CN111856299A - Method, device and equipment for determining power supply state - Google Patents
Method, device and equipment for determining power supply state Download PDFInfo
- Publication number
- CN111856299A CN111856299A CN202010742827.5A CN202010742827A CN111856299A CN 111856299 A CN111856299 A CN 111856299A CN 202010742827 A CN202010742827 A CN 202010742827A CN 111856299 A CN111856299 A CN 111856299A
- Authority
- CN
- China
- Prior art keywords
- cnn
- model
- state
- storage battery
- trained
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/385—Arrangements for measuring battery or accumulator variables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computational Linguistics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The embodiment of the invention provides a method, a device and equipment for determining a power supply state, wherein the method comprises the following steps: acquiring operation characteristic parameters of each storage battery in power supply equipment; inputting the operation characteristic parameters into a trained detection model, and processing the operation characteristic parameters by the detection model to determine that the respective state of each storage battery is a normal state or a fault state; and determining the running state of the power supply equipment according to the respective states of the storage batteries. Through the process, the automatic detection of the power state is realized, the performance parameters of each storage battery do not need to be checked manually one by one, the labor cost and the time cost of the power state detection are reduced, and the efficiency of the power state detection is improved. In addition, the detection of the power supply state is realized through the detection model obtained through machine learning training, and compared with a manual checking mode, the accuracy of the detection result is improved.
Description
Technical Field
The present invention relates to the field of data processing technologies, and in particular, to a method, an apparatus, and a device for determining a power state.
Background
The power supply device is an important component of the communication system, and if the power supply device fails, the power supply quality is reduced or the power supply is interrupted, so that the communication system fails. Therefore, in practical applications, the operating state of the power supply device needs to be detected periodically.
In the prior art, a detection method is usually adopted in which a professional manually collects performance parameters of each storage battery in power supply equipment, and then checks whether the performance parameters of each storage battery exceed a normal range, thereby determining the operating state of the power supply equipment.
However, the above detection method has low working efficiency and large workload, and requires much labor cost and time cost.
Disclosure of Invention
The invention provides a method, a device and equipment for determining a power state, which are used for reducing the labor cost and the time cost required by power state detection and improving the detection efficiency of the power state.
In a first aspect, the present invention provides a method for determining a power state, including:
acquiring operation characteristic parameters of each storage battery in power supply equipment;
inputting the operation characteristic parameters into a trained detection model, and processing the operation characteristic parameters by the detection model to determine that the respective state of each storage battery is a normal state or a fault state;
and determining the running state of the power supply equipment according to the respective states of the storage batteries.
In a possible implementation manner, acquiring operation characteristic parameters of each storage battery in the power supply device includes:
respectively acquiring a plurality of index parameters corresponding to each section of storage battery, wherein the index parameters are acquired in a charging and discharging test of the storage battery;
and determining a first index parameter meeting a preset condition in the index parameters as an operation characteristic parameter of the storage battery.
In one possible implementation, the preset condition includes at least one of the following:
a first association relation exists between the first index parameter and a preset alarm;
alternatively, the first and second electrodes may be,
a second incidence relation exists between the first index parameter and a second index parameter, wherein the second index parameter is other index parameters except the first index parameter in the plurality of index parameters;
alternatively, the first and second electrodes may be,
the oscillogram corresponding to the first index parameter meets the preset characteristics.
In a possible implementation manner, the detection model is a convolutional neural network CNN-support vector machine SVM model.
In a possible implementation manner, the detection model is obtained by training in the following manner:
acquiring a plurality of groups of first training samples, wherein each group of first training samples comprises sample operation characteristic parameters and sample states corresponding to a sample storage battery;
and constructing a CNN-SVM model, and training the CNN-SVM model by adopting the multiple groups of first training samples to obtain a trained CNN-SVM model.
In one possible implementation, constructing a CNN-SVM model, and training the CNN-SVM model using the plurality of groups of first training samples to obtain a trained CNN-SVM model, includes:
constructing a CNN model to be trained, wherein the CNN model comprises a convolutional layer, a sampling layer and a classification layer;
training the CNN model to be trained by adopting the multiple groups of first training samples to obtain a trained CNN model;
connecting the sampling layer and the classification layer in the trained CNN model with an SVM classifier to obtain a CNN-SVM model to be trained;
and training the CNN-SVM model to be trained by adopting the multiple groups of first training samples to obtain the trained CNN-SVM model.
In a possible implementation manner, after obtaining the trained CNN-SVM model, the method further includes:
acquiring a plurality of groups of second training samples, wherein each group of second training samples comprises sample operation characteristic parameters and sample states corresponding to the sample storage battery;
and testing the trained CNN-SVM model by adopting the multiple groups of second training samples, and determining that the test result meets a preset condition.
In a second aspect, the present invention provides an apparatus for determining a power state, comprising:
the acquisition module is used for acquiring the operation characteristic parameters of each storage battery in the power supply equipment;
the detection module is used for inputting the operation characteristic parameters into a trained detection model, processing the operation characteristic parameters by the detection model and determining that the respective state of each storage battery is a normal state or a fault state;
and the determining module is used for determining the running state of the power supply equipment according to the respective states of the storage batteries.
In a possible implementation manner, the obtaining module is specifically configured to:
respectively acquiring a plurality of index parameters corresponding to each section of storage battery, wherein the index parameters are acquired in a charging and discharging test of the storage battery;
and determining a first index parameter meeting a preset condition in the index parameters as an operation characteristic parameter of the storage battery.
In one possible implementation, the preset condition includes at least one of the following:
a first association relation exists between the first index parameter and a preset alarm;
alternatively, the first and second electrodes may be,
a second incidence relation exists between the first index parameter and a second index parameter, wherein the second index parameter is other index parameters except the first index parameter in the plurality of index parameters;
alternatively, the first and second electrodes may be,
the oscillogram corresponding to the first index parameter meets the preset characteristics.
In a possible implementation manner, the detection model is a convolutional neural network CNN-support vector machine SVM model.
In a possible implementation manner, the detection model is obtained by training in the following manner:
acquiring a plurality of groups of first training samples, wherein each group of first training samples comprises sample operation characteristic parameters and sample states corresponding to a sample storage battery;
and constructing a CNN-SVM model, and training the CNN-SVM model by adopting the multiple groups of first training samples to obtain a trained CNN-SVM model.
In one possible implementation, constructing a CNN-SVM model, and training the CNN-SVM model using the plurality of groups of first training samples to obtain a trained CNN-SVM model, includes:
constructing a CNN model to be trained, wherein the CNN model comprises a convolutional layer, a sampling layer and a classification layer;
training the CNN model to be trained by adopting the multiple groups of first training samples to obtain a trained CNN model;
connecting the sampling layer and the classification layer in the trained CNN model with an SVM classifier to obtain a CNN-SVM model to be trained;
and training the CNN-SVM model to be trained by adopting the multiple groups of first training samples to obtain the trained CNN-SVM model.
In a possible implementation manner, after obtaining the trained CNN-SVM model, the method further includes:
acquiring a plurality of groups of second training samples, wherein each group of second training samples comprises sample operation characteristic parameters and sample states corresponding to the sample storage battery;
and testing the trained CNN-SVM model by adopting the multiple groups of second training samples, and determining that the test result meets a preset condition.
In a third aspect, an embodiment of the present invention provides an electronic device, including: a memory for storing a computer program and a processor for executing the computer program to perform the method according to any of the first aspect.
In a fourth aspect, the present invention provides a computer-readable storage medium including a computer program, which when executed by a processor implements the method according to any one of the first aspect.
The embodiment of the invention provides a method, a device and equipment for determining a power supply state, wherein the method comprises the following steps: acquiring operation characteristic parameters of each storage battery in power supply equipment; inputting the operation characteristic parameters into a trained detection model, and processing the operation characteristic parameters by the detection model to determine that the respective state of each storage battery is a normal state or a fault state; and determining the running state of the power supply equipment according to the respective states of the storage batteries. Through the process, the automatic detection of the power state is realized, the performance parameters of each storage battery do not need to be checked manually one by one, the labor cost and the time cost of the power state detection are reduced, and the efficiency of the power state detection is improved. In addition, the detection of the power supply state is realized through the detection model obtained through machine learning training, and compared with a manual checking mode, the accuracy of the detection result is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a diagram illustrating a possible system architecture to which embodiments of the present invention are applicable;
fig. 2 is a schematic flowchart of a method for determining a power state according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a power state determination process provided by an embodiment of the invention;
FIG. 4 is a schematic flowchart of a training method for a detection model according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a CNN-SVM model provided in an embodiment of the present invention;
fig. 6 is a schematic structural diagram of a power state determination apparatus according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The terms "first," "second," "third," "fourth," and the like in the description and in the claims, as well as in the drawings, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
The power supply device is an important component of the communication system, and if the power supply device fails, the power supply quality is reduced or the power supply is interrupted, so that the communication system fails. Therefore, in practical applications, the operating state of the power supply device needs to be detected periodically.
In general, the number of power supply devices in a communication system is large. For example, a communication system may include a plurality of (e.g., 8) rooms, each of which has a plurality of (e.g., 120) power supply devices disposed therein. Each power supply device includes a plurality of (e.g., 24) storage batteries, and each power supply device may also be referred to as a battery pack.
In a communication system, a lead-acid battery pack operates in a float charge mode. In order to avoid lead sulfate precipitation on the polar plate caused by improper control of the floating charging current and further influence the capacity and the service life of the storage battery, the storage battery is charged and discharged periodically. The process of the floating charge of the storage battery is as follows: firstly, the storage battery pack is charged, and then the charging equipment and the storage battery pack are connected in parallel to work together. The charging equipment is used for supplying power to a normal load on the direct current bus and floating charging the storage battery pack with a small current so as to compensate the electric quantity lost due to self-discharge. This allows the battery to be constantly fully charged, thereby extending the life of the battery. When the direct current bus has impact load, the storage battery pack plays a power supply task (such as providing closing current) of the impact load due to small internal resistance. When the charging equipment is powered off due to the fault of the alternating current system, the storage battery pack is responsible for the power supply task of all the direct current loads until the fault is relieved and the charging equipment recovers power supply. The accumulator can be operated in floating charge mode.
When the storage battery is charged and discharged periodically, the storage battery is generally charged and discharged in a check manner once every predetermined time period (for example, three months). The comparative charge/discharge is to discharge 60% of the battery capacity and then fully charge the battery pack so that the full capacity of the entire battery pack is achieved. When the charge and the discharge are carried out regularly, the current with the discharge rate of 10h is required to be used, and the discharge with small current, especially the discharge with small current and the charge with large current, cannot be used. This is because the lead-acid battery has different chemical reactions of the plates due to different charging and discharging currents during charging and discharging.
In order to ensure the normal operation of the storage battery, the operation state of the storage battery after charging and discharging needs to be detected. In the prior art, the charging and discharging time of the storage battery is generally arranged in a time window from 12 am to 5 pm in the evening for safety. After the charging and discharging test is finished, 5 hours are needed to check the performance parameters of each storage battery to judge whether the storage battery has faults or hidden trouble faults. In the process, the state of the storage battery needs to be checked and analyzed with high labor cost and time cost after the charge and discharge test. Taking 23040 storage batteries in 8 machine rooms as an example, the data checked after each charge and discharge test is up to 453 tens of thousands, and the checking of the data requires a great deal of effort of professional maintenance personnel. In addition, when the storage battery has the hidden trouble of failure, the failure is difficult to find through the manual checking process.
In order to solve at least one of the above problems, embodiments of the present invention provide a method for determining a power state, which can monitor an operating state of a power supply device by a power state determining device instead of manually, thereby reducing labor cost and time cost.
Fig. 1 is a schematic diagram of a possible system architecture to which the embodiment of the present invention is applicable. As shown in fig. 1, each power supply device in the computer room is connected to the database. And in the charge and discharge test of each power supply device, acquiring the index parameters of each storage battery and storing the index parameters into a database. For example, each power supply device or each storage battery may be connected with a data acquisition device, and in the process of charging and discharging the storage battery, the data acquisition device acquires index parameters of the storage battery and uploads the acquired data to a database for storage. The data acquisition device can acquire data in real time and also can acquire data once every preset time (for example, 3 minutes).
With continued reference to fig. 1, the database is connected to a determination means of the power status. The power supply state determining device may read the index parameters of the storage batteries from the database, and determine the state of the power supply apparatus according to the read index parameters.
In this embodiment, the database and the power state determination device may be integrated in the same electronic device, or may be integrated in different electronic devices, which is not limited in this embodiment.
The technical solution of the present invention will be described in detail below with specific examples. The following several specific embodiments may be combined with each other, and details of the same or similar concepts or processes may not be repeated in some embodiments.
Fig. 2 is a schematic flow chart of a method for determining a power state according to an embodiment of the present invention. The method of the present embodiment may be performed by the determination means of the power status in fig. 1. As shown in fig. 2, the method of this embodiment may include:
s201: and acquiring the operating characteristic parameters of each storage battery in the power supply equipment.
With reference to fig. 1, the determining device of the power state can obtain the operation characteristic parameters of each storage battery in the power supply equipment from the database.
It should be noted that the method for determining the power state in this embodiment may be executed in real time during the process of performing the charge and discharge test on the power supply device. Illustratively, the power supply device reports the acquired data to the database in real time during the charging and discharging processes, and the determining device of the power supply state acquires the data acquired by the power supply device from the database. The method for determining the power supply state in this embodiment may also be performed after the power supply device has completed the charge and discharge test. Illustratively, the power supply device reports the acquired data to the database in real time during the charging and discharging processes. After the power supply equipment is charged and discharged, the determining device of the power supply state can read the data collected by the power supply equipment to be detected from the database according to the actual application requirement.
In order to ensure the completeness of data recorded in the database, in the charging and discharging process of each storage battery, a plurality of index parameters of the storage battery are acquired in real time, and the acquired index parameters are stored in the database. For example, the collected index parameters of each battery may include, but are not limited to: the system comprises a machine room identifier, a machine room name, a power supply device name, an alarm name, a voltage value, a current value, a resistance value, an impedance value, a current floating value, a voltage floating value, single internal resistance, single voltage, single battery temperature, a storage battery pack section identifier, a storage battery working state, a battery pack working state, an internal resistance initial value ratio, an internal resistance initial value ratio, an acquisition time, a recording time and the like.
The operation characteristic parameter in the present embodiment refers to one or more index parameters that can be used to determine the state of the storage battery.
In a possible implementation manner, S201 may specifically include: respectively acquiring a plurality of index parameters corresponding to each storage battery from a database, wherein the index parameters are acquired in a charging and discharging test of the storage battery; and determining a first index parameter meeting a preset condition in the index parameters as an operation characteristic parameter of the storage battery.
The preset condition may include one or more of the following conditions.
(1) A first association relation exists between the first index parameter and the preset alarm.
Specifically, if the value of the first index parameter exceeds a preset range, some alarms are generated, and the first index parameter is used as the operation characteristic parameter of the storage battery. That is, the first index parameter having the alarm sensitivity may be selected from the plurality of index parameters as the operation characteristic parameter. For example, since index parameters such as a voltage value, a current value, a resistance value, an impedance value, a current floating value, a voltage floating value, a cell internal resistance, a cell voltage, and a cell temperature have alarm sensitivity, and a change in the index parameters more easily causes alarm information to appear in the power supply device, the index parameters may be determined as the operation characteristic parameters of the storage battery.
(2) And a second incidence relation exists between the first index parameter and a second index parameter, wherein the second index parameter is other index parameters except the first index parameter in the plurality of index parameters.
Specifically, if the change of the first index parameter is likely to cause the change of the second index parameter, both the first index parameter and the second index parameter may be used as the operation characteristic parameters of the storage battery. That is, an index parameter having a relationship may be selected from a plurality of index parameters as the operation characteristic parameter. For example, since the resistance value and the impedance value have a mathematical relationship with the voltage value, the current floating value and the voltage floating value, the index parameter may be determined as the operation characteristic parameter of the battery.
(3) The oscillogram corresponding to the first index parameter meets the preset characteristics.
Specifically, if the oscillogram corresponding to the first index parameter is convenient to be described by a mathematical formula, the first index parameter may be used as the operation characteristic parameter of the storage battery. That is, an index parameter that is convenient to be described using a mathematical formula may be selected from a plurality of index parameters as the operation characteristic parameter. For example, since the waveform diagrams corresponding to the voltage value and the current value satisfy the characteristics of a sine function, and the waveform diagrams corresponding to the resistance value and the impedance value are also convenient to describe by using a mathematical formula, the index parameter can be determined as the operation characteristic parameter of the storage battery.
