CN117805652A - Health evaluation method, device and equipment for valve-controlled sealed lead-acid storage battery - Google Patents
Health evaluation method, device and equipment for valve-controlled sealed lead-acid storage battery Download PDFInfo
- Publication number
- CN117805652A CN117805652A CN202311801077.4A CN202311801077A CN117805652A CN 117805652 A CN117805652 A CN 117805652A CN 202311801077 A CN202311801077 A CN 202311801077A CN 117805652 A CN117805652 A CN 117805652A
- Authority
- CN
- China
- Prior art keywords
- data
- battery
- predicted
- short
- long
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 74
- 238000011156 evaluation Methods 0.000 title claims abstract description 46
- 239000002253 acid Substances 0.000 title claims abstract description 40
- 230000015654 memory Effects 0.000 claims abstract description 98
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000012549 training Methods 0.000 claims abstract description 26
- 238000012545 processing Methods 0.000 claims description 28
- 238000012360 testing method Methods 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 16
- 230000001105 regulatory effect Effects 0.000 claims description 15
- 230000004913 activation Effects 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 5
- 238000010561 standard procedure Methods 0.000 abstract description 5
- 230000000694 effects Effects 0.000 abstract description 4
- 230000002265 prevention Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 230000007246 mechanism Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000005686 electrostatic field Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Landscapes
- Secondary Cells (AREA)
Abstract
The embodiment of the invention discloses a health degree assessment method, a device and equipment of a valve-controlled sealed lead-acid storage battery. The method comprises the following steps: acquiring battery use data of a storage battery to be monitored in a history time; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increase data at two adjacent moments; inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain predicted use data in predicted duration; the long-short-time memory network comprises an attention module; and determining health evaluation data of the storage battery to be monitored based on the predicted usage data. The technical scheme provided by the embodiment of the invention solves the problem that the state of the lead-acid storage battery is not evaluated by a unified standard method at present, so that whether the lead-acid storage battery has faults or not cannot be effectively determined in advance, namely, the lead-acid storage battery cannot be timely handled, and the effect of early prevention is achieved.
Description
Technical Field
The embodiment of the invention relates to a computer processing technology, in particular to a health degree assessment method, a device and equipment of a valve-controlled sealed lead-acid storage battery.
Background
The technical advantages of the current direct current system new equipment enable the direct current system of the transformer substation to operate more reliably, but the overhaul and the operation of the new direct current equipment require higher technical level and more accurate technology of users.
At present, a plurality of problems needing to be emphasized exist in the installation, overhaul, use and maintenance work of a direct current system of a valve-controlled sealed lead-acid storage battery of a transformer substation. However, there is no unified standard method for evaluating the state of the lead-acid storage battery, and thus it is not possible to effectively determine in advance whether there is a fault in the lead-acid storage battery, that is, the problem that it cannot be dealt with in time.
Disclosure of Invention
The embodiment of the invention provides a health degree evaluation method, a device and equipment of a valve-controlled sealed lead-acid storage battery, which can be used for predicting battery use data at a certain moment in the future by combining battery use data in historical time, so that corresponding countermeasures are adopted for the battery use data.
In a first aspect, an embodiment of the present invention provides a method for evaluating the health of a valve-regulated sealed lead-acid battery, including:
acquiring battery use data of a storage battery to be monitored in a history time; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increase data at two adjacent moments;
inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain predicted use data in predicted duration; the long-short-time memory network comprises an attention module;
and determining health evaluation data of the storage battery to be monitored based on the predicted usage data.
In a second aspect, an embodiment of the present invention further provides a health degree evaluation device for a valve-controlled sealed lead-acid battery, where the device includes:
the data acquisition module is used for acquiring battery use data of the storage battery to be monitored in the history time; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increase data at two adjacent moments;
the data prediction module is used for inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain prediction use data in a prediction duration; the long-short-time memory network comprises an attention module;
and the evaluation result determining module is used for determining the health evaluation data of the storage battery to be monitored based on the predicted use data.
In a third aspect, an embodiment of the present invention further provides an apparatus, including:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method for health assessment of a valve-regulated sealed lead-acid battery according to any of the embodiments of the present invention.
