiber, portable Compact Disc Read-Only Memory (CD-ROM), optical storage device, magnetic storage device, or any suitable of the above The combination. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code therein. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device . Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination of the foregoing.

The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Wherein, each block in the flowchart or block diagram may represent a module, program segment, or part of code, and the above-mentioned module, program segment, or part of code contains one or more executables for realizing the specified logical function instruction. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams or flowchart illustrations, and combinations of blocks in the block diagrams or flowchart illustrations, can be implemented in special purpose hardware-based systems that perform the specified functions or operations, or can be implemented using A combination of dedicated hardware and computer instructions is implemented.

The units involved in the embodiments of the present application may be implemented in software or hardware, and the described units may also be provided in a processor. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances.

As another aspect, the present application also provides a computer-readable medium. The computer-readable medium may be included in the electronic device described in the above embodiments; it may also exist alone without being assembled into the electronic device. middle. The above-mentioned computer-readable medium carries one or more programs, and when the above-mentioned one or more programs are executed by an electronic device, enables the electronic device to implement the methods described in the above-mentioned embodiments.

It should be noted that although several modules or units of the apparatus for action performance are mentioned in the above detailed description, this division is not mandatory. Indeed, according to embodiments of the present application, the features and functions of two or more modules or units described above may be embodied in one module or unit. Conversely, the features and functions of one module or unit described above may be further divided into multiple modules or units to be embodied.

From the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein may be implemented by software, or may be implemented by software combined with necessary hardware. Therefore, the technical solutions according to the embodiments of the present application may be embodied in the form of software products, and the software products may be stored in a non-volatile storage medium (which may be CD-ROM, U disk, mobile hard disk, etc.) or on the network , which includes several instructions to cause a computing device (which may be a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

Other embodiments of the present application will readily occur to those skilled in the art upon consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses or adaptations of this application that follow the general principles of this application and include common knowledge or conventional techniques in the technical field not disclosed in this application .

It is to be understood that the present application is not limited to the precise structures described above and illustrated in the accompanying drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (18)