In one example, the operation characteristic parameters of the storage battery determined by adopting the one or more preset conditions include: the device comprises a voltage value, a current value, a resistance value, an impedance value, a current floating value, a voltage floating value, single internal resistance, single voltage, single 1 battery temperature, a storage battery section identifier, a storage battery working state, an internal resistance initial value ratio, an internal resistance initial ratio and an internal resistance upper ratio.
It should be understood that the operation characteristic parameters of the storage battery are obtained by screening from the index parameters by adopting the one or more preset conditions, so that the number of the index parameters is reduced, and the calculated amount is reduced; on the other hand, the selected index parameters are easier to reflect the running performance characteristics of the storage battery, so that the state of the storage battery determined by the index parameters is more accurate.
S202: and inputting the operation characteristic parameters into a trained detection model, and processing the operation characteristic parameters by the detection model to determine that the respective state of each storage battery is a normal state or a fault state.
In this embodiment, after the operation characteristic parameters of the storage battery are obtained, the state of the storage battery can be determined by using a detection model trained in advance. The state of the battery can be classified into a normal state or a fault state. The normal state refers to a state that the storage battery is in normal operation, and the fault state refers to a state that the storage battery is in fault or about to be in fault.
In this embodiment, the fault state includes both a state in which the storage battery has failed and a state in which the storage battery is about to fail (or has a hidden fault hazard). That is to say, when the storage battery is in a normal state at present but has a potential fault, the state of the storage battery is also determined as a fault state, so that the fault can be found and avoided in time, and the working safety of the storage battery is further ensured.
Fig. 3 is a schematic diagram of a determination process of a power state according to an embodiment of the present invention. As shown in fig. 3, the power supply state determination device is provided with a detection pattern. The detection model is obtained by adopting a deep learning-based method for training in advance. The structure and the training process of the detection model are not limited in this embodiment, and a possible training manner may be referred to in the detailed description of the subsequent embodiments. Referring to fig. 3, the operation characteristic parameters of the storage battery are input into the detection model, and the detection model processes the operation characteristic parameters and outputs the state of the storage battery as a normal state or a fault state.
In some examples, the detection model may detect the states of the batteries in the power supply device at the same time, that is, the operation characteristic parameters of the batteries are input into the detection model at the same time, and the states of the batteries are output by the detection model at the same time. In other examples, the detection model may detect the states of each storage battery in sequence, that is, the operation characteristic parameters of each storage battery are respectively input into the detection model, and the states of each storage battery are sequentially output by the detection model.
In a possible embodiment, before inputting the operation characteristic parameter to the detection model, the method may further include: and preprocessing the operation characteristic parameters. Among them, the pretreatment includes but is not limited to: data cleaning processing, numeralization processing, normalization processing and the like.
For example, since the communication system may include power supply devices generated by different manufacturers, the operating characteristic parameters of the storage battery collected from the respective power supply devices may have different attributes, for example, some of the operating characteristic parameters are numeric types and some of the operating characteristic parameters are character types, or even if the types are the same, the value ranges of the respective parameters may be different. Therefore, the running characteristic parameters of the character types can be subjected to numerical processing, so that the detection model can be conveniently used; moreover, normalization processing can be performed on the operation characteristic parameters of the numerical value types, so that prediction errors of the detection model caused by different value ranges are avoided.
S203: and determining the running state of the power supply equipment according to the respective states of the storage batteries.
For a certain power supply device, after the state of each storage battery in the power supply device is determined, the running state of the power supply device can be determined. Specifically, if a storage battery in a failure state is present in the power supply apparatus, the operating state of the power supply apparatus is determined as the failure state. And if the storage battery in the fault state does not exist in the power supply equipment, determining the running state of the power supply equipment as a normal state.
Optionally, after the operating state of the power supply device is determined, the operating state of the power supply device may be visually displayed. For example, if the operation state of the power supply apparatus is a normal state, the power supply apparatus displays a first color (for example, green), and if the operation state of the power supply apparatus is a failure state, the power supply apparatus displays a second color (for example, red). When a user clicks the power supply equipment in the fault state, the storage batteries in the power supply equipment in the fault state and the corresponding operation characteristic parameters of the storage batteries in the fault state can be further displayed, so that maintenance personnel can find the fault in time and conveniently troubleshoot the fault.
The method for determining the power state provided by the embodiment includes: acquiring operation characteristic parameters of each storage battery in power supply equipment; inputting the operation characteristic parameters into a trained detection model, and processing the operation characteristic parameters by the detection model to determine that the respective state of each storage battery is a normal state or a fault state; and determining the running state of the power supply equipment according to the respective states of the storage batteries. Through the process, the automatic detection of the power state is realized, the performance parameters of each storage battery do not need to be checked manually one by one, the labor cost and the time cost of the power state detection are reduced, and the efficiency of the power state detection is improved. In addition, the detection of the power supply state is realized through the detection model obtained through machine learning training, and compared with a manual checking mode, the accuracy of the detection result is improved.
The above embodiments describe a method of detecting an operation state of a power supply apparatus using a detection model. The detection model employed in the above-described embodiments may be any model based on deep learning.
Optionally, the detection model is a Convolutional Neural Networks (CNN) -Support Vector Machine (SVM) model.
The following describes the training process of the detection model by taking the CNN-SVM model as an example and combining with the embodiment shown in fig. 4.