According to the technical scheme, the battery use data of the storage battery to be monitored in the history duration is obtained; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increase data at two adjacent moments; inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain predicted use data in predicted duration; the long-short-time memory network comprises an attention module; based on the predicted use data, the health evaluation data of the storage battery to be monitored is determined, the problem that whether the lead-acid storage battery has faults or not cannot be effectively determined in advance due to the fact that a unified standard method is not available at present is solved, namely, the problem that the lead-acid storage battery cannot be timely handled is solved, the predicted use data is determined by combining the battery use data in the history duration, the health evaluation data of the storage battery to be monitored is determined based on the predicted data, and whether the lead-acid storage battery has faults or not can be determined based on the health evaluation data, so that the effect of preventing is effectively achieved.
Drawings
In order to more clearly illustrate the technical solution of the exemplary embodiments of the present invention, a brief description is given below of the drawings required for describing the embodiments. It is obvious that the drawings presented are only drawings of some of the embodiments of the invention to be described, and not all the drawings, and that other drawings can be made according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a method for evaluating the health of a valve-regulated sealed lead-acid battery according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a long-short-time memory network according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for evaluating the health of a valve-regulated sealed lead-acid battery according to a second embodiment of the present invention;
fig. 4 is a block diagram of a health evaluation device for a valve-regulated sealed lead-acid battery according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Example 1
Fig. 1 is a flowchart of a method for evaluating the health of a sealed valve-regulated lead-acid battery according to an embodiment of the present invention, where the method may be performed by a device for evaluating the health of a sealed valve-regulated lead-acid battery, and the device may be configured in a computing device, and the method for evaluating the health of a sealed valve-regulated lead-acid battery according to the embodiment specifically includes the following steps:
s110, acquiring battery usage data of the storage battery to be monitored in the history time.
The storage battery to be monitored can be any battery to be monitored. The historical time period may be understood as a time period before the current time, alternatively, the time period before the current time may be a 10 minute time period. The battery usage data includes at least one battery capacity data, at least one voltage data, and an internal resistance value increases dramatically at two adjacent times. The battery capacity data is understood to mean the amount of electricity discharged from the battery under certain conditions (discharge rate, temperature, end voltage, etc.); voltage data can be understood as a physical quantity of the difference in energy of the charges inside the battery due to the difference in electric potential in the electrostatic field.
Specifically, battery usage data in a history period of time before the current time may be obtained in real time to determine battery data at a predicted time or within a predicted period of time based on the battery usage data.
S120, inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain predicted use data in predicted duration; the long-short-time memory network comprises an attention module.
The long-short-time memory network is an LSTM model, and the LSTM model belongs to one of deep-circulation neural networks. The model has input, output, forget and update gates, the regulation information of the gates flows, a hidden state is maintained, n times of t are used as variables to be input into an LSTM network, and the output at the time of t+1 is predicted. h (t) is long-term memory information of a time sequence, s (t) is short-term memory information of a sequence, and the structure is shown in fig. 2. Based on the processing content of the model, the long-time and short-time memory network can be adopted to process the battery use data. The predicted usage data is battery usage data at a time in the future determined based on battery usage data within the historical time period.
In this embodiment, the long-short-term memory network includes an attention module, where the attention module may be a mode of special probability distribution, and focuses on information distribution and focuses on the influence of important information, so as to finally achieve the purpose of ideal prediction accuracy. Therefore, the attention module arranged in the long-short-time memory network can perform attention processing on the characteristics output by each convolution layer, so that the accuracy of the characteristic processing is improved, and the accuracy of prediction is further improved.
In this embodiment, the reason and benefit of using the long-short-time memory network is that the battery usage data has time continuity, and the long-short-time memory network can process the time-series data, i.e. learn the time-series information, so as to improve the accuracy of the prediction result, and further solve the problems of gradient disappearance and gradient explosion of the traditional RNN in long-series training.
In this embodiment, the determination of the predicted usage data may be: and inputting the battery usage data into the long-short-time memory network, extracting a first characteristic through at least one embedded layer, inputting the battery usage data into the long-short-time memory network to process the first characteristic to obtain a second characteristic, carrying out weighted attention processing on the first characteristic and the second characteristic extracted by at least one embedded layer based on the attention module, outputting a third characteristic, and processing the third characteristic based on an output layer in the long-short-time memory network to obtain the predicted usage data in the predicted duration.
