CN116452042A - Intelligent Internet of things safety supervision method and system for photovoltaic power station - Google Patents
Intelligent Internet of things safety supervision method and system for photovoltaic power station Download PDFInfo
- Publication number
- CN116452042A CN116452042A CN202310350880.4A CN202310350880A CN116452042A CN 116452042 A CN116452042 A CN 116452042A CN 202310350880 A CN202310350880 A CN 202310350880A CN 116452042 A CN116452042 A CN 116452042A
- Authority
- CN
- China
- Prior art keywords
- temperature
- photovoltaic
- power station
- data
- power
- 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 42
- 238000010248 power generation Methods 0.000 claims abstract description 52
- 238000004458 analytical method Methods 0.000 claims abstract description 24
- 238000012423 maintenance Methods 0.000 claims abstract description 15
- 238000005516 engineering process Methods 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 9
- 230000005855 radiation Effects 0.000 claims description 27
- 239000000428 dust Substances 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000009826 distribution Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 9
- 230000008859 change Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000004140 cleaning Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 6
- 238000007405 data analysis Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 6
- 239000012535 impurity Substances 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000006978 adaptation Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 230000007717 exclusion Effects 0.000 claims description 3
- 210000003608 fece Anatomy 0.000 claims description 3
- 239000012634 fragment Substances 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 231100000817 safety factor Toxicity 0.000 claims description 3
- 239000004576 sand Substances 0.000 claims description 3
- 230000035945 sensitivity Effects 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000003860 storage Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 238000001931 thermography Methods 0.000 claims description 3
- 238000003908 quality control method Methods 0.000 abstract description 6
- 238000010276 construction Methods 0.000 abstract description 4
- 238000003745 diagnosis Methods 0.000 abstract description 3
- 230000007774 longterm Effects 0.000 abstract description 3
- 230000007246 mechanism Effects 0.000 abstract description 3
- 238000011160 research Methods 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 229920006395 saturated elastomer Polymers 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003211 malignant effect Effects 0.000 description 1
- 230000006855 networking Effects 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
- G06Q10/06395—Quality analysis or management
-
- 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
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Game Theory and Decision Science (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Photovoltaic Devices (AREA)
Abstract
The invention discloses a method and a system for intelligent internet-of-things safety supervision of a photovoltaic power station, which realize the purpose of indicating the power generation condition of the power station by stably acquiring and displaying the operation information of main equipment of the photovoltaic power station in real time, and specifically comprise the following contents: the following information is monitored in real time: meteorological resource data including irradiance, ambient temperature, component back plate temperature, wind speed, wind direction, etc.; generating capacity data including daily generating capacity, monthly generating capacity, annual generating capacity, and real-time power. The invention can realize a long-term quality control mechanism from an engineering construction period to an operation period for a photovoltaic power generation enterprise, provides powerful technology and management guarantee for the photovoltaic power generation enterprise through multiple means such as performance detection, energy efficiency analysis, fault diagnosis, operation and maintenance management, intelligent analysis technology research and application, and the like, meanwhile, the problems found by the follow-up nodes can be fed back to the lead-in nodes, the gateway moves forward and achieves the aim of quality control virtuous circle, and the safe, efficient, economic and stable operation of the photovoltaic power station is realized.
Description
Technical Field
The invention relates to the technical field of photovoltaic power station safety, in particular to a method and a system for intelligent internet-of-things safety supervision of a photovoltaic power station.
Background
With the subsequent construction and operation of a large-scale photovoltaic power station, the operation condition of the power station is known in real time, and the meeting of the monitoring requirement of a superior system or a power grid dispatching system becomes an urgent need to be solved. In addition, the photovoltaic power station is mostly built in remote areas, the occupied area is wide, the terrain distribution is complex, the photovoltaic power station is influenced by heavy rain, wind, snow and severe weather, the operating personnel of the power station are few, the mobility is large, the problems of disorder management, low operation and maintenance efficiency, high failure rate, large electric energy loss and the like are easily caused, and a plurality of risks and challenges are brought to subsequent operation and management and development of the photovoltaic power station.
Against the current situation of rapid growth of photovoltaic power stations, the establishment of a perfect, fine and intelligent operation and maintenance mode is a trend, and high-quality intelligent operation and maintenance service is necessarily a scarce resource. From this, this scheme provides one can realize intelligent collection, the intelligent transmission of information high-speed and the intelligent analysis in photovoltaic power plant intelligent safety monitoring system of mass information of photovoltaic power plant part information in an organic whole based on relevant technologies such as thing networking, big data, really realizes intelligent management, intelligent control and intelligent operation and maintenance of photovoltaic power plant.
Disclosure of Invention
The technical problem to be solved by the invention is to overcome the defects of the prior art, and provide the intelligent internet-of-things safety supervision method and system for the photovoltaic power station, which are used for carrying out omnibearing, fine, digital and intelligent management on the power station, realizing an integrated scheme of remote online monitoring, intelligent analysis, early warning and forecasting, personnel and technology joint defense and full-flow closed-loop treatment on the photovoltaic power station, being beneficial to preventing malignant accidents of the photovoltaic power generation equipment, avoiding personal casualties and huge economic losses, and taking action to resist risks before extreme weather arrives.
The invention provides the following technical scheme:
the invention provides a method and a system for intelligent internet-of-things safety supervision of a photovoltaic power station, which realize the purpose of indicating the power generation condition of the power station by stably acquiring and displaying the operation information of main equipment of the photovoltaic power station in real time, and specifically comprise the following contents:
1. the following information is monitored in real time: meteorological resource data including irradiance, ambient temperature, component back plate temperature, wind speed, wind direction, etc.; generating capacity data including daily generating capacity, monthly generating capacity, annual generating capacity, real-time power;
2. the operation management of the power station can be continuously optimized through the power station data analysis, the temperature rise loss analysis, the PR value analysis of each array and each string and the equivalent utilization hours of the inverter and the string are carried out, the conversion efficiency and the energy efficiency analysis are further carried out, and the power generation efficiency and the electric quantity output of the whole life cycle of the power station are maintained and improved;
3. according to the equipment monitoring condition, performance management and operation and maintenance are carried out on core equipment such as a photovoltaic module, an inverter, a combiner box and the like, and potential faults of the power station are analyzed and alarmed in real time, so that potential risks are prevented.
The first step comprises the following steps:
collecting meteorological data in real time, converging meteorological resource indexes and marking to reflect actual solar resource conditions of the photovoltaic power station in a statistical period; the method is characterized by adopting indexes such as average wind speed, average air temperature, relative humidity, total radiation of a horizontal plane, total radiation of an inclined plane, sunshine hours and the like; the method is specifically as follows:
(1) Average wind speed
The average wind speed is the average value of the instantaneous wind speed in a statistical period, and is measured by an environment monitor in a photovoltaic power station, and the unit is that: m/s;
(2) Average air temperature
The average air temperature refers to the average value of the ambient temperature in the photovoltaic power plant measured by the ambient monitor during the statistical period, in units of: the temperature is lower than the temperature;
(3) Relative temperature
The relative temperature refers to the comparison value of the absolute temperature in the air and the saturated absolute humidity at the same temperature, and is expressed as a percentage (%);
(4) Total radiation level
The total radiation quantity in the horizontal plane is the totalSolar radiation energy per unit area irradiated to a horizontal plane in a counting period, unit: KW.h/m 2 (or MJ/m) 2 )；
(5) Total radiation quantity on inclined plane
The total radiant quantity of the inclined surface refers to the solar radiant energy irradiated to a unit area of a certain inclined surface in a statistical period, and the unit is: KW.h/m 2 (or MJ/m) 2 )；
(6) Number of sunshine hours
The solar radiation time number is also called real time number, and means that the solar radiation intensity reaches or exceeds 120W/m in the statistical period 2 Time sum of (a) units: h, performing H;
cleaning the collected related data, and automatically removing impurity data according to a preset algorithm by a data combination system for processing and collecting the related data according to various impurities such as format errors, data anomalies, data missing, duplication, contradiction, logic relation confusion and the like; in particular, the reasons for the lack of data are manifold, which makes the system lack a lot of useful information, while uncertainty in the data may lead to unreliable output, by taking regression methods to replace the missing values, mainly by building a suitable piecewise difference function on the known data, the missing values being replaced by using this function to calculate an approximation;