1. a battery state monitoring method, is characterized in that, described monitoring method comprises: acquiring a first characteristic parameter of the battery, where the first characteristic parameter includes at least one of a voltage value without abnormality and an internal resistance value; When the first characteristic parameter includes a voltage value, a second characteristic parameter of the battery is determined according to the first characteristic parameter of the battery, and the second characteristic parameter includes a relative voltage value and/or a voltage change value and / or voltage gradient value; When the first characteristic parameter includes an internal resistance value, a second characteristic parameter of the battery is determined according to the first characteristic parameter of the battery, and the second characteristic parameter includes a relative internal resistance value and/or an internal resistance change value and/or internal resistance gradient value; When the first characteristic parameter includes a voltage value and an internal resistance value, a second characteristic parameter of the battery is determined according to the first characteristic parameter of the battery, and the second characteristic parameter includes a relative voltage value and/or a relative Internal resistance value and/or voltage change value and/or internal resistance change value and/or voltage gradient value and/or internal resistance gradient value and/or voltage-to-resistance ratio; Inputting the first characteristic parameter and the second characteristic parameter of the battery into the battery state monitoring model trained in advance, and outputting the battery state parameter; monitoring the state of the battery based on the battery state parameter; The battery state monitoring model can be obtained in the following ways: acquiring first characteristic parameters of the battery at various moments in history, so as to determine second characteristic parameters of the battery at various moments in history according to the first characteristic parameters; Obtaining the decay time interval of the battery in the history, so as to determine the battery state of the battery at each moment in the history according to the decay time interval of the battery in the history; Based on the first characteristic parameter and the second characteristic parameter of the battery at each time in history, and the battery state at each time in history, a machine learning model is trained to generate the battery state monitoring model. 2. The method according to claim 1, wherein the acquiring the first characteristic parameter of the battery at each moment in history comprises: collecting the initial characteristic parameters of the battery at various moments in history; Detecting whether the initial feature parameter is abnormal; The initial characteristic parameter without abnormality is acquired as the first characteristic parameter. 3. The method according to claim 2, wherein the collecting the initial characteristic parameters of the battery at various moments in history comprises: At least one of the voltage value and the internal resistance value of the battery at various moments in history is collected. 4. The method according to claim 1, wherein the first characteristic parameter of the battery at each time in history comprises the current value of the battery at each time in history, Before determining the second characteristic parameter of the battery at each moment in history according to the first characteristic parameter, the method further includes: Detecting whether the current value of the battery at each moment in history is greater than a predetermined threshold; Filter the first characteristic parameter corresponding to the moment when the current value is greater than the predetermined threshold. 5. The method according to claim 1, wherein the first characteristic parameter of the battery at each time in history comprises at least one of a voltage value and an internal resistance value of the battery at each time in history, The determining, according to the first characteristic parameter, the second characteristic parameter of the battery at each moment in history, including: When the first characteristic parameter includes a voltage value, determine the relative voltage value and/or the voltage change value and/or the voltage gradient of the battery at each historical moment according to the voltage value of the battery at each historical moment value; When the first characteristic parameter includes an internal resistance value, according to the internal resistance value of the battery at each historical moment, determine the relative internal resistance value and/or the internal resistance change value and/or the internal resistance value of the battery at each historical moment. / or internal resistance gradient value; When the first characteristic parameter includes a voltage value and an internal resistance value, determine the relative voltage value and/or relative voltage value of the battery at each historical moment according to the voltage value and internal resistance value of the battery at each historical moment Internal resistance value and/or voltage change value and/or internal resistance change value and/or voltage gradient value and/or internal resistance gradient value and/or voltage-to-resistance ratio. 6 . The method according to claim 1 , wherein the acquiring the historical decay time interval of the battery comprises: 6 . determining a first moment when the battery satisfies the fault replacement condition and a second moment when the battery is replaced; determining the degradation time that the battery experiences before entering a fault state; According to the first time and the second time, and the performance degradation time experienced by the battery before the battery enters the fault state, the historical degradation time interval of the battery is determined. 7 . The method according to claim 1 , wherein the determining the battery state of the battery at various moments in history according to the historical decay time interval of the battery, comprising: 8 . determining the battery state at each moment in the decay time interval as an early warning state; The state of the battery at each moment in the time interval other than the decay time interval is determined as the healthy state. 8. The method according to claim 7, wherein determining the battery state at each moment in the decay time interval as an early warning state, comprising: determining sub-decay time intervals within the decay time interval, and the battery has different degradation degrees in different sub-decay time intervals; According to the degradation degree of the battery in different sub-decay time intervals, the warning state level of the battery in different sub-decay time intervals is determined. 9. A battery state monitoring device, comprising: an acquisition unit, configured to acquire a first characteristic parameter of the battery, where the first characteristic parameter includes at least one of a voltage value without abnormality and an internal resistance value; a determining unit, configured to determine a second characteristic parameter of the battery according to the first characteristic parameter of the battery when the first characteristic parameter includes a voltage value, the second characteristic parameter includes a relative voltage value and /or voltage change value and/or voltage gradient value; when the first characteristic parameter includes an internal resistance value, the second characteristic parameter of the battery is determined according to the first characteristic parameter of the battery, and the second characteristic parameter of the battery is determined. The characteristic parameter includes a relative internal resistance value and/or an internal resistance change value and/or an internal resistance gradient value; when the first characteristic parameter includes a voltage value and an internal resistance value, the first characteristic parameter of the battery is determined. The second characteristic parameter of the battery, the second characteristic parameter includes the relative voltage value and/or the relative internal resistance value and/or the voltage change value and/or the internal resistance change value and/or the voltage gradient value and/or the internal resistance gradient value and/or voltage resistance ratio; an output unit, configured to input the first characteristic parameter and the second characteristic parameter of the battery into the battery state monitoring model trained in advance, and output the battery state parameter; a monitoring unit, configured to monitor the state of the battery based on the battery state parameter; The obtaining unit is further configured to: obtain the first characteristic parameter of the battery at each moment in history and the decay time interval of the battery in history; The determining unit is further configured to: determine, according to the first characteristic parameter, second characteristic parameters of the battery at various moments in history, and determine, according to the decline time interval of the battery in the history, that the battery is in the history of the battery. The battery status at each moment; The battery state monitoring device further includes: a model training unit, used for training a machine learning model based on the first characteristic parameter and the second characteristic parameter of the battery at various times in history, and the battery state at various times in history The battery condition monitoring model is generated. 10 . The device according to claim 9 , wherein the acquisition unit is configured to: collect initial characteristic parameters of the battery at various moments in history; detect whether the initial characteristic parameters are abnormal; An abnormal initial feature parameter is used as the first feature parameter. 11 . The device according to claim 10 , wherein the acquiring unit is configured to acquire at least one of a voltage value and an internal resistance value of the battery at various moments in history. 12 . 12 . The device according to claim 9 , wherein the first characteristic parameters of the battery at various moments in history include current values of the battery at various moments in history, and the acquisition unit is configured to: For the first characteristic parameter, before determining the second characteristic parameter of the battery at each time in history, detect whether the current value of the battery at each time in history is greater than a predetermined threshold; filter the time when the current value is greater than the predetermined threshold The corresponding first characteristic parameter. 13 . The device according to claim 9 , wherein the first characteristic parameter of the battery at each time in history comprises at least one of a voltage value and an internal resistance value of the battery at each time in history, 13 . The determining unit is configured to: when the first characteristic parameter includes a voltage value, determine the relative voltage value and/or voltage of the battery at each historical moment according to the voltage value of the battery at each historical moment change value and/or voltage gradient value; when the first characteristic parameter includes an internal resistance value, determine the relative internal resistance of the battery at each historical moment according to the internal resistance value of the battery at each historical moment value and/or internal resistance change value and/or internal resistance gradient value; when the first characteristic parameter includes voltage value and internal resistance value, according to the voltage value and internal resistance value of the battery at various moments in history, determine The relative voltage value and/or the relative internal resistance value and/or the voltage change value and/or the internal resistance change value and/or the voltage gradient value and/or the internal resistance gradient value and/or the voltage value of the battery at various times in history resistance ratio. 14 . The apparatus according to claim 9 , wherein the obtaining unit is configured to: determine a first moment when the battery satisfies a fault replacement condition and a second moment when the battery is replaced; determine the battery The performance degradation time experienced before entering the fault state; the historical degradation time interval of the battery is determined according to the first moment and the second moment, and the performance degradation time experienced before the battery enters the fault state. 15. The device according to claim 9, wherein the determining unit is configured to: determine the battery state at each moment in the decay time interval as an early warning state; The battery state at each moment in the time interval is determined as the healthy state. 16 . The apparatus according to claim 15 , wherein the determining unit is configured to: determine sub-decay time intervals within the decay time interval, and the battery has different degradation degrees in different sub-decay time intervals; 16 . According to the degradation degree of the battery in different sub-decay time intervals, the warning state level of the battery in different sub-decay time intervals is determined. 17. A computer-readable storage medium having stored thereon a computer program comprising executable instructions that, when executed by a processor, implement the method as claimed in any one of claims 1 to 8 method. 18. An electronic device, characterized in that, comprising: processor; and a memory for storing executable instructions for the processor; wherein the processor is arranged to execute the executable instructions to implement the method of any of claims 1 to 8.

Images