CN116738865A - Energy storage power supply evaluation method and system based on Internet of things - Google Patents
Energy storage power supply evaluation method and system based on Internet of things Download PDFInfo
- Publication number
- CN116738865A CN116738865A CN202311007558.8A CN202311007558A CN116738865A CN 116738865 A CN116738865 A CN 116738865A CN 202311007558 A CN202311007558 A CN 202311007558A CN 116738865 A CN116738865 A CN 116738865A
- Authority
- CN
- China
- Prior art keywords
- energy storage
- power supply
- storage power
- debugging
- abnormal
- 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.)
- Granted
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 426
- 238000011156 evaluation Methods 0.000 title claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 163
- 238000000034 method Methods 0.000 claims abstract description 54
- 238000003066 decision tree Methods 0.000 claims abstract description 50
- 238000005094 computer simulation Methods 0.000 claims abstract description 34
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000012544 monitoring process Methods 0.000 claims abstract description 10
- 238000012216 screening Methods 0.000 claims abstract description 7
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims description 23
- 230000000694 effects Effects 0.000 claims description 21
- 230000011218 segmentation Effects 0.000 claims description 17
- 238000007405 data analysis Methods 0.000 claims description 11
- 238000000354 decomposition reaction Methods 0.000 claims description 10
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000007476 Maximum Likelihood Methods 0.000 claims description 4
- 238000011418 maintenance treatment Methods 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000007547 defect Effects 0.000 description 15
- 238000012423 maintenance Methods 0.000 description 7
- 230000001276 controlling effect Effects 0.000 description 5
- 230000001105 regulatory effect Effects 0.000 description 5
- 238000001914 filtration Methods 0.000 description 4
- 230000002146 bilateral effect Effects 0.000 description 3
- 230000000704 physical effect Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 239000002184 metal Substances 0.000 description 2
- 238000005498 polishing Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000011282 treatment Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000013138 pruning Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000005477 standard model Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N7/00—Computing arrangements based on specific mathematical models
- G06N7/01—Probabilistic graphical models, e.g. probabilistic networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y10/00—Economic sectors
- G16Y10/35—Utilities, e.g. electricity, gas or water
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Y—INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE INTERNET OF THINGS [IoT]
- G16Y40/00—IoT characterised by the purpose of the information processing
- G16Y40/20—Analytics; Diagnosis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Mathematical Physics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Medical Informatics (AREA)
- Mathematical Optimization (AREA)
- Computational Linguistics (AREA)
- Geometry (AREA)
- Entrepreneurship & Innovation (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Quality & Reliability (AREA)
- Algebra (AREA)
- Computer Hardware Design (AREA)
- Pure & Applied Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Probability & Statistics with Applications (AREA)
- Primary Health Care (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Biomedical Technology (AREA)
Abstract
The invention discloses an energy storage power supply evaluation method and system based on the Internet of things, and the method comprises the following steps: the method comprises the steps of obtaining a standard energy storage power supply prediction model and standard energy storage power supply prediction parameters through a decision tree model algorithm, obtaining the energy storage power supply prediction parameters through collecting the operation parameters of an energy storage power supply, comparing and analyzing the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters to obtain abnormal sub-equipment and abnormal operation parameters, constructing an energy storage power supply dynamic simulation model based on the abnormal operation parameters, screening an optimal debugging scheme of the energy storage power supply, inputting the optimal debugging scheme into the energy storage power supply for debugging, monitoring the operation parameters during debugging, and processing the conditions during debugging.
Description
Technical Field
The invention relates to the field of energy storage power supply evaluation, in particular to an energy storage power supply evaluation method and system based on the Internet of things.
Background
An energy storage power supply is a device that is capable of converting and storing electrical energy, and converting the stored electrical energy back to a power supply system when needed. The energy storage power supply can solve the problems of intermittence, instability and the like of renewable energy sources, so that the energy sources are more stable and reliable to supply. In the working process of the energy storage power supply, energy loss can be generated, the cycle life of the energy storage power supply is influenced, the scrapping of the energy storage power supply is accelerated, and the environment is influenced. The energy storage power supply is evaluated, so that the stability of voltage and frequency can be promoted, and the energy quality of electric power can be improved; the power supply requirement of the energy storage power supply is optimized, the utilization efficiency of energy in the energy storage power supply is maximized, waste is reduced, meanwhile, the power supply structure of the electric power energy can be optimized, the energy conservation and emission reduction of traditional fossil energy are realized. The evaluation of the energy storage power supply comprises the evaluation of the charge-discharge response speed, the power supply service life and the like of the energy storage power supply, and the energy storage power supply is regulated and controlled based on the Internet of things by acquiring abnormal parameters of the energy storage power supply.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides an energy storage power supply evaluation method and system based on the Internet of things.
In order to achieve the above purpose, the invention adopts the following technical scheme:
the invention provides an energy storage power supply evaluation method based on the Internet of things, which comprises the following steps of:
based on the decision tree model and the historical data information, a standard energy storage power supply prediction model is constructed, and standard energy storage power supply prediction parameters are generated;
acquiring operation parameters of an energy storage power supply, and importing the operation parameters of the energy storage power supply into a standard energy storage power supply prediction model to obtain energy storage power supply prediction parameters;
performing data analysis on the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters, and determining abnormal sub-equipment and abnormal operation parameters of the energy storage power supply according to analysis results;
constructing an energy storage power supply dynamic simulation model, and acquiring and outputting an optimal energy storage power supply debugging scheme by combining the energy storage power supply dynamic simulation model through big data retrieval based on the abnormal operation parameters;
outputting the optimal energy storage power supply debugging scheme to an energy storage power supply for debugging, monitoring the operation parameters of the energy storage power supply in the debugging process, and processing abnormal conditions during the debugging process.
Further, in a preferred embodiment of the present invention, the method constructs a standard energy storage power supply prediction model based on the decision tree model and the historical data information, and generates standard energy storage power supply prediction parameters, which specifically includes:
acquiring historical data information of the energy storage power supplies with the same specification and the same model, and importing the historical data information into a decision tree model;
acquiring characteristics of different operation parameters in the history data information of the energy storage power supply, generating operation parameter characteristic points, and determining operation parameter partitioning points based on the operation parameter characteristic points and combining with the base non-purity of the history data information of the energy storage power supply;
determining a root node in the decision tree model, performing data segmentation on the historical data information of the energy storage power supply based on an operation parameter segmentation point by taking the root node as a starting point to obtain two data subsets, repeating the steps by taking the two data subsets as starting points, performing data segmentation on the data subsets, and defining the segmentation point as a leaf node;
presetting the maximum depth of a decision tree and the minimum value of data samples in a data subset, wherein the maximum depth of the decision tree is the number of nodes on a path from a root node to a farthest leaf node, the data samples in the data subset reach the minimum value of the data samples in the data subset, or the depth after the data subset is segmented reaches the maximum depth, and the segmentation of the data subset is stopped to obtain an energy storage power supply decision tree;
Carrying out data analysis on the energy storage power supply decision tree, judging the fitting condition of the energy storage power supply decision tree, and screening and removing leaf nodes of the energy storage power supply decision tree based on the fitting condition to obtain a complete energy storage power supply decision tree;
and extracting internal parameters of the complete energy storage power supply decision tree, constructing a standard energy storage power supply prediction model, and generating standard energy storage power supply prediction parameters based on the standard energy storage power supply prediction model.
Further, in a preferred embodiment of the present invention, the obtaining the operation parameter of the energy storage power supply, and importing the operation parameter of the energy storage power supply into a standard energy storage power supply prediction model to obtain the energy storage power supply prediction parameter specifically includes:
the current input and output ends of the energy storage power supply are connected with a universal meter, the current of the energy storage power supply is measured, and the initial SOC value of the energy storage power supply is obtained;
presetting a time step, multiplying and accumulating the current value of the energy storage power supply and the time step to obtain a charge and discharge amount predicted value of the battery in the current time step, and subtracting the initial SOC value of the energy storage power supply from the charge and discharge amount predicted value of the battery in the current time step to obtain a real-time SOC value of the energy storage power supply;
Installing a sensor in an energy storage power supply, acquiring sensor data, removing abnormal values and repeated values in the sensor data, filling the missing values in the sensor data by using an interpolation method, and obtaining the sensor data after data cleaning;
performing multi-scale decomposition on the sensor data after data cleaning according to a preset threshold value to obtain a high-frequency wavelet coefficient and a low-frequency wavelet coefficient, setting the low-frequency wavelet coefficient to 0, continuing to decompose the high-frequency wavelet coefficient, stopping decomposition when the decomposition times reach the preset value, and performing wavelet inverse transformation on the low-frequency wavelet coefficient to obtain preprocessed sensor data;
and combining the preprocessed sensor data with the real-time SOC value of the energy storage power supply to generate the operation parameters of the energy storage power supply, importing the operation parameters of the energy storage power supply into a standard energy storage power supply prediction model to generate an energy storage power supply prediction model, and obtaining the energy storage power supply prediction parameters through the energy storage power supply prediction model.
Further, in a preferred embodiment of the present invention, the data analysis is performed on the standard energy storage power supply prediction parameter and the energy storage power supply prediction parameter, and the abnormal sub-device and the abnormal operation parameter of the energy storage power supply are determined according to the analysis result, which specifically includes:
Performing data fitting on the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters, deleting a data fitting part, and obtaining a data deviation value, wherein the data deviation value comprises voltage deviation, resistance deviation, temperature deviation and SOC value deviation;
based on the data deviation value, determining a random variable of the Bayesian network model, expressing a random variable as a node in a Bayesian network, and determining directed edges between nodes in the Bayesian network;
based on a maximum likelihood method, obtaining a conditional probability table of each node of a Bayesian network, carrying out structure learning on the Bayesian network based on directed edges among nodes in the Bayesian network, generating a Bayesian network model, importing the conditional probability table of each node of the Bayesian network into the Bayesian network model for carrying out probability reasoning, and determining abnormal sub-equipment of a corresponding energy storage power supply causing a data deviation value;
acquiring a topological structure of an electronic circuit in an energy storage power supply, and establishing a circuit equation based on the topological structure of the electronic circuit in the energy storage power supply and the preprocessed sensor data, wherein the circuit equation comprises a node tide equation and a branch tide equation;
Initializing voltage of each node in an electronic circuit in the energy storage power supply, solving the operation parameter value of each piece of equipment in the energy storage power supply by an iteration method based on the circuit equation, stopping performing iterative calculation when the iteration times reach a preset value, and outputting the operation parameter value of each piece of equipment in the energy storage power supply;
and acquiring the operation parameter value of the abnormal sub-equipment of the energy storage power supply based on the operation parameter value of each sub-equipment in the energy storage power supply, and defining the operation parameter value as an abnormal operation parameter.
Further, in a preferred embodiment of the present invention, the construction of the energy storage power supply dynamic simulation model, based on the abnormal operation parameters, obtains and outputs an optimal energy storage power supply debugging scheme by combining with the energy storage power supply dynamic simulation model through big data retrieval, specifically:
based on a production drawing of an energy storage power supply and operation parameter values of all sub-equipment in the energy storage power supply, an energy storage power supply three-dimensional model is built in three-dimensional software, the energy storage power supply three-dimensional model is converted into an energy storage power supply three-dimensional model file according to a data format of dynamic simulation software, and the energy storage power supply three-dimensional model file is imported into the dynamic simulation software to obtain an energy storage power supply dynamic simulation model;
Importing the abnormal operation parameters into a big data network for network retrieval, acquiring all debugging schemes of the abnormal operation parameters in abnormal sub-equipment of the energy storage power supply, and summarizing all the debugging schemes to obtain an initial debugging scheme set;
importing the initial debugging scheme set into an energy storage electric dynamic simulation model to obtain a debugging result, and eliminating the corresponding debugging scheme of which the operation parameters of the abnormal sub-equipment are not in the preset operation parameter range in the initial debugging scheme set to obtain a second debugging scheme set;
obtaining the debugging efficiency of all the debugging results in the second debugging scheme set, extracting the debugging schemes with the debugging efficiency larger than a preset threshold value, and obtaining a third debugging scheme set;
obtaining the debugging properties of all the debugging schemes in the third debugging scheme set, and eliminating the debugging schemes with the debugging properties not meeting the preset debugging properties to obtain a fourth debugging scheme set;
and based on the debugging efficiency of all the debugging schemes in the fourth debugging scheme set, carrying out efficiency sorting, outputting the debugging scheme with the highest debugging efficiency, and defining the debugging scheme with the highest debugging efficiency as the optimal energy storage power supply debugging scheme.
Further, in a preferred embodiment of the present invention, the outputting the optimal energy storage power supply debugging scheme to the energy storage power supply for debugging, monitoring the operation parameters of the energy storage power supply during the debugging process, and processing the abnormal situation occurring during the debugging process, specifically:
outputting the optimal energy storage power supply debugging scheme to an energy storage power supply, wherein the energy storage power supply carries out debugging on abnormal sub-equipment based on the optimal energy storage power supply debugging scheme, and obtains real-time debugging operation parameters of all sub-equipment in the energy storage power supply through tide calculation in the debugging process;
outputting the optimal energy storage power supply debugging scheme in an energy storage power supply dynamic simulation model to obtain ideal debugging operation parameters, and generating an ideal debugging result-actual debugging result comparison table based on the ideal debugging operation parameters and the real-time debugging operation parameters;
analyzing the ideal debugging result-actual debugging result comparison table, if the difference between the actual debugging result and the ideal debugging result in the same time is within a preset value, evaluating the corresponding time debugging effect as A, and if the difference between the actual debugging result and the ideal debugging result in the same time is smaller than the preset value, evaluating the corresponding time debugging effect as B;
Recording corresponding debugging time with the debugging effect of being evaluated as B, defining the debugging time as abnormal debugging time, acquiring sub-equipment for debugging in the abnormal debugging time, and defining the sub-equipment as second abnormal sub-equipment;
and disassembling the second abnormal sub-equipment and performing maintenance treatment, wherein the second abnormal sub-equipment is reinstalled into the energy storage power supply after being maintained, the real-time operation parameters of the reinstalled second abnormal sub-equipment are calculated by using a tide algorithm, and if the real-time operation parameters output by the maintained second abnormal sub-equipment are smaller than a preset value, the second abnormal sub-equipment is replaced.
The second aspect of the present invention also provides an energy storage power supply evaluation system based on the internet of things, the energy storage power supply evaluation system includes a memory and a processor, the memory stores an energy storage power supply evaluation program, and when the energy storage power supply evaluation program is executed by the processor, the following steps are implemented:
based on the decision tree model and the historical data information, a standard energy storage power supply prediction model is constructed, and standard energy storage power supply prediction parameters are generated;
acquiring operation parameters of an energy storage power supply, and importing the operation parameters of the energy storage power supply into a standard energy storage power supply prediction model to obtain energy storage power supply prediction parameters;
Performing data analysis on the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters, and determining abnormal sub-equipment and abnormal operation parameters of the energy storage power supply according to analysis results;
constructing an energy storage power supply dynamic simulation model, and acquiring and outputting an optimal energy storage power supply debugging scheme by combining the energy storage power supply dynamic simulation model through big data retrieval based on the abnormal operation parameters;
outputting the optimal energy storage power supply debugging scheme to an energy storage power supply for debugging, monitoring the operation parameters of the energy storage power supply in the debugging process, and processing abnormal conditions during the debugging process.
The invention solves the technical defects in the background technology, and has the following beneficial effects: the method comprises the steps of obtaining a standard energy storage power supply prediction model and standard energy storage power supply prediction parameters through a decision tree model algorithm, obtaining the energy storage power supply prediction parameters through collecting the operation parameters of an energy storage power supply, comparing and analyzing the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters to obtain abnormal sub-equipment and abnormal operation parameters, constructing an energy storage power supply dynamic simulation model based on the abnormal operation parameters, screening an optimal debugging scheme of the energy storage power supply, inputting the optimal debugging scheme into the energy storage power supply for debugging, monitoring the operation parameters during debugging, and processing the conditions during debugging. The invention can promote the stability of voltage and frequency and improve the energy quality of electric power; the power supply requirement of the energy storage power supply is optimized, the utilization efficiency of energy in the energy storage power supply is maximized, the waste is reduced, and the economic benefit is met.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the application, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows a flow chart of an energy storage power supply evaluation method based on the Internet of things;
FIG. 2 illustrates a flow chart for obtaining energy storage power supply prediction parameters and determining abnormal sub-equipment and abnormal operating parameters of the energy storage power supply based on the energy storage power supply prediction parameters;
FIG. 3 is a flow chart showing the steps of obtaining an optimal energy storage power supply debugging scheme and processing abnormal conditions of the energy storage power supply debugged by the optimal energy storage power supply debugging scheme;
fig. 4 shows a program diagram of an energy storage power supply evaluation system based on the internet of things.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flowchart of an energy storage power supply evaluation method based on the internet of things, which comprises the following steps:
s102: based on the decision tree model and the historical data information, a standard energy storage power supply prediction model is constructed, and standard energy storage power supply prediction parameters are generated;
s104: acquiring operation parameters of an energy storage power supply, and importing the operation parameters of the energy storage power supply into a standard energy storage power supply prediction model to obtain energy storage power supply prediction parameters;
s106: performing data analysis on the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters, and determining abnormal sub-equipment and abnormal operation parameters of the energy storage power supply according to analysis results;
s108: constructing an energy storage power supply dynamic simulation model, and acquiring and outputting an optimal energy storage power supply debugging scheme by combining the energy storage power supply dynamic simulation model through big data retrieval based on the abnormal operation parameters;
s110: outputting the optimal energy storage power supply debugging scheme to an energy storage power supply for debugging, monitoring the operation parameters of the energy storage power supply in the debugging process, and processing abnormal conditions during the debugging process.
Further, in a preferred embodiment of the present invention, the method constructs a standard energy storage power supply prediction model based on the decision tree model and the historical data information, and generates standard energy storage power supply prediction parameters, which specifically includes:
acquiring historical data information of the energy storage power supplies with the same specification and the same model, and importing the historical data information into a decision tree model;
acquiring characteristics of different operation parameters in the history data information of the energy storage power supply, generating operation parameter characteristic points, and determining operation parameter partitioning points based on the operation parameter characteristic points and combining with the base non-purity of the history data information of the energy storage power supply;
determining a root node in the decision tree model, performing data segmentation on the historical data information of the energy storage power supply based on an operation parameter segmentation point by taking the root node as a starting point to obtain two data subsets, repeating the steps by taking the two data subsets as starting points, performing data segmentation on the data subsets, and defining the segmentation point as a leaf node;
presetting the maximum depth of a decision tree and the minimum value of data samples in a data subset, wherein the maximum depth of the decision tree is the number of nodes on a path from a root node to a farthest leaf node, the data samples in the data subset reach the minimum value of the data samples in the data subset, or the depth after the data subset is segmented reaches the maximum depth, and the segmentation of the data subset is stopped to obtain an energy storage power supply decision tree;
Carrying out data analysis on the energy storage power supply decision tree, judging the fitting condition of the energy storage power supply decision tree, and screening and removing leaf nodes of the energy storage power supply decision tree based on the fitting condition to obtain a complete energy storage power supply decision tree;
and extracting internal parameters of the complete energy storage power supply decision tree, constructing a standard energy storage power supply prediction model, and generating standard energy storage power supply prediction parameters based on the standard energy storage power supply prediction model.
It should be noted that, the decision tree model is a prediction model based on a tree structure, and a predicted value can be obtained by gradually judging input data. The evaluation of the energy storage power supply requires the prediction of the future condition of the energy storage power supply, so that the decision tree model is required to be used for obtaining the prediction parameters of the energy storage power supply. The purpose of using the historical data information is to build a standard model, providing preconditions for future predictions. The operation parameter characteristic points are characteristic values for dividing the history data information of the energy storage power supply, and the operation parameter dividing points are cutting threshold points for dividing the history data information of the energy storage power supply. The Indonesia is used for selecting optimal characteristics and dividing points in the decision tree, and the dividing point which enables the Indonesia to decrease the maximum is selected as the operating parameter dividing point. And dividing nodes of the decision tree model according to the operation parameter dividing points to obtain an energy storage power supply decision tree. And leaf node screening and removing and pruning operation are carried out on the energy storage power supply decision tree, so that the generalization capability of a decision tree model can be improved, and a complete energy storage power supply decision tree is obtained. According to the method, the standard energy storage power supply prediction model can be built through the decision tree model, and the standard energy storage power supply prediction parameters are obtained, and can provide preconditions for the evaluation of the energy storage power supply.
FIG. 2 shows a flowchart for obtaining energy storage power supply prediction parameters and determining abnormal sub-equipment and abnormal operation parameters of the energy storage power supply based on the energy storage power supply prediction parameters, comprising the steps of:
s202: acquiring operation parameters of an energy storage power supply, and importing the operation parameters of the energy storage power supply into a standard energy storage power supply prediction model to obtain energy storage power supply prediction parameters;
s204: acquiring abnormal sub-equipment of the energy storage power supply based on a Bayesian network;
s206: and carrying out load flow operation on the electronic circuit of the energy storage power supply to obtain abnormal operation parameters.
Further, in a preferred embodiment of the present invention, the obtaining the operation parameter of the energy storage power supply, and importing the operation parameter of the energy storage power supply into a standard energy storage power supply prediction model to obtain the energy storage power supply prediction parameter specifically includes:
the current input and output ends of the energy storage power supply are connected with a universal meter, the current of the energy storage power supply is measured, and the initial SOC value of the energy storage power supply is obtained;
presetting a time step, multiplying and accumulating the current value of the energy storage power supply and the time step to obtain a charge and discharge amount predicted value of the battery in the current time step, and subtracting the initial SOC value of the energy storage power supply from the charge and discharge amount predicted value of the battery in the current time step to obtain a real-time SOC value of the energy storage power supply;
Installing a sensor in an energy storage power supply, acquiring sensor data, removing abnormal values and repeated values in the sensor data, filling the missing values in the sensor data by using an interpolation method, and obtaining the sensor data after data cleaning;
performing multi-scale decomposition on the sensor data after data cleaning according to a preset threshold value to obtain a high-frequency wavelet coefficient and a low-frequency wavelet coefficient, setting the low-frequency wavelet coefficient to 0, continuing to decompose the high-frequency wavelet coefficient, stopping decomposition when the decomposition times reach the preset value, and performing wavelet inverse transformation on the low-frequency wavelet coefficient to obtain preprocessed sensor data;
and combining the preprocessed sensor data with the real-time SOC value of the energy storage power supply to generate the operation parameters of the energy storage power supply, importing the operation parameters of the energy storage power supply into a standard energy storage power supply prediction model to generate an energy storage power supply prediction model, and obtaining the energy storage power supply prediction parameters through the energy storage power supply prediction model.
Note that, the SOC represents a ratio between the current power of the energy storage power supply and the full charge state thereof, and represents the energy level currently stored by the energy storage power supply. The operation parameters of the energy storage power supply comprise data such as an SOC value, voltage, current, resistance, temperature and the like. The data acquired by the sensor may have abnormal values, the abnormal values need to be removed, the acquired data is large in noise, and the signals need to be denoised by wavelet decomposition. The operation parameters of the energy storage power supply are led into the standard energy storage power supply prediction model, so that the standard energy storage power supply prediction model can be changed into the energy storage power supply prediction model, and the energy storage power supply prediction parameters are obtained. According to the method, the system and the device, the SOC value and other operation parameter values of the energy storage power supply can be obtained, and the obtained SOC value and other operation parameter values are imported into a standard energy storage power supply prediction model to obtain the energy storage power supply prediction parameter.
Further, in a preferred embodiment of the present invention, the abnormal subset for acquiring the energy storage power based on the bayesian network specifically includes:
performing data fitting on the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters, deleting a data fitting part, and obtaining a data deviation value, wherein the data deviation value comprises voltage deviation, resistance deviation, temperature deviation and SOC value deviation;
based on the data deviation value, determining a random variable of the Bayesian network model, expressing a random variable as a node in a Bayesian network, and determining directed edges between nodes in the Bayesian network;
based on a maximum likelihood method, obtaining a conditional probability table of each node of the Bayesian network, based on directed edges among nodes in the Bayesian network, carrying out structure learning on the Bayesian network, generating a Bayesian network model, importing the conditional probability table of each node of the Bayesian network into the Bayesian network model for carrying out probability reasoning, and determining abnormal sub-equipment of the corresponding energy storage power supply causing data deviation values.
It should be noted that, because there is loss during the operation of the energy storage power supply, the standard energy storage power supply prediction parameter and the energy storage power supply prediction parameter are compared to obtain the data deviation value. Using a bayesian network, the position where the abnormality is generated in the data can be determined by the abnormal value of the data. The directed edges point to the connecting lines between the other nodes for one node, and represent the conditional dependency relationship between variables. The maximum likelihood method is used for observing the data to estimate model parameters, and can find the position with the highest possibility of data occurrence. The conditional probability table of each node of the Bayesian network is imported into the Bayesian network model, and abnormal sub-equipment of the corresponding energy storage power supply causing the data deviation value can be deduced. The invention can cause abnormal sub-equipment of the corresponding energy storage power supply of the data deviation value through the Bayesian network model.
Further, in a preferred embodiment of the present invention, the method for performing load flow operation on the electronic circuit of the energy storage power supply to obtain abnormal operation parameters includes:
acquiring a topological structure of an electronic circuit in an energy storage power supply, and establishing a circuit equation based on the topological structure of the electronic circuit in the energy storage power supply and the preprocessed sensor data, wherein the circuit equation comprises a node tide equation and a branch tide equation;
initializing voltage of each node in an electronic circuit in the energy storage power supply, solving the operation parameter value of each piece of equipment in the energy storage power supply by an iteration method based on the circuit equation, stopping performing iterative calculation when the iteration times reach a preset value, and outputting the operation parameter value of each piece of equipment in the energy storage power supply;
and acquiring the operation parameter value of the abnormal sub-equipment of the energy storage power supply based on the operation parameter value of each sub-equipment in the energy storage power supply, and defining the operation parameter value as an abnormal operation parameter.
It should be noted that, obtaining the operation parameters of the abnormal sub-equipment requires carrying out the tide operation on the energy storage power supply. The power flow operation is used for calculating the distribution and change of voltage, probability, current and other related electric quantity in the power system, and the operation parameters of the abnormal sub-equipment can be obtained by using the power flow operation. The topology structure of the electronic circuit inside the energy storage power supply represents the types of elements and connection relations contained in the circuit, the node flow equation is used for describing the voltage of each node of the electronic circuit inside the energy storage power supply, and the branch flow equation is used for describing the power flow direction and the power flow of each branch of the electronic circuit inside the energy storage power supply. The reason for initializing the voltage of each node in the electronic circuit in the energy storage power supply is to provide preconditions for tide operation, the iteration method can gradually improve the estimated values of the voltage of the node of the electronic circuit, the power of the branch circuit and the like until convergence conditions are met, iteration calculation can be stopped, and at the moment, the operation parameter values of each piece of sub-equipment in the energy storage power supply are calculated. The invention can acquire the operation parameters of the abnormal sub-equipment through the tide operation, and define the operation parameters as the abnormal operation parameters.
FIG. 3 shows a flowchart for obtaining an optimal energy storage power supply debugging scheme and processing abnormal conditions of the energy storage power supply debugged by the optimal energy storage power supply debugging scheme, comprising the following steps:
s302: constructing an energy storage power supply dynamic simulation model, and acquiring and outputting an optimal energy storage power supply debugging scheme by combining the energy storage power supply dynamic simulation model through big data retrieval based on the abnormal operation parameters;
s304: acquiring an ideal debugging result-actual debugging result comparison table, and judging the debugging effect based on the ideal debugging result-actual debugging result comparison table;
s306: and regulating and controlling the energy storage power supply sub-equipment with unqualified regulating and controlling effect.
Further, in a preferred embodiment of the present invention, the construction of the energy storage power supply dynamic simulation model, based on the abnormal operation parameters, obtains and outputs an optimal energy storage power supply debugging scheme by combining with the energy storage power supply dynamic simulation model through big data retrieval, specifically:
based on a production drawing of an energy storage power supply and operation parameter values of all sub-equipment in the energy storage power supply, an energy storage power supply three-dimensional model is built in three-dimensional software, the energy storage power supply three-dimensional model is converted into an energy storage power supply three-dimensional model file according to a data format of dynamic simulation software, and the energy storage power supply three-dimensional model file is imported into the dynamic simulation software to obtain an energy storage power supply dynamic simulation model;
Importing the abnormal operation parameters into a big data network for network retrieval, acquiring all debugging schemes of the abnormal operation parameters in abnormal sub-equipment of the energy storage power supply, and summarizing all the debugging schemes to obtain an initial debugging scheme set;
importing the initial debugging scheme set into an energy storage electric dynamic simulation model to obtain a debugging result, and eliminating the corresponding debugging scheme of which the operation parameters of the abnormal sub-equipment are not in the preset operation parameter range in the initial debugging scheme set to obtain a second debugging scheme set;
obtaining the debugging efficiency of all the debugging results in the second debugging scheme set, extracting the debugging schemes with the debugging efficiency larger than a preset threshold value, and obtaining a third debugging scheme set;
obtaining the debugging properties of all the debugging schemes in the third debugging scheme set, and eliminating the debugging schemes with the debugging properties not meeting the preset debugging properties to obtain a fourth debugging scheme set;
and based on the debugging efficiency of all the debugging schemes in the fourth debugging scheme set, carrying out efficiency sorting, outputting the debugging scheme with the highest debugging efficiency, and defining the debugging scheme with the highest debugging efficiency as the optimal energy storage power supply debugging scheme.
It should be noted that, when the energy storage power supply is debugged in an ideal state, a dynamic simulation model of the energy storage power supply needs to be constructed, and the debugging is performed in the dynamic simulation model. Multiple debugging schemes can be obtained after the big data is retrieved, the debugging effect of each debugging scheme on the energy storage power supply is different, and the debugging scheme output with the best debugging effect is required to be screened. And eliminating the debugging scheme with the debugging effect which does not meet the preset effect, eliminating the debugging scheme with the debugging efficiency lower than the preset value, eliminating the debugging scheme which needs manual intervention in the debugging process, and finally screening to obtain the debugging scheme with the highest debugging efficiency and outputting. According to the invention, the optimal energy storage power supply debugging scheme can be obtained by constructing the energy storage power supply dynamic simulation model and according to the debugging conditions from big data.
Further, in a preferred embodiment of the present invention, the obtaining an ideal debug result-actual debug result comparison table, and judging the debug effect based on the ideal debug result-actual debug result comparison table specifically includes:
outputting the optimal energy storage power supply debugging scheme to an energy storage power supply, wherein the energy storage power supply carries out debugging on abnormal sub-equipment based on the optimal energy storage power supply debugging scheme, and obtains real-time debugging operation parameters of all sub-equipment in the energy storage power supply through tide calculation in the debugging process;
Outputting the optimal energy storage power supply debugging scheme in an energy storage power supply dynamic simulation model to obtain ideal debugging operation parameters, and generating an ideal debugging result-actual debugging result comparison table based on the ideal debugging operation parameters and the real-time debugging operation parameters.
It should be noted that in actual debugging, the debugging result will be different from the ideal result, the optimal energy storage power source debugging scheme is introduced into the energy storage power source for debugging, the obtained debugging result may be different from the ideal result, the current operation parameters of the abnormal sub-equipment need to be obtained through load flow calculation, and the current operation parameters are compared with the ideal parameters to obtain an ideal debugging result-actual debugging result comparison table. The ideal debugging result-actual debugging result comparison table can intuitively obtain the difference between the ideal debugging result and the actual debugging result at the same time. According to the invention, the optimal energy storage power supply debugging scheme can be imported into the energy storage power supply for debugging, so that an ideal debugging result-actual debugging result comparison table is obtained.
Further, in a preferred embodiment of the present invention, the adjusting and controlling the energy storage power supply sub-device with failed adjusting and controlling effect specifically includes:
analyzing the ideal debugging result-actual debugging result comparison table, if the difference between the actual debugging result and the ideal debugging result in the same time is within a preset value, evaluating the corresponding time debugging effect as A, and if the difference between the actual debugging result and the ideal debugging result in the same time is smaller than the preset value, evaluating the corresponding time debugging effect as B;
Recording corresponding debugging time with the debugging effect of being evaluated as B, defining the debugging time as abnormal debugging time, acquiring sub-equipment for debugging in the abnormal debugging time, and defining the sub-equipment as second abnormal sub-equipment;
and disassembling the second abnormal sub-equipment and performing maintenance treatment, wherein the second abnormal sub-equipment is reinstalled into the energy storage power supply after being maintained, the real-time operation parameters of the reinstalled second abnormal sub-equipment are calculated by using a tide algorithm, and if the real-time operation parameters output by the maintained second abnormal sub-equipment are smaller than a preset value, the second abnormal sub-equipment is replaced.
It should be noted that, when the energy storage power supply is debugged in the same time, some debugging effects are normal, some debugging effects are abnormal, and the abnormal sub-equipment with abnormal debugging effects in the same time needs to be processed. And in the same time, judging the debugging effect of which the actual debugging effect is not within the preset value as B, wherein the reason that the debugging result is not within the preset value is possibly that the sub-equipment is in fault and needs to be maintained or replaced. And (3) firstly maintaining the abnormal sub-equipment, and if the maintained abnormal sub-equipment cannot output normal operation parameters, replacing the abnormal sub-equipment. According to the invention, the abnormal sub-equipment can be maintained or replaced according to the debugging effect of the sub-equipment in the same time.
In addition, the energy storage power supply evaluation method based on the Internet of things further comprises the following steps:
acquiring internal parameters of abnormal sub-equipment through ultrasonic flaw detection, and defining the abnormal sub-equipment as scrapped equipment if the internal parameters of the abnormal sub-equipment are out of a preset range;
if the internal parameters of the abnormal sub-equipment are within a preset range, acquiring a surface gray level image of the abnormal sub-equipment by using a camera, selecting a bilateral filter to carry out filtering treatment on the surface gray level image, defining a sliding window in the bilateral filter, and setting an origin pixel at the central position of the sliding window;
the sliding window is placed on a surface gray level image of the abnormal sub-equipment to slide, the distance between each pixel in the sliding window and the original pixel is calculated, and the space weight value of each pixel in the sliding window is obtained;
multiplying the space weight value of each pixel in the sliding window with the gray value of the pixel, and generating a surface filtering gray image based on the multiplication result;
extracting surface texture features of the abnormal sub-equipment from the surface filtering gray level image by a threshold segmentation method, and comparing and analyzing the surface texture features of the abnormal sub-equipment with the surface texture features of ideal sub-equipment with the same specification to obtain the surface defect condition of the abnormal sub-equipment, wherein the surface defect condition of the abnormal sub-equipment is that surface cracks are generated;
Acquiring the surface crack depth of the abnormal sub-equipment, and defining the abnormal sub-equipment as scrapped equipment if the surface crack depth of the abnormal sub-equipment is larger than a preset value;
if the surface crack depth of the abnormal sub-equipment is smaller than the preset value, polishing and maintaining the abnormal sub-equipment to obtain the maintained abnormal sub-equipment, wherein the abnormal sub-equipment is defined as maintenance equipment;
and installing the maintenance equipment into the energy storage power supply, and scrapping the maintenance equipment if the maintenance equipment cannot output the operation parameters within the preset value in the operation process of the energy storage power supply.
It should be noted that, the fault of the abnormal sub-equipment may be internal on the surface, and when the internal parameters of the abnormal sub-equipment are abnormal, it is proved that the physical properties of the abnormal sub-equipment are changed, and the abnormal sub-equipment is completely scrapped and needs to be directly replaced; if the internal parameters of the abnormal sub-equipment are normal, judging the surface parameters of the abnormal sub-equipment, and clearly obtaining the surface defect condition of the abnormal sub-equipment by a bilateral filtering method and a threshold segmentation method, wherein when the depth of the surface crack is too large, the size parameters and the physical properties of the abnormal sub-equipment are greatly changed after the abnormal sub-equipment is maintained, so that the abnormal sub-equipment is directly scrapped without maintenance; the abnormal sub-equipment with the surface crack depth within the preset value can be polished and maintained, and when the abnormal sub-equipment subjected to maintenance cannot output normal working parameters, the physical properties of the abnormal sub-equipment are judged to be changed after polishing and maintenance, and the abnormal sub-equipment cannot be used and needs to be replaced. The invention can formulate a treatment scheme for repairing or replacing the abnormal sub-equipment by judging the internal parameters and the external defects of the abnormal sub-equipment.
In addition, the energy storage power supply evaluation method based on the Internet of things further comprises the following steps:
acquiring the abnormal probability of the surface defect of the abnormal sub-equipment, analyzing the abnormal probability of the surface defect of the abnormal sub-equipment and the preset probability, and acquiring the working environment element of the corresponding abnormal sub-equipment if the abnormal probability of the surface defect of the abnormal sub-equipment is larger than the preset probability;
calculating information entropy and weight between the surface defect and the working environment element by an entropy weight method to obtain a correlation value between the surface defect and the working environment;
analyzing the association value, and regulating and controlling the working environment if the association value is larger than a preset value;
in the regulation and control process, recording a correlation value between the surface defect and the working environment, and recording the working environment factors and keeping the working environment factors constant when the correlation value is smaller than a preset value.
It should be noted that, the working environment includes working temperature and humidity, and an excessive working temperature and humidity may cause irreversible defects on the surface of the sub-equipment, such as metal melting, metal corrosion, and the like, so as to affect the operation parameters of the energy storage power supply, such as affecting the service life of the battery, affecting the response speed of charging and discharging, and the like. The association value of the environmental factors and the surface defects of the abnormal sub-equipment can be obtained through an entropy weight method, the weight of each criterion can be determined through the entropy weight method, and the association degree among different factors is obtained. The working environment is required to be regulated and controlled, the constant temperature and humidity of the working environment is maintained, and the correlation value is smaller than a preset value, so that the current working environment is proved to not influence abnormal sub-equipment. The invention can realize the regulation and control of the working environment by judging the association degree of the working environment and the surface defects of the abnormal sub-equipment.
As shown in fig. 4, the second aspect of the present invention further provides an energy storage power supply evaluation system based on the internet of things, where the energy storage power supply evaluation system includes a memory 41 and a processor 42, where an energy storage power supply evaluation program is stored in the memory 41, and when the energy storage power supply evaluation program is executed by the processor 42, the following steps are implemented:
based on the decision tree model and the historical data information, a standard energy storage power supply prediction model is constructed, and standard energy storage power supply prediction parameters are generated;
acquiring operation parameters of an energy storage power supply, and importing the operation parameters of the energy storage power supply into a standard energy storage power supply prediction model to obtain energy storage power supply prediction parameters;
performing data analysis on the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters, and determining abnormal sub-equipment and abnormal operation parameters of the energy storage power supply according to analysis results;
constructing an energy storage power supply dynamic simulation model, and acquiring and outputting an optimal energy storage power supply debugging scheme by combining the energy storage power supply dynamic simulation model through big data retrieval based on the abnormal operation parameters;
outputting the optimal energy storage power supply debugging scheme to an energy storage power supply for debugging, monitoring the operation parameters of the energy storage power supply in the debugging process, and processing abnormal conditions during the debugging process.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
1. The energy storage power supply evaluation method based on the Internet of things is characterized by comprising the following steps of:
based on the decision tree model and the historical data information, a standard energy storage power supply prediction model is constructed, and standard energy storage power supply prediction parameters are generated;
acquiring operation parameters of an energy storage power supply, and importing the operation parameters of the energy storage power supply into a standard energy storage power supply prediction model to obtain energy storage power supply prediction parameters;
performing data analysis on the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters, and determining abnormal sub-equipment and abnormal operation parameters of the energy storage power supply according to analysis results;
constructing an energy storage power supply dynamic simulation model, and acquiring and outputting an optimal energy storage power supply debugging scheme by combining the energy storage power supply dynamic simulation model through big data retrieval based on the abnormal operation parameters;
Outputting the optimal energy storage power supply debugging scheme to an energy storage power supply for debugging, monitoring the operation parameters of the energy storage power supply in the debugging process, and processing abnormal conditions during the debugging process.
2. The method for evaluating the energy storage power supply based on the internet of things according to claim 1, wherein the method is characterized in that a standard energy storage power supply prediction model is constructed based on a decision tree model and historical data information, and standard energy storage power supply prediction parameters are generated, specifically:
acquiring historical data information of the energy storage power supplies with the same specification and the same model, and importing the historical data information into a decision tree model;
acquiring characteristics of different operation parameters in the history data information of the energy storage power supply, generating operation parameter characteristic points, and determining operation parameter partitioning points based on the operation parameter characteristic points and combining with the base non-purity of the history data information of the energy storage power supply;
determining a root node in the decision tree model, performing data segmentation on the historical data information of the energy storage power supply based on an operation parameter segmentation point by taking the root node as a starting point to obtain two data subsets, repeating the steps by taking the two data subsets as starting points, performing data segmentation on the data subsets, and defining the segmentation point as a leaf node;
Presetting the maximum depth of a decision tree and the minimum value of data samples in a data subset, wherein the maximum depth of the decision tree is the number of nodes on a path from a root node to a farthest leaf node, the data samples in the data subset reach the minimum value of the data samples in the data subset, or the depth after the data subset is segmented reaches the maximum depth, and the segmentation of the data subset is stopped to obtain an energy storage power supply decision tree;
carrying out data analysis on the energy storage power supply decision tree, judging the fitting condition of the energy storage power supply decision tree, and screening and removing leaf nodes of the energy storage power supply decision tree based on the fitting condition to obtain a complete energy storage power supply decision tree;
and extracting internal parameters of the complete energy storage power supply decision tree, constructing a standard energy storage power supply prediction model, and generating standard energy storage power supply prediction parameters based on the standard energy storage power supply prediction model.
3. The method for evaluating the energy storage power supply based on the internet of things according to claim 1, wherein the steps of obtaining the operation parameters of the energy storage power supply, and importing the operation parameters of the energy storage power supply into a standard energy storage power supply prediction model to obtain the prediction parameters of the energy storage power supply are as follows:
the current input and output ends of the energy storage power supply are connected with a universal meter, the current of the energy storage power supply is measured, and the initial SOC value of the energy storage power supply is obtained;
Presetting a time step, multiplying and accumulating the current value of the energy storage power supply and the time step to obtain a charge and discharge amount predicted value of the battery in the current time step, and subtracting the initial SOC value of the energy storage power supply from the charge and discharge amount predicted value of the battery in the current time step to obtain a real-time SOC value of the energy storage power supply;
installing a sensor in an energy storage power supply, acquiring sensor data, removing abnormal values and repeated values in the sensor data, filling the missing values in the sensor data by using an interpolation method, and obtaining the sensor data after data cleaning;
performing multi-scale decomposition on the sensor data after data cleaning according to a preset threshold value to obtain a high-frequency wavelet coefficient and a low-frequency wavelet coefficient, setting the low-frequency wavelet coefficient to 0, continuing to decompose the high-frequency wavelet coefficient, stopping decomposition when the decomposition times reach the preset value, and performing wavelet inverse transformation on the low-frequency wavelet coefficient to obtain preprocessed sensor data;
and combining the preprocessed sensor data with the real-time SOC value of the energy storage power supply to generate the operation parameters of the energy storage power supply, importing the operation parameters of the energy storage power supply into a standard energy storage power supply prediction model to generate an energy storage power supply prediction model, and obtaining the energy storage power supply prediction parameters through the energy storage power supply prediction model.
4. The method for evaluating the energy storage power supply based on the internet of things according to claim 1, wherein the data analysis is performed on the standard energy storage power supply prediction parameter and the energy storage power supply prediction parameter, and the abnormal sub-equipment and the abnormal operation parameter of the energy storage power supply are determined according to the analysis result, specifically:
performing data fitting on the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters, deleting a data fitting part, and obtaining a data deviation value, wherein the data deviation value comprises voltage deviation, resistance deviation, temperature deviation and SOC value deviation;
based on the data deviation value, determining a random variable of the Bayesian network model, expressing a random variable as a node in a Bayesian network, and determining directed edges between nodes in the Bayesian network;
based on a maximum likelihood method, obtaining a conditional probability table of each node of a Bayesian network, carrying out structure learning on the Bayesian network based on directed edges among nodes in the Bayesian network, generating a Bayesian network model, importing the conditional probability table of each node of the Bayesian network into the Bayesian network model for carrying out probability reasoning, and determining abnormal sub-equipment of a corresponding energy storage power supply causing a data deviation value;
Acquiring a topological structure of an electronic circuit in an energy storage power supply, and establishing a circuit equation based on the topological structure of the electronic circuit in the energy storage power supply and the preprocessed sensor data, wherein the circuit equation comprises a node tide equation and a branch tide equation;
initializing voltage of each node in an electronic circuit in the energy storage power supply, solving the operation parameter value of each piece of equipment in the energy storage power supply by an iteration method based on the circuit equation, stopping performing iterative calculation when the iteration times reach a preset value, and outputting the operation parameter value of each piece of equipment in the energy storage power supply;
and acquiring the operation parameter value of the abnormal sub-equipment of the energy storage power supply based on the operation parameter value of each sub-equipment in the energy storage power supply, and defining the operation parameter value as an abnormal operation parameter.
5. The method for evaluating the energy storage power supply based on the internet of things according to claim 1, wherein the constructing the energy storage power supply dynamic simulation model, based on the abnormal operation parameters, obtains and outputs an optimal energy storage power supply debugging scheme by combining the energy storage power supply dynamic simulation model through big data retrieval, specifically comprises:
based on a production drawing of an energy storage power supply and operation parameter values of all sub-equipment in the energy storage power supply, an energy storage power supply three-dimensional model is built in three-dimensional software, the energy storage power supply three-dimensional model is converted into an energy storage power supply three-dimensional model file according to a data format of dynamic simulation software, and the energy storage power supply three-dimensional model file is imported into the dynamic simulation software to obtain an energy storage power supply dynamic simulation model;
Importing the abnormal operation parameters into a big data network for network retrieval, acquiring all debugging schemes of the abnormal operation parameters in abnormal sub-equipment of the energy storage power supply, and summarizing all the debugging schemes to obtain an initial debugging scheme set;
importing the initial debugging scheme set into an energy storage electric dynamic simulation model to obtain a debugging result, and eliminating the corresponding debugging scheme of which the operation parameters of the abnormal sub-equipment are not in the preset operation parameter range in the initial debugging scheme set to obtain a second debugging scheme set;
obtaining the debugging efficiency of all the debugging results in the second debugging scheme set, extracting the debugging schemes with the debugging efficiency larger than a preset threshold value, and obtaining a third debugging scheme set;
obtaining the debugging properties of all the debugging schemes in the third debugging scheme set, and eliminating the debugging schemes with the debugging properties not meeting the preset debugging properties to obtain a fourth debugging scheme set;
and based on the debugging efficiency of all the debugging schemes in the fourth debugging scheme set, carrying out efficiency sorting, outputting the debugging scheme with the highest debugging efficiency, and defining the debugging scheme with the highest debugging efficiency as the optimal energy storage power supply debugging scheme.
6. The method for evaluating the energy storage power supply based on the internet of things according to claim 1, wherein the outputting the optimal energy storage power supply debugging scheme to the energy storage power supply for debugging, monitoring the operation parameters of the energy storage power supply in the debugging process, and processing abnormal conditions occurring in the debugging process is specifically as follows:
outputting the optimal energy storage power supply debugging scheme to an energy storage power supply, wherein the energy storage power supply carries out debugging on abnormal sub-equipment based on the optimal energy storage power supply debugging scheme, and obtains real-time debugging operation parameters of all sub-equipment in the energy storage power supply through tide calculation in the debugging process;
outputting the optimal energy storage power supply debugging scheme in an energy storage power supply dynamic simulation model to obtain ideal debugging operation parameters, and generating an ideal debugging result-actual debugging result comparison table based on the ideal debugging operation parameters and the real-time debugging operation parameters;
analyzing the ideal debugging result-actual debugging result comparison table, if the difference between the actual debugging result and the ideal debugging result in the same time is within a preset value, evaluating the corresponding time debugging effect as A, and if the difference between the actual debugging result and the ideal debugging result in the same time is smaller than the preset value, evaluating the corresponding time debugging effect as B;
Recording corresponding debugging time with the debugging effect of being evaluated as B, defining the debugging time as abnormal debugging time, acquiring sub-equipment for debugging in the abnormal debugging time, and defining the sub-equipment as second abnormal sub-equipment;
and disassembling the second abnormal sub-equipment and performing maintenance treatment, wherein the second abnormal sub-equipment is reinstalled into the energy storage power supply after being maintained, the real-time operation parameters of the reinstalled second abnormal sub-equipment are calculated by using a tide algorithm, and if the real-time operation parameters output by the maintained second abnormal sub-equipment are smaller than a preset value, the second abnormal sub-equipment is replaced.
7. The energy storage power supply evaluation system based on the Internet of things is characterized by comprising a memory and a processor, wherein an energy storage power supply evaluation program is stored in the memory, and when the energy storage power supply evaluation program is executed by the processor, the following steps are realized:
based on the decision tree model and the historical data information, a standard energy storage power supply prediction model is constructed, and standard energy storage power supply prediction parameters are generated;
acquiring operation parameters of an energy storage power supply, and importing the operation parameters of the energy storage power supply into a standard energy storage power supply prediction model to obtain energy storage power supply prediction parameters;
Performing data analysis on the standard energy storage power supply prediction parameters and the energy storage power supply prediction parameters, and determining abnormal sub-equipment and abnormal operation parameters of the energy storage power supply according to analysis results;
constructing an energy storage power supply dynamic simulation model, and acquiring and outputting an optimal energy storage power supply debugging scheme by combining the energy storage power supply dynamic simulation model through big data retrieval based on the abnormal operation parameters;
outputting the optimal energy storage power supply debugging scheme to an energy storage power supply for debugging, monitoring the operation parameters of the energy storage power supply in the debugging process, and processing abnormal conditions during the debugging process.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311007558.8A CN116738865B (en) | 2023-08-11 | 2023-08-11 | Energy storage power supply evaluation method and system based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311007558.8A CN116738865B (en) | 2023-08-11 | 2023-08-11 | Energy storage power supply evaluation method and system based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116738865A true CN116738865A (en) | 2023-09-12 |
| CN116738865B CN116738865B (en) | 2023-12-19 |
Family
ID=87909925
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311007558.8A Active CN116738865B (en) | 2023-08-11 | 2023-08-11 | Energy storage power supply evaluation method and system based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116738865B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117323578A (en) * | 2023-12-01 | 2024-01-02 | 深圳恩多克医疗有限公司 | Intelligent control method and system for infrared therapeutic apparatus |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011481A (en) * | 2021-03-10 | 2021-06-22 | 广东电网有限责任公司计量中心 | Electric energy meter function abnormity evaluation method and system based on decision tree algorithm |
| CN114493919A (en) * | 2022-01-18 | 2022-05-13 | 杭州安脉盛智能技术有限公司 | Training method of energy storage power station operation monitoring model and monitoring system of energy storage power station |
| CN115514005A (en) * | 2022-10-12 | 2022-12-23 | 北京双登慧峰聚能科技有限公司 | Economical evaluation method and device for photovoltaic power station energy storage system configuration |
| CN115663936A (en) * | 2022-09-19 | 2023-01-31 | 华电内蒙古能源有限公司 | Method and system for evaluating and improving energy storage full life cycle SOH (self-organizing hydrogen) staged utilization value |
| CN116050262A (en) * | 2023-01-04 | 2023-05-02 | 中能建数字科技集团有限公司 | Safety state evaluation method, device and system of compressed air energy storage power station |
| CN116150655A (en) * | 2023-01-06 | 2023-05-23 | 国网湖南省电力有限公司 | Method, system and medium for evaluating fault severity degree of breaker energy storage spring |
-
2023
- 2023-08-11 CN CN202311007558.8A patent/CN116738865B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113011481A (en) * | 2021-03-10 | 2021-06-22 | 广东电网有限责任公司计量中心 | Electric energy meter function abnormity evaluation method and system based on decision tree algorithm |
| CN114493919A (en) * | 2022-01-18 | 2022-05-13 | 杭州安脉盛智能技术有限公司 | Training method of energy storage power station operation monitoring model and monitoring system of energy storage power station |
| CN115663936A (en) * | 2022-09-19 | 2023-01-31 | 华电内蒙古能源有限公司 | Method and system for evaluating and improving energy storage full life cycle SOH (self-organizing hydrogen) staged utilization value |
| CN115514005A (en) * | 2022-10-12 | 2022-12-23 | 北京双登慧峰聚能科技有限公司 | Economical evaluation method and device for photovoltaic power station energy storage system configuration |
| CN116050262A (en) * | 2023-01-04 | 2023-05-02 | 中能建数字科技集团有限公司 | Safety state evaluation method, device and system of compressed air energy storage power station |
| CN116150655A (en) * | 2023-01-06 | 2023-05-23 | 国网湖南省电力有限公司 | Method, system and medium for evaluating fault severity degree of breaker energy storage spring |
Non-Patent Citations (1)
| Title |
|---|
| 赵泽昆;黄宇丹;张真;赵媛杰;宋春蕊;李国伟;: "基于小波神经网络的光伏电站储能电池SOC状态评估", 电器与能效管理技术, no. 01 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117323578A (en) * | 2023-12-01 | 2024-01-02 | 深圳恩多克医疗有限公司 | Intelligent control method and system for infrared therapeutic apparatus |
| CN117323578B (en) * | 2023-12-01 | 2024-01-30 | 深圳恩多克医疗有限公司 | Intelligent control method and system for infrared therapeutic apparatus |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116738865B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116738865B (en) | Energy storage power supply evaluation method and system based on Internet of things | |
| CN111210024A (en) | Model training method and device, computer equipment and storage medium | |
| CN110119787B (en) | Working condition detection method and equipment for rotary mechanical equipment | |
| CN113671394A (en) | Lithium ion battery expected life prediction method and system | |
| CN113076689B (en) | Battery state evaluation method based on automatic encoder | |
| CN113657030A (en) | Method for predicting remaining service life of lithium battery based on Gaussian process regression | |
| CN110766236A (en) | Power equipment state trend prediction method based on statistical analysis and deep learning | |
| CN111025041A (en) | Electric vehicle charging pile monitoring method and system, computer equipment and medium | |
| CN117169761A (en) | Battery state evaluation method, apparatus, device, storage medium, and program product | |
| CN109921462B (en) | New energy consumption capability assessment method and system based on LSTM | |
| CN115081597A (en) | Method, system, equipment and medium for performing carbon check by using electricity based on machine learning | |
| CN114547969A (en) | EMD-MRVR-based multi-stress battery life prediction method | |
| CN118169582A (en) | Lithium ion battery health state and residual life prediction method | |
| CN114201825A (en) | Method and system for evaluating equipment performance degradation state based on combination characteristics | |
| CN117728421A (en) | Micro-grid cluster coordinated scheduling method, system, computer equipment and storage medium | |
| CN117350662A (en) | Full life cycle calculation method of SoH (solar energy generation) of energy storage system | |
| CN117312763A (en) | Variable frequency household appliance performance visual supervision system and method based on cloud platform | |
| CN108123436B (en) | Voltage out-of-limit prediction model based on principal component analysis and multiple regression algorithm | |
| CN115409367A (en) | Intelligent power grid health state assessment method and system based on Internet of things | |
| KR102542488B1 (en) | Method and Apparatus for Predicting Appliance Power Usage State Using Non Intrusive Load Monitoring Based on Long-Short Term Memory | |
| CN115528684A (en) | Ultra-short-term load prediction method and device and electronic equipment | |
| CN113809789A (en) | Power control method, energy router, power control system and storage medium | |
| Zhang et al. | Wind energy forecasting framework based on new perspective | |
| CN108960588A (en) | A kind of integrated evaluating method for Wind turbines standby redundancy | |
| CN118584363B (en) | Fusion characteristic-based lithium ion battery residual service life prediction method |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |