CN114186756A - Method for predicting energy storage capacity of storage battery of power distribution network terminal - Google Patents
Method for predicting energy storage capacity of storage battery of power distribution network terminal Download PDFInfo
- Publication number
- CN114186756A CN114186756A CN202210024011.8A CN202210024011A CN114186756A CN 114186756 A CN114186756 A CN 114186756A CN 202210024011 A CN202210024011 A CN 202210024011A CN 114186756 A CN114186756 A CN 114186756A
- Authority
- CN
- China
- Prior art keywords
- gray
- sample
- energy storage
- training
- storage battery
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000004146 energy storage Methods 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 48
- 238000013528 artificial neural network Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 4
- 238000012360 testing method Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 9
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 7
- 230000009471 action Effects 0.000 claims description 4
- 238000011161 development Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 3
- 238000007599 discharging Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000006467 substitution reaction Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract 1
- 230000008859 change Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
- G06F17/13—Differential equations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Analysis (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Marketing (AREA)
- Computational Linguistics (AREA)
- Operations Research (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Databases & Information Systems (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Algebra (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method for predicting the energy storage capacity of a storage battery of a power distribution network terminal, which comprises the steps of data acquisition and processing, establishing a gray differential equation according to a training sample X, constructing a gray prediction model of the gray differential equation, and calculating a gray prediction valuePredicting the gray value obtained in the S2With the training sampleTraining an RBF neural network by taking the Y as input and output to obtain an error compensator; the method can effectively solve the problem that the estimation of the energy storage capacity of the storage battery of the power distribution network is inaccurate under the small sample condition of less data, considers the influence of environmental variables, and improves the prediction precision compared with the traditional estimation method.
Description
Technical Field
The invention relates to the field of power systems, in particular to a method for predicting the energy storage capacity of a storage battery of a power distribution network terminal.
Background
The storage battery is used as a core component in the distribution network automation system, and the stable operation of the storage battery can ensure that the distribution network terminal continues to operate after power failure fault occurs, so that fault area isolation and power restoration in a non-fault area are completed. In the operation process of the storage battery, the storage battery is influenced by the working environment and can age gradually along with the increase of working time, the energy storage capacity of the storage battery, which is a main index of the storage battery, is reduced gradually, and when the energy storage capacity of the storage battery is reduced to a certain degree, the storage battery needs to be maintained or replaced in time so as to ensure the stability of power supply.
The energy storage capacity of the storage battery is mainly related to the internal resistance of the battery, the operation temperature, the float charge voltage, the uniform charge time, the discharge frequency, the air humidity and the like. Limited by the working life of the storage battery, only a small amount of operation data of the storage battery in a short period can be obtained, the operation environment and operation parameters of the storage battery are not considered in detail in the conventional estimation method, a large error exists in estimation precision, the current operation state of the storage battery is difficult to accurately master, and the development of storage battery maintenance and troubleshooting work is not facilitated.
Disclosure of Invention
The invention aims to provide a method for predicting the energy storage capacity of a storage battery at a power distribution network terminal to solve the problem that the energy storage state of the storage battery cannot be accurately estimated under the condition that a large amount of data is difficult to obtain.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides a method for predicting the energy storage capacity of a storage battery at a power distribution network terminal, which comprises the following steps:
s1, data acquisition and processing: collecting the energy storage capacity C, the internal resistance R, the operating temperature T and the float charging voltage V of the storage battery by taking a month as a unitfThe average charging time J, the discharging times N and the air humidity M are acquired for multiple times and averaged to be used as a sample input X and a sample output Y; after a sample set is obtained, dividing the sample set into a training sample X, a training sample Y, a test sample X 'and a test sample Y';
s2, establishing a gray differential equation according to the training sample X, establishing a gray prediction model of the gray differential equation, and calculating a gray prediction value
S3, the grey prediction value obtained in the S2Training the RBF neural network by taking the training sample Y as input and output to obtain an error compensator;
s4, calculating test samples X 'and Y' by using the gray prediction model, and obtaining the gray prediction valueThe output of the error compensator is the predicted value of the energy storage capacity of the storage battery;
and S5, performing precision evaluation on the gray prediction model by using a model inspection method, wherein the gray prediction model can be used when meeting the precision requirement and can be corrected when not meeting the requirement.
Further, in S1, in consideration of the fact that the storage battery energy storage capacity and the battery internal resistance change are small, collecting storage battery operation data for 24 months as a sample data set in a month unit; wherein the energy storage capacity C is obtained by a nuclear capacity test, the internal resistance R of the battery, the operating temperature T and the float charging voltage VfThe data of the uniform charging time J, the discharging times N and the air humidity M are collected by monitoring equipment, and the data of each monthData are collected for multiple times, an average value is taken and put into a sample set, and the format of the average value is as follows:
after a sample set is obtained, the sample set is divided into the training sample X, the training sample Y, the test sample X 'and the test sample Y'.
Further, in S2, the gray prediction model accumulates the original data of the training sample X and weakens the irregularity of the data, and establishes a differential equation for data fitting and prediction, where the construction process is as follows:
s201, constructing an adjacent mean equal weight generation sequence
Setting the X original data of the training sample as X(0)The original data sequence X(0)Through one-time accumulation, X is generated(1)I.e. by
Computing adjacent mean equal weight generation sequence Z(1)(k) The calculation formula is as follows:
s202, constructing the gray differential equation
Wherein, a is a development coefficient, and b is an ash action amount;
S203, solving the gray differential equation and calculating a gray prediction sequence
To obtainThereafter, the equation (4) becomes an n-order ordinary differential equation; since the order n of the formula (4) is unknown, the solution can not be directly obtained, and the numerical solution is obtained by Runge-Kutta;
assuming that the order number n in the formula (4) is two, the formula (7) is reduced by algebraic substitution:
equation (7) then becomes:
the above formula was adapted using the Runge-Kutta recursion:
further, in the step S3, the gray prediction value obtained in the step S2 is usedAnd training the RBF neural network by taking the training sample Y as input and output to obtain an error compensator, wherein the training process is as follows:
s301, initializing parameters including a basis function center c, a width sigma and a weight w;
s302, calculating parameters of a hidden layer and an output layer by using a radial basis function, and calculating a loss function E;
s303, judging the loss, stopping training in the acceptance range, and updating the center, the width and the weight by using a gradient updating method if the loss is not in the acceptance range, wherein the gradient updating formula is shown as the following formula:
where η is the learning factor and E is the loss function.
And S304, finishing training to obtain the error compensator.
Further, in S5, the accuracy evaluation calculation formula is as follows:
wherein, RMSE is the root mean square error, MAE is the average absolute error, and is used for evaluating the accuracy of the prediction model.
The invention has the beneficial effects that: the problem of inaccurate estimation of the storage battery energy storage capacity of the power distribution network under the small sample condition of 'few data' is solved, and the efficiency of a storage battery management system in the distribution network automation system can be improved to a certain extent.
The influence of the storage battery operation environment variable on the storage battery energy storage capacity is considered, and the prediction precision is improved compared with the traditional estimation method.
Drawings
FIG. 1 is a flow chart of the present gray neural network;
FIG. 2 is a 3RBF neural network architecture;
fig. 3 is a diagram of the prediction result of the storage battery energy storage capacity.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Please refer to a method for predicting the energy storage capacity of a storage battery of a terminal of a power distribution network, which comprises the following steps:
s1, data acquisition and processing: collecting the energy storage capacity C, the internal resistance R, the operating temperature T and the float charging voltage V of the storage battery by taking a month as a unitfCollecting and averaging for multiple times as sample input X and sample output Y; after a sample set is obtained, dividing the sample set into a training sample X, a training sample Y, a test sample X 'and a test sample Y';
s2, establishing a gray differential equation according to the training sample X, establishing a gray prediction model of the gray differential equation, and calculating a gray prediction value
S3, the grey prediction value obtained in the S2With the training sample Y as input and outputTraining an RBF neural network to obtain an error compensator;
s4, calculating test samples X 'and Y' by using the gray prediction model, and obtaining the gray prediction valueThe output of the error compensator is the predicted value of the energy storage capacity of the storage battery;
and S5, performing precision evaluation on the gray prediction model by using a model inspection method, wherein the gray prediction model can be used when meeting the precision requirement and can be corrected when not meeting the requirement.
In the step S1, in consideration of small changes in the energy storage capacity and the internal resistance of the battery, 24-month operation data of the battery is acquired as a sample data set in a month unit; wherein the energy storage capacity C is obtained by a nuclear capacity test, the internal resistance R of the battery, the operating temperature T and the float charging voltage VfThe data of the charging time J, the discharge times N and the air humidity M are collected through monitoring equipment, the data of each month are collected for multiple times, the average value is taken and put into a sample set, and the format is as follows:
after a sample set is obtained, the sample set is divided into the training sample X, the training sample Y, the test sample X 'and the test sample Y'.
And constructing a gray model (GM (n,1)) of the energy storage capacity of the storage battery under the current state based on the storage battery operation data sample set X, Y, and strengthening the action characteristics of different parameters in the operation process of the storage battery on the change of the energy storage capacity. In the process, the data distribution characteristics of the training sample X need to be analyzed, and the gray predicted value is calculated by adopting differential equations with different orders to perform curve fitting according to the data distribution characteristics.
In S2, the gray prediction model accumulates the original data of the training sample X, weakens the irregularity of the data, and establishes a differential equation for data fitting and prediction, and the construction process is as follows:
s201, constructing an adjacent mean equal weight generation sequence
Setting the X original data of the training sample as X(0)The original data sequence X(0)Through one-time accumulation, X is generated(1)I.e. by
Computing adjacent mean equal weight generation sequence Z(1)(k) The calculation formula is as follows:
s202, constructing the gray differential equation
Wherein, a is a development coefficient, and b is an ash action amount;
S203, solving the gray differential equation and calculating a gray prediction sequence
To obtainThereafter, the equation (4) becomes an n-order ordinary differential equation; since the order n of the formula (4) is unknown, the solution can not be directly obtained, and the numerical solution is obtained by Runge-Kutta;
assuming that the order number n in the formula (4) is two, the formula (7) is reduced by algebraic substitution:
equation (7) then becomes:
the above formula was adapted using the Runge-Kutta recursion:
the RBF (radial basis function) comprises three layers of feedforward neural networks, namely an input layer, a hidden layer and an output layer, wherein network nodes adopt radial basis functions as activation functions, and the model structure of the RBF is shown in figure 2. After obtaining the grey prediction value X, the RBF neural network is trained by using X and the expected output Y in the training sample.
In the S3, the gray prediction value obtained in the S2 is usedAnd training the RBF neural network by taking the training sample Y as input and output to obtain an error compensator, wherein the training process is as follows:
s301, initializing parameters including a basis function center c, a width sigma and a weight w;
s302, calculating parameters of a hidden layer and an output layer by using a radial basis function, and calculating a loss function E;
s303, judging the loss, stopping training in the acceptance range, and updating the center, the width and the weight by using a gradient updating method if the loss is not in the acceptance range, wherein the gradient updating formula is shown as the following formula:
where η is the learning factor and E is the loss function.
And S304, finishing training to obtain the error compensator.
In S5, the accuracy evaluation calculation formula is as follows:
wherein, RMSE is the root mean square error, MAE is the average absolute error, and is used for evaluating the accuracy of the prediction model.
DETAILED DESCRIPTION OF EMBODIMENT (S) OF INVENTION
In order to verify the prediction effect of the method, a storage battery of a certain terminal device in the power distribution network is selected as a verification object, the operation data is acquired, and the data is processed as shown in the following table 1.
TABLE 1 24-month operating data of storage battery
The data of the first 20 months of operation are arranged into a training set X, Y, and the data of the remaining 4 months are used as test sample sets X 'and Y'. And inputting the training data into a model to train a grey neural network, and performing learning and evolution on the network for 100 times. And after training is finished, evaluating the prediction performance of the network by using the test sample set. The prediction of the gray neural network is shown in fig. 3, and the evaluation indexes RMSE and MAE obtained through calculation are 0.47 and 0.42 respectively, so that the gray neural network prediction method provided by the invention can be verified to have a good prediction effect under the condition of a small sample.
The above-mentioned embodiments only express the embodiments of the present invention, and the description thereof is more specific and detailed, but not construed as limiting the scope of the present invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the inventive concept, which falls within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.
Claims (5)
1. A method for predicting the energy storage capacity of a storage battery of a power distribution network terminal is characterized by comprising the following steps: the method comprises the following steps:
s1, data acquisition and processing: collecting the energy storage capacity C, the internal resistance R, the operating temperature T and the float charging voltage V of the storage battery by taking a month as a unitfThe average charging time J, the discharging times N and the air humidity M are acquired for multiple times and averaged to be used as a sample input X and a sample output Y; after a sample set is obtained, dividing the sample set into a training sample X, a training sample Y, a test sample X 'and a test sample Y';
s2, establishing a gray differential equation according to the training sample X, establishing a gray prediction model of the gray differential equation, and calculating a gray prediction value
S3, mixingThe predicted gray value obtained in S2Training the RBF neural network by taking the training sample Y as input and output to obtain an error compensator;
s4, calculating test samples X 'and Y' by using the gray prediction model, and obtaining the gray prediction valueThe output of the error compensator is the predicted value of the energy storage capacity of the storage battery;
and S5, performing precision evaluation on the gray prediction model by using a model inspection method, wherein the gray prediction model can be used when meeting the precision requirement and can be corrected when not meeting the requirement.
2. The method for predicting the energy storage capacity of the storage battery of the power distribution network terminal according to claim 1, wherein the method comprises the following steps: in the step S1, in consideration of small changes in the energy storage capacity and the internal resistance of the battery, 24-month operation data of the battery is acquired as a sample data set in a month unit; wherein the energy storage capacity C is obtained by a nuclear capacity test, the internal resistance R of the battery, the operating temperature T and the float charging voltage VfLength of uniform chargingJThe discharge times N and the air humidity M data are collected through monitoring equipment, the data in each month are collected for multiple times, an average value is taken and put into a sample set, and the format is as follows:
after a sample set is obtained, the sample set is divided into the training sample X, the training sample Y, the test sample X 'and the test sample Y'.
3. The method for predicting the energy storage capacity of the storage battery of the power distribution network terminal according to claim 1, wherein the method comprises the following steps: in S2, the gray prediction model accumulates the original data of the training sample X, weakens the irregularity of the data, and establishes a differential equation for data fitting and prediction, and the construction process is as follows:
s201, constructing an adjacent mean equal weight generation sequence
Setting the X original data of the training sample as X(0)The original data sequence X(0)Through one-time accumulation, X is generated(1)I.e. by
Computing adjacent mean equal weight generation sequence Z(1)(k) The calculation formula is as follows:
s202, constructing the gray differential equation
Wherein, a is a development coefficient, and b is an ash action amount;
S203, solving the gray differential equation and calculating a gray prediction sequence
To obtainThereafter, the equation (4) becomes an n-order ordinary differential equation; since the order n of the formula (4) is unknown, the solution can not be directly obtained, and the numerical solution is obtained by Runge-Kutta;
assuming that the order number n in the formula (4) is two, the formula (7) is reduced by algebraic substitution:
equation (7) then becomes:
the above formula was adapted using the Runge-Kutta recursion:
4. the method for predicting the energy storage capacity of the storage battery of the power distribution network terminal according to claim 1, wherein the method comprises the following steps: in the S3, the gray prediction value obtained in the S2 is usedAnd training the RBF neural network by taking the training sample Y as input and output to obtain an error compensator, wherein the training process is as follows:
s301, initializing parameters including a basis function center c, a width sigma and a weight w;
s302, calculating parameters of a hidden layer and an output layer by using a radial basis function, and calculating a loss function E;
s303, judging the loss, stopping training in the acceptance range, and updating the center, the width and the weight by using a gradient updating method if the loss is not in the acceptance range, wherein the gradient updating formula is shown as the following formula:
where η is the learning factor and E is the loss function.
And S304, finishing training to obtain the error compensator.
5. The method for predicting the energy storage capacity of the storage battery of the power distribution network terminal according to claim 1, wherein the method comprises the following steps: in S5, the accuracy evaluation calculation formula is as follows:
wherein, RMSE is the root mean square error, MAE is the average absolute error, and is used for evaluating the accuracy of the prediction model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210024011.8A CN114186756A (en) | 2022-01-11 | 2022-01-11 | Method for predicting energy storage capacity of storage battery of power distribution network terminal |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210024011.8A CN114186756A (en) | 2022-01-11 | 2022-01-11 | Method for predicting energy storage capacity of storage battery of power distribution network terminal |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114186756A true CN114186756A (en) | 2022-03-15 |
Family
ID=80606750
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210024011.8A Pending CN114186756A (en) | 2022-01-11 | 2022-01-11 | Method for predicting energy storage capacity of storage battery of power distribution network terminal |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114186756A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111105104A (en) * | 2020-02-20 | 2020-05-05 | 河南理工大学 | Short-term power load prediction method based on similar day and RBF neural network |
CN111525197A (en) * | 2020-04-30 | 2020-08-11 | 镇江市百汇电器有限公司 | Storage battery SOH real-time estimation system and method |
JP2020202739A (en) * | 2019-06-06 | 2020-12-17 | 国立大学法人九州大学 | Electric power demand forecasting device and electric power demand forecasting method |
CN113094981A (en) * | 2021-03-28 | 2021-07-09 | 西北工业大学 | Lithium ion battery reliability evaluation method based on grey neural network model and self-service method |
CN113901707A (en) * | 2021-12-08 | 2022-01-07 | 南昌师范学院 | SOH time sequence prediction method for vehicle lithium ion power battery |
-
2022
- 2022-01-11 CN CN202210024011.8A patent/CN114186756A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2020202739A (en) * | 2019-06-06 | 2020-12-17 | 国立大学法人九州大学 | Electric power demand forecasting device and electric power demand forecasting method |
CN111105104A (en) * | 2020-02-20 | 2020-05-05 | 河南理工大学 | Short-term power load prediction method based on similar day and RBF neural network |
CN111525197A (en) * | 2020-04-30 | 2020-08-11 | 镇江市百汇电器有限公司 | Storage battery SOH real-time estimation system and method |
CN113094981A (en) * | 2021-03-28 | 2021-07-09 | 西北工业大学 | Lithium ion battery reliability evaluation method based on grey neural network model and self-service method |
CN113901707A (en) * | 2021-12-08 | 2022-01-07 | 南昌师范学院 | SOH time sequence prediction method for vehicle lithium ion power battery |
Non-Patent Citations (1)
Title |
---|
李士勇 等, 北京航空航天大学出版社 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107957562B (en) | Online prediction method for residual life of lithium ion battery | |
CN104134999B (en) | Distribution network based on multi-data source measures the practical method of calculation of efficiency analysis | |
CN107870306A (en) | A kind of lithium battery charge state prediction algorithm based under deep neural network | |
CN110796368B (en) | Bayesian network-based dynamic risk assessment method and device for community power distribution network | |
CN107292502B (en) | Power distribution network reliability assessment method | |
CN111798095B (en) | Power cable state evaluation method based on neural network | |
CN104316879B (en) | A kind of prediction technique in lead-acid batteries service life | |
CN113064093A (en) | Energy storage battery state of charge and state of health joint estimation method and system | |
CN108075470A (en) | A kind of power grid transient frequency feature Forecasting Methodology based on SFR and ELM | |
CN111143973B (en) | Valve-regulated lead-acid storage battery degradation trend prediction method based on Gauss process regression | |
CN109002781B (en) | Fault prediction method for energy storage converter | |
CN111736084A (en) | Valve-regulated lead-acid storage battery health state prediction method based on improved LSTM neural network | |
CN115456304A (en) | Offshore wind farm reliability index calculation method and device considering typhoon influence | |
CN109299552A (en) | A kind of appraisal procedure and its assessment system of battery power status | |
CN110443481B (en) | Power distribution automation terminal state evaluation system and method based on hybrid K-nearest neighbor algorithm | |
CN110412417B (en) | Micro-grid data fault diagnosis method based on intelligent power monitoring instrument | |
CN113791351B (en) | Lithium battery life prediction method based on transfer learning and difference probability distribution | |
CN112287605B (en) | Power flow checking method based on graph convolution network acceleration | |
CN106056305A (en) | Power generation system reliability rapid assessment method based on state clustering | |
CN113591402A (en) | Digital power transformer health state fuzzy comprehensive evaluation method | |
CN110675276B (en) | Method and system for inversion droop control of direct current power transmission system | |
CN111091141B (en) | Photovoltaic backboard fault diagnosis method based on layered Softmax | |
CN110571788A (en) | static voltage stability domain boundary coefficient calculation method based on dynamic equivalent circuit | |
CN113176530A (en) | On-service electric energy meter batch fault diagnosis method based on meter-dismantling operation characteristics | |
CN114186756A (en) | Method for predicting energy storage capacity of storage battery of power distribution network terminal |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220315 |
|
RJ01 | Rejection of invention patent application after publication |