CN117332920A - New energy station operation fault evolution analysis method - Google Patents
New energy station operation fault evolution analysis method Download PDFInfo
- Publication number
- CN117332920A CN117332920A CN202311211129.2A CN202311211129A CN117332920A CN 117332920 A CN117332920 A CN 117332920A CN 202311211129 A CN202311211129 A CN 202311211129A CN 117332920 A CN117332920 A CN 117332920A
- Authority
- CN
- China
- Prior art keywords
- data
- fault
- equipment
- new energy
- energy station
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 36
- 238000012423 maintenance Methods 0.000 claims abstract description 100
- 230000007613 environmental effect Effects 0.000 claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 42
- 230000002159 abnormal effect Effects 0.000 claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000010248 power generation Methods 0.000 claims description 8
- 230000009191 jumping Effects 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 3
- 230000005856 abnormality Effects 0.000 abstract description 9
- 230000008859 change Effects 0.000 abstract description 8
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008901 benefit Effects 0.000 abstract description 3
- 238000012806 monitoring device Methods 0.000 abstract 3
- 230000005855 radiation Effects 0.000 description 5
- 230000002265 prevention Effects 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- -1 Polytetrafluoroethylene Polymers 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000013136 deep learning model Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 239000000428 dust Substances 0.000 description 3
- 238000004146 energy storage Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 239000004698 Polyethylene Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000007787 long-term memory Effects 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 229920000573 polyethylene Polymers 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 238000011895 specific detection Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000000429 assembly Methods 0.000 description 1
- 230000000712 assembly Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 229920003020 cross-linked polyethylene Polymers 0.000 description 1
- 239000004703 cross-linked polyethylene Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000011810 insulating material Substances 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000015654 memory Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000006386 neutralization reaction Methods 0.000 description 1
- 229920001343 polytetrafluoroethylene Polymers 0.000 description 1
- 239000004810 polytetrafluoroethylene Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000000246 remedial effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000000779 smoke Substances 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/001—Methods to deal with contingencies, e.g. abnormalities, faults or failures
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
- H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/22—The renewable source being solar energy
- H02J2300/24—The renewable source being solar energy of photovoltaic origin
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
- H02J2300/20—The dispersed energy generation being of renewable origin
- H02J2300/28—The renewable source being wind energy
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Power Engineering (AREA)
- Data Mining & Analysis (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Artificial Intelligence (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Educational Administration (AREA)
- Life Sciences & Earth Sciences (AREA)
- Development Economics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Game Theory and Decision Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
A new energy station operation fault evolution analysis method belongs to the technical field of new energy station management. The method comprises fault evolution prediction and fault analysis, which can realize the prediction of the fault damage of the new energy station equipment and the analysis, positioning and remedy of the fault damage; the running loss of part of new energy stations can be predicted in advance; the loss of the new energy station in daily operation can be reduced; the method can help workers to know the influence of environmental change on the new energy station equipment before the environmental change, is convenient for the workers to change maintenance plans, is convenient for the workers to reasonably arrange time, and can fully reduce the influence of environmental factors on the operation of the new energy station equipment; the monitoring device has the advantages that the monitoring device can effectively reduce the influence caused by the abnormality of the data acquisition of the detection device by carrying out repeated acquisition and check on the data when the monitoring data are abnormal, so that the accuracy in state abnormality analysis can be ensured, the using effect is good, and the monitoring device has good use prospects.
Description
Technical Field
The invention belongs to the technical field of new energy station management, and particularly relates to a new energy station operation fault evolution analysis method.
Background
At present, a distributed energy storage mechanism represented by a new energy electric vehicle fully interacts with a power grid to realize energy supply of various forms of social new energy. The new energy station is connected into a wind power plant or a solar power station of a power system in a centralized way, all equipment below a grid connection point comprises a transformer, a bus, a circuit, a converter, energy storage, a wind turbine, photovoltaic power generation equipment, reactive power regulation equipment, auxiliary equipment and the like, and the real-time monitoring and fault prevention of the primary equipment are key to the operation and maintenance of the new energy station. In order to help operation and maintenance personnel to locate the fault point of the new energy station and find out the fault reason in time after the new energy station is abnormal in operation and faults occur, the new energy station is provided with a fault monitoring system, and the existing fault monitoring system realizes the functions of acquisition and storage of operation and maintenance data of the new energy station, monitoring of communication link states and alarming of abnormal information.
The prior patent with the publication number of CN109586239B is a patent with the name of real-time diagnosis and fault early warning method of an intelligent substation, and provides an implementation of intelligent diagnosis and prediction technology aiming at the current situation that the operation, maintenance and repair mode of the intelligent substation is low in efficiency, combines the advantages of the technologies such as supervised machine learning, unsupervised machine learning and the like, fundamentally changes the operation and diagnosis modes of the existing substation, improves the operation and maintenance working efficiency of the substation, diagnoses the health condition of the substation in real time on line, perceives and gives out prevention guidance comments on possible problems in advance, does not have rainy silk, and timely cuts off the seedling head of the fault, thereby having higher social and economic benefits;
through researches, the scheme described in the patent has the following defects as the prior art: the currently proposed solution is mainly to process and analyze data of a new energy station (some patents are only applied to a transformer substation) in operation to judge whether abnormality exists, but the wind power station and the photovoltaic power station are in remote areas, faults occurring in normal operation are fewer, damage is caused to the new energy station mainly by weather influence, only the operation data of the new energy station is analyzed, only a remedial effect can be achieved, and active prevention and adjustment cannot be achieved.
There is a need in the art for a new solution to this problem.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the new energy station operation fault evolution analysis method is used for solving the technical problems that in the prior art, data of a new energy station or a transformer station in operation are processed and analyzed to judge whether abnormality exists, and damage to a wind power plant and a photovoltaic power station caused by weather influence can only be remedied, and active prevention and adjustment cannot be achieved.
The new energy station operation fault evolution analysis method comprises the following steps of:
step one, carrying out fault evolution on new energy station electronic equipment, predicting maintenance time points of the new energy station electronic equipment and obtaining fault evolution prediction data of each equipment under various types of faults:
constructing a fault database, wherein the fault data comprise fault evolution prediction data and actual fault data, and an association relation between the fault data and a fault scheme is constructed;
comparing the type of the fault data detected in real time with corresponding type data in a fault database to determine the type of the fault; comparing the fault data detected in real time with fault evolution prediction data in the corresponding type of faults to determine the equipment with faults;
and feeding back fault data, fault types, equipment with faults and associated fault solution generation reports to new energy station operation and maintenance personnel.
The prediction method of the maintenance time point of the new energy station electronic equipment in the first step comprises the following steps:
(1) Collecting equipment loss data of all new energy station equipment under various environmental data to establish a prediction database, wherein the data stored in the prediction database are loss data in the actual scene of the existing new energy station and new energy station loss data recorded in a simulation experiment;
the environmental data comprises environmental temperature, environmental humidity, ground air pressure, environmental wind direction and environmental wind speed;
(2) Analyzing the loss of different equipment of the new energy station under the single environmental data factor one by one according to all the data in the step (1), calculating and calculating a loss average value for a plurality of times, and constructing the association relation between the loss average value and the corresponding environment; setting an environment data range of normal weather, and obtaining equipment loss data and equipment maintenance percentage nodes under the normal weather;
(3) Predicting loss data of the standby normal weather in a specified day according to a time sequence, and calculating and marking equipment maintenance time points according to the total loss which can be used by equipment, wherein the predicted environmental data range of the normal weather is different because of different ranges of the environmental data of the normal weather which are set in spring, summer, autumn and winter, so that the consumption data are also different in spring, summer, autumn and winter;
(4) Receiving weather data which is issued by a weather bureau and is of a specified day in the future, recalculating equipment loss under the environmental data in the future according to the environmental data in the weather data and the association relation between the loss average value obtained in the step (2) and the corresponding environment, and generating a new equipment maintenance time point;
(5) Checking whether the new equipment maintenance time point is suitable or not, finally determining the equipment maintenance time point, and carrying out equipment maintenance by staff in the finally determined equipment maintenance time point.
And (3) marking the equipment maintenance time point, wherein the loss percentage data of the used equipment is larger than the loss percentage data of the equipment when the equipment is required to be maintained, and the difference value of the loss percentage data and the loss percentage data is 1% -3%.
The specific method for finally determining the equipment maintenance time point in the step (5) comprises the following steps:
when the received future environmental data is in the set severe weather range, and the occurrence time of the severe weather coincides with the new equipment maintenance time point, modifying the equipment maintenance time point to be before the severe weather comes and taking the modified equipment maintenance time point as the latest equipment maintenance time point;
when the received future environmental data is not in the set bad weather range or the occurrence time of the bad weather is not overlapped with the new equipment maintenance time point, the new equipment maintenance time point is the latest equipment maintenance time point.
The specific method for determining the fault type and screening the fault equipment in the second step comprises the following steps:
collecting fault data and fault solutions, constructing a fault database, and constructing an association relationship between the fault data and the fault solutions, wherein the fault data comprises fault evolution prediction data and actual fault data; the fault evolution prediction data comprises maintenance time points, equipment loss data at different time points in the past and predicted equipment loss data at different time points in the future;
II, periodically connecting new energy station detection equipment, collecting detection data of the new energy station detection equipment, and storing and updating the detection data; the detection data comprise data for monitoring the on-off of a line and data for monitoring the power generation of the photovoltaic module;
when the acquired detection data is abnormal, feeding back signals to the corresponding sensors, and acquiring the data of the corresponding positions, so that the integrity of the acquired data is maintained;
III, judging whether the state is abnormal according to the detection data, and if so, performing the step IV, otherwise, repeating the step II;
IV, when the state is abnormal, comparing the fault data type with corresponding type data in a fault database to determine the fault type;
the equipment close to the maintenance time point in the fault evolution prediction data is automatically searched, actual fault data when the equipment close to the maintenance time point is in fault is called from the equipment closest to the maintenance time point, the fault data detected in real time are compared with the actual fault data, the error of the fault data and the actual fault data is smaller than a set threshold value, and the equipment with the fault is judged to be the equipment close to the maintenance time point; the error of the error detection result is larger than or equal to a threshold value, and the fault data detected in real time at this time is compared with the actual fault data of the next equipment close to the maintenance time point until the equipment with the fault is determined;
and V, summarizing the related fault solutions, and feeding back fault data, fault types, equipment with faults and fault solution generation reports to new energy station operation and maintenance personnel.
And in the step III, the abnormal state is that a plurality of fault data exist simultaneously, the fault data is detected for more than N/2 times by detecting the fault data type > M or N times.
In the step III, the step of judging whether the state is abnormal according to the detection data is as follows:
A. b, detecting collected operation data of the new energy plant, judging whether fault data exist according to a set threshold range, and if so, performing the step B, otherwise, repeating the step II;
B. when fault data exist, firstly judging the variety and the quantity of the fault data;
judging that the state is abnormal when the fault data type is more than M, and jumping to the step IV;
when the fault data type is less than or equal to M, recording abnormal time, feeding back a signal to new energy station detection equipment, entering a monitoring state, and performing the step D;
D. collecting data for N times at fixed time, receiving and detecting the collected operation data of the new energy plant station in real time, and judging the times of fault data;
F. judging whether the same kind of fault data exceeds N/2 times, judging that the state is abnormal if the same kind of fault data exceeds N/2 times, jumping to the step IV, marking the fault data if the same kind of fault data does not exceed the state, generating a fault data report, storing the fault data report in a fault database, and repeating the step II.
Through the design scheme, the invention has the following beneficial effects:
firstly, the invention comprises fault evolution prediction and fault analysis, which can realize the prediction of the equipment fault damage of the new energy station and the analysis, positioning and remedy of the fault damage place, can predict the loss of the operation of part of the new energy station in advance, can reduce the loss of the new energy station in daily operation, and can facilitate the staff to carry out equipment maintenance in advance before the arrival of bad weather so as to better cope with the influence of external environment change on the new energy station.
Secondly, the invention records the fault evolution prediction for predicting the maintenance time point of the new energy station electronic equipment, can help workers know the influence of environmental change on the new energy station equipment before the environmental change, is convenient for the workers to change maintenance plans, is convenient for the workers to reasonably arrange time, and can fully reduce the influence of environmental factors on the operation of the new energy station equipment, so that the equipment in the new energy station can operate for a long time.
Thirdly, the invention records the fault analysis for judging the fault type of the new energy station according to the detection data of the new energy station sensor in daily use, and performs multiple collection and check on the data when the monitoring data are abnormal, thereby effectively reducing the influence caused by the abnormality of the collected data of the detection device, ensuring the accuracy in the state abnormality analysis, having good use effect and good use prospect.
Drawings
The invention is further described with reference to the drawings and detailed description which follow:
fig. 1 is a flowchart of a step one of the new energy station operation fault evolution analysis method according to the present invention.
Fig. 2 is a flowchart of a second step in the new energy station operation fault evolution analysis method according to the present invention.
Detailed Description
The new energy station operation fault evolution analysis method comprises the following steps of:
step one, performing fault evolution on new energy station electronic equipment, and predicting a maintenance time point of the new energy station electronic equipment:
(1) Collecting equipment loss data of all new energy station equipment under various environmental data to establish a prediction database, wherein the data stored in the prediction database are loss data in the actual scene of the existing new energy station and new energy station loss data recorded in a simulation experiment;
the environmental data comprises environmental temperature, environmental humidity, ground air pressure, environmental wind direction and environmental wind speed;
(2) Analyzing the loss of different equipment of the new energy station under the single environmental data factor one by one according to all the data in the step (1), calculating and calculating a loss average value for a plurality of times, and constructing the association relation between the loss average value and the corresponding environment; setting an environment data range of normal weather, and obtaining equipment loss data and equipment maintenance percentage nodes under the normal weather;
(3) Predicting loss data of normal weather of all equipment in a specified day according to a time sequence, and calculating and marking equipment maintenance time points according to total loss which can be used by the equipment, wherein the predicted loss data used in spring, summer, autumn and winter are different because environment data ranges of the normal weather set in spring, summer, autumn and winter are different;
the equipment has loss during normal use, and the equipment is required to be maintained in advance to avoid damage when the loss reaches a certain degree, so that the loss percentage data of the used equipment is larger than the loss percentage data when the equipment is required to be maintained, the difference range of the loss percentage data and the loss percentage data is 1% -3%, the reserved 1% -3% is used for preventing loss caused by daily environmental fluctuation, the maintenance time is reserved, and the occurrence of damage is avoided.
The prediction is a normal weather, namely a daily stable environment, the overall fluctuation is small, the average value of normal loss is taken, and the use loss data of spring, summer, autumn and winter are different because the normal environments of spring, summer, autumn and winter are different, for example, the use loss data is influenced by the high temperature in summer and the low temperature in autumn and winter, and the loss is far higher than that in spring, autumn and winter.
(4) Receiving weather data which is issued by a weather bureau and is of a specified day in the future, recalculating equipment loss under the environmental data in the future according to the environmental data in the weather data and the association relation between the loss average value obtained in the step (2) and the corresponding environment, and generating a new equipment maintenance time point;
and receiving future data issued by a weather bureau, extracting abnormal weather data, and recording the abnormal weather data into a time line, wherein the loss value of the corresponding new energy station equipment on the time line is used for reducing the average value corresponding to the loss data.
(5) Checking whether the new equipment maintenance time point is suitable or not, finally determining the equipment maintenance time point, and carrying out equipment maintenance by staff in the finally determined equipment maintenance time point;
step two, fault analysis:
collecting fault data and fault solutions, constructing a fault database, and constructing an association relationship between the fault data and the fault solutions, wherein the fault data comprises fault evolution prediction data and actual fault data; the fault evolution prediction data comprises maintenance time points, equipment loss data at different time points in the past and predicted equipment loss data at different time points in the future;
II, periodically connecting new energy station detection equipment, collecting detection data of the new energy station detection equipment, and storing and updating the detection data; the detection data comprise data for monitoring the on-off of a line and data for monitoring the power generation of the photovoltaic module;
when the detection data of the new energy station detection equipment are collected, the collected data are processed, the collected operation data are subjected to data cleaning and repeated data deleting, when the collected detection data are abnormal, signals are fed back to the corresponding sensors, and the data of the corresponding positions are collected, so that the integrity of the collected data is maintained, and the comprehensive analysis can be realized.
III, judging whether the state is abnormal according to the detection data, and if so, performing the step IV, otherwise, repeating the step II;
IV, when the state is abnormal, comparing the fault data type with corresponding type data in a fault database to determine the fault type;
the equipment close to the maintenance time point in the fault evolution prediction data is automatically searched, the fault evolution prediction data of the equipment close to the maintenance time point when the corresponding type of faults occur is compared with the fault data detected in real time, the error of the fault evolution prediction data and the fault data is smaller than a set threshold value, and the equipment with the faults is judged to be the equipment close to the maintenance time point; the error of the two is larger than or equal to a threshold value, and the fault data detected in real time at this time is compared with the equipment fault evolution prediction data close to the maintenance time point until the equipment with the fault is determined;
the equipment is damaged when the loss reaches a certain degree during normal use, which equipment is large in daily loss and easy to damage can be judged by checking the failure evolution prediction data, then the real-time detected failure data is compared with the actual failure data close to the damaged equipment, and the specific equipment failures can be judged.
For example, when in use, a problem may be caused by a plurality of devices, and at this time, according to the predicted data of the fault evolution, it may be determined which devices are in a near maintenance state, and in general, the fault is caused by the device fault near the maintenance date, and the operation data of these devices are collected preferentially, so that rapid screening can be performed, and efficiency can be improved.
And V, summarizing fault solutions, and feeding back fault data, fault types and fault solution generation reports to new energy station operation and maintenance personnel.
And (3) marking the equipment maintenance time point, wherein the loss percentage data of the used equipment is larger than the loss percentage data of the equipment when the equipment is required to be maintained, and the difference value of the loss percentage data and the loss percentage data is 1% -3%.
The specific method for finally determining the equipment maintenance time point in the step (5) comprises the following steps:
when the received future environmental data is in the set severe weather range, and the occurrence time of the severe weather coincides with the new equipment maintenance time point, modifying the equipment maintenance time point to be before the severe weather comes and taking the modified equipment maintenance time point as the latest equipment maintenance time point;
when the received future environmental data is not in the set bad weather range or the occurrence time of the bad weather is not overlapped with the new equipment maintenance time point, the new equipment maintenance time point is the latest equipment maintenance time point.
And in the step III, the abnormal state is that a plurality of fault data exist simultaneously, the fault data is detected for more than N/2 times by detecting the fault data type > M or N times.
In the step III, the step of judging whether the state is abnormal according to the detection data is as follows:
A. b, detecting collected operation data of the new energy plant, judging whether fault data exist according to a set threshold range, and if so, performing the step B, otherwise, repeating the step II;
B. when fault data exist, firstly judging the variety and the quantity of the fault data;
judging that the state is abnormal when the fault data type is more than M, and jumping to the step IV;
when the fault data type is less than or equal to M, recording abnormal time, feeding back a signal to new energy station detection equipment, entering a monitoring state, and performing the step D;
D. collecting data for N times at fixed time, receiving and detecting the collected operation data of the new energy plant station in real time, and judging the times of fault data;
F. judging whether the same kind of fault data exceeds N/2 times, judging that the state is abnormal if the same kind of fault data exceeds N/2 times, jumping to the step IV, marking the fault data if the same kind of fault data does not exceed the state, generating a fault data report, storing the fault data report in a fault database, and repeating the step II.
The new energy plant operation data includes operation data of all devices, such as power generation device operation data (voltage, current, power generation amount), transformer operation data, photovoltaic cell energy storage data source, and the like.
Analysis was performed in conjunction with the following examples:
1. the fault evolution prediction focuses on reducing the interference of environmental factors on the equipment, and is mainly suitable for predicting the operation faults of the equipment.
For example, the normal service life of the inverter is 10 years, so the daily loss is about 0.0274%, when the total loss reaches 15% (when the total loss exceeds the value, no maintenance is easy to cause abnormal conditions, the maintenance cost is greatly increased), the loss is reduced to 10% after the maintenance, and then the maintenance is needed when the total loss reaches 25%;
therefore, in use, the maintenance time point of the equipment is marked in the step (3) to be the time point when the daily loss is about 0.0274% and the total loss reaches 13%, and the total loss is a predicted value, namely the daily loss under normal conditions. Generally, the actual loss is set to be 13% between 12% and 14%, according to the environment, about 474 days is selected, when abnormal weather is predicted, abnormal weather loss data replace existing loss data, for example, the loss is 0.1542% in level 8 wind power for 1 day, the loss is 0.0138 in heavy rain for 1 day, and then the actual loss in the day is 0.1954%, which can greatly accelerate the loss of equipment, so that the time point when the total loss reaches 13% can be compared with the time point when the total loss reaches 23% in advance, and similarly, the time point of second maintenance is continuously predicted according to 10% calculation after maintenance, namely, the total loss reaches 23% and the like.
When the equipment loss is more than 12%, the latest abnormal weather data are combined to help related staff to judge whether the time is adjusted or not, the equipment maintenance time point always fluctuates along with the change of the environment, the prediction accuracy is high, and the use effect is good.
When the method is used, a circulating neural network deep learning model based on long-term and short-term memory can be constructed based on information of a prediction database, the LSTM model is improved by a traditional RNN model, and compared with the RNN, a unit control mechanism is added, so that the problem of gradient explosion caused by an original long sequence is solved. The model allows the RNN model to remember long-term information by designing specific structural elements. And by designing three kinds of gate structures: forgetting a door layer, inputting the door layer and outputting the door layer. When control information passes through a cell, information can be selectively added and removed by the cell structure.
And after the construction, the influence of the circulating neural network deep learning model based on long-term and short-term memory on the output power is constructed based on the information of the prediction database, single factors are analyzed independently, then the single factors are summarized, future weather data are input, and the future output power is predicted.
For example, the illumination factor:
the direct radiation, the position of the sun, the azimuth and altitude angle of the receiving surface and the like have great research systems for predicting the output power of the photovoltaic power station and diagnosing the faults of the components, and generally occupy great space when the weather is clear. Scattered radiation is related to atmospheric conditions such as dust, smoke, water vapor, air molecules and other suspended matter content, and the path of sunlight through the atmosphere. In cloudy days and in the case of a lot of dust, the scattered radiation is of a larger composition.
For example, temperature factors:
in the mechanism level, the temperature has an influence on the carrier flow in the component, so that the correlation between the component temperature and the output power is large, but a certain tailing effect exists. In particular, when the ambient temperature slightly rises in the afternoon, the output power of the photovoltaic power station gradually decreases, and the negative correlation characteristic is presented.
For example, temperature factors:
when the humidity in the environment is high, a large amount of water drops in the air are suspended in the atmosphere, the concentration of fog can be reflected by the humidity to a great extent, the humidity is different, and the power output is influenced by the scattered radiation of the water drops in the air.
For example, wind factors:
wind speed and direction can influence the temperature of the assembly, dust of air, water drops and the like, so that solar radiation absorbed by the assembly is indirectly influenced by the output power of the photovoltaic power station.
The circulating neural network deep learning model based on long-short-term memory performs neutralization analysis on all the factors, so that the actual power generation amount of a new energy station in one day under different conditions can be obtained, and workers can be helped to better manage the new energy station.
2. The fault analysis focuses on supervision of daily operation, and is mainly applicable to maintenance of daily fault damage. The fault data comprise fault evolution prediction data and actual fault data, the fault evolution prediction data are compared with the actual fault data, and the critical value of equipment fault damage is checked, so that the rapid judgment of which part of equipment is damaged is facilitated, and the analysis efficiency is improved.
For example, when in use, a problem may be caused by a plurality of devices, and at this time, according to the predicted data of the fault evolution, it may be determined which devices are in a near maintenance state, and in general, the fault is caused by the device fault near the maintenance date, and the operation data of these devices are collected preferentially, so that rapid screening can be performed, and efficiency can be improved.
When collecting and monitoring the power generation data of the photovoltaic module:
each branch is provided with A photovoltaic cell assemblies, and each branch is connected in series with a current sensor for measuring the working current of the branch; each branch is provided with B voltage sensors, where b=a/3. The voltage sensor mounting method consists in detecting M/3 battery packs at a time.
The specific detection principle is as follows:
under normal conditions, each branch current of the photovoltaic array should be equal.
When a certain branch fails, the output current is smaller than that of a normal branch. The standard value takes 90% of the maximum value of the current in all branches. In order to reduce the interference of the environmental interference to fault detection, all the branch currents are compared with a standard value, and if the branch currents are smaller than the standard value, the branch current is determined to be a fault branch.
The standard value can also obtain the output current generated by the normal operation of the photovoltaic array in the past year,
the optimal scheme is that the standard value adopts 90% of the maximum value of the current in all branches obtained by the detection.
When the position of the photovoltaic module is positioned, the branch can be determined through the current sensor of the feedback signal, and the approximate position of the photovoltaic module is judged through the voltage sensor, so that the positioning is realized, and the maintenance of staff is facilitated.
When data are collected, collecting all data measured by the current sensors on each branch, and judging whether a state abnormality exists according to a step III in fault analysis;
when the measured data of the current sensors on the multiple groups of branches are smaller than the standard value at one time and the fault is not an adjacent area, (the photovoltaic module is special, the current is influenced by illumination, irradiance of all modules is reduced when the cloud shielding exists, so that the detected value is lower than the standard value), namely abnormal data are judged, at the moment, the detected data of the voltage sensors on the circuit are obtained, the positions of the faults are compared, the fault solutions are summarized, and fault data, fault types and fault solution generation reports are fed back to staff.
When the data measured by the current sensor on the single branch is smaller than the standard value, feeding back a signal to the current sensor, enabling the current sensor to collect data once every a set time interval, collecting the data for N times, judging the abnormal times in the N times of collected data, and when the abnormal times in the N times of collected data exceeds N/2 times, judging that abnormal data exists, at the moment, acquiring the detection data of the voltage sensor on the circuit, comparing the detection data, determining the position of a fault, summarizing a fault solution, and feeding back fault data, fault types and fault solution generation reports to staff;
when the data measured by the current sensor on the single branch is larger than or equal to the standard value, no abnormality is judged, and the data are collected regularly according to the normal period.
When the number of times of abnormality in the N times of acquisition data is not more than N/2 times, marking fault data, generating a fault data report and storing the fault data report into a file, periodically acquiring data according to a normal period, and correspondingly overhauling the staff when the staff patrol is carried out subsequently.
The reason for the multiple detection and judgment is that the current sensor may fail, and the condition that the floating object temporarily covers the photovoltaic module may exist, so that the accuracy of the detection is greatly improved after a period of time.
Thus, the case of collecting N times is collected every a short period of time.
When 3 or more fault data reports are generated in one normal overhaul, information is called, the voltage sensor detection data on the circuit is obtained during detection, comparison is carried out, the position of the fault is determined, and workers are directly distributed for maintenance.
When data of the on-off of the monitoring line are collected:
the specific detection principle is as follows:
when the cable is grounded or has an open circuit fault, the impedance of the fault point is not matched with the characteristic impedance of the original cable. When the high-frequency signal encounters an impedance mismatch point, a phenomenon that the signal is reflected back occurs. If the difference between the characteristic impedance of the cable and the impedance value of the fault point is small, part of the high-frequency signal is transmitted through the unmatched point to continue to propagate forwards, and the electromagnetic wave signal carries a large amount of state information of the tested line just because of the phenomenon, so that the fault on the transmission line can be calculated according to the reflection coefficient of the electromagnetic wave.
When the equivalent load of the transmission line port is exactly equal to the characteristic impedance of the transmission line, no reflection occurs at the place where no impedance mutation occurs at this time:
when open, the reflected signal is in phase with the original signal:
when short-circuited, the reflected signal is inverted from the original signal.
The traveling wave propagation speed of the test signal in the common power cable material is shown in the following table;
| type of insulating material | Traveling wave propagation velocity (m/s) in cable |
| Polytetrafluoroethylene | 214 |
| Polyethylene | 202 |
| Filled polyethylene | 193 |
| Crosslinked polyethylene | 180 |
When the injected test signal is transmitted in the cable, the propagation time can be obtained by the time difference between the transmitted wave and the reflected wave, and the propagation speed of the electromagnetic wave in the cable can be obtained through experiments and is a constant value.
Therefore, as long as the time interval between the emission signal and the reflection signal is measured, the position of the fault point can be calculated, so that the worker can conveniently and rapidly find the abnormal fault point, the worker can conveniently and rapidly maintain the fault point, the loss is reduced, the workload of the related worker is reduced, and the method has good use prospect.
Claims (7)
1. A new energy station operation fault evolution analysis method is characterized in that: comprising the following steps, and the following steps are carried out in sequence:
step one, carrying out fault evolution on new energy station electronic equipment, predicting maintenance time points of the new energy station electronic equipment and obtaining fault evolution prediction data of each equipment under various types of faults:
constructing a fault database, wherein the fault data comprise fault evolution prediction data and actual fault data, and an association relation between the fault data and a fault scheme is constructed;
comparing the type of the fault data detected in real time with corresponding type data in a fault database to determine the type of the fault; determining the judging sequence of equipment damage through the fault evolution prediction data, calling actual fault data corresponding to the fault equipment, and comparing the fault data detected in real time with the actual fault data to determine the equipment with the fault;
and feeding back fault data, fault types, equipment with faults and associated fault solution generation reports to new energy station operation and maintenance personnel.
2. The new energy station operation fault evolution analysis method according to claim 1, wherein the new energy station operation fault evolution analysis method is characterized in that: the prediction method of the maintenance time point of the new energy station electronic equipment in the first step comprises the following steps:
(1) Collecting equipment loss data of all new energy station equipment under various environmental data to establish a prediction database, wherein the data stored in the prediction database are loss data in the actual scene of the existing new energy station and new energy station loss data recorded in a simulation experiment;
the environmental data comprises environmental temperature, environmental humidity, ground air pressure, environmental wind direction and environmental wind speed;
(2) Analyzing the loss of different equipment of the new energy station under the single environmental data factor one by one according to all the data in the step (1), calculating and calculating a loss average value for a plurality of times, and constructing the association relation between the loss average value and the corresponding environment; setting an environment data range of normal weather, and obtaining equipment loss data and equipment maintenance percentage nodes under the normal weather;
(3) Predicting loss data of the standby normal weather in a specified day according to a time sequence, and calculating and marking equipment maintenance time points according to the total loss which can be used by equipment, wherein the predicted environmental data range of the normal weather is different because of different ranges of the environmental data of the normal weather which are set in spring, summer, autumn and winter, so that the consumption data are also different in spring, summer, autumn and winter;
(4) Receiving weather data which is issued by a weather bureau and is of a specified day in the future, recalculating equipment loss under the environmental data in the future according to the environmental data in the weather data and the association relation between the loss average value obtained in the step (2) and the corresponding environment, and generating a new equipment maintenance time point;
(5) Checking whether the new equipment maintenance time point is suitable or not, finally determining the equipment maintenance time point, and carrying out equipment maintenance by staff in the finally determined equipment maintenance time point.
3. The new energy station operation fault evolution analysis method according to claim 2, wherein the new energy station operation fault evolution analysis method is characterized in that: and (3) marking the equipment maintenance time point, wherein the loss percentage data of the used equipment is larger than the loss percentage data of the equipment when the equipment is required to be maintained, and the difference value of the loss percentage data and the loss percentage data is 1% -3%.
4. The new energy station operation fault evolution analysis method according to claim 2, wherein the new energy station operation fault evolution analysis method is characterized in that: the specific method for finally determining the equipment maintenance time point in the step (5) comprises the following steps:
when the received future environmental data is in the set severe weather range, and the occurrence time of the severe weather coincides with the new equipment maintenance time point, modifying the equipment maintenance time point to be before the severe weather comes and taking the modified equipment maintenance time point as the latest equipment maintenance time point;
when the received future environmental data is not in the set bad weather range or the occurrence time of the bad weather is not overlapped with the new equipment maintenance time point, the new equipment maintenance time point is the latest equipment maintenance time point.
5. The new energy station operation fault evolution analysis method according to claim 1, wherein the new energy station operation fault evolution analysis method is characterized in that: the specific method for determining the fault type and screening the fault equipment in the second step comprises the following steps:
collecting fault data and fault solutions, constructing a fault database, and constructing an association relationship between the fault data and the fault solutions, wherein the fault data comprises fault evolution prediction data and actual fault data; the fault evolution prediction data comprises maintenance time points, equipment loss data at different time points in the past and predicted equipment loss data at different time points in the future;
II, periodically connecting new energy station detection equipment, collecting detection data of the new energy station detection equipment, and storing and updating the detection data; the detection data comprise data for monitoring the on-off of a line and data for monitoring the power generation of the photovoltaic module;
when the acquired detection data is abnormal, feeding back signals to the corresponding sensors, and acquiring the data of the corresponding positions, so that the integrity of the acquired data is maintained;
III, judging whether the state is abnormal according to the detection data, and if so, performing the step IV, otherwise, repeating the step II;
IV, when the state is abnormal, comparing the fault data type with corresponding type data in a fault database to determine the fault type;
the equipment close to the maintenance time point in the fault evolution prediction data is automatically searched, actual fault data when the equipment close to the maintenance time point is in fault is called from the equipment closest to the maintenance time point, the fault data detected in real time are compared with the actual fault data, the error of the fault data and the actual fault data is smaller than a set threshold value, and the equipment with the fault is judged to be the equipment close to the maintenance time point; the error of the error detection result is larger than or equal to a threshold value, and the fault data detected in real time at this time is compared with the actual fault data of the next equipment close to the maintenance time point until the equipment with the fault is determined;
and V, summarizing the related fault solutions, and feeding back fault data, fault types, equipment with faults and fault solution generation reports to new energy station operation and maintenance personnel.
6. The new energy station operation fault evolution analysis method according to claim 5, wherein the new energy station operation fault evolution analysis method is characterized in that: and in the step III, the abnormal state is that a plurality of fault data exist simultaneously, the fault data is detected for more than N/2 times by detecting the fault data type > M or N times.
7. The new energy station operation fault evolution analysis method according to claim 5, wherein the new energy station operation fault evolution analysis method is characterized in that: in the step III, the step of judging whether the state is abnormal according to the detection data is as follows:
A. b, detecting collected operation data of the new energy plant, judging whether fault data exist according to a set threshold range, and if so, performing the step B, otherwise, repeating the step II;
B. when fault data exist, firstly judging the variety and the quantity of the fault data;
judging that the state is abnormal when the fault data type is more than M, and jumping to the step IV;
when the fault data type is less than or equal to M, recording abnormal time, feeding back a signal to new energy station detection equipment, entering a monitoring state, and performing the step D;
D. collecting data for N times at fixed time, receiving and detecting the collected operation data of the new energy plant station in real time, and judging the times of fault data;
F. judging whether the same kind of fault data exceeds N/2 times, judging that the state is abnormal if the same kind of fault data exceeds N/2 times, jumping to the step IV, marking the fault data if the same kind of fault data does not exceed the state, generating a fault data report, storing the fault data report in a fault database, and repeating the step II.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311211129.2A CN117332920A (en) | 2023-09-20 | 2023-09-20 | New energy station operation fault evolution analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311211129.2A CN117332920A (en) | 2023-09-20 | 2023-09-20 | New energy station operation fault evolution analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117332920A true CN117332920A (en) | 2024-01-02 |
Family
ID=89294360
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311211129.2A Pending CN117332920A (en) | 2023-09-20 | 2023-09-20 | New energy station operation fault evolution analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117332920A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117907845A (en) * | 2024-03-20 | 2024-04-19 | 山东泰开电力电子有限公司 | Electrochemical energy storage system insulation detection method based on electrical parameter analysis |
-
2023
- 2023-09-20 CN CN202311211129.2A patent/CN117332920A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117907845A (en) * | 2024-03-20 | 2024-04-19 | 山东泰开电力电子有限公司 | Electrochemical energy storage system insulation detection method based on electrical parameter analysis |
| CN117907845B (en) * | 2024-03-20 | 2024-05-17 | 山东泰开电力电子有限公司 | Electrochemical energy storage system insulation detection method based on electrical parameter analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108964606B (en) | Hot spot fault detection method for photovoltaic system | |
| KR101238620B1 (en) | Trouble Recognition Apparatus for Photovoltaic System and Methord thereof | |
| CN107346899A (en) | A kind of photovoltaic power station system stability assessment method and system | |
| CN105375878A (en) | Method for online detection and assessment of photovoltaic system | |
| CN105337575B (en) | Photovoltaic plant status predication and method for diagnosing faults and system | |
| CN104796082A (en) | System and method for diagnosing faults of photovoltaic power generation systems in online manner | |
| KR102230548B1 (en) | Power generation prediction and efficiency diagnosis system of solar power generation facilities using FRBFNN model | |
| CN116800200B (en) | Solar panel safety monitoring system based on data analysis | |
| CN112003564B (en) | Distributed photovoltaic system branch power abnormity early warning method based on intelligent terminal | |
| CN108599724A (en) | A kind of photovoltaic module on-line monitoring system and monitoring method | |
| CN114898232A (en) | Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic string data analysis | |
| CN117332920A (en) | New energy station operation fault evolution analysis method | |
| Chen et al. | A novel fault diagnosis method of PV based-on power loss and IV characteristics | |
| Yun et al. | Research on fault diagnosis of photovoltaic array based on random forest algorithm | |
| CN107065829A (en) | A kind of photovoltaic module pollution diagnosis method supervised based on solar power generation under big data is excavated | |
| CN117318111B (en) | Weather prediction-based dynamic adjustment method and system for light energy storage source | |
| Haba | Monitoring solar panels using machine learning techniques | |
| CN110022130A (en) | A kind of photovoltaic array fault test set and method | |
| CN117743794A (en) | Distributed photovoltaic power station fault diagnosis and efficiency loss evaluation system | |
| CN112764130A (en) | Power grid meteorological monitoring and early warning device and monitoring method | |
| CN104601107A (en) | Cloud photovoltaic fault diagnosis system | |
| CN213661567U (en) | Photovoltaic array detection and evaluation device for small-scale photovoltaic off-grid base station | |
| CN109474069B (en) | Distributed power station state monitoring method | |
| CN116418292B (en) | Performance test method and system for photovoltaic module | |
| CN117117862B (en) | Intelligent analysis method and system for running state of solar photovoltaic system |
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 |