CN117169751A - Energy storage power station fault monitoring management system and method based on machine learning - Google Patents
Energy storage power station fault monitoring management system and method based on machine learning Download PDFInfo
- Publication number
- CN117169751A CN117169751A CN202311101887.9A CN202311101887A CN117169751A CN 117169751 A CN117169751 A CN 117169751A CN 202311101887 A CN202311101887 A CN 202311101887A CN 117169751 A CN117169751 A CN 117169751A
- Authority
- CN
- China
- Prior art keywords
- data
- battery
- energy storage
- machine learning
- power station
- 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
- 238000004146 energy storage Methods 0.000 title claims abstract description 59
- 238000010801 machine learning Methods 0.000 title claims abstract description 59
- 238000012544 monitoring process Methods 0.000 title claims abstract description 31
- 238000000034 method Methods 0.000 title claims description 17
- 238000012545 processing Methods 0.000 claims abstract description 38
- 230000007613 environmental effect Effects 0.000 claims abstract description 24
- 238000004891 communication Methods 0.000 claims description 52
- 238000004364 calculation method Methods 0.000 claims description 28
- 230000007246 mechanism Effects 0.000 claims description 9
- 230000002159 abnormal effect Effects 0.000 claims description 8
- 230000036541 health Effects 0.000 claims description 6
- 239000000178 monomer Substances 0.000 claims description 5
- 238000012216 screening Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 3
- 239000000835 fiber Substances 0.000 claims description 3
- 238000009413 insulation Methods 0.000 claims description 3
- 238000010295 mobile communication Methods 0.000 claims description 3
- 238000013434 data augmentation Methods 0.000 claims 1
- 238000007726 management method Methods 0.000 abstract description 49
- 238000012549 training Methods 0.000 description 22
- 238000003062 neural network model Methods 0.000 description 13
- 230000006870 function Effects 0.000 description 10
- 238000012360 testing method Methods 0.000 description 9
- 238000004458 analytical method Methods 0.000 description 6
- 238000003066 decision tree Methods 0.000 description 5
- 238000010606 normalization Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 239000013598 vector Substances 0.000 description 4
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 229910001416 lithium ion Inorganic materials 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013523 data management Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000036632 reaction speed Effects 0.000 description 1
Landscapes
- Remote Monitoring And Control Of Power-Distribution Networks (AREA)
Abstract
The application provides a machine learning-based energy storage power station fault monitoring management system and a machine learning-based energy storage power station fault monitoring management method, wherein the system comprises the following components: the acquisition equipment is used for acquiring environmental data outside the energy storage battery prefabricated cabin; the battery management device is used for collecting operation data of the energy storage battery; the side end device is used for carrying out standardized processing on the environment data and the operation data to obtain target data; the cloud end device is used for inputting the target data subjected to the standardization processing into a preset machine learning prediction model to predict battery state parameters so as to obtain early warning information; and the alarm device is used for carrying out fault reminding based on the early warning information. According to the application, the battery management data and the environmental data are rapidly collected and processed in a cloud-edge combination mode, the data utilization rate is improved, and the early warning accuracy and the early warning speed are improved based on the machine learning prediction model aiming at the difference of the environmental factors of the region where the energy storage power station is located and the battery performance index used by the energy storage power station.
Description
Technical Field
The application relates to the technical field of energy storage type lithium batteries and data management, in particular to an energy storage power station fault monitoring management system and method based on machine learning.
Background
At present, the large-scale energy storage technology is widely applied to a source network charge storage system, and the lithium ion battery is widely applied to the large-scale energy storage field due to the highest technical maturity and optimal cost performance. Although the lithium ion battery monomer has the advantages of small volume, high safety, high efficiency, no pollution and the like, the problems of overcharge/discharge, short service life, thermal runaway and the like still exist in the application process of the energy storage system, and finally the high-efficiency utilization of the lithium ion battery is seriously influenced.
The battery management system can improve the running efficiency of the battery, ensure the safety of the battery and prolong the service life of the battery by means of on-line monitoring various electrical parameters of the energy storage battery system, evaluating the relevant state of the battery, reasonably controlling the charge and discharge of the battery and the like. However, most of the current battery management systems are locally deployed, so that the computing power is low, the residual capacity, the health state and the like of the battery cannot be accurately estimated, faults can be rapidly diagnosed and processed, and an accident recall analysis function cannot be realized.
Disclosure of Invention
The application aims to provide a machine learning-based energy storage power station fault monitoring management system and method, which are used for solving the problems that the management calculation force of a lithium battery is low, and the residual capacity and the health state of the battery cannot be accurately estimated.
In a first aspect, the present application provides a machine learning-based fault monitoring management system for an energy storage power station, the system comprising:
the acquisition equipment is used for acquiring environmental data outside the energy storage battery prefabricated cabin;
the battery management device is used for collecting operation data of the energy storage battery;
the side end device is used for carrying out standardized processing on the environment data and the operation data to obtain target data;
the cloud end device is used for inputting the target data subjected to the standardization processing into a preset machine learning prediction model to predict battery state parameters so as to obtain early warning information;
the alarm device is used for carrying out fault reminding based on the early warning information;
the communication equipment is used for realizing the communication connection between the acquisition equipment and the side equipment, the communication connection between the battery management device and the side equipment, the communication connection between the side equipment and the cloud equipment, and the communication connection between the cloud equipment and the alarm device.
In one possible implementation of the present application, the collecting device includes at least a temperature sensor, a humidity sensor, a wind speed sensor, and a wind direction identifier, and the environmental data collected based on the collecting period includes at least temperature data, humidity data, wind speed data, and wind direction data.
In one possible implementation manner of the present application, the battery management device includes a battery cell management unit, a battery cluster management unit, and a battery array management unit, and the operation data collected based on the collection period includes at least a battery cell voltage, a current, a battery module temperature, a terminal voltage, a loop current, and a battery system insulation resistance.
In one possible implementation manner of the present application, the battery management device is further configured to calculate, based on the operation data, calculation data of the battery cell and the battery module, where the calculation data includes a battery state of charge value and a battery state of health value.
In one possible implementation manner of the present application, the processing mechanism for performing the normalization processing on the environmental data and the operation data specifically includes performing data filtering, data removing, and data adding on the environmental data and the operation data based on a preset evaluation criterion.
In one possible implementation manner of the present application, the edge device is further configured to perform normalization processing on the computing data, and specifically perform processing operation based on the processing mechanism, where the target data specifically includes the environment data, the operation data, and the data after the normalization processing on the computing data.
In one possible implementation manner of the application, the cloud device inputs the target data into a machine learning prediction model to predict a state parameter of a battery in the future normal operation, and compares the state parameter with data of a next acquisition period to detect whether an actual state parameter accords with the predicted parameter, wherein if the actual state parameter does not accord with the predicted parameter, a control instruction is issued to position an abnormal battery cell based on the side device, so that the early warning information is obtained.
In one possible implementation manner of the application, the alarm device is used for displaying the early warning information and carrying out hierarchical fault reminding based on the early warning information, wherein the early warning level comprises a level I and a level II.
In one possible implementation manner of the present application, the communication mechanism of the communication device includes local communication and remote communication, wherein the local communication adopts a three-layer two-network architecture, and an IEC61850 communication protocol and a Modbus communication protocol; the remote communication may be fiber optic communication, 4G/5G mobile communication, wiFi and/or industrial Ethernet communication.
In a second aspect, the application provides a machine learning-based fault monitoring and management method for an energy storage power station, which specifically comprises the following steps:
collecting environment data outside the energy storage battery prefabricated cabin;
collecting operation data of an energy storage battery;
calculating to obtain calculation data of the battery monomer and the battery module based on the operation data;
performing standardized processing on the environment data, the operation data and the calculation data to obtain target data;
inputting the target data subjected to standardization processing into a preset machine learning prediction model to predict battery state parameters so as to obtain early warning information;
and carrying out fault reminding based on the early warning information.