It can be understood that the capacitance data, the voltage data and the internal resistance value increasing data of each time in the history length and the adjacent two times of the storage battery are input into the long-short memory network model, the first characteristic is extracted through at least one embedded layer in the long-short memory network, and the first characteristic is input into the long-short memory network again for processing to obtain the second characteristic. The attention module performs weighted fusion processing on the first feature and the second feature to obtain a third feature. And the output layer of the long and short memory network model processes the third characteristic to obtain the predicted use data. The predicted usage data may be battery usage data corresponding to the predicted time, i.e., battery usage data for a certain time period or a certain time in the future.
The future time period or time point is determined based on the predicted time length and time corresponding to the predicted data of the training sample used in training the model.
In this embodiment, the method further includes: inputting the characteristics corresponding to the predicted use data into an activation function layer to obtain a predicted classification result corresponding to the predicted use data; wherein the prediction classification result comprises a health degree evaluation category.
Wherein the activation function layer is mainly an activation function. The activation function refers to the Softmax function being an activation function for a multi-class classification problem in which more than two class labels require class membership. For any real vector of length K, the softmax function may compress it to a real vector of length K, with values in the range of 0,1, and the sum of the elements in the vector being 1.
Specifically, the features corresponding to the predicted usage data are input to an activation function layer to obtain a predicted classification result corresponding to the predicted usage data.
And S130, determining the health evaluation data of the storage battery to be monitored based on the predicted usage data.
The health evaluation data is used for representing the health degree of the storage battery to be monitored, and optionally, the health evaluation data can be data that the storage battery to be monitored can work normally or work abnormally. Or, the battery usage data of the storage battery to be detected at the predicted time can be used for determining whether the storage battery to be monitored can work normally or not according to the battery usage data and the data in the mapping relation table under the normal state which is created in advance.
In this embodiment, the determining, based on the predicted usage data, the health evaluation data of the battery to be detected includes: determining health evaluation data of the storage battery to be detected based on the predicted usage data and predetermined battery data of the storage battery in various health states; wherein the health assessment data includes a health assessment grade.
It can be understood that: and predicting the storage battery health evaluation data through a long short-time memory network model. Typically, the battery data for a battery in a state of health is that each battery capacity cannot be lower than 80%, the voltage cannot generally be lower than 1.8V and higher than 2.4V, and the internal resistance value of the adjacent two internal resistance tests cannot be increased by more than 50%. The health evaluation level of the battery to be detected may be determined from the predicted usage data and the battery data in the state of health. The health evaluation level may be a level of normal or abnormal use of the battery to be monitored.
According to the technical scheme provided by the embodiment of the invention, if the sequence and the number of the influence factors input into the model can be reasonably arranged, the reality and the accuracy of the battery health degree prediction can be better reflected by the data input into the model, and the data input into the model is weighted by using an attention mechanism, so that the characteristic of larger influence on the model is highlighted, and a new input quantity is formed; simultaneously inputting new input quantities into the model for subsequent prediction; and finally, transmitting the data obtained through model training to a linear transformation layer and a softmax layer, so as to obtain a final short-term storage battery aging prediction result.
The invention provides a deep learning model containing an attention mechanism long-term memory network (AT-LSTM) for predicting the health degree of a storage battery. And taking the historical storage battery data as input, and learning the characteristic internal change rule through modeling. The weights of the LSTM hidden states are assigned corresponding values by mapping the weighted sum learning parameter matrix. The weight vector is then generated by the attention mechanism layer. And multiplying the feature vector matrix to ensure that the features of the data in each iteration are combined into integral features, and finally outputting the feature vector through an output layer to achieve the aim of accurate prediction.
According to the technical scheme, the battery use data of the storage battery to be monitored in the history duration is obtained; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increase data at two adjacent moments; inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain predicted use data in predicted duration; the long-short-time memory network comprises an attention module; based on the predicted use data, the health evaluation data of the storage battery to be monitored is determined, the problem that whether the lead-acid storage battery has faults or not cannot be effectively determined in advance due to the fact that a unified standard method is not available at present is solved, namely, the problem that the lead-acid storage battery cannot be timely handled is solved, the predicted use data is determined by combining the battery use data in the history duration, the health evaluation data of the storage battery to be monitored is determined based on the predicted data, and whether the lead-acid storage battery has faults or not can be determined based on the health evaluation data, so that the effect of preventing is effectively achieved.
Example two
Fig. 3 is a flowchart of a method for evaluating the health of a valve-regulated sealed lead-acid battery according to a second embodiment of the present invention, where the device may be configured in a computing apparatus, and technical terms that are the same as or corresponding to the above embodiments are not repeated in this embodiment.
The health evaluation method of the valve-controlled sealed lead-acid storage battery provided by the embodiment specifically comprises the following steps:
s210, acquiring a plurality of test samples, wherein the test samples comprise historical battery use data in historical time and actual battery use data in predicted time.
The number of test samples may include a plurality of test samples, and training samples may be obtained as much as possible to improve accuracy of the model. The test sample may include historical battery usage data for a historical time period and actual battery usage data for a predicted time period corresponding to the historical time period.
In this embodiment, the long-short-term memory network continuously updates input data of the network by collecting various data (voltage, current, internal resistance and active power) of the storage battery, provides more influencing factors for predicting a load value at the next moment, and then constructs a data set of the LSTM network.
S220, for the plurality of test samples, historical battery usage data in the current test sample is input into the long-short-time memory network, and predicted battery usage data in the predicted time length is obtained. It can be understood that: the processing manner adopted for each test sample is the same, and in this embodiment, a test sample is taken as an example. The currently said test sample may be taken as the current test sample. And inputting historical battery use data in the current test sample into a long-short time memory network model for processing to obtain predicted battery use data in predicted time length.
It should be noted that, before training to obtain the long-short time memory network, the long-short time memory network may be constructed first, where the construction of the long-short time memory network may be: and setting an attention module at the previous level of the output layer of the long-short-time memory network to perform attention processing on the extracted features based on the attention module so as to obtain the predicted usage data. It is understood that the attention module is set in the previous layer of the output layer of the long-short-term memory network, so as to perform attention processing on the extracted features based on the attention module, and obtain the predicted usage data.
And S230, correcting model parameters in the long-short-time memory network based on the predicted battery use data and the actual battery use data.
It can be understood that the actual battery usage data and the predicted battery usage data in the current test sample are obtained, and the loss value can be determined through two data loss processes, so as to correct the model parameters in the long-short-term memory network based on the loss value. S240, converging the loss function in the long-short-time memory network model to serve as a training target, and obtaining the long-short-time memory network.
It can be understood that when the loss function in the long-short-time memory network model is detected to be converged, the obtained long-short-time memory network model can be used as a long-short-time memory network for subsequent data processing.
In this embodiment, the predicted usage data is the predicted usage data obtained by inputting the capacitance data, the voltage data and the internal resistance value increase data of the storage battery at two adjacent moments into the long-short memory network model, obtaining a first feature through an embedded extraction, inputting the first feature into the long-short memory network again for processing to obtain a second feature, and performing weighted attention processing on the first feature and the second feature by the attention module to obtain a third feature, wherein the long-short memory network model processes the predicted usage data of the third feature.
According to the technical scheme, the long-short-time memory network is constructed; the construction of the long-short-time memory network comprises the following steps: and an attention module is arranged at the previous level of the output layer of the long-short-time memory network so as to perform attention processing on the extracted features based on the attention module to obtain the predicted use data, thereby improving the accurate and effective judgment of whether the storage battery is healthy or not.
Example III
Fig. 4 is a block diagram of a health evaluation device for a valve-regulated sealed lead-acid battery according to a third embodiment of the present invention. The device comprises: a data acquisition module 410, a data prediction module 420, and an evaluation result determination module 430.
A data acquisition module 410, configured to acquire battery usage data of the battery to be monitored in a history period; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increase data at two adjacent moments; the data prediction module 420 is configured to input the battery usage data into a long-short-time memory network obtained by training in advance, so as to obtain predicted usage data within a predicted duration; the long-short-time memory network comprises an attention module; the evaluation result determination module 430 determines the health evaluation data of the battery to be monitored based on the predicted usage data.
According to the technical scheme provided by the embodiment of the invention, the battery use data of the storage battery to be monitored in the history duration is obtained; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increase data at two adjacent moments; inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain predicted use data in predicted duration; the long-short-time memory network comprises an attention module; and determining health evaluation data of the storage battery to be monitored based on the predicted usage data.
On the basis of the technical scheme, the device further comprises: the network construction module is used for constructing the long-short-time memory network, and the network construction module is specifically used for: and setting an attention module at the previous level of the output layer of the long-short-time memory network to perform attention processing on the extracted features based on the attention module so as to obtain the predicted usage data.
On the basis of the technical schemes, the device further comprises: the network training module is used for specifically: training the constructed long-short-time memory network; obtaining a plurality of test samples, wherein the test samples comprise historical battery usage data in a historical time period and actual battery usage data in a predicted time period, inputting the historical battery usage data in a current test sample into the long-short-time memory network for the plurality of test samples to obtain predicted battery usage data in the predicted time period, correcting model parameters in the long-short-time memory network based on the predicted battery usage data and the actual battery usage data, and converging a loss function in the long-short-time memory network model to serve as a training target to obtain the long-short-time memory network.
On the basis of the technical scheme, the historical time comprises at least one acquisition time point, the time intervals of two adjacent acquisition time points are the same, the predicted time comprises at least one predicted time point, and the predicted time point and the acquisition time point are continuous.
On the basis of the technical scheme, the data prediction module comprises:
the feature extraction unit is used for inputting the battery use data into the long-short-time memory network, extracting first features through at least one embedded layer, and then inputting the battery use data into the long-short-time memory network to process the first features so as to obtain second features;
the feature processing unit is used for carrying out weighted attention processing on the first features extracted by the at least one embedded layer based on the attention module and outputting second features;
the data prediction unit is used for processing the second characteristic based on an output layer in the long-short-time memory network to obtain predicted use data in the predicted duration;
the prediction classification unit is used for inputting the characteristics corresponding to the prediction use data into the activation function layer to obtain a prediction classification result corresponding to the prediction use data;
a health degree evaluation data determining unit for determining health evaluation data of the storage battery to be detected based on the predicted usage data and predetermined battery data of the storage battery in various health states;
wherein the health assessment data comprises a health assessment grade
On the basis of the technical scheme, the data acquisition module is further used for:
acquiring battery use data of a storage battery to be monitored in a history time; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increasing data at two adjacent moments.
On the basis of the above technical solutions, the data prediction module is further configured to:
inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain predicted use data in predicted duration; the long-short-time memory network comprises an attention module.
On the basis of the technical schemes, the evaluation result determining module is used for determining health evaluation data of the storage battery to be detected based on the predicted usage data and battery data of the storage battery in various health states, which are determined in advance;
wherein the health assessment data includes a health assessment grade.
According to the technical scheme, the battery use data of the storage battery to be monitored in the history duration is obtained; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increase data at two adjacent moments; inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain predicted use data in predicted duration; the long-short-time memory network comprises an attention module; based on the predicted use data, the health evaluation data of the storage battery to be monitored is determined, the problem that whether the lead-acid storage battery has faults or not cannot be effectively determined in advance due to the fact that a unified standard method is not available at present is solved, namely, the problem that the lead-acid storage battery cannot be timely handled is solved, the predicted use data is determined by combining the battery use data in the history duration, the health evaluation data of the storage battery to be monitored is determined based on the predicted data, and whether the lead-acid storage battery has faults or not can be determined based on the health evaluation data, so that the effect of preventing is effectively achieved.
The health degree evaluation device of the valve-controlled sealed lead-acid storage battery provided by the embodiment of the invention can execute the health degree evaluation method of the valve-controlled sealed lead-acid storage battery provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 5 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. Fig. 5 shows a block diagram of an exemplary electronic device 50 suitable for use in implementing the embodiments of the present invention. The electronic device 50 shown in fig. 5 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 5, the electronic device 50 is embodied in the form of a general purpose computing device. Components of electronic device 50 may include, but are not limited to: one or more processors or processing units 501, a system memory 502, and a bus 503 that connects the various system components (including the system memory 502 and processing units 501).
Bus 503 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Electronic device 50 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by electronic device 50 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 502 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 504 and/or cache memory 505. Electronic device 50 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 506 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 5, commonly referred to as a "hard disk drive"). Although not shown in fig. 5, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 503 through one or more data medium interfaces. Memory 502 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the invention.
A program/utility 508 having a set (at least one) of program modules 507 may be stored, for example, in memory 502, such program modules 507 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 507 typically perform the functions and/or methods of the described embodiments of the invention.
The electronic device 50 may also communicate with one or more external devices 509 (e.g., keyboard, pointing device, display 510, etc.), one or more devices that enable a user to interact with the electronic device 50, and/or any device (e.g., network card, modem, etc.) that enables the electronic device 50 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 511. Also, the electronic device 50 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet, through a network adapter 512. As shown, the network adapter 512 communicates with other modules of the electronic device 50 over the bus 503. It should be appreciated that although not shown in fig. 5, other hardware and/or software modules may be used in connection with electronic device 50, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 501 executes various functional applications and data processing by running a program stored in the system memory 502, for example, to implement the method for evaluating the health of a valve-regulated sealed lead-acid battery according to the embodiment of the present invention.
Example five
The fifth embodiment of the present invention also provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are for performing a method of health assessment of a valve-regulated sealed lead-acid battery. The method comprises the following steps:
acquiring battery use data of a storage battery to be monitored in a history time; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increase data at two adjacent moments;
inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain predicted use data in predicted duration; the long-short-time memory network comprises an attention module;
and determining health evaluation data of the storage battery to be monitored based on the predicted usage data.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for embodiments of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (10)
1. A health evaluation method of a valve-controlled sealed lead-acid storage battery is characterized by being applied to a power grid and comprising the following steps:
acquiring battery use data of a storage battery to be monitored in a history time; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increase data at two adjacent moments;
inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain predicted use data in predicted duration; the long-short-time memory network comprises an attention module;
and determining health evaluation data of the storage battery to be monitored based on the predicted usage data.
2. The method as recited in claim 1, further comprising:
constructing the long-short-time memory network;
the construction of the long-short-time memory network comprises the following steps:
and setting an attention module at the previous level of the output layer of the long-short-time memory network to perform attention processing on the extracted features based on the attention module so as to obtain the predicted usage data.
3. The method as recited in claim 2, further comprising:
training the constructed long-short-time memory network,
the training of the constructed long-short-time memory network comprises the following steps:
obtaining a plurality of test samples, wherein the test samples comprise historical battery use data in historical time and actual battery use data in predicted time;
for the plurality of test samples, historical battery usage data in the current test sample is input into the long-short-time memory network to obtain predicted battery usage data in the predicted time length;
correcting model parameters in the long-short-term memory network based on the predicted battery usage data and the actual battery usage data;
and converging the loss function in the long-short-time memory network model to be used as a training target, so as to obtain the long-short-time memory network.
4. A method according to claim 1 or 3, wherein the historical time period comprises at least one acquisition time point, the time periods of two adjacent acquisition time points are the same, the predicted time period comprises at least one predicted time point, and the predicted time point and the acquisition time point are continuous.
5. The method of claim 1, wherein the inputting the battery usage data into a pre-trained long and short duration memory network to obtain predicted usage data for a predicted duration comprises:
inputting the battery use data into the long-short-time memory network, extracting first characteristics through at least one embedded layer, and processing the first characteristics to obtain second characteristics;
the attention module carries out weighted attention processing on the first feature and the second feature extracted by at least one embedded layer and outputs a third feature;
and processing the third characteristic based on an output layer in the long-short time memory network to obtain the predicted use data in the predicted time length.
6. The method as recited in claim 5, further comprising:
inputting the characteristics corresponding to the predicted use data into an activation function layer to obtain a predicted classification result corresponding to the predicted use data;
wherein the prediction classification result comprises a health degree evaluation category.
7. The method of claim 1, wherein the determining health assessment data for the battery to be monitored based on the predicted usage data comprises:
determining health evaluation data of the storage battery to be monitored based on the predicted usage data and predetermined battery data of the storage battery in various health states;
wherein the health assessment data includes a health assessment grade.
8. A health assessment device for a valve-regulated sealed lead-acid battery, applied to a power grid, comprising:
the data acquisition module is used for acquiring battery use data of the storage battery to be monitored in the history time; the battery usage data comprises at least one battery capacity data, at least one voltage data and internal resistance value increase data at two adjacent moments;
the data prediction module is used for inputting the battery use data into a long-short-time memory network obtained through pre-training to obtain prediction use data in a prediction duration; the long-short-time memory network comprises an attention module;
and the evaluation result determining module is used for determining the health evaluation data of the storage battery to be monitored based on the predicted use data.
9. An electronic device, the electronic device comprising:
one or more processors;
storage means for storing one or more programs,
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of health assessment of a valve-regulated sealed lead-acid battery of claims 1-7.
10. A storage medium containing computer executable instructions, which when executed by a computer processor, are for performing the method of health assessment of a valve-regulated sealed lead-acid battery of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311801077.4A CN117805652A (en) | 2023-12-25 | 2023-12-25 | Health evaluation method, device and equipment for valve-controlled sealed lead-acid storage battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311801077.4A CN117805652A (en) | 2023-12-25 | 2023-12-25 | Health evaluation method, device and equipment for valve-controlled sealed lead-acid storage battery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117805652A true CN117805652A (en) | 2024-04-02 |
Family
ID=90424782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311801077.4A Pending CN117805652A (en) | 2023-12-25 | 2023-12-25 | Health evaluation method, device and equipment for valve-controlled sealed lead-acid storage battery |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117805652A (en) |
-
2023
- 2023-12-25 CN CN202311801077.4A patent/CN117805652A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| James et al. | Intelligent time-adaptive transient stability assessment system | |
| KR102439041B1 (en) | Method and apparatus for diagnosing defect of battery cell based on neural network | |
| CN107870306A (en) | A kind of lithium battery charge state prediction algorithm based under deep neural network | |
| CN111126700B (en) | Energy consumption prediction method, device, equipment and storage medium | |
| KR102615145B1 (en) | Battery effective charging data identification method and device based on deep learning, and medium | |
| CN115356639B (en) | Intelligent health monitoring method and system for bidirectional lithium ion battery | |
| CN112380773A (en) | Fuel cell degradation prediction method, device and equipment based on transfer learning | |
| WO2022252729A1 (en) | Method and apparatus for detecting vehicle battery imbalance, electronic device and storage medium | |
| CN114386537A (en) | Lithium battery fault diagnosis method and device based on Catboost and electronic equipment | |
| CN112115636A (en) | Method and system for predicting insulation aging life of power cable in advance | |
| CN113987294A (en) | CVT (continuously variable transmission) online fault diagnosis method based on genetic optimization GRU (generalized regression Unit) neural network | |
| Guomin et al. | Deep learning‐based fault location of DC distribution networks | |
| Yang et al. | Investigating black-box model for wind power forecasting using local interpretable model-agnostic explanations algorithm: Why should a model be trusted? | |
| Qu et al. | A parameter and resolution adaptive algorithm for rapid detection of ramp events in different timescale databases of the power system | |
| Mei et al. | A data‐driven approach to state assessment of the converter valve based on oversampling and Shapley additive explanations | |
| CN117273376A (en) | Electric quantity prediction method, system, computer equipment and storage medium | |
| CN117805652A (en) | Health evaluation method, device and equipment for valve-controlled sealed lead-acid storage battery | |
| Chi et al. | Zoning‐based candidate bus selection for dynamic VAR planning in power system towards voltage resilience | |
| Zhang et al. | CNN‐LSTM based power grid voltage stability emergency control coordination strategy | |
| CN112685900B (en) | Power load simulation method for representing impact load power characteristics | |
| CN114487643A (en) | On-spot handing-over of extra-high voltage GIL equipment is accepted and is synthesized test platform | |
| CN115267586A (en) | Lithium battery SOH evaluation method | |
| Hu et al. | Health factor analysis and remaining useful life prediction for batteries based on a cross-cycle health factor clustering framework | |
| Ma et al. | Remaining Useful Life Prediction Based on LSTM with Peephole for PEMFC | |
| An et al. | Transient stability margin prediction under the concept of security region of power systems based on the long short-term memory network and attention mechanism |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |