CN109284882A - A kind of method and system that photovoltaic module performance determines - Google Patents
A kind of method and system that photovoltaic module performance determines Download PDFInfo
- Publication number
- CN109284882A CN109284882A CN201710599224.2A CN201710599224A CN109284882A CN 109284882 A CN109284882 A CN 109284882A CN 201710599224 A CN201710599224 A CN 201710599224A CN 109284882 A CN109284882 A CN 109284882A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic module
- measured
- data
- sample
- performance
- 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 31
- 230000006870 function Effects 0.000 claims abstract description 55
- 238000011156 evaluation Methods 0.000 claims abstract description 19
- 238000005286 illumination Methods 0.000 claims abstract description 17
- 238000012360 testing method Methods 0.000 claims abstract description 13
- 238000013461 design Methods 0.000 claims description 10
- 210000002569 neuron Anatomy 0.000 claims description 10
- 230000004913 activation Effects 0.000 claims description 8
- 239000012141 concentrate Substances 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 abstract description 6
- 230000007547 defect Effects 0.000 abstract description 2
- 239000000306 component Substances 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000007630 basic procedure Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 210000004027 cell Anatomy 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000005538 encapsulation Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Photovoltaic Devices (AREA)
- Photometry And Measurement Of Optical Pulse Characteristics (AREA)
Abstract
The present invention provides the method and systems that a kind of photovoltaic module performance determines, the function model between output power of photovoltaic module and ambient temperature and intensity of illumination is provided according to historical data, then the temperature of actual measurement, illumination intensity value are substituted into the model, obtain the ideal output power of photovoltaic module under this condition, ideal output power and real output are calculated finally by scoring functions, provide final Performance Evaluation value.Compared with the immediate prior art, this method can realize the Real-time Performance Evaluation of component, and overcome Traditional measurements method and require test condition stringent defect.
Description
Technical field
The invention belongs to photovoltaic module Performance Evaluation field, method that in particular to a kind of photovoltaic module performance determines and
System.
Background technique
Luminous energy is directly become direct current energy by photovoltaic module, is one of core component of photovoltaic generating system, performance
Quality directly affects the generating efficiency of photovoltaic generating system, it is therefore necessary to carry out real-time monitor and performance evaluation to it.Light
The performance of volt component is influenced by more multifactor, the decaying of the efficiency of photovoltaic cell, the aging of encapsulation auxiliary material, superficial dust,
Hot spot problem etc. can all cause the performance of photovoltaic module to decline.
The fault detection and failure cause to photovoltaic module are focused primarily on to the correlative study of photovoltaic module performance at present
Positioning qualitatively judges the operating status of system.And the correlative study for carrying out quantitative evaluation to the performance of photovoltaic module is less, it is main
It to be realized by photovoltaic module attenuation rate:
This method measures photovoltaic module initial maximum output power Pmax according to 6495.1 standard of GB/T regulation and (puts into operation just
Phase) after, it is mounted under same environment with other components that same batch produces and operates normally power generation, from operation after 1 year
Its peak power output Pmax (operation a period of time) is measured again, then calculates photovoltaic module attenuation rate, attenuation rate is lower, says
It is better that Mingguang City lies prostrate assembly property.However there are the following problems for this method: 1. can only the photovoltaic module to one period carry out performance
Assessment, and cannot achieve real-time assessment；2. measurement is higher to extraneous environmental requirement, when needing to measure twice, extraneous temperature,
Weather, intensity of illumination are as consistent as possible.
Summary of the invention
To overcome above-mentioned the deficiencies in the prior art, the present invention proposes a kind of method and system that photovoltaic module performance determines.
Realize solution used by above-mentioned purpose are as follows:
A kind of method that photovoltaic module performance determines, thes improvement is that:
The data of photovoltaic module to be measured are acquired, the data of the photovoltaic module to be measured include: the photovoltaic module to be measured
Realtime power and matching weather data；
According to the light to be measured of the relationship and acquisition of the realtime power for the photovoltaic module being fitted in advance and weather data
The data for lying prostrate component, determine the performance of the photovoltaic module to be measured.
First optimal technical scheme provided by the invention, it is improved in that the reality of the preparatory fitting photovoltaic module
When power and the relationship of weather data therewith include:
By the realtime power P and matching weather data of the preparatory collected photovoltaic module, sample set is formedWherein i is sample serial number, and h is total sample number, and T is ambient temperature, and S is intensity of illumination；
According to the sample set, it is fitted using following formula:
P '=f (T, S, G, M) (1)
Wherein: P ' is the function prediction value fitted using extreme learning machine, and G is activation primitive, and M is hidden layer neuron
Number point.
Second optimal technical scheme provided by the invention, it is improved in that the preparatory acquisition includes: in advance pre-
If time-domain in, at regular intervals, acquire the data of the photovoltaic module to be measured.
Third optimal technical scheme provided by the invention, it is improved in that according to the sample set, before being fitted
Further include: the repeated sample in the sample set is rejected, k group sample is obtainedK is to reject the sample set
In repeated sample after sample size.
4th optimal technical scheme provided by the invention, it is improved in that the light that the basis is fitted in advance
The data for lying prostrate the photovoltaic module to be measured of the realtime power of component and the relationship and acquisition of weather data, determine photovoltaic to be measured
The performance of component includes:
According to the function prediction value P ' fitted using extreme learning machine, scoring functions are designed；
It is given a mark using data of the scoring functions to the photovoltaic module to be measured, obtains score value set
A best result and one minimum point are deleted in the score value set respectively, obtain marking collection
Concentrate the mean value of score value as the Performance Evaluation value of photovoltaic module to be measured using all marking, calculation method is such as
Under:
Wherein Mark is the score value that the scoring functions calculate.
5th optimal technical scheme provided by the invention, it is improved in that the scoring functions are as follows:
6th optimal technical scheme provided by the invention, it is improved in that the number of the acquisition photovoltaic module to be measured
According to including:
Using with acquire identical time interval in advance, acquire the realtime power P of photovoltaic module to be measuredtestWith it is matching
Weather data, formed sample to be tested collectionWherein j is sample to be tested serial number, and n is sample to be tested
Sum, TtestFor ambient temperature, StestFor intensity of illumination.
A kind of system that photovoltaic module performance determines, it is improved in that including that data acquisition module and performance determine
Module；
The data acquisition module is used to acquire the data of photovoltaic module to be measured, the data packet of the photovoltaic module to be measured
It includes: the realtime power and matching weather data of the photovoltaic module to be measured；
The performance determining module is used for the relationship of realtime power and weather data according to the photovoltaic module being fitted in advance
And the data of the photovoltaic module to be measured of acquisition, determine the performance of photovoltaic module to be measured.
7th optimal technical scheme provided by the invention, it is improved in that further including data fitting module, the number
It is used to form the realtime power P and matching weather data of the preparatory collected photovoltaic module according to fitting module
Sample setWherein i is sample serial number, and h is total sample number, and T is ambient temperature, and S is intensity of illumination；
According to the sample set, it is fitted using following formula:
P '=f (T, S, G, M) (1)
Wherein: P ' is the function prediction value fitted using extreme learning machine, and G is activation primitive, and M is hidden layer neuron
Number point.
8th optimal technical scheme provided by the invention, it is improved in that the performance determining module includes marking
Function designs subelement, marking subelement and Performance Evaluation subelement；
The function prediction value P ' that the scoring functions design subelement is used to fit using extreme learning machine, design marking
Function；
The marking subelement is obtained for being given a mark using data of the scoring functions to the photovoltaic module to be measured
To score value set, and a best result and one minimum point are deleted in the score value set, obtains marking collection；
The Performance Evaluation subelement is used to calculate all marking and concentrates the mean value of score value as photovoltaic module to be measured
Performance Evaluation value.
Compared with the immediate prior art, the device have the advantages that as follows:
According to the photovoltaic group to be measured of the relationship and acquisition of the realtime power for the photovoltaic module being fitted in advance and weather data
The data of part determine the performance of photovoltaic module to be measured, can realize light to be measured under conditions of different ambient temperatures and intensity of illumination
The Performance Evaluation for lying prostrate component, overcome conventional method can only the photovoltaic module to one period carry out Performance Evaluation, and require
When measurement, extraneous temperature and intensity of illumination defect as consistent as possible.
Detailed description of the invention
Fig. 1 is the method basic procedure schematic diagram that a kind of photovoltaic module performance provided by the invention determines；
Fig. 2 is the Method And Principle schematic diagram that a kind of photovoltaic module performance provided by the invention determines；
Fig. 3 is the method idiographic flow schematic diagram that a kind of photovoltaic module performance provided by the invention determines；
Fig. 4 is extreme learning machine parameter optimization process in a kind of determining method of photovoltaic module performance provided by the invention
Figure.
Specific embodiment
A specific embodiment of the invention is described in further detail with reference to the accompanying drawing.
A kind of photovoltaic module performance estimating method based on short term power prediction, it is defeated to provide photovoltaic module according to historical data
Then the temperature of actual measurement, illumination intensity value are substituted into the mould by the function model between power and ambient temperature and intensity of illumination out
Type obtains the ideal output power of photovoltaic module under this condition, defeated to ideal output power and reality finally by scoring functions
Power is calculated out, provides final Performance Evaluation value, its principle is as shown in Figure 2.
A kind of photovoltaic module performance estimating method basic procedure schematic diagram predicted based on short term power is as shown in Figure 1, packet
It includes:
The data of photovoltaic module to be measured are acquired, the data of the photovoltaic module to be measured include: the photovoltaic module to be measured
Realtime power and matching weather data；
According to the light to be measured of the relationship and acquisition of the realtime power for the photovoltaic module being fitted in advance and weather data
The data for lying prostrate component, determine the performance of photovoltaic module to be measured.
A kind of photovoltaic module performance estimating method idiographic flow schematic diagram based on short term power prediction is as shown in Figure 3.
The realtime power and matching weather data of acquisition photovoltaic module in advance, comprising:
In advance in preset time-domain, at regular intervals, the realtime power P and therewith of photovoltaic module is acquired
The weather data matched forms sample setWherein i is sample serial number, and h is total sample number, and T is ambient temperature,
S is intensity of illumination, and sample set is further processed, and the repeated sample that Rejection of samples is concentrated obtains k group sample K is the sample size after the repeated sample rejected in the sample set.In the present invention, preset time-domain is usually light
Volt component puts into operation First Year, can also be set as other times according to actual needs, such as photovoltaic module puts into operation the first half or preceding two
Year etc..Preset Fixed Time Interval is usually in 07:00-19:00, every other hour in the present invention；Can according to the actual situation,
Adjustment time range, to adapt to the working time section of photovoltaic module；Also it can adjust according to actual demand and acquire the frequency, such as between
It was acquired every two hours, or interval half an hour acquisition.
According to sample set, it is fitted using following formula:
P '=f (T, S, G, M) (1)
Wherein P ' is the function prediction value fitted using extreme learning machine, and G is activation primitive, and M is hidden layer neuron
Number point.
Extreme learning machine ELM is that Nanyang Technolohy University Huang Guangbin in 2004 teaches a kind of feedforward neural network mentioned, should
Algorithm can learn outputting and inputting for sample, fit the functional relation between input and output.Compared to traditional artificial mind
Through network method, this method pace of learning is fast, and required parameter is few, and local minimum problem is not present.
The performance of the algorithm depends on two big parameters: the activation primitive G of 1. hidden layer neurons, value can be '
Sigmoid ' function, ' sin ' function and ' hardlim ' function；2. the number M of hidden layer neuron.
According to the relationship of fitting, the scoring functions of design are
Wherein Mark is the score value that the scoring functions calculate.
The realtime power and matching weather data for acquiring photovoltaic module to be measured include:
Using with acquire identical time interval in advance, acquire the realtime power P of photovoltaic module to be measuredtestWith it is matching
Weather data, formed sample to be tested collectionWherein j is sample to be tested serial number, and n is sample to be tested
Sum, TtestFor ambient temperature, StestFor intensity of illumination.For example, can be in the intraday time in the 07:00-19:00 period
It is interior, it is primary at interval of hour, acquire the data T of photovoltaic module to be measuredtest、StestAnd Ptest, form sample to be tested collection Wherein j is sample to be tested serial number.Those skilled in the art can have determine according to actual needs
The acquisition time of body and acquisition time interval.It should be noted that specific acquisition time section and time interval will with adopt in advance
It is consistent when collection.
According to scoring functions and sample to be tested collection, the performance for assessing photovoltaic module to be measured includes:
Using scoring functions, i.e. formula (3) gives a mark to sample to be tested collection, obtains score value set
To avoid exceptional sample to the influence of subsequent processes, a best result, one minimum point of removal are removed, is given a mark
Collection
Using the mean value of score value as the Performance Evaluation value of photovoltaic module to be measured, value is bigger, represents the photovoltaic module performance
Better, Performance Evaluation value calculates as follows:
ELM parameter has: the activation primitive G of 1. hidden layer neurons, value can be ' sigmoid ' function, ' sin ' function
With ' hardlim ' function；2. the number M of hidden layer neuron.The realtime power of the photovoltaic module and outer is fitted using ELM
When functional relation between the temperature on boundary, intensity of illumination, ELM parameter optimization process is as shown in Figure 4.
In the case where equipped with k group training sample, G-function is enabled to take first ' then sigmoid ' function enables hidden layer neural
First number M is 2*1, the study of ELM is carried out using the parameter, while calculating target function value R at this time, in the present invention, taken
Target function R is the absolute value of the difference of the performance number P of actual measurement and the performance number P ' of fitting function prediction, i.e. Ri,j=| P-P ' |
=| P-fi,j(T,S,G,M)|；After completion, the continuous value for increasing M, enabling its value is respectively 2*2,2*3 ..., 2*k, meter
It calculates target function value R in this case and gives and record.
When ' in the case of sigmoid ' function, after the target function value R under variant M value setting is recorded, then enable respectively
G-function takes ' sin ' function and ' hardlim ' function, repeats the above process, the target function value R under the conditions of record is each.Amount to
To after 3*k target function value, minimum R value is found, the corresponding G-function of target function value and M value are the optimal parameter of ELM
Setting.
The present invention also provides a kind of photovoltaic module performance evaluation systems in short term power prediction, including data acquisition module
Block and performance determining module；
Data acquisition module includes: described for acquiring photovoltaic module data to be measured, the data of the photovoltaic module to be measured
The realtime power of photovoltaic module to be measured and matching weather data；
Performance determining module be used for according to the realtime power of photovoltaic module that is fitted in advance and the relationship of weather data and
The data of the photovoltaic module to be measured of acquisition, determine the performance of photovoltaic module to be measured.
The system further includes data fitting module, and the data fitting module is used for:
By the realtime power P and matching weather data of the preparatory collected photovoltaic module, sample set is formedWherein i is sample serial number, and h is total sample number, and T is ambient temperature, and S is intensity of illumination；
According to sample set, it is fitted using following formula:
P '=f (T, S, G, M) (1)
Wherein P ' is the function prediction value fitted using extreme learning machine, and G is activation primitive, and M is hidden layer neuron
Number point.
Performance determining module includes scoring functions design subelement, marking subelement and Performance Evaluation subelement；
The function prediction value P ' that scoring functions design subelement is used to fit using extreme learning machine, design marking letter
Number；
Marking subelement is used to give a mark using data of the scoring functions to photovoltaic module to be measured, obtains score value set,
And a best result and one minimum point are deleted in score value set, obtain marking collection；
Performance Evaluation subelement is used to calculate all marking and the mean value of score value is concentrated to comment as the performance of photovoltaic module to be measured
Valuation.
Finally it should be noted that: above embodiments are merely to illustrate the technical solution of the application rather than to its protection scopes
Limitation, although the application is described in detail referring to above-described embodiment, those of ordinary skill in the art should
Understand: those skilled in the art read the specific embodiment of application can still be carried out after the application various changes, modification or
Person's equivalent replacement, but these changes, modification or equivalent replacement, are applying within pending claims.
Claims (10)
1. a kind of method that photovoltaic module performance determines, it is characterised in that:
The data of photovoltaic module to be measured are acquired, the data of the photovoltaic module to be measured include: the real-time of the photovoltaic module to be measured
Power and matching weather data；
According to the photovoltaic group to be measured of the relationship and acquisition of the realtime power for the photovoltaic module being fitted in advance and weather data
The data of part determine the performance of the photovoltaic module to be measured.
2. the method as described in claim 1, which is characterized in that the realtime power of the preparatory fitting photovoltaic module and therewith
The relationship of weather data include: by the realtime power P and matching weather data of the preparatory collected photovoltaic module,
Form sample setWherein i is sample serial number, and h is total sample number, and T is ambient temperature, and S is intensity of illumination；
According to the sample set, it is fitted using following formula:
P '=f (T, S, G, M) (1)
Wherein: P ' is the function prediction value fitted using extreme learning machine, and G is activation primitive, and M is of hidden layer neuron
Several points.
3. method according to claim 2, which is characterized in that it is described it is preparatory acquisition include: in advance in preset time-domain,
At regular intervals, the data of the photovoltaic module to be measured are acquired.
4. method according to claim 2, which is characterized in that according to the sample set, before being fitted further include: reject institute
The repeated sample in sample set is stated, k group sample is obtainedAfter k is the repeated sample rejected in the sample set
Sample size.
5. the method as described in claim 1-4 is any, which is characterized in that the photovoltaic module that the basis is fitted in advance
The data of the photovoltaic module to be measured of the relationship and acquisition of realtime power and weather data, determine the property of photovoltaic module to be measured
Can include:
According to the function prediction value P ' fitted using extreme learning machine, scoring functions are designed；
It is given a mark using data of the scoring functions to the photovoltaic module to be measured, obtains score value set
A best result and one minimum point are deleted in the score value set respectively, obtain marking collection
Concentrate the mean value of score value as the Performance Evaluation value of photovoltaic module to be measured using all marking, calculation method is as follows:
Wherein Mark is the score value that the scoring functions calculate.
6. method as claimed in claim 5, which is characterized in that the scoring functions are as follows:
7. method as claimed in claim 5, which is characterized in that the data of acquisition photovoltaic module to be measured include:
Using with acquire identical time interval in advance, acquire the realtime power P of photovoltaic module to be measuredtestWith matching day
Destiny evidence forms sample to be tested collectionWherein j is sample to be tested serial number, and n is that sample to be tested is total
Number, TtestFor ambient temperature, StestFor intensity of illumination.
8. the system that a kind of photovoltaic module performance determines, which is characterized in that including data acquisition module and performance determining module；
The data acquisition module is used to acquire the data of photovoltaic module to be measured, and the data of the photovoltaic module to be measured include: institute
State the realtime power and matching weather data of photovoltaic module to be measured；
The performance determining module be used for according to the realtime power of photovoltaic module that is fitted in advance and the relationship of weather data and
The data of the photovoltaic module to be measured of acquisition, determine the performance of photovoltaic module to be measured.
9. system as claimed in claim 8, which is characterized in that further include data fitting module, the data fitting module is used
In by the realtime power P and matching weather data of the preparatory collected photovoltaic module, sample set is formedWherein i is sample serial number, and h is total sample number, and T is ambient temperature, and S is intensity of illumination；
According to the sample set, it is fitted using following formula:
P '=f (T, S, G, M) (1)
Wherein: P ' is the function prediction value fitted using extreme learning machine, and G is activation primitive, and M is of hidden layer neuron
Several points.
10. system as claimed in claim 9, which is characterized in that the performance determining module includes that scoring functions design is single
Member, marking subelement and Performance Evaluation subelement；
The function prediction value P ' that the scoring functions design subelement is used to fit using extreme learning machine, design marking letter
Number；
The marking subelement is divided for being given a mark using data of the scoring functions to the photovoltaic module to be measured
Value set, and a best result and one minimum point are deleted in the score value set, obtain marking collection；
The Performance Evaluation subelement is used to calculate all marking and concentrates property of the mean value of score value as photovoltaic module to be measured
It can assessed value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710599224.2A CN109284882A (en) | 2017-07-21 | 2017-07-21 | A kind of method and system that photovoltaic module performance determines |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710599224.2A CN109284882A (en) | 2017-07-21 | 2017-07-21 | A kind of method and system that photovoltaic module performance determines |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109284882A true CN109284882A (en) | 2019-01-29 |
Family
ID=65185636
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710599224.2A Pending CN109284882A (en) | 2017-07-21 | 2017-07-21 | A kind of method and system that photovoltaic module performance determines |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109284882A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111929586A (en) * | 2020-06-22 | 2020-11-13 | 山东信通电子股份有限公司 | Charging state evaluation method and device of passive wireless monitoring device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446440A (en) * | 2016-10-11 | 2017-02-22 | 天津大学 | Short-term photovoltaic generation power prediction method based on online sequential extreme learning machine |
-
2017
- 2017-07-21 CN CN201710599224.2A patent/CN109284882A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106446440A (en) * | 2016-10-11 | 2017-02-22 | 天津大学 | Short-term photovoltaic generation power prediction method based on online sequential extreme learning machine |
Non-Patent Citations (1)
| Title |
|---|
| 卢怡含等: "基于Spiking神经网络的光伏发电系统功率预测", 《黑龙江电力》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111929586A (en) * | 2020-06-22 | 2020-11-13 | 山东信通电子股份有限公司 | Charging state evaluation method and device of passive wireless monitoring device |
| CN111929586B (en) * | 2020-06-22 | 2023-09-05 | 山东信通电子股份有限公司 | Method and equipment for evaluating charging state of passive wireless monitoring device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105846780B (en) | A kind of photovoltaic module method for diagnosing faults based on decision-tree model | |
| CN104391189B (en) | Large-sized photovoltaic array fault diagnosis localization method based on three-level diagnosis | |
| CN104407589B (en) | Workshop manufacturing process-oriented active sensing and anomaly analysis method of real-time production performance | |
| CN101413901B (en) | Surface fatigue crack detecting method based on CCD image characteristic | |
| CN108680244A (en) | A kind of rotating machinery vibrating wireless monitoring device and method | |
| CN110411580B (en) | Diagnosis method and diagnosis system for heating defects of electric equipment | |
| CN104390657A (en) | Generator set operating parameter measuring sensor fault diagnosis method and system | |
| CN110363334B (en) | Grid line loss prediction method of photovoltaic grid connection based on gray neural network model | |
| CN112669305B (en) | Metal surface rust resistance test bench and rust resistance evaluation method | |
| CN104601109A (en) | Photovoltaic hot spot effect detection method for electricity-graph model | |
| CN114619292A (en) | Milling cutter wear monitoring method based on fusion of wavelet denoising and attention mechanism with GRU network | |
| CN106959422B (en) | A kind of detection method of battery life time early warning device | |
| CN111679176A (en) | Circuit fault monitoring system for power saving | |
| CN111537888A (en) | Data-driven echelon battery SOC prediction method | |
| CN109284882A (en) | A kind of method and system that photovoltaic module performance determines | |
| CN105093163A (en) | Error debugging method for electronic electric energy meter | |
| CN106325258B (en) | Relay protection device state evaluation method based on online monitoring information | |
| CN110033181A (en) | A kind of generating equipment state evaluating method based on self-encoding encoder | |
| CN109521001A (en) | A kind of flying marking measuring method based on PSO and ε-SVR | |
| CN104253586A (en) | Online measurement and evaluation device and method for electrical parameters of solar cell panel | |
| CN108678815A (en) | The minimum technology output measurement device and method of extraction condensing type Turbo-generator Set | |
| CN102095953A (en) | On-line detection method for performance of accumulator charger | |
| CN109239056A (en) | A kind of high-temp liquid ingredient on-line detection device and method | |
| CN112034048A (en) | Beam structure crack positioning method based on multiple frequency response function estimation | |
| CN109933031A (en) | A kind of system and method automatically correcting soft measuring instrument according to analysis data |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190129 |