As described above, the machine learning-based energy storage power station fault monitoring management system and method of the present application have the following beneficial effects:
1. according to the application, the calculation pressure of the fault monitoring management system is transferred to the cloud, so that the contradiction between strong calculation force required by accurate early warning and limited calculation force of an energy storage power station is solved, and the rapid collection and processing of data such as Battery Management System (BMS) data, prefabricated cabin external temperature/humidity/wind speed/wind direction and the like are realized in a cloud-edge combination mode, so that the data utilization rate is improved;
2. according to the application, a machine learning program is integrated into the early warning model to obtain a machine learning prediction model, so that the self-improvement and the update of the early warning model can be realized, the early warning model is continuously and iteratively updated through machine learning, the early warning model with pertinence and high accuracy is formed, and the early warning accuracy and the early warning speed can be improved according to the environmental factors of the region where the energy storage power station is located and the difference of the performance indexes of the battery used by the energy storage power station;
3. according to the method, the data such as the temperature/humidity/wind speed/wind direction outside the prefabricated cabin is additionally monitored, a targeted early warning result can be given out according to the environmental factors of the region where the energy storage power station is located, and an accident recall analysis function can be realized through the strong storage capacity of the cloud.
Drawings
FIG. 1 is a schematic diagram of a machine learning-based fault monitoring and management system for an energy storage plant according to an embodiment of the present application;
FIG. 2 is a schematic diagram showing steps of a machine learning-based fault monitoring and management method for an energy storage power station according to an embodiment of the present application;
description of element reference numerals
S202-S212 step 10 machine learning-based fault monitoring and management system for energy storage power station
11. Acquisition device
111. Temperature sensor
112. Humidity sensor
113. Wind speed sensor
114. Wind direction identifier
12. Battery management device
121. Battery cell management unit
122. Battery cluster management unit
123. Battery array management unit
13. Edge device
14. Cloud device
15. Alarm device
16. Communication apparatus
Detailed Description
Other advantages and effects of the present application will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present application with reference to specific examples. The application may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present application. It should be noted that the following embodiments and features in the embodiments may be combined with each other without conflict.
It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present application by way of illustration, and only the components related to the present application are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, and the form, number and proportion of the components in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
It should be noted that the purpose of the application has three points, namely, the application aims at the problems of low data acquisition frequency and low reaction speed caused by limited local calculation force of the energy storage power station management system in the prior art, and adopts a cloud-edge combination mode to realize the rapid processing of a large amount of data collected by the sensor; secondly, aiming at the problem that the fixed model of the existing energy storage power station management system is not suitable for different climatic environments and the performance index difference of battery modules of different manufacturers, a machine learning continuous iteration optimization early warning model is adopted to form a model with specificity, so that early warning accuracy is improved; aiming at the problem of missing of the accident recall analysis function in the prior art, recording and analyzing of abnormal data are achieved through cloud storage, and an early warning model is optimized through machine learning according to continuous iteration of the abnormal data.
Specifically, referring to fig. 1, in an embodiment of the application, a machine learning-based fault monitoring and management system 10 for an energy storage power station according to the present application specifically includes:
the acquisition equipment 11 is used for acquiring environmental data outside the energy storage battery prefabricated cabin;
a battery management device 12 for collecting operation data of the energy storage battery;
the side device 13 is configured to perform normalization processing on the environmental data and the operation data to obtain target data;
the cloud device 14 is configured to input the target data after the normalization processing into a preset machine learning prediction model to perform battery state parameter prediction, so as to obtain early warning information;
the alarm device 15 is used for carrying out fault reminding based on the early warning information;
the communication device 16 is configured to implement communication connection between the collecting device and the edge device, communication connection between the battery management apparatus and the edge device, communication connection between the edge device and the cloud device, and communication connection between the cloud device and the alarm apparatus.
It should be noted that, as shown in fig. 1, the collecting device 11 includes at least a temperature sensor 111, a humidity sensor 112, a wind speed sensor 113, and a wind direction identifier 114, the environmental data collected based on a collecting period includes at least temperature data, humidity data, wind speed data, wind direction data, and the like, and the corresponding environmental data is obtained based on other collecting devices, and the battery management device 12 is a device controlled by BMS (Battery Management System), specifically includes a battery cell management unit 121, a battery cluster management unit 122, and a battery array management unit 123, the operating data collected based on the collecting period includes at least a battery cell voltage, a current, a battery module temperature, a terminal voltage, a loop current, and a battery system insulation resistance, where the battery management device 12 is further configured to calculate, based on the operating data, calculation data including a battery cell and a battery module State of Charge value (SOC, state of Charge) and a battery State of Health value (SOH, state of Health).
Further, the processing mechanism for performing standardization processing on the environmental data and the operation data specifically includes performing data screening, data removal and data addition on the environmental data and the operation data based on a preset evaluation standard, and the side device 13 is further configured to perform standardization processing on the calculation data specifically based on the processing mechanism, where the target data specifically includes the environmental data, the operation data and the data after the standardization processing on the calculation data, and accordingly, the cloud device 14 inputs the target data into a machine learning prediction model to predict a state parameter of a battery that normally operates in the future, where the machine learning prediction model may be iteratively updated, and compare the prediction parameter with data of a next acquisition period to detect whether the actual state parameter accords with the prediction parameter, and if the actual state parameter does not accord with the prediction parameter, issues a control instruction to locate a state abnormal battery cell position based on the side device, so as to obtain the early warning information, where the machine learning model applied in this embodiment is a machine learning prediction model and the machine learning model is a mixed model, and the machine learning model is not used as a training model, and the model is not updated in a real-time sample, so as to ensure that the machine learning model is mixed, and the machine learning model is used as an accurate model is updated.
Further, in an embodiment of the present application, the alarm device 15 is configured to display the early warning information and perform a hierarchical fault alert based on the early warning information, where an early warning level includes a level I and a level II, and a communication mechanism of the communication device 16 includes local communication and remote communication, where the local communication adopts a three-layer two-network architecture, and an IEC61850 communication protocol and a Modbus communication protocol; the remote communication may be fiber optic communication, 4G/5G mobile communication, wiFi and/or industrial Ethernet communication.
It should be noted that, the data collected and/or calculated by the collecting device 11 and the battery management apparatus 12 are transmitted to the side device 13 through the communication device 16, and after the side device 13 performs standardized processing such as screening, rejecting or adding the corresponding data, the corresponding data is remotely transmitted to the cloud device 14 through the communication device, and the cloud device 14 inputs the corresponding data into a prediction model based on machine learning to predict, so that the predicted parameter is compared with the data of the next collecting period, so as to detect whether the actual state parameter meets the expected parameter, where if the actual state parameter does not meet the expected parameter, the computing part of the cloud device 14 issues an instruction to the computing part of the side device 13 through the remote communication system of the communication device, so as to locate the abnormal battery cell position in the state, and transmit a thermal management scheme required for recovering to normal state, so that the side device 13 can report to an operation and maintenance personnel terminal based on early warning information and a processing scheme, that is, through the early warning apparatus 15, and the warning apparatus 15 displays that the early warning information is the level I is the level, and the required failure level is the normal state is required, and the failure level is required for recovering the operation level (the normal state is the failure level is required).
Further, if the fault parameters fall back into the normal range, the early warning result is fed back to the calculation part of the cloud device to record the fault type and the solution, so that the accident recall analysis function can be realized through the strong storage capacity of the cloud; if the fault parameters are still abnormal, firstly isolating the fault battery module according to the deviation degree of the parameters, and if the deviation degree reaches the safety accident threshold values such as explosion, isolating and disposing the whole battery prefabricated cabin; and meanwhile, the early warning information is reported to an operation and maintenance personnel terminal, and the early warning grade at the moment is II grade.
Referring to fig. 2, the embodiment provides a machine learning-based fault monitoring and management method for an energy storage power station, which specifically includes the following steps:
step S202, collecting environment data outside an energy storage battery prefabricated cabin;
step S204, collecting operation data of an energy storage battery;
step S206, calculating to obtain the calculation data of the battery monomer and the battery module based on the operation data;
step S208, performing standardization processing on the environmental data, the operation data and the calculation data to obtain target data;
step S210, inputting the target data subjected to the standardization processing into a preset machine learning prediction model for battery state parameter prediction so as to obtain early warning information;
and step S212, carrying out fault reminding based on the early warning information.
The machine learning-based fault monitoring management method for the energy storage power station described in the embodiment is applied to the machine learning-based fault monitoring management system for the energy storage power station described in the embodiment, specifically, the preset collecting device is used for collecting environment data outside a pure battery prefabricated cabin, and the battery management device is used for collecting operation data of the energy storage battery, so that calculation data of a battery monomer and a battery module are obtained based on the operation data, and then the environment data, the operation data and the calculation data are subjected to standardized processing to obtain target data, wherein the target data are data obtained by carrying out standardized operations such as data screening, data eliminating and data adding on the environment data, the operation data and the calculation data, and therefore, the target data after standardized processing can be input into a preset machine learning prediction model to carry out battery state parameter prediction to obtain battery state information, and accordingly, fault reminding can be carried out based on the early warning information, and accordingly, early warning grade is divided into class I and class II, and accordingly, early warning grade is different corresponding to early warning grade, and early warning grade information is obtained based on a cloud terminal calculation scheme; if the fault parameters fall back into the normal range, the fault type and the solution are recorded based on the early warning result, so that the accident recall analysis function can be realized through the strong storage capacity of the cloud; if the fault parameters are still abnormal, firstly isolating the fault battery module according to the deviation degree of the parameters, and if the deviation degree reaches the safety accident threshold values such as explosion, isolating and disposing the whole battery prefabricated cabin; and meanwhile, the early warning information is reported to an operation and maintenance personnel terminal, and the early warning grade at the moment is II grade.
Further, the machine learning prediction model is a hybrid model of a neural network model and a decision tree prediction model, wherein the training step of machine learning specifically includes:
acquiring environment data, operation data and calculation data in the historical data to obtain a training sample set and a test sample set;
inputting the training sample set into an initialized neural network model for training to obtain initial input data;
classifying and regressing the initial input data based on a decision tree prediction model to obtain a feature vector;
and performing iterative training on the neural network model based on the feature vector, and performing model precision testing by using the test sample set to obtain the final machine learning prediction model.
The specific training process is as follows:
1. dividing training samples in historical data into a training sample set and a test sample set, wherein the preset ratio of the training sample set to the test sample set is 9:1;
2. the standard Softmax function is adopted as a loss function of the neural network model, and the ADAM training method is adopted as a training method of the neural network model, wherein the training parameter beta of the ADAM training method 1 ＝0.9、β 2 ＝0.99；
3. Randomly sending the training sample set according to the standard batch into an initialized neural network model for training to obtain initial input data;
4. classifying and regressing the initial input data based on a CART algorithm to obtain association relations among multiple variables so as to obtain feature vectors;
5. inputting the feature vector based on each batch into a neural network model for training, performing model precision test by using a test sample set, and stopping training after the input of the training sample sets of all batches is finished;
6. and selecting the model with highest precision on the test sample set as a corresponding target neural network model, and obtaining the machine learning prediction model based on the target neural network model and combining with the decision tree model.
It should be noted that, the decision tree model adopts CART (Classification And Regression Tree) classification and regression tree algorithm, in this embodiment, because a neural network is used as a model in machine learning, a large amount of historical data is required to train, so that for the CART algorithm, the more complex the data and the more variable, the more significant the superiority of the algorithm, and for the neural network, the larger the training data amount, the more accurate the result, specifically, the neural network model in this embodiment can train through the environmental data, the operation data and the calculation data in the historical data as input, and meanwhile, the input data is subjected to classification regression by using the CART algorithm, so that the relevance among the data parameters is improved, therefore, a hybrid machine learning prediction model combining the neural network model and the decision tree model can be obtained after training is finished, of course, when the neural network model is trained, training is not only carried out through historical data, but also combined with determined battery state parameters, and the accuracy of model output is calculated through comparing a large amount of test data with real data, so that model screening is carried out based on a preset accuracy threshold, and further the model accuracy of the neural network model is further improved.
As described above, the machine learning-based energy storage power station fault monitoring management system and method of the present application have the following beneficial effects: the calculation pressure of the fault monitoring management system is transferred to the cloud, so that the contradiction between strong calculation power required by accurate early warning and limited calculation power of the energy storage power station is solved, the rapid collection and processing of data such as battery management system data, prefabricated cabin external temperature/humidity/wind speed/wind direction and the like are realized in a cloud-edge combination mode, and the data utilization rate is improved; the machine learning program is integrated into the early warning model to obtain a machine learning prediction model, so that the self-improvement and the update of the early warning model can be realized, the early warning model is continuously and iteratively updated through machine learning, the early warning model with pertinence and high accuracy is formed, and the early warning accuracy and the early warning speed can be improved according to the environmental factors of the region where the energy storage power station is located and the difference of the performance indexes of the battery used by the energy storage power station; and the data such as the outside temperature/humidity/wind speed/wind direction of the monitoring prefabricated cabin are added, a targeted early warning result can be given to the environmental factors of the region where the energy storage power station is located, and an accident recall analysis function can be realized through the strong storage capacity of the cloud.
In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus, or method may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of modules/units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple modules or units may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules or units, which may be in electrical, mechanical or other forms.
The modules/units illustrated as separate components may or may not be physically separate, and components shown as modules/units may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules/units may be selected according to actual needs to achieve the objectives of the embodiments of the present application. For example, functional modules/units in various embodiments of the application may be integrated into one processing module, or each module/unit may exist alone physically, or two or more modules/units may be integrated into one module/unit.
Those of ordinary skill would further appreciate that the elements and algorithm steps of the examples described in connection with the embodiments disclosed herein may be embodied in electronic hardware, in computer software, or in a combination of the two, and that the elements and steps of the examples have been generally described in terms of function in the foregoing description to clearly illustrate the interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The descriptions of the processes or structures corresponding to the drawings have emphasis, and the descriptions of other processes or structures may be referred to for the parts of a certain process or structure that are not described in detail.
The above embodiments are merely illustrative of the principles of the present application and its effectiveness, and are not intended to limit the application. Modifications and variations may be made to the above-described embodiments by those skilled in the art without departing from the spirit and scope of the application. Accordingly, it is intended that all equivalent modifications and variations of the application be covered by the claims, which are within the ordinary skill of the art, be within the spirit and scope of the present disclosure.
Claims (10)
1. Machine learning-based energy storage power station fault monitoring management system, which is characterized by comprising:
the acquisition equipment is used for acquiring environmental data outside the energy storage battery prefabricated cabin;
the battery management device is used for collecting operation data of the energy storage battery;
the side end device is used for carrying out standardized processing on the environment data and the operation data to obtain target data;
the cloud end device is used for inputting the target data subjected to the standardization processing into a preset machine learning prediction model to predict battery state parameters so as to obtain early warning information;
the alarm device is used for carrying out fault reminding based on the early warning information;
the communication equipment is used for realizing the communication connection between the acquisition equipment and the side equipment, the communication connection between the battery management device and the side equipment, the communication connection between the side equipment and the cloud equipment, and the communication connection between the cloud equipment and the alarm device.
2. The machine learning based energy storage power station fault monitoring management system of claim 1, wherein the acquisition device comprises at least a temperature sensor, a humidity sensor, a wind speed sensor, and a wind direction identifier, and the environmental data acquired based on the acquisition cycle comprises at least temperature data, humidity data, wind speed data, and wind direction data.
3. The machine learning based energy storage power station fault monitoring management system of claim 2, wherein the battery management device comprises a battery cell management unit, a battery cluster management unit and a battery array management unit, and the operational data collected based on the collection period at least comprises a battery cell voltage, a battery current, a battery module temperature, a terminal voltage, a loop current, and a battery system insulation resistance.
4. The machine learning based energy storage power station fault monitoring management system of claim 3, wherein the battery management device is further configured to calculate, based on the operational data, calculation data of the battery cells and the battery modules, the calculation data including a battery state of charge value and a battery state of health value.
5. The machine learning based energy storage power station fault monitoring management system of claim 4, wherein the processing mechanism for normalizing the environmental data and the operational data specifically comprises data screening, data culling, and data augmentation of the environmental data and the operational data based on preset evaluation criteria.
6. The machine learning based energy storage power station fault monitoring management system of claim 5, wherein the edge device is further configured to perform standardized processing on the computing data, and in particular perform processing operations based on the processing mechanism, wherein the target data specifically includes the environment data, the operation data, and the data after the standardized processing of the computing data.
7. The machine learning based energy storage power station fault monitoring management system of claim 6, wherein the cloud device inputs the target data into a machine learning prediction model to predict a state parameter of a battery for future normal operation, and compares the predicted state parameter with data of a next acquisition period to detect whether an actual state parameter meets the predicted parameter, wherein if the actual state parameter does not meet the predicted parameter, a control instruction is issued to locate a state abnormal battery cell position based on the edge device, so as to obtain the early warning information.
8. The machine learning based energy storage power station fault monitoring management system of claim 1, wherein the alarm device is configured to display the early warning information and perform a hierarchical fault alert based on the early warning information, and wherein the early warning level includes a level I and a level II.
9. The machine learning based energy storage power station fault monitoring management system of claim 1, wherein the communication mechanism of the communication device comprises local communication and remote communication, wherein the local communication adopts a three-layer two-network architecture, and an IEC61850 communication protocol and a Modbus communication protocol; the remote communication may be fiber optic communication, 4G/5G mobile communication, wiFi and/or industrial Ethernet communication.
10. The machine learning-based energy storage power station fault monitoring and managing method is characterized by comprising the following steps of:
collecting environment data outside the energy storage battery prefabricated cabin;
collecting operation data of an energy storage battery;
calculating to obtain calculation data of the battery monomer and the battery module based on the operation data;
performing standardized processing on the environment data, the operation data and the calculation data to obtain target data;
inputting the target data subjected to standardization processing into a preset machine learning prediction model to predict battery state parameters so as to obtain early warning information;
and carrying out fault reminding based on the early warning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311101887.9A CN117169751A (en) | 2023-08-29 | 2023-08-29 | Energy storage power station fault monitoring management system and method based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311101887.9A CN117169751A (en) | 2023-08-29 | 2023-08-29 | Energy storage power station fault monitoring management system and method based on machine learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117169751A true CN117169751A (en) | 2023-12-05 |
Family
ID=88940388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311101887.9A Pending CN117169751A (en) | 2023-08-29 | 2023-08-29 | Energy storage power station fault monitoring management system and method based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117169751A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117458572A (en) * | 2023-12-22 | 2024-01-26 | 深圳市超思维电子股份有限公司 | Power supply management system for energy storage cabinet BMS |
| CN118101426A (en) * | 2024-04-17 | 2024-05-28 | 深圳市光网视科技有限公司 | Monitoring operation and maintenance system based on Internet of things equipment |
| CN118348444A (en) * | 2024-06-18 | 2024-07-16 | 江苏亿锂新能源科技有限公司 | Battery pack fault intelligent detection system based on data analysis |
| CN118410905A (en) * | 2024-04-28 | 2024-07-30 | 西安中创新能网络科技有限责任公司 | Intelligent operation strategy optimization system and method for new energy power station |
-
2023
- 2023-08-29 CN CN202311101887.9A patent/CN117169751A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117458572A (en) * | 2023-12-22 | 2024-01-26 | 深圳市超思维电子股份有限公司 | Power supply management system for energy storage cabinet BMS |
| CN117458572B (en) * | 2023-12-22 | 2024-03-15 | 深圳市超思维电子股份有限公司 | Power supply management system for energy storage cabinet BMS |
| CN118101426A (en) * | 2024-04-17 | 2024-05-28 | 深圳市光网视科技有限公司 | Monitoring operation and maintenance system based on Internet of things equipment |
| CN118410905A (en) * | 2024-04-28 | 2024-07-30 | 西安中创新能网络科技有限责任公司 | Intelligent operation strategy optimization system and method for new energy power station |
| CN118348444A (en) * | 2024-06-18 | 2024-07-16 | 江苏亿锂新能源科技有限公司 | Battery pack fault intelligent detection system based on data analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117169751A (en) | Energy storage power station fault monitoring management system and method based on machine learning | |
| CN111624494B (en) | Battery analysis method and system based on electrochemical parameters | |
| CN113156917B (en) | Power grid equipment fault diagnosis method and system based on artificial intelligence | |
| CN116455085B (en) | Intelligent monitoring system of battery energy storage power station | |
| CN116154900B (en) | Active safety three-stage prevention and control system and method for battery energy storage power station | |
| EP4207432A2 (en) | Method and system for predicting thermal runaway of battery based on machine learning | |
| CN116614177B (en) | Optical fiber state multidimensional parameter monitoring system | |
| CN116308304B (en) | New energy intelligent operation and maintenance method and system based on meta learning concept drift detection | |
| CN111509319A (en) | PHM management system for energy storage power supply | |
| Li et al. | A Novel Method for Lithium‐Ion Battery Fault Diagnosis of Electric Vehicle Based on Real‐Time Voltage | |
| CN116029699A (en) | Power information system based on data twinning and operation and maintenance method | |
| CN114579659A (en) | System and method for estimating and sorting utilization potential of power battery by gradient utilization | |
| CN117665595A (en) | Battery state monitoring method, device, electronic equipment and storage medium | |
| CN117491872A (en) | Reconfigurable battery module fault multistage diagnosis method | |
| CN117607531A (en) | Transformer substation direct current system fault investigation system and investigation method thereof | |
| CN116901707A (en) | Power battery pack fault early warning method, system and vehicle | |
| Xia et al. | Technologies for Energy Storage Power Stations Safety Operation: Battery State Evaluation Survey and a Critical Analysis | |
| CN112801815B (en) | Power communication network fault early warning method based on federal learning | |
| Cui et al. | Remaining useful life prediction of aviation lithium-ion battery based on SVR-MC | |
| Zhao et al. | Reliable Life Prediction and Evaluation Analysis of Lithium-ion Battery Based on Long-Short Term Memory Model | |
| CN117394409B (en) | Intelligent assessment method and system for equipment state of energy storage power station | |
| CN112485676B (en) | Battery energy storage system state estimation early warning method under digital mirror image | |
| US20240241180A1 (en) | Battery management apparatus and battery testing system including the same | |
| Zheng et al. | Review of Research on Fault Diagnosis of Electric Vehicle Battery System | |
| Sun et al. | A Data-Driven Algorithm for Short Circuit Fault Diagnosis of Power Batteries |
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 |