CN113743588A - Method for evaluating state of direct current charging pile - Google Patents

Method for evaluating state of direct current charging pile Download PDF

Info

Publication number
CN113743588A
CN113743588A CN202111060290.5A CN202111060290A CN113743588A CN 113743588 A CN113743588 A CN 113743588A CN 202111060290 A CN202111060290 A CN 202111060290A CN 113743588 A CN113743588 A CN 113743588A
Authority
CN
China
Prior art keywords
fuzzy
charging pile
direct current
current charging
model
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
Application number
CN202111060290.5A
Other languages
Chinese (zh)
Inventor
邓礼敏
杨爱超
范亚军
刘仕萍
王毅
裴茂林
胡琛
李敏
吴宇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Power Supply Service Management Center Of State Grid Jiangxi Electric Power Co ltd
State Grid Corp of China SGCC
Original Assignee
Power Supply Service Management Center Of State Grid Jiangxi Electric Power Co ltd
State Grid Corp of China SGCC
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Power Supply Service Management Center Of State Grid Jiangxi Electric Power Co ltd, State Grid Corp of China SGCC filed Critical Power Supply Service Management Center Of State Grid Jiangxi Electric Power Co ltd
Priority to CN202111060290.5A priority Critical patent/CN113743588A/en
Publication of CN113743588A publication Critical patent/CN113743588A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06N3/043—Architecture, e.g. interconnection topology based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N5/00—Computing arrangements using knowledge-based models
    • G06N5/04—Inference or reasoning models

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Mathematical Analysis (AREA)
  • Fuzzy Systems (AREA)
  • Computational Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Charge And Discharge Circuits For Batteries Or The Like (AREA)

Abstract

The invention discloses a method for evaluating the state of a direct current charging pile, which comprises the following steps of 1: a collecting device is additionally arranged on the direct current charging pile, so that electric quantity collection, charging message information, temperature, humidity value and smoke concentration collection are realized and are used as a real-time data source for state evaluation; step 2: constructing a proper fuzzy neural network model, generating a training sample by using the collected historical state data, setting training times, repeatedly training the model to obtain a direct current charging pile state evaluation model, and performing real-time state evaluation on the direct current charging pile by combining with real-time collected data; and step 3: and periodically updating training data, and periodically training the evaluation model to ensure the real-time performance of the model. By applying the method and the device, the remote state evaluation of the direct current charging pile can be conveniently realized in real time, a reliable basis is provided for daily operation and maintenance and fault diagnosis of the direct current charging pile, and the problems that the current state evaluation of the direct current charging pile highly depends on manual inspection, huge manpower and material resources are consumed, and the efficiency is low are solved.

Description

Method for evaluating state of direct current charging pile
Technical Field
The invention relates to the technical field of charging pile fault analysis, in particular to a direct current charging pile state evaluation method.
Background
Under the aim of 'double carbon', the industries of electric automobiles and charging piles are developed vigorously, wherein the safety problem is particularly obvious due to large charging voltage and current of the quick-charging direct-current charging pile, and the safe and reliable operation of the charging pile is an important prerequisite for ensuring the sustainable development of the charging pile. Fill electric pile and have characteristics such as wide in distribution, in large quantity, environment complicacy, current direct current fills electric pile state evaluation and highly relies on the manual work to patrol and examine, consumes huge manpower and materials, and inefficiency realizes how direct current fills electric pile state evaluation convenient, in real time, is exactly the current problem that awaits the solution.
Disclosure of Invention
The invention aims to provide a method for evaluating the state of a direct current charging pile, which aims to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme: a direct current charging pile state evaluation method comprises the following steps:
step 1: a collecting device is additionally arranged on the direct current charging pile, so that electric quantity collection, charging message information, temperature, humidity value and smoke concentration collection are realized and are used as a real-time data source for state evaluation;
step 2: constructing a proper fuzzy neural network model, generating a training sample by using the collected historical state data, setting training times, repeatedly training the model to obtain a direct current charging pile state evaluation model, and performing real-time state evaluation on the direct current charging pile by combining with real-time collected data;
and step 3: and periodically updating training data, and periodically training the evaluation model to ensure the real-time performance of the model.
Further, the step 2 specifically includes:
the T-S fuzzy neural network is adopted and is defined by the following 'if-then' rule form, and the rule is set at RiIn the case of (2), the fuzzy inference is:
Figure BDA0003256123910000011
wherein
Figure BDA0003256123910000012
A fuzzy set which is a fuzzy system;
Figure BDA0003256123910000013
is a neural network parameter; y isiFor output obtained according to the fuzzy rule, the input part, namely if part is processed in a fuzzy way, and the output part, namely then part is determined;
let x be [ x ] for the input quantity x1,x2,…,xk]Each output variable x is calculated according to the fuzzy rulejDegree of membership of:
Figure BDA0003256123910000014
wherein,
Figure BDA0003256123910000021
are respectively an affiliationThe center and width of the attribute function; k is the number of input parameters; n is the number of fuzzy subsets;
then, fuzzy calculation is carried out on each membership degree, and a fuzzy operator is used as a continuous multiplication operator:
Figure BDA0003256123910000022
calculating the output value y of the fuzzy model according to the fuzzy calculation resulti：
Figure BDA0003256123910000023
The model is divided into four layers of an input layer, a fuzzy rule calculation layer and an output layer, wherein the input layer and an input vector xiConnecting, wherein the number of nodes is the same as the dimension of the input vector; fuzzification layer fuzzifies the input value by adopting a membership function (1) to obtain a fuzzy membership value mu; the fuzzy rule calculation layer calculates omega by adopting a fuzzy multiplication formula (2); the output layer adopts a formula (3) to calculate the output of the fuzzy neural network; the learning algorithm is as in formulas (4) - (8):
(1) error calculation
Figure BDA0003256123910000024
In the formula, ydIs the network expected output value; y iscIs the actual output value of the network; e is the error of the desired output and the actual output;
(2) coefficient correction
Figure BDA0003256123910000025
Figure BDA0003256123910000026
In the formula,
Figure BDA0003256123910000027
is a neural network parameter; alpha is the network learning rate; x is the number ofjInputting parameters for the network; omegaiIs the product of the membership degree of the input parameters; m is the number of hidden nodes.
(3) Parameter correction
Figure BDA0003256123910000028
Figure BDA0003256123910000029
Figure BDA00032561239100000210
Respectively the center and the width of the membership function; beta is the parameter correction rate.
And b, determining the number of input/output nodes of the model and the number of fuzzy membership function according to the state evaluation data dimension of the direct current charging pile, wherein in the function selection parameters, b and c are randomly generated by the system.
The invention has the beneficial effects that:
by applying the method and the device, the remote state evaluation of the direct current charging pile can be conveniently realized in real time, a reliable basis is provided for daily operation and maintenance and fault diagnosis of the direct current charging pile, and the problems that the current state evaluation of the direct current charging pile highly depends on manual inspection, huge manpower and material resources are consumed, and the efficiency is low are solved.
Drawings
Fig. 1 is a flowchart of a dc charging pile state evaluation method according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and embodiments. The embodiments described herein are only for explaining the technical solution of the present invention and are not limited to the present invention.
The direct current charging pile state evaluation is to calculate and determine the state evaluation level of the current direct current charging pile through a certain mathematical model according to the direct current charging pile state evaluation standard, various electrical parameters of the direct current charging pile and message information. The analysis indexes of the state evaluation of the direct current charging pile are multiple, and the analysis indexes mainly comprise indexes such as internal temperature, humidity, smoke concentration, difference value of actual output power and required power, charging loss and standby power consumption. Wherein, inside humiture, smog concentration are the inside index of discovering unusually of direct current charging stake of direct-viewing reflection. The difference value between the actual output power and the required power is an index reflecting the output capacity of the direct current charging pile. The charging loss is an index reflecting the conversion efficiency of the direct current charging pile. The standby power consumption is an index reflecting the internal components and heat dissipation conditions of the direct current charging pile. And then, corresponding the index values to different state grades of the direct current charging pile to form a state evaluation grade table.
A collecting device is additionally arranged on the direct current charging pile, so that electric quantity collection, charging message information, temperature, humidity value and smoke concentration collection are achieved and serve as a real-time data source for state evaluation. The method comprises the steps of constructing a proper fuzzy neural network model, generating a training sample by utilizing collected historical state data, setting training times, repeatedly training the model to obtain a direct-current charging pile state evaluation model, and carrying out real-time state evaluation on the direct-current charging pile by combining with real-time collected data, wherein the specific flow is shown in figure 1. And the training data is periodically updated, and the evaluation model is periodically trained to ensure the real-time performance of the model.
The invention adopts a T-S fuzzy neural network, and the T-S fuzzy neural network is defined by the following 'if-then' rule form, and the rule is in RiIn the case of (2), the fuzzy inference is:
Figure BDA0003256123910000031
wherein
Figure BDA0003256123910000032
A fuzzy set which is a fuzzy system;
Figure BDA0003256123910000033
is a neural network parameter; y isiFor output according to the fuzzy rule, the input part (i.e., if part) is fuzzy processed, and the output part (i.e., then part) is determined.
Let x be [ x ] for the input quantity x1,x2,…,xk]Each output variable x is calculated according to the fuzzy rulejDegree of membership of:
Figure BDA0003256123910000034
wherein,
Figure BDA0003256123910000041
respectively the center and the width of the membership function; k is the number of input parameters; n is the number of fuzzy subsets.
Then, fuzzy calculation is carried out on each membership degree, and a fuzzy operator is used as a continuous multiplication operator:
Figure BDA0003256123910000042
the output value y of the fuzzy model can be calculated according to the fuzzy calculation resulti：
Figure BDA0003256123910000043
The model is divided into four layers of an input layer, a fuzzy rule calculation layer and an output layer, wherein the input layer and an input vector xiConnecting, wherein the number of nodes is the same as the dimension of the input vector; fuzzification layer fuzzifies the input value by adopting a membership function (1) to obtain a fuzzy membership value mu; the fuzzy rule calculation layer calculates omega by adopting a fuzzy multiplication formula (2); the output layer adopts a formula (3) to calculate the output of the fuzzy neural network; the learning algorithm is as in formulas (4) - (8):
(1) error calculation
Figure BDA0003256123910000044
In the formula, ydIs the network expected output value; y iscIs the actual output value of the network; e is the error of the desired output and the actual output;
(2) coefficient correction
Figure BDA0003256123910000045
Figure BDA0003256123910000046
In the formula,
Figure BDA0003256123910000047
is a neural network parameter; alpha is the network learning rate; x is the number ofjInputting parameters for the network; omegaiIs the product of the membership degree of the input parameters; m is the number of hidden nodes.
(3) Parameter correction
Figure BDA0003256123910000048
Figure BDA0003256123910000049
Figure BDA00032561239100000410
Respectively the center and the width of the membership function; beta is the parameter correction rate.
Therefore, the number of the input/output nodes of the model and the number of the fuzzy membership function are determined according to the state evaluation data dimension of the direct current charging pile, and in the function selection parameters, b and c are randomly generated by the system.
The foregoing merely represents preferred embodiments of the invention, which are described in some detail and detail, and therefore should not be construed as limiting the scope of the invention. It should be noted that, for those skilled in the art, various changes, modifications and substitutions can be made without departing from the spirit of the present invention, and these are all within the scope of the present invention. Therefore, the protection scope of the present patent shall be subject to the appended claims.

Claims (2)

1. A method for evaluating the state of a direct current charging pile is characterized by comprising the following steps: the method comprises the following steps:
step 1: a collecting device is additionally arranged on the direct current charging pile, so that electric quantity collection, charging message information, temperature, humidity value and smoke concentration collection are realized and are used as a real-time data source for state evaluation;
step 2: constructing a proper fuzzy neural network model, generating a training sample by using the collected historical state data, setting training times, repeatedly training the model to obtain a direct current charging pile state evaluation model, and performing real-time state evaluation on the direct current charging pile by combining with real-time collected data;
and step 3: and periodically updating training data, and periodically training the evaluation model to ensure the real-time performance of the model.
2. The method for evaluating the state of the direct-current charging pile according to claim 1, wherein the method comprises the following steps: the step 2 specifically comprises:
the T-S fuzzy neural network is adopted and is defined by the following 'if-then' rule form, and the rule is set at RiIn the case of (2), the fuzzy inference is:
Figure FDA0003256123900000011
wherein
Figure FDA0003256123900000012
A fuzzy set which is a fuzzy system;
Figure FDA0003256123900000013
is a neural network parameter; y isiFor output obtained according to the fuzzy rule, the input part, namely if part is processed in a fuzzy way, and the output part, namely then part is determined;
let x be [ x ] for the input quantity x1,x2,…,xk]Each output variable x is calculated according to the fuzzy rulejDegree of membership of:
Figure FDA0003256123900000014
wherein,
Figure FDA0003256123900000015
respectively the center and the width of the membership function; k is the number of input parameters; n is the number of fuzzy subsets;
then, fuzzy calculation is carried out on each membership degree, and a fuzzy operator is used as a continuous multiplication operator:
Figure FDA0003256123900000016
calculating the output value y of the fuzzy model according to the fuzzy calculation resulti：
Figure FDA0003256123900000017
The model is divided into four layers of an input layer, a fuzzy rule calculation layer and an output layer, wherein the input layer and an input vector xiConnecting, wherein the number of nodes is the same as the dimension of the input vector; fuzzification layer fuzzifies the input value by adopting a membership function (1) to obtain a fuzzy membership value mu; the fuzzy rule calculation layer calculates omega by adopting a fuzzy multiplication formula (2); the output layer adopts a formula (3) to calculate the output of the fuzzy neural network; the learning algorithm is as in formulas (4) - (8):
(1) error calculation
Figure FDA0003256123900000018
In the formula, ydIs the network expected output value; y iscIs the actual output value of the network; e is the error of the desired output and the actual output;
(2) coefficient correction
Figure FDA0003256123900000021
Figure FDA0003256123900000022
In the formula,
Figure FDA0003256123900000023
is a neural network parameter; alpha is the network learning rate; x is the number ofjInputting parameters for the network; omegaiIs the product of the membership degree of the input parameters; m is the number of hidden nodes;
(3) parameter correction
Figure FDA0003256123900000024
Figure FDA0003256123900000025
Figure FDA0003256123900000026
Respectively the center and the width of the membership function; beta is a parameter correction rate;
and b, determining the number of input/output nodes of the model and the number of fuzzy membership function according to the state evaluation data dimension of the direct current charging pile, wherein in the function selection parameters, b and c are randomly generated by the system.
CN202111060290.5A 2021-09-10 2021-09-10 Method for evaluating state of direct current charging pile Pending CN113743588A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111060290.5A CN113743588A (en) 2021-09-10 2021-09-10 Method for evaluating state of direct current charging pile

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111060290.5A CN113743588A (en) 2021-09-10 2021-09-10 Method for evaluating state of direct current charging pile

Publications (1)

Publication Number Publication Date
CN113743588A true CN113743588A (en) 2021-12-03

Family

ID=78737885

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111060290.5A Pending CN113743588A (en) 2021-09-10 2021-09-10 Method for evaluating state of direct current charging pile

Country Status (1)

Country Link
CN (1) CN113743588A (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109495296A (en) * 2018-11-02 2019-03-19 国网四川省电力公司电力科学研究院 Intelligent substation communication network state evaluation method based on clustering and neural network

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109495296A (en) * 2018-11-02 2019-03-19 国网四川省电力公司电力科学研究院 Intelligent substation communication network state evaluation method based on clustering and neural network

Similar Documents

Publication Publication Date Title
CN113159339B (en) One-area one-index line loss management method and system based on big data
Chen et al. Degradation model of proton exchange membrane fuel cell based on a novel hybrid method
Li et al. Big data driven vehicle battery management method: A novel cyber-physical system perspective
CN110266010B (en) Grid structure of direct-current power distribution network and distributed photovoltaic multi-target collaborative optimization method
CN104933505A (en) Decision and evaluation method for intelligent power distribution network group based on fuzzy assessment
CN111967777B (en) Comprehensive evaluation method for energy storage and clean energy utilization value promotion
CN110826228A (en) Regional power grid operation quality limit evaluation method
Huo et al. Integrating learning and explicit model predictive control for unit commitment in microgrids
CN113743588A (en) Method for evaluating state of direct current charging pile
Hassan et al. Optimizing photovoltaic models: A leader artificial ecosystem approach for accurate parameter estimation of dynamic and static three diode systems
CN112116305A (en) Power grid probability visualization model construction method and system for machine learning
Sudha et al. GA-ANN hybrid approach for load forecasting
Pang Short-term harmonic forecasting and evaluation affected by electrified railways on the power grid based on stack auto encoder neural network method and the comparison to BP method
CN114186811B (en) Construction method and application of real-time scheduling model of micro-grid system
CN116068303A (en) Private capacity-increasing on-line monitoring method for special transformer based on data driving
Feng et al. Hybrid energy storage sizing in energy hubs: A continuous spectrum splitting approach
CN109586309A (en) Var Optimization Method in Network Distribution based on big data free entropy theory and scene matching
Liu et al. Dynamic Prediction Algorithm for Low-Voltage Distribution Network Power Loss in a Smart City Based on Classification Decision Tree and Marketing Data
Wei et al. Predicting Electricity Usage Based on Deep Neural Network
Basia et al. Comparison of data driven algorithms for SoH estimation of Lithium-ion batteries
Upadhya et al. A dispatch optimization model for hybrid renewable and battery systems incorporating a battery degradation model
CN113505468B (en) Method for constructing and analyzing interval linear alternating current maximum transmission capacity model
Zhang et al. Power Quality Evaluation Based on the Fusion of Improved Entropy and Analytic Hierarchy Process
CN116256647B (en) Online identification prediction method and system for fuel cell performance
CN116894568B (en) Comprehensive management prediction method for carbon emission of charging pile and storage medium

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination