Battery status monitoring method and device

Abstract

The present disclosure relates to a battery status monitoring method and device, and a computer storable medium, and relates to the field of computer technology. The battery status monitoring method includes: obtaining the parameter values ​​of the multidimensional characteristic parameters of the battery to be monitored in the current time period; converting the parameter values ​​of the multidimensional characteristic parameters of the battery to be monitored into a multi-channel matrix of the battery to be monitored; and determining the state of the battery to be monitored based on the multi-channel matrix of the battery to be monitored using a neural network model, wherein the state includes a normal state or an abnormal state. According to the present disclosure, it is beneficial to extend the actual service life of the battery and ensure the power supply safety of the data center.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technologies, and particularly to a method and device for monitoring the state of a storage battery, and a computer-readable storage medium. Background Art

[0002] As a backup power supply, storage batteries are widely used in UPS (Uninterruptible Power Supply), communication power supplies, power DC systems, etc. due to their advantages such as small size, light weight, high discharge performance, safety and reliability, and low maintenance requirements.

[0003] The main reason for the early failure of a storage battery pack is the appearance of deteriorated single cells in the battery pack, which causes inconsistency among the single cells of the battery pack. As the battery is continuously charged and discharged, the differences between the single cells continue to increase, and finally the battery pack cannot work properly due to the early failure of individual single cells. In addition, the deteriorated battery will first affect the single cells near it and gradually spread, finally resulting in the entire battery pack being unable to work properly, seriously affecting the power supply safety of key equipment and the power supply safety in emergency situations. Therefore, the health monitoring of UPS storage batteries in data centers is particularly important. At present, there is a lack of effective means for monitoring the battery state. Summary of the Invention

[0004] In the related art, due to the lack of effective means for monitoring the battery state, the UPS storage batteries in data centers far from reach the rated service life in actual use, and often have problems of insufficient power supply capacity.

[0005] In view of the above technical problems, the present disclosure proposes a solution, which is beneficial to extending the actual service life of the storage battery and can ensure the power supply safety of the data center.

[0006] According to a first aspect of the present disclosure, there is provided a method for monitoring the state of a storage battery, including: obtaining parameter values of multi-dimensional characteristic parameters of a storage battery to be monitored in a current time period; converting the parameter values of the multi-dimensional characteristic parameters of the storage battery to be monitored into a multi-channel matrix of the storage battery to be monitored; and determining a state of the storage battery to be monitored according to the multi-channel matrix of the storage battery to be monitored by using a neural network model, where the state includes a normal state or an abnormal state.

[0007] In some embodiments, each channel matrix in the multi-channel matrix of the storage battery to be monitored represents an association relationship between different dimensional characteristic parameters, and the element values of each channel matrix are composed of the parameter values of different dimensional characteristic parameters.

[0008] In some embodiments, the multi-dimensional characteristic parameters include a plurality of target voltages, a plurality of target currents, and a plurality of target temperatures of the storage battery to be monitored in the current time period.

[0009] In some embodiments, the multi-channel matrix of the battery to be monitored includes a first channel matrix, a second channel matrix, and a third channel matrix. The first channel matrix represents the correlation between the multiple target voltages and the multiple target currents. The second channel matrix represents the correlation between the multiple target voltages and the multiple target temperatures. The third channel matrix represents the correlation between the multiple target currents and the multiple target temperatures.

[0010] In some embodiments, different target voltages reflect different voltage characteristics, different target currents reflect different current characteristics, and different target temperatures reflect different temperature characteristics.

[0011] In some embodiments, the target voltage includes the valley voltage and the peak voltage of the battery to be monitored during the current time period; and / or the target current includes the valley current and the peak current of the battery to be monitored during the current time period; and / or the target temperature includes the valley temperature and the peak temperature of the battery to be monitored during the current time period.

[0012] In some embodiments, converting the parameter values of the multi-dimensional characteristic parameters of the battery to be monitored into the multi-channel matrix of the battery to be monitored includes: normalizing the parameter values of the multi-dimensional characteristic parameters of the battery to be monitored to obtain the normalized parameter values of the battery to be monitored; converting the normalized parameter values of the multi-dimensional characteristic parameters of the battery to be monitored into the multi-channel matrix of the battery to be monitored.

[0013] In some embodiments, the state monitoring method further includes: obtaining training data, where the training data includes the parameter values of the multi-dimensional characteristic parameters of multiple reference batteries during a reference time period and the state labels of each reference battery during each reference time period. The state labels include a first label and a second label. The first label represents a normal state, and the second label represents an abnormal state; converting the parameter values of the multi-dimensional characteristic parameters of each reference battery during each reference time period into the multi-channel matrix of each reference battery during each reference time period; training the neural network model according to the multi-channel matrix of each reference battery during each reference time period and its corresponding state label.

[0014] According to a second aspect of the present disclosure, there is provided a battery state monitoring device, including: an acquisition module configured to acquire parameter values of multi-dimensional characteristic parameters of a battery to be monitored in a current time period; a conversion module configured to convert the parameter values of the multi-dimensional characteristic parameters of the battery to be monitored into a multi-channel matrix of the battery to be monitored; and a determination module configured to determine a state of the battery to be monitored based on the multi-channel matrix of the battery to be monitored by using a neural network model, where the state includes a normal state or an abnormal state.

[0015] According to a third aspect of the present disclosure, there is provided a battery state monitoring device, including: a memory; and a processor coupled to the memory, the processor being configured to execute the battery state monitoring method according to any one of the above embodiments based on instructions stored in the memory.

[0016] According to a fourth aspect of the present disclosure, there is provided a computer-readable storage medium having computer program instructions stored thereon, and when the instructions are executed by a processor, the battery state monitoring method according to any one of the above embodiments is implemented.

[0017] In the above embodiments, it is beneficial to extend the actual service life of the battery and ensure the power supply safety of the data center. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings forming a part of the specification depict embodiments of the present disclosure and, together with the specification, are used to explain the principles of the present disclosure.

[0019] Referring to the drawings, the present disclosure can be more clearly understood from the following detailed description, where:

[0020] Figure 1 is a flowchart showing a battery state monitoring method according to some embodiments of the present disclosure;

[0021] Figure 2 is a block diagram showing a battery state monitoring device according to some embodiments of the present disclosure;

[0022] Figure 3 is a block diagram showing a battery state monitoring device according to some other embodiments of the present disclosure;

[0023] Figure 4 is a block diagram showing a computer system for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0024] Now, various exemplary embodiments of the present disclosure will be described in detail with reference to the drawings. It should be noted that: unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure.

[0025] Meanwhile, it should be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn in actual proportional relationship.

[0026] The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way a limitation on the present disclosure, its application, or use.

[0027] Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the said technologies, methods, and devices should be regarded as part of the specification.

[0028] In all the examples shown and discussed herein, any specific values should be construed as merely exemplary and not as a limitation. Thus, other examples of the exemplary embodiments may have different values.

[0029] It should be noted that like reference numerals and letters denote like items in the following drawings, and thus, once an item is defined in one drawing, further discussion thereof is not required in subsequent drawings.

[0030] Figure 1 is a flowchart showing a method for monitoring the state of a storage battery according to some embodiments of the present disclosure.

[0031] As Figure 1 shown, the method for monitoring the state of a storage battery includes: step S110 of obtaining parameter values of multi-dimensional characteristic parameters of the storage battery to be monitored in the current time period; step S120 of converting the parameter values of the multi-dimensional characteristic parameters of the storage battery to be monitored into a multi-channel matrix of the storage battery to be monitored; and step S130 of determining the state of the storage battery to be monitored according to the multi-channel matrix of the storage battery to be monitored by using a neural network model, where the state includes a normal state or an abnormal state.

[0032] In the above embodiment, by converting the parameter values of the multi-dimensional characteristic parameters of the storage battery to be monitored into a multi-channel matrix and using the neural network model to perform feature learning on the multi-channel matrix, the parameter characteristics of the storage battery to be monitored in the current time period are learned, so as to predict the state of the storage battery to be monitored, thereby achieving the purpose of monitoring the health state of the storage battery. In this way, the internal characteristics of the storage battery in the current time period can be fully learned, and the deteriorated single battery can be discovered in time, which is beneficial to both extending the actual service life of the storage battery and ensuring the power supply safety of the data center. The conversion of the multi-channel matrix enables the multi-dimensional characteristic parameters of the storage battery to be represented like the multi-channel matrix of an image, so that the advantages of the neural network in image feature processing can be fully utilized, and the neural network model can fully learn the internal characteristics of the storage battery. The degree of automation of monitoring using the neural network model is relatively high.

[0033] In step S110, parameter values of multi-dimensional characteristic parameters of the battery to be monitored in the current time period are obtained. For example, through data acquisition technology, parameter values of multi-dimensional characteristic parameters of the battery to be monitored in the current time period are obtained.

[0034] In some embodiments, the multi-dimensional characteristic parameters include multiple target voltages, multiple target currents, and multiple target temperatures of the battery to be monitored in the current time period. In some embodiments, different target voltages reflect different voltage characteristics, different target currents reflect different current characteristics, and different target temperatures reflect different temperature characteristics.

[0035] In some embodiments, the target voltages include the valley voltage and the peak voltage of the battery to be monitored in the current time period; and / or the target currents include the valley current and the peak current of the battery to be monitored in the current time period; and / or the target temperatures include the valley temperature and the peak temperature of the battery to be monitored in the current time period.

[0036] Taking the target voltages including the valley voltage U t and the peak voltage U p , the target currents including the valley current I t and the peak current I p , and the target temperatures including the valley temperature T t and the peak temperature T p as an example, the parameter values of the multi-dimensional characteristic parameters can be represented as a vector (U t , I t , T t , U p , I p , T p ).

[0037] In step S120, the parameter values of the multi-dimensional characteristic parameters of the battery to be monitored are converted into a multi-channel matrix of the battery to be monitored. In some embodiments, each channel matrix in the multi-channel matrix of the battery to be monitored represents the correlation relationship between different dimensional characteristic parameters, and the element values of each channel matrix are composed of the parameter values of different dimensional characteristic parameters.

[0038] In some embodiments, the multi-channel matrix includes a first channel matrix, a second channel matrix, and a third channel matrix. The first channel matrix represents the correlation relationship between the multiple target voltages and the multiple target currents, the second channel matrix represents the correlation relationship between the multiple target voltages and the multiple target temperatures, and the third channel matrix represents the correlation relationship between the multiple target currents and the multiple target temperatures.

[0039] Taking the target voltages including the valley voltage U t and the peak voltage U p, the target current includes the valley current I t and the peak current I p , the target temperature includes the valley temperature T t and the peak temperature T p For example, the element values of the first channel matrix are composed of (U t , I t ), (U t , I p ), (U p , I p ) and (U p , I t ). The element values of the second channel matrix are composed of (U t , T t ), (U t , T p ), (U p , T p ) and (U p , T t ). The element values of the third channel matrix are composed of (I t , T t ), (I t , T p ), (I p , T p ) and (I p , T t ). The element value (U t , I t ) can also be (I t , U t ), and the representation of other element values can also be adjusted with reference to this method. The multi-channel matrix can be represented as (U, I, T).

[0040] In some embodiments, the above step S120 can be implemented in the following manner.

[0041] First, normalize the parameter values of the multi-dimensional characteristic parameters of the battery to be monitored to obtain the normalized parameter values of the battery to be monitored. In some embodiments, the normalized parameter values are obtained by normalizing the parameter values of the multi-dimensional characteristic parameters of the battery to be monitored. For example, the value range of the normalized parameter values is 0 to 1. Through normalization, the dimensionality effect between different types of parameters can be eliminated, the accuracy of state monitoring can be improved, and thus the power supply safety of the data center can be further improved.

[0042] Then, convert the normalized parameter values of the multi-dimensional characteristic parameters of the battery to be monitored into the multi-channel matrix of the battery to be monitored.

[0043] In step S130, according to the multi-channel matrix of the battery to be monitored, the state of the battery to be monitored is determined by using a neural network model. The state includes a normal state or an abnormal state. In some embodiments, the multi-channel matrix of the battery to be monitored is input into the neural network model to obtain a prediction result, and according to the prediction result, the state of the battery to be monitored is determined. For example, the prediction result can be a state label characterizing the state of the battery to be monitored, or the state itself.

[0044] In some embodiments, the neural network model includes, but is not limited to, a Convolutional Neural Network (CNN) model and its derivatives.

[0045] In some embodiments, before using the neural network model to determine the state of the battery to be monitored, the neural network model can also be trained.

[0046] First, training data is obtained. The training data includes the parameter values of the multi-dimensional characteristic parameters of multiple reference batteries in a reference time period and the state labels of each reference battery in each reference time period. The state labels include a first label and a second label. The first label characterizes the normal state, and the second label characterizes the abnormal state. In some embodiments, the first label is a positive label, and the second label is a negative label.

[0047] In some embodiments, each reference battery may have the parameter values of the multi-dimensional characteristic parameters of one reference time period, or may have the parameter values of the multi-dimensional characteristic parameters of multiple reference time periods. For example, the reference time periods of different reference batteries may be exactly the same, may be completely different, or may be partially the same.

[0048] Then, the parameter values of the multi-dimensional characteristic parameters of each reference battery in each reference time period are converted into the multi-channel matrix of each reference battery in each reference time period. The conversion process can refer to the above description of step S120.

[0049] Finally, the neural network model is trained according to the multi-channel matrix of each reference battery in each reference time period and its corresponding state label.

[0050] In some embodiments, in the initial state, the weight matrix W and the bias matrix ξ of the neural network model are initialized. The output layer of the neural network model is a softmax layer. During the training process, the neural network model updates the loss function each gradient, as well as the weight matrix and the bias matrix, until the loss function is less than the preset threshold ρ, and the training is completed.

[0051] In some embodiments, after determining the state of the battery to be monitored, the state of the battery to be monitored is displayed. By visually displaying the state of the battery to be monitored, it can serve as a reference for relevant personnel such as operation and maintenance personnel to perform operation and maintenance operations on the battery.

[0052] Figure 2 It is a block diagram showing a battery state monitoring device according to some embodiments of the present disclosure.

[0053] As Figure 2 shown, the battery state monitoring device 2 includes an acquisition module 21, a conversion module 22, and a determination module 23.

[0054] The acquisition module 21 is configured to acquire the parameter values of the multi-dimensional characteristic parameters of the battery to be monitored in the current time period, for example, execute the steps as Figure 1 shown in step S110.

[0055] The conversion module 22 is configured to convert the parameter values of the multi-dimensional characteristic parameters of the battery to be monitored into a multi-channel matrix of the battery to be monitored, for example, execute the steps as Figure 1 shown in step S120.

[0056] The determination module 23 is configured to determine the state of the battery to be monitored according to the multi-channel matrix of the battery to be monitored, using a neural network model, where the state includes a normal state or an abnormal state, for example, execute the steps as Figure 1 shown in step S130.

[0057] In some embodiments, the battery state monitoring device 2 further includes a display module 24. The display module 24 is configured to display or present the state of the battery to be monitored.

[0058] Figure 3 It is a block diagram showing a battery state monitoring device according to other embodiments of the present disclosure.

[0059] As Figure 3 shown, the battery state monitoring device 3 includes a memory 31; and a processor 32 coupled to the memory 31. The memory 31 is used to store instructions for implementing corresponding embodiments of the battery state monitoring method. The processor 32 is configured to execute the battery state monitoring method in any of the embodiments of the present disclosure based on the instructions stored in the memory 31.

[0060] Figure 4 It is a block diagram showing a computer system for implementing some embodiments of the present disclosure.

[0061] As Figure 4 shown, the computer system 40 may be represented in the form of a general-purpose computing device. The computer system 40 includes a memory 410, a processor 420, and a bus 400 connecting different system components.

[0062] The memory 410 can include, for example, a system memory, a non-volatile storage medium, etc. The system memory stores, for example, an operating system, application programs, a boot loader, and other programs. The system memory can include a volatile storage medium, such as a random access memory (RAM) and / or a cache memory. The non-volatile storage medium stores, for example, instructions for implementing the corresponding embodiments of the battery state monitoring method. The non-volatile storage medium includes, but is not limited to, a disk memory, an optical memory, a flash memory, etc.

[0063] The processor 420 can be implemented in the form of a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates, or discrete hardware components such as transistors. Correspondingly, each module such as a judgment module and a determination module can be implemented by a central processing unit (CPU) running instructions for executing corresponding steps in the memory, or by a dedicated circuit for executing the corresponding steps.

[0064] The bus 400 can use any bus structure among a variety of bus structures. For example, the bus structure includes, but is not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, and a Peripheral Component Interconnect (PCI) bus.

[0065] The computer system 40 can further include an input / output interface 430, a network interface 440, a storage interface 450, etc. These interfaces 430, 440, 450 can be connected to the memory 410 and the processor 420 through the bus 400. The input / output interface 430 can provide a connection interface for input / output devices such as a display, a mouse, and a keyboard. The network interface 440 provides a connection interface for various networking devices. The storage interface 450 provides a connection interface for external storage devices such as a floppy disk, a USB flash drive, and an SD card.

[0066] Here, various aspects of the present disclosure have been described with reference to the flowcharts and / or block diagrams of methods, apparatuses, and computer program products according to embodiments of the present disclosure. It should be understood that each block of the flowcharts and / or block diagrams, and the combinations of the blocks, can be implemented by computer-readable program instructions.

[0067] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable devices to generate a machine, such that the device implemented by executing the instructions by the processor realizes the functions specified in one or more blocks in the flowcharts and / or block diagrams.

[0068] These computer-readable program instructions can also be stored in a computer-readable memory, which causes a computer to operate in a particular manner, resulting in a manufacture including instructions implementing the functions specified in one or more boxes in the flowchart and / or block diagram.

[0069] The present disclosure may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects.

[0070] Through the battery state monitoring method, device, and computer-readable storage medium in the above embodiments, it is beneficial to extend the actual service life of the battery and ensure the power supply safety of the data center.

[0071] So far, the data transmission method, device, and computer-readable storage medium according to the present disclosure have been described in detail. To avoid obscuring the concept of the present disclosure, some details well known in the art have not been described. Those skilled in the art can fully understand how to implement the technical solutions disclosed herein based on the above description.

Claims

1. A method for monitoring a battery state, comprising: Acquire parameter values ​​of a multidimensional characteristic parameter of the battery to be monitored in a current time period, wherein the multidimensional characteristic parameter includes a plurality of target voltages, a plurality of target currents, and a plurality of target temperatures of the battery to be monitored in the current time period; Converting the parameter values ​​of the multi-dimensional characteristic parameters of the battery to be monitored into a multi-channel matrix of the battery to be monitored, wherein each channel matrix in the multi-channel matrix of the battery to be monitored represents the correlation relationship between the characteristic parameters of different dimensions, and the element values ​​of each channel matrix are composed of the parameter values ​​of the characteristic parameters of different dimensions, and the multi-channel matrix of the battery to be monitored includes a first channel matrix, a second channel matrix and a third channel matrix, wherein the first channel matrix represents the correlation relationship between the multiple target voltages and the multiple target currents, the second channel matrix represents the correlation relationship between the multiple target voltages and the multiple target temperatures, and the third channel matrix represents the correlation relationship between the multiple target currents and the multiple target temperatures; The multi-channel matrix of the battery to be monitored is input into a neural network model to determine the state of the battery to be monitored, wherein the state includes a normal state or an abnormal state.

2. The condition monitoring method according to claim 1, wherein: Different target voltages reflect different voltage characteristics, different target currents reflect different current characteristics, and different target temperatures reflect different temperature characteristics.

3. The condition monitoring method according to claim 1, wherein: The target voltage includes the valley voltage and peak voltage of the battery to be monitored in the current time period; and / or The target current includes the valley current and the peak current of the battery to be monitored in the current time period; and / or The target temperature includes a valley temperature and a peak temperature of the monitored storage battery in the current time period.

4. The condition monitoring method according to claim 1, wherein: Converting the parameter values ​​of the multi-dimensional characteristic parameters of the battery to be monitored into a multi-channel matrix of the battery to be monitored comprises: Standardizing the parameter values ​​of the multi-dimensional characteristic parameters of the battery to be monitored to obtain standardized parameter values ​​of the battery to be monitored; The standardized parameter values ​​of the multi-dimensional characteristic parameters of the battery to be monitored are converted into a multi-channel matrix of the battery to be monitored.

5. The condition monitoring method according to claim 1, further comprising: Acquire training data, wherein the training data includes parameter values ​​of multidimensional feature parameters of multiple reference batteries in a reference time period and a state label of each reference battery in each reference time period, the state label includes a first label and a second label, the first label represents a normal state, and the second label represents an abnormal state; Converting the parameter value of the multidimensional characteristic parameter of each reference storage battery in each reference time period into a multi-channel matrix of each reference storage battery in each reference time period; The neural network model is trained according to the multi-channel matrix of each reference battery in each reference time period and its corresponding state label.

6. A battery status monitoring device, comprising: an acquisition module, configured to acquire parameter values ​​of a multidimensional characteristic parameter of the battery to be monitored in a current time period, wherein the multidimensional characteristic parameter includes a plurality of target voltages, a plurality of target currents and a plurality of target temperatures of the battery to be monitored in the current time period; a conversion module, configured to convert the parameter values ​​of the multi-dimensional characteristic parameters of the battery to be monitored into a multi-channel matrix of the battery to be monitored, wherein each channel matrix in the multi-channel matrix of the battery to be monitored represents the association relationship between the characteristic parameters of different dimensions, and the element values ​​of each channel matrix are composed of the parameter values ​​of the characteristic parameters of different dimensions, and the multi-channel matrix of the battery to be monitored includes a first channel matrix, a second channel matrix and a third channel matrix, wherein the first channel matrix represents the association relationship between the multiple target voltages and the multiple target currents, the second channel matrix represents the association relationship between the multiple target voltages and the multiple target temperatures, and the third channel matrix represents the association relationship between the multiple target currents and the multiple target temperatures; The determination module is configured to input the multi-channel matrix of the battery to be monitored into a neural network model to determine the state of the battery to be monitored, wherein the state includes a normal state or an abnormal state.

7. A battery status monitoring device, comprising: Memory; as well as A processor coupled to the memory, wherein the processor is configured to execute the battery status monitoring method according to any one of claims 1 to 5 based on instructions stored in the memory.

8. A computer-readable storage medium having computer program instructions stored thereon, wherein the instructions, when executed by a processor, implement the battery status monitoring method according to any one of claims 1 to 5.

Images