Fig. 4 is a schematic flow chart of a training method of a detection model according to an embodiment of the present invention. The method of the present embodiment may be performed by a power state determination device. The method of this embodiment may also be executed by other devices or apparatuses, and deploy the detection model obtained by training the detection model to the apparatus for determining the power state. As shown in fig. 4, the method of this embodiment may include:
s401: and acquiring multiple groups of first training samples, wherein each group of first training samples comprises sample operation characteristic parameters and sample states corresponding to the sample storage battery.
Specifically, a plurality of sets of first training samples may be generated according to historical acquisition data stored in the database. Each first training sample comprises a sample operation characteristic parameter and a sample state corresponding to the sample storage battery. The sample operation characteristic parameters refer to index parameters extracted from a plurality of historical index parameters corresponding to the sample storage battery acquired from the database. It can be understood that the process of extracting the index parameter is similar to the embodiment shown in fig. 3, and is not described herein again.
After the sample operation characteristic parameters corresponding to the sample storage battery are obtained, manual labeling can be performed according to the sample operation characteristic parameters. If the sample operation characteristic parameters indicate that the sample storage battery is in a normal working state, marking the sample state of the sample storage battery as a normal state; and if the sample operation characteristic parameters indicate that the sample storage battery is in a fault state or in an impending fault state, marking the sample state of the sample storage battery as the fault state.
Further, in order to ensure the robustness of the training model, the multiple sets of first training samples may include storage batteries in power supply devices generated by different manufacturers, so as to ensure the comprehensiveness of the training samples.
S402: and constructing a CNN-SVM model, and training the CNN-SVM model by adopting the multiple groups of first training samples to obtain a trained CNN-SVM model.
The CNN-SVM model comprises a CNN model and an SVM classifier. The CNN model is used for learning the sample operation characteristic parameters of the storage battery by adopting a deep learning algorithm, and the SVM classifier is used for classifying the state of the storage battery.
In this embodiment, the training process of the CNN-SVM model may include two stages, where the first stage is used to tune parameters of each layer in the CNN model, and the second stage is used to tune parameters of the SVM classifier.
In a possible implementation, S402 may specifically include the following steps (1) to (4).
(1) And constructing a CNN model to be trained, wherein the CNN model comprises a convolutional layer, a sampling layer and a classification layer.
Optionally, the CNN model may employ a LeNet-5 network structure.
(2) And training the CNN model to be trained by adopting the multiple groups of first training samples to obtain the trained CNN model.
Specifically, step (2) is a first stage training process. The parameters of each layer in the CNN model are first initialized. And inputting the sample operation characteristic parameters in the first training sample into the CNN model, and transmitting the sample operation characteristic parameters to the classification layer through the convolution layer and the sampling layer to obtain a classification result output by the CNN model. The error between the CNN model output value and the sample state in the first training sample is calculated. And adjusting parameters of each layer in the CNN model according to the error until the obtained error is smaller than the expected error or the convergence condition of the CNN model is reached. The training process of the first phase ends.
(3) And connecting the sampling layer and the classification layer in the trained CNN model with an SVM classifier to obtain the CNN-SVM model to be trained.
Fig. 5 is a schematic structural diagram of a CNN-SVM model provided in an embodiment of the present invention. As shown in fig. 5, the CNN-SVM model includes: an input layer, a convolutional layer C1, a sampling layer S2, a convolutional layer C3, a sampling layer S4, and an SVM classifier. Illustrated in fig. 5 is a case where the sample operation feature parameter is a 64 × 64-dimensional feature vector. Obtaining 4 64 × 64-dimensional feature vectors after the treatment of the convolutional layer C1; after the processing of the sampling layer S2 layer, 4 feature vectors with 30 x 30 dimensions are obtained; after the treatment of the convolution layer C3, 14 characteristic vectors with 26 x 26 dimensions are obtained; after the processing of S4 layers, 14 13 × 13 dimensional feature vectors are obtained. And finally, predicting by an SVM classifier to obtain whether the state of the storage battery is a normal state or a fault state.
(4) And training the CNN-SVM model to be trained by adopting the multiple groups of first training samples to obtain the trained CNN-SVM model.
Specifically, step (4) is a second stage training process. And inputting the sample operation characteristic parameters in the first training sample into the CNN-SVM model to obtain a detection result output by the CNN-SVM model. And calculating the error between the detection result output by the CNN-SVM model and the sample state in the first training sample. And adjusting parameters of the SVM classifier in the CNN-SVM model according to the error until the obtained error is smaller than the expected error or the convergence condition of the CNN-SVM model is reached. The second phase of the training process ends.
Optionally, when the parameters of the SVM classifier are adjusted, the parameters of the SVM classifier can be adjusted and optimized by using a particle swarm algorithm.
Optionally, in order to verify the effect of the trained CNN-SVM model, the method of this embodiment may further include S403 and S404.
S403: and acquiring a plurality of groups of second training samples, wherein each group of second training samples comprises sample operation characteristic parameters and sample states corresponding to the sample storage battery.
In this embodiment, the plurality of groups of first training samples may also be referred to as training set samples, and the plurality of groups of second training samples may also be referred to as test set samples. The process of obtaining the test set samples is similar to that of obtaining the training set samples, and is not described herein again. In some examples, the ratio of the number of training set samples to the number of test set samples is 6: 4.
S404: and testing the trained CNN-SVM model by adopting the multiple groups of second training samples, and determining that the test result meets a preset condition.
Specifically, after the CNN-SVM model is trained by using the training set samples, the trained CNN-SVM model is tested by using the test set samples, and the accuracy of the CNN-SVM model is obtained according to the test result. If the accuracy is less than the predetermined value (e.g., 90%), the parameters of the CNN-SVM model may be continuously adjusted until the accuracy of the CNN-SVM model is greater than or equal to the predetermined value. And finishing the training process to obtain the trained CNN-SVM model.
Through the training process of the embodiment, the obtained CNN-SVM model can be used for detecting the state of the storage battery. The CNN-SVM model is deployed in a power supply state determining device, and the state of the storage battery can be automatically detected through the power supply state determining device.
In the embodiment, the CNN model is adopted to carry out deep learning on the running state parameters of the storage battery, and the SVM classifier is adopted to carry out classification prediction on the state of the storage battery, so that the accuracy of the state of the storage battery output by the CNN-SVM model is ensured.
Fig. 6 is a schematic structural diagram of a power state determination apparatus according to an embodiment of the present invention. The apparatus of the present embodiment may be in the form of software and/or hardware. As shown in fig. 6, the power state determination apparatus 10 provided in this embodiment may include: an acquisition module 11, a detection module 12 and a determination module 13.
The acquisition module 11 is used for acquiring operation characteristic parameters of each storage battery in the power supply equipment;
the detection module 12 is configured to input the operation characteristic parameters into a trained detection model, and the detection model processes the operation characteristic parameters to determine that the respective state of each storage battery is a normal state or a fault state;
and the determining module 13 is configured to determine the operating state of the power supply device according to the respective states of the storage batteries.
In a possible implementation manner, the obtaining module 11 is specifically configured to:
respectively acquiring a plurality of index parameters corresponding to each section of storage battery, wherein the index parameters are acquired in a charging and discharging test of the storage battery;
and determining a first index parameter meeting a preset condition in the index parameters as an operation characteristic parameter of the storage battery.
In one possible implementation, the preset condition includes at least one of the following:
a first association relation exists between the first index parameter and a preset alarm;
alternatively, the first and second electrodes may be,
a second incidence relation exists between the first index parameter and a second index parameter, wherein the second index parameter is other index parameters except the first index parameter in the plurality of index parameters;
alternatively, the first and second electrodes may be,
the oscillogram corresponding to the first index parameter meets the preset characteristics.
In a possible implementation manner, the detection model is a convolutional neural network CNN-support vector machine SVM model.
In a possible implementation manner, the detection model is obtained by training in the following manner:
acquiring a plurality of groups of first training samples, wherein each group of first training samples comprises sample operation characteristic parameters and sample states corresponding to a sample storage battery;
and constructing a CNN-SVM model, and training the CNN-SVM model by adopting the multiple groups of first training samples to obtain a trained CNN-SVM model.
In one possible implementation, constructing a CNN-SVM model, and training the CNN-SVM model using the plurality of groups of first training samples to obtain a trained CNN-SVM model, includes:
constructing a CNN model to be trained, wherein the CNN model comprises a convolutional layer, a sampling layer and a classification layer;
training the CNN model to be trained by adopting the multiple groups of first training samples to obtain a trained CNN model;
connecting the sampling layer and the classification layer in the trained CNN model with an SVM classifier to obtain a CNN-SVM model to be trained;
and training the CNN-SVM model to be trained by adopting the multiple groups of first training samples to obtain the trained CNN-SVM model.
In a possible implementation manner, after obtaining the trained CNN-SVM model, the method further includes:
acquiring a plurality of groups of second training samples, wherein each group of second training samples comprises sample operation characteristic parameters and sample states corresponding to the sample storage battery;
and testing the trained CNN-SVM model by adopting the multiple groups of second training samples, and determining that the test result meets a preset condition.
The apparatus for determining a power state provided in this embodiment may be configured to implement the technical solution in any of the above method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
Fig. 7 is a schematic structural diagram of an electronic device according to an embodiment of the present invention. As shown in fig. 7, the electronic device 20 of the present embodiment may include: a processor 21 and a memory 22; a memory 22 for storing a computer program; the processor 21 is configured to execute the computer program stored in the memory to implement the method for determining the power supply status in the above embodiment. Reference may be made in particular to the description relating to the method embodiments described above. Alternatively, the memory 22 may be separate or integrated with the processor 21.
When the memory 22 is a device independent from the processor 21, the electronic device 21 may further include: a bus 23 for connecting the memory 22 and the processor 21.
The electronic device provided in this embodiment may be configured to execute the technical solution in any of the method embodiments, and the implementation principle and the technical effect are similar, which are not described herein again.
An embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a computer program, and the computer program is used to implement the technical solutions in any of the above method embodiments.
An embodiment of the present invention further provides a chip, including: the system comprises a memory, a processor and a computer program, wherein the computer program is stored in the memory, and the processor runs the computer program to execute the technical scheme of any one of the method embodiments.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the modules is only one logical division, and other divisions may be realized in practice, for example, a plurality of modules may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or modules, and may be in an electrical, mechanical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing unit, or each module may exist alone physically, or two or more modules are integrated into one unit. The unit formed by the modules can be realized in a hardware form, and can also be realized in a form of hardware and a software functional unit.
The integrated module implemented in the form of a software functional module may be stored in a computer-readable storage medium. The software functional module is stored in a storage medium and includes several instructions to enable a computer device (which may be a personal computer, a server, or a network device) or a processor (processor) to execute some steps of the methods according to the embodiments of the present invention.
It should be understood that the Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of a method disclosed in the incorporated application may be directly implemented by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.
The memory may comprise a high-speed RAM memory, and may further comprise a non-volatile storage NVM, such as at least one disk memory, and may also be a usb disk, a removable hard disk, a read-only memory, a magnetic or optical disk, etc.
The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, the buses in the figures of the present invention are not limited to only one bus or one type of bus.
The storage medium may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disks. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.
An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an Application Specific Integrated Circuits (ASIC). Of course, the processor and the storage medium may reside as discrete components in an electronic device or host device.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for determining a power state, comprising:
acquiring operation characteristic parameters of each storage battery in power supply equipment;
inputting the operation characteristic parameters into a trained detection model, and processing the operation characteristic parameters by the detection model to determine that the respective state of each storage battery is a normal state or a fault state;
and determining the running state of the power supply equipment according to the respective states of the storage batteries.
2. The method of claim 1, wherein obtaining operating characteristic parameters of each battery in the power supply device comprises:
respectively acquiring a plurality of index parameters corresponding to each section of storage battery, wherein the index parameters are acquired in a charging and discharging test of the storage battery;
and determining a first index parameter meeting a preset condition in the index parameters as an operation characteristic parameter of the storage battery.
3. The method of claim 2, wherein the preset condition comprises at least one of:
a first association relation exists between the first index parameter and a preset alarm;
alternatively, the first and second electrodes may be,
a second incidence relation exists between the first index parameter and a second index parameter, wherein the second index parameter is other index parameters except the first index parameter in the plurality of index parameters;
alternatively, the first and second electrodes may be,
the oscillogram corresponding to the first index parameter meets the preset characteristics.
4. The method according to any one of claims 1 to 3, characterized in that the detection model is a Convolutional Neural Network (CNN) -Support Vector Machine (SVM) model.
5. The method of claim 4, wherein the detection model is trained by:
acquiring a plurality of groups of first training samples, wherein each group of first training samples comprises sample operation characteristic parameters and sample states corresponding to a sample storage battery;
and constructing a CNN-SVM model, and training the CNN-SVM model by adopting the multiple groups of first training samples to obtain a trained CNN-SVM model.
6. The method of claim 5, wherein constructing a CNN-SVM model and training the CNN-SVM model using the plurality of sets of first training samples to obtain a trained CNN-SVM model comprises:
constructing a CNN model to be trained, wherein the CNN model comprises a convolutional layer, a sampling layer and a classification layer;
training the CNN model to be trained by adopting the multiple groups of first training samples to obtain a trained CNN model;
connecting the sampling layer and the classification layer in the trained CNN model with an SVM classifier to obtain a CNN-SVM model to be trained;
and training the CNN-SVM model to be trained by adopting the multiple groups of first training samples to obtain the trained CNN-SVM model.
7. The method of claim 5, wherein after obtaining the trained CNN-SVM model, further comprising:
acquiring a plurality of groups of second training samples, wherein each group of second training samples comprises sample operation characteristic parameters and sample states corresponding to the sample storage battery;
and testing the trained CNN-SVM model by adopting the multiple groups of second training samples, and determining that the test result meets a preset condition.
8. An apparatus for determining a power state, comprising:
the acquisition module is used for acquiring the operation characteristic parameters of each storage battery in the power supply equipment;
the detection module is used for inputting the operation characteristic parameters into a trained detection model, processing the operation characteristic parameters by the detection model and determining that the respective state of each storage battery is a normal state or a fault state;
and the determining module is used for determining the running state of the power supply equipment according to the respective states of the storage batteries.
9. An electronic device, comprising: a memory for storing a computer program and a processor for executing the computer program to perform the method of any of claims 1 to 7.
10. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a computer program which, when executed by a processor, implements the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010742827.5A CN111856299A (en) | 2020-07-29 | 2020-07-29 | Method, device and equipment for determining power supply state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010742827.5A CN111856299A (en) | 2020-07-29 | 2020-07-29 | Method, device and equipment for determining power supply state |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111856299A true CN111856299A (en) | 2020-10-30 |
Family
ID=72944938
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010742827.5A Pending CN111856299A (en) | 2020-07-29 | 2020-07-29 | Method, device and equipment for determining power supply state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111856299A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3123127A1 (en) * | 2021-05-18 | 2022-11-25 | Psa Automobiles Sa | ESTIMATING THE MAXIMUM POWER OF A VEHICLE BATTERY IN THE ABSENCE OF MODELING |
| CN116923100A (en) * | 2023-09-19 | 2023-10-24 | 江西五十铃汽车有限公司 | Power battery pack repairing method and system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160003912A1 (en) * | 2013-03-14 | 2016-01-07 | Furukawa Electric Co., Ltd. | Secondary battery state detecting device and secondary battery state detecting method |
| CN107688576A (en) * | 2016-08-04 | 2018-02-13 | 中国科学院声学研究所 | The structure and tendentiousness sorting technique of a kind of CNN SVM models |
| CN109115501A (en) * | 2018-07-12 | 2019-01-01 | 哈尔滨工业大学（威海） | A kind of Civil Aviation Engine Gas path fault diagnosis method based on CNN and SVM |
| CN109740802A (en) * | 2018-12-24 | 2019-05-10 | 斑马网络技术有限公司 | Discharged or defective battery prediction processing method, device, equipment and readable storage medium storing program for executing |
| US20190157891A1 (en) * | 2017-11-20 | 2019-05-23 | The Trustees Of Columbia University In The City Of New York | Neural-network state-of-charge estimation |
| CN110188920A (en) * | 2019-04-26 | 2019-08-30 | 华中科技大学 | A kind of lithium battery method for predicting residual useful life |
| CN110190306A (en) * | 2019-06-04 | 2019-08-30 | 昆山知氢信息科技有限公司 | A kind of on-line fault diagnosis method for fuel cell system |
| US20200164763A1 (en) * | 2017-07-21 | 2020-05-28 | Quantumscape Corporation | Predictive model for estimating battery states |
| CN111308355A (en) * | 2020-03-14 | 2020-06-19 | 智洋创新科技股份有限公司 | Transformer substation storage battery state detection and analysis method based on deep learning |
| CN111652348A (en) * | 2020-02-29 | 2020-09-11 | 上海电力大学 | Power battery pack fault fusion diagnosis method and system based on improved CNN |
| US20200303938A1 (en) * | 2019-03-21 | 2020-09-24 | Microsoft Technology Licensing, Llc | Predictive management of battery operation |
-
2020
- 2020-07-29 CN CN202010742827.5A patent/CN111856299A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160003912A1 (en) * | 2013-03-14 | 2016-01-07 | Furukawa Electric Co., Ltd. | Secondary battery state detecting device and secondary battery state detecting method |
| CN107688576A (en) * | 2016-08-04 | 2018-02-13 | 中国科学院声学研究所 | The structure and tendentiousness sorting technique of a kind of CNN SVM models |
| US20200164763A1 (en) * | 2017-07-21 | 2020-05-28 | Quantumscape Corporation | Predictive model for estimating battery states |
| US20190157891A1 (en) * | 2017-11-20 | 2019-05-23 | The Trustees Of Columbia University In The City Of New York | Neural-network state-of-charge estimation |
| CN109115501A (en) * | 2018-07-12 | 2019-01-01 | 哈尔滨工业大学（威海） | A kind of Civil Aviation Engine Gas path fault diagnosis method based on CNN and SVM |
| CN109740802A (en) * | 2018-12-24 | 2019-05-10 | 斑马网络技术有限公司 | Discharged or defective battery prediction processing method, device, equipment and readable storage medium storing program for executing |
| US20200303938A1 (en) * | 2019-03-21 | 2020-09-24 | Microsoft Technology Licensing, Llc | Predictive management of battery operation |
| CN110188920A (en) * | 2019-04-26 | 2019-08-30 | 华中科技大学 | A kind of lithium battery method for predicting residual useful life |
| CN110190306A (en) * | 2019-06-04 | 2019-08-30 | 昆山知氢信息科技有限公司 | A kind of on-line fault diagnosis method for fuel cell system |
| CN111652348A (en) * | 2020-02-29 | 2020-09-11 | 上海电力大学 | Power battery pack fault fusion diagnosis method and system based on improved CNN |
| CN111308355A (en) * | 2020-03-14 | 2020-06-19 | 智洋创新科技股份有限公司 | Transformer substation storage battery state detection and analysis method based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| 李圣普等: "基于PSO-SVM的电机故障检测", 《计算机系统应用》 * |
| 李圣普等: "基于PSO-SVM的电机故障检测", 《计算机系统应用》, no. 03, 15 March 2016 (2016-03-15) * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3123127A1 (en) * | 2021-05-18 | 2022-11-25 | Psa Automobiles Sa | ESTIMATING THE MAXIMUM POWER OF A VEHICLE BATTERY IN THE ABSENCE OF MODELING |
| CN116923100A (en) * | 2023-09-19 | 2023-10-24 | 江西五十铃汽车有限公司 | Power battery pack repairing method and system |
| CN116923100B (en) * | 2023-09-19 | 2024-01-26 | 江西五十铃汽车有限公司 | Power battery pack repairing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8306781B2 (en) | Professional diagnosis method of battery performance analysis | |
| CN106154180B (en) | Energy-storage battery charge/discharge anomaly detection method and detection system | |
| KR20200017367A (en) | Apparatus for battery diagnosis | |
| CN108333548A (en) | Insulation resistance measuring apparatus and fault self-diagnosis method | |
| CN111856299A (en) | Method, device and equipment for determining power supply state | |
| CN115061049B (en) | Method and system for rapidly detecting UPS battery fault of data center | |
| CN108802535A (en) | Screening technique, dominant interferer recognition methods and device, server and storage medium | |
| CN111239633B (en) | Battery pack pressure difference reason analysis method and device and computer equipment | |
| CN115480180A (en) | New energy battery health diagnosis and analysis method | |
| CN114720899A (en) | Retired battery echelon utilization and sorting method and system, electronic equipment and storage medium | |
| US20240027537A1 (en) | Battery management apparatus and method | |
| CN114878960A (en) | Fault diagnosis method, storage medium, power acquisition terminal, and fault diagnosis system | |
| CN113447840A (en) | Lithium ion battery sorting method and device | |
| JP2001250590A (en) | Method for deciding deterioration of storage battery | |
| US20220268843A1 (en) | Battery analysis apparatus and method | |
| CN114487884A (en) | Battery detection method and device, battery system and electronic equipment | |
| CN114002603B (en) | Method and device for identifying battery cell and computer storage medium | |
| CN109492913B (en) | Modular risk prediction method and device for power distribution terminal and storable medium | |
| CN114200331A (en) | Vehicle battery detection method and device, vehicle and storage medium | |
| CN113866644A (en) | Method and device for predicting usable time and capacity of battery | |
| US20210190873A1 (en) | Automated battery reconditioning control system | |
| CN114002517A (en) | Device diagnosis method, platform, system and readable storage medium | |
| KR101384898B1 (en) | The battery function testing system for the smart battery | |
| Salameh et al. | Battery modeling and lifetime prediction | |
| CN117648612B (en) | Parallel battery pack fault detection method, device, electronic equipment and storage medium |
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 |