interference data inaccurate in scene description still exists in the middle of the simply cleaned data, and the noise data can influence the convergence speed of the data, so that noise is removed by adopting a normal distribution method;
according to the normal distribution formula,wherein σ can be expressed as a standard deviation of the dataset, μ represents a mean of the dataset, and x represents data of the dataset; noise data can be understood as small probability data relative to normal data; the normal distribution has the following characteristics: the probability that x falls outside (mu-3 sigma, mu+3 sigma) is less than three thousandths; according to this feature, points three times the standard deviation of the data set can be assumed to be noise data exclusion by calculating the standard deviation of the data set;
the influence of continuous overcast and rainy weather, sand and dust weather, solar radiation and the like on power generation and safety factors is analyzed by monitoring meteorological conditions, and the influence of weather changes on a power station is studied mainly from the time dimension according to collected meteorological data such as wind, temperature, humidity, pressure, rain and the like;
(1) Firstly, weather change is predicted in advance, an Paiyun-dimensional time is reasonable, and solar energy resources are utilized to the greatest extent;
(2) Secondly, disaster damage is difficult to avoid, and the starting and stopping time is accurately predicted to reduce the loss to the greatest extent.
(3) Comparing whether the monitoring data of the power station is consistent with the data used in project feasibility research and evaluation, and taking the data as the basis of suitability judgment of whether the equipment environment is suitable and the expected power generation target setting;
generating data:
the data acquisition device is used for acquiring related data of a power station related photovoltaic module, a combiner, an inverter, a box transformer and the like in real time, establishing a photovoltaic module power generation model, and acquiring the radiation quantity H, the environment temperature T and the module backboard temperature T according to the radiation quantity T m Component operating voltage V m And current I m Judging whether the real-time working state of the photovoltaic module is abnormal or not; the ideal working temperature of the photovoltaic power generation assembly is about 25 ℃, and when the temperature rises by 1 ℃, the output power is reduced, and the generated energy is correspondingly reduced;
photovoltaic module working current and irradiance H, environment temperature T and module backboard temperature T m The equal correlation factor correspondence function is as follows:
establishing an equation of component voltage and current:
V m (T)＝V m0 +p×β(T-25)-I m ΔR s (T)
the current change influence factor is calculated as follows:
ΔR s (T)＝p×0.1264×(T-25)
according to the voltage and the current, the overall power of the photovoltaic module is calculated as follows:
P m ＝I m ×V m
according to the power station performance evaluation index, the power generation performance of the whole power station is evaluated by adopting the equivalent utilization hours and the overall efficiency of the photovoltaic power station system;
equivalent utilization hours Y p Means that in the statistical period, the power generation capacity of the power station is converted into the whole power station
The number of power generation hours under installed full load operating conditions, also referred to as the equivalent full load power generation hours; units: h, performing H;
wherein E is p The unit is generated energy: KWh, P 0 The unit KWP is the installed power (peak watt power) of the power station;
calculating the ratio of the actual power generation amount to the theoretical power generation amount in the statistical period, and converting the overall efficiency (PR value) of the photovoltaic power station system into:
the performance ratio can be influenced by different climate areas or seasons due to different environmental temperatures, and PR (power plant) caused by different temperatures does not belong to the quality problem of the power station; to exclude the influence of temperature, the standard performance ratio PR can be used stc Evaluating the photovoltaic power plant, wherein the standard performance ratio is a performance ratio obtained by correcting a temperature condition to a standard test condition (25 ℃); for temperature correction, a temperature correction coefficient C is introduced i ：
C i ＝1+δ i ×(T cell -25)
Wherein delta is the power temperature coefficient of the photovoltaic module, and Tcell is the average working junction temperature of the battery in the evaluation period; according to the types of photovoltaic modules of a power station, taking the duty ratio of only the reserved power generation amount of the photovoltaic modules of different types as the duty ratio of the rated power of the modules, calculating the rated power of the modules, and obtaining the standard performance ratio PR by using the temperature correction coefficient stc Calculation ofThe formula is as follows:
and obtaining a curve graph of the standard performance ratio with respect to the irradiance change of the sunlight under different weather conditions.
The core device in the third step performs performance management and operation and maintenance, including the following contents:
the method can be used for basic evaluation of the operation condition of the power station according to the calculated related data analysis of the power generation capacity of the photovoltaic power station; however, the situation of insufficient generated energy can still be met in the running process of the power station, besides the equivalent utilization hours and the efficiency analysis, the electric quantity loss is also a very important aspect, and the electric quantity loss comprises power attenuation caused by dirt and dust shielding of the photovoltaic module, photovoltaic module series connection adaptation loss, MPPT loss, direct current line loss from a group string to a junction box, photovoltaic array temperature rise loss, junction box parallel connection mismatch loss and the like;
firstly, a mismatch loss model of the photovoltaic array with the NxL x M structure is obtained by using a hybrid modeling method, wherein the mismatch loss model comprises the following steps:
according to the power attenuation nominal power of the photovoltaic module, setting module attenuation rate thresholds of which the attenuation is not more than 2.5% and 3% respectively after the photovoltaic module runs for 1 year, and the attenuation is not more than 0.7% annually and is not more than 20% in the 25-year life period; considering the stain and dust shielding loss of the photovoltaic module, and cleaning when the power difference of the module reaches 5%; under the stable illumination condition, the difference of the group string current values is within 5%, the group string mismatch loss is not more than 1%, the group string average MPPT deviation loss is not more than 2%, the average direct current line loss is not more than 1.5%, and the group string parallel mismatch loss is not more than 2%;
the string problem positioning is carried out according to the string threshold condition, the instant process of system electricity limiting or inverter working state adjustment is intercepted, and the fault judgment can be completed in a short period by combining the characteristic of 'the current difference is increased when the voltage is increased' of the fault string and the 'factor decomposition' method, so that the accuracy and the sensitivity are obviously improved;
in addition, in order to perform accurate string position, infrared image mode is adopted to perform string fault identification and detection, including but not limited to string non-power generation, component surface damage, diode fault, poor consistency, broken grid, unfilled corner, fragments, hidden cracks, vegetation shielding, dust, bird droppings and the like;
performing accurate fault identification on the shot image by adopting an image processing technology; firstly, carrying out group string segmentation, automatically removing invalid information from a video by an image recognition algorithm, segmenting an image into each group string, calculating average temperature of all the group strings, and finding out a different group string;
the gradient image segmentation step of the preliminary separation set string and the background is as follows: firstly, acquiring a vertical gradient image according to a photovoltaic power station shooting image;
graImage(x，y)＝I(x，y+1)-I(x，y)
then thresholding the photovoltaic vertical image using a maximum inter-class variance method (Otsu algorithm);
graInv＝Otsu(graImage)
then reversing the thresholded gradient image to reserve a photovoltaic array region with smaller temperature difference and remove a background region with larger temperature difference;
graInv＝1-graOtsu
finally, optimizing a background area possibly contained in a part with smaller temperature difference, defining all pixel points with temperature values larger than the ambient temperature T in the temperature set storage image by utilizing the characteristic that the temperature of the background area is obviously lower than that of the photovoltaic string area, sequencing from large to small, averaging elements in the set, setting 0.5 time of the average value as a temperature threshold value, and marking the image with the temperature value lower than the temperature threshold value as a background image;
secondly, carrying out component segmentation, identifying and segmenting each component, calculating the average temperature of all components in a picture, and finding out a differential component;
aiming at the components after pretreatment, which comprise a photovoltaic array area and a ground area with smaller temperature difference, taking the average value as a central reference point for the optimization result, taking k times of standard deviation as the lower limit (mu-k sigma) and the upper limit (mu+k sigma) of a threshold interval, and acquiring a corrected image recognition result;
graMod＝graInv，(x，y)∈[μ-kσ，μ+kσ]
optimizing the photovoltaic assembly area, counting the median value of the heights of all the photovoltaic array areas, taking the median value as the average height of the photovoltaic array area, taking the area with the difference value between the area height and the average height of the photovoltaic array exceeding a threshold value as an area to be adjusted, searching horizontal or vertical reference information, if the searching is successful, carrying out area cutting, otherwise, not cutting to avoid the condition of hot spot missing detection;
then, performing fault identification, calculating the average temperature of each component, finding out hot spots in the component, recording the shape of the hot spots, and analyzing and identifying various faults and fouling types;
the K-means algorithm is improved, and the problems that the clustering effect and the time required by the clustering process are greatly influenced by an initial clustering center and the calculated amount is large and the clustering effect is low are solved; the core thought is to optimize the selection mode of the initial cluster and reduce the iterative calculation amount;
specifically, the first step searches for the sample pair with the farthest distance, sorts all samples according to any dimension, and searches for a pair of samples S1 and S2 with the farthest distance from both ends; secondly, taking two samples with the highest density in the same class set as S1 and S2 as initial clustering centers based on a distance criterion between each sample in the minimized unified class; thirdly, clustering the rest samples by combining a triangle inequality theorem, and determining the class of the sample to be clustered by comparing the sample center with the cluster with the nearest cluster center; finally, judging that if the stability of the original clustering center is higher than that of the new clustering center, replacing the clustered center with the original clustering center, otherwise, keeping the original clustering center;
according to the cluster analysis, the photovoltaic module area is measured and calculated, various typical hidden crack characteristics can be collected and analyzed, and thermal imaging and appearance comparison analysis results can be given to module infrared hot spot conditions caused by various different reasons, wherein the conditions comprise local shielding, dust or foreign matter shielding and the like; the fault condition is monitored by combining the total station equipment, the fault assembly and the fault equipment are accurately positioned, and the equipment state is accurately mastered.
Compared with the prior art, the invention has the following beneficial effects:
the intelligent internet of things safety supervision system of the photovoltaic power station is built, a long-term quality control mechanism from an engineering construction period to an operation period can be realized for a photovoltaic power generation enterprise, powerful technology and management guarantee are provided for the photovoltaic power generation enterprise through multiple means such as performance detection, energy efficiency analysis, fault diagnosis, operation and maintenance management, intelligent analysis technology research and development and application, meanwhile, problems found by subsequent nodes can be fed back to the preamble node, a gateway moves forward and the aim of quality control virtuous circle is achieved, and finally, safe, efficient, economical and stable operation of the photovoltaic power station is realized.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a graph showing the standard performance ratio versus irradiance of sunlight under various weather conditions;
FIG. 2 is a schematic view of the power attenuation of a photovoltaic module according to the present invention;
FIG. 3 is a schematic diagram illustrating a step of region clipping in a photovoltaic module according to the present invention;
fig. 4 is a flowchart of the photovoltaic module fault alert pushing process in the present invention.
Detailed Description
The preferred embodiments of the present invention will be described below with reference to the accompanying drawings, it being understood that the preferred embodiments described herein are for illustration and explanation of the present invention only, and are not intended to limit the present invention. Wherein like reference numerals refer to like elements throughout.
Example 1
1-4, the invention provides a method and a system for intelligent internet-of-things safety supervision of a photovoltaic power station, which can stably acquire and display the operation information of main equipment of the photovoltaic power station in real time, so as to realize the electricity generation condition of the power station as a finger palm, and specifically comprises the following contents:
1. the following information is monitored in real time: meteorological resource data including irradiance, ambient temperature, component back plate temperature, wind speed, wind direction, etc.; generating capacity data including daily generating capacity, monthly generating capacity, annual generating capacity, real-time power;
2. the operation management of the power station can be continuously optimized through the power station data analysis, the temperature rise loss analysis, the PR value analysis of each array and each string and the equivalent utilization hours of the inverter and the string are carried out, the conversion efficiency and the energy efficiency analysis are further carried out, and the power generation efficiency and the electric quantity output of the whole life cycle of the power station are maintained and improved;
3. according to the equipment monitoring condition, performance management and operation and maintenance are carried out on core equipment such as a photovoltaic module, an inverter, a combiner box and the like, and potential faults of the power station are analyzed and alarmed in real time, so that potential risks are prevented.
The first step comprises the following steps:
collecting meteorological data in real time, converging meteorological resource indexes and marking to reflect actual solar resource conditions of the photovoltaic power station in a statistical period; the method is characterized by adopting indexes such as average wind speed, average air temperature, relative humidity, total radiation of a horizontal plane, total radiation of an inclined plane, sunshine hours and the like; the method is specifically as follows:
(1) Average wind speed
The average wind speed is the average value of the instantaneous wind speed in a statistical period, and is measured by an environment monitor in a photovoltaic power station, and the unit is that: m/s;
(2) Average air temperature
The average air temperature refers to the average value of the ambient temperature in the photovoltaic power plant measured by the ambient monitor during the statistical period, in units of: the temperature is lower than the temperature;
(3) Relative temperature
The relative temperature refers to the comparison value of the absolute temperature in the air and the saturated absolute humidity at the same temperature, and is expressed as a percentage (%);
(4) Total radiation level
The total radiation quantity in the horizontal plane is countedSolar radiation energy per unit area irradiated to a horizontal plane in a cycle, unit: KW.h/m 2 (or MJ/m) 2 )；
(5) Total radiation quantity on inclined plane
The total radiant quantity of the inclined surface refers to the solar radiant energy irradiated to a unit area of a certain inclined surface in a statistical period, and the unit is: KW.h/m 2 (or MJ/m) 2 )；
(6) Number of sunshine hours
The solar radiation time number is also called real time number, and means that the solar radiation intensity reaches or exceeds 120W/m in the statistical period 2 Time sum of (a) units: h, performing H;
cleaning the collected related data, and automatically removing impurity data according to a preset algorithm by a data combination system for processing and collecting the related data according to various impurities such as format errors, data anomalies, data missing, duplication, contradiction, logic relation confusion and the like; in particular, the reasons for the lack of data are manifold, which makes the system lack a lot of useful information, while uncertainty in the data may lead to unreliable output, by taking regression methods to replace the missing values, mainly by building a suitable piecewise difference function on the known data, the missing values being replaced by using this function to calculate an approximation;
interference data inaccurate in scene description still exists in the middle of the simply cleaned data, and the noise data can influence the convergence speed of the data, so that noise is removed by adopting a normal distribution method;
according to the normal distribution formula,wherein σ can be expressed as a standard deviation of the dataset, μ represents a mean of the dataset, and x represents data of the dataset; noise data can be understood as small probability data relative to normal data; the normal distribution has the following characteristics: the probability that x falls outside (mu-3 sigma, mu+3 sigma) is less than three thousandths; according to this feature, points three times the standard deviation of the data set can be assumed to be noise data exclusion by calculating the standard deviation of the data set;
the influence of continuous overcast and rainy weather, sand and dust weather, solar radiation and the like on power generation and safety factors is analyzed by monitoring meteorological conditions, and the influence of weather changes on a power station is studied mainly from the time dimension according to collected meteorological data such as wind, temperature, humidity, pressure, rain and the like;
(1) Firstly, weather change is predicted in advance, an Paiyun-dimensional time is reasonable, and solar energy resources are utilized to the greatest extent;
(2) Secondly, disaster damage is difficult to avoid, and the starting and stopping time is accurately predicted to reduce the loss to the greatest extent.
(3) Comparing whether the monitoring data of the power station is consistent with the data used in project feasibility research and evaluation, and taking the data as the basis of suitability judgment of whether the equipment environment is suitable and the expected power generation target setting;
generating data:
the data acquisition device is used for acquiring related data of a power station related photovoltaic module, a combiner, an inverter, a box transformer and the like in real time, establishing a photovoltaic module power generation model, and acquiring the radiation quantity H, the environment temperature T and the module backboard temperature T according to the radiation quantity T m Component operating voltage V m And current I m Judging whether the real-time working state of the photovoltaic module is abnormal or not; the ideal working temperature of the photovoltaic power generation assembly is about 25 ℃, and when the temperature rises by 1 ℃, the output power is reduced, and the generated energy is correspondingly reduced;
the corresponding functions of the working current of the photovoltaic module and irradiance H, ambient temperature T, module backboard temperature Tm and other factors are as follows:
establishing an equation of component voltage and current:
V m (T)＝V m0 +p×β(T-25)-I m ΔR s (T)
the current change influence factor is calculated as follows:
ΔR s (T)＝p×0.1264×(T-25)
according to the voltage and the current, the overall power of the photovoltaic module is calculated as follows:
P m ＝I m ×V m
according to the power station performance evaluation index, the power generation performance of the whole power station is evaluated by adopting the equivalent utilization hours and the overall efficiency of the photovoltaic power station system;
equivalent utilization hours Y p Means that in the statistical period, the power generation capacity of the power station is converted into the whole power station
The number of power generation hours under installed full load operating conditions, also referred to as the equivalent full load power generation hours; units: h, performing H;
wherein Ep is the amount of power generation, unit: KWh, P 0 The unit KWP is the installed power (peak watt power) of the power station;
calculating the ratio of the actual power generation amount to the theoretical power generation amount in the statistical period, and converting the overall efficiency (PR value) of the photovoltaic power station system into:
the performance ratio can be influenced by different climate areas or seasons due to different environmental temperatures, and PR (power plant) caused by different temperatures does not belong to the quality problem of the power station; to exclude the influence of temperature, the standard performance ratio PR can be used stc Evaluating the photovoltaic power plant, wherein the standard performance ratio is a performance ratio obtained by correcting a temperature condition to a standard test condition (25 ℃); for temperature correction, a temperature correction coefficient C is introduced i ：
C i ＝1+δ i ×(T cell -25)
Wherein delta is the power temperature coefficient of the photovoltaic module, and Tcell is the average working junction temperature of the battery in the evaluation period; according to the types of photovoltaic modules of a power station, taking the duty ratio of only the reserved power generation amount of the photovoltaic modules of different types as the duty ratio of the rated power of the modules, calculating the rated power of the modules, and obtaining the standard performance ratio PR by using the temperature correction coefficient stc The calculation formula is as follows:
the standard performance ratio versus solar irradiance curves for different weather conditions are shown in figure 1 below.
The core device in the third step performs performance management and operation and maintenance, including the following contents:
the method can be used for basic evaluation of the operation condition of the power station according to the calculated related data analysis of the power generation capacity of the photovoltaic power station; however, the situation of insufficient generated energy can still be met in the running process of the power station, besides the equivalent utilization hours and the efficiency analysis, the electric quantity loss is also a very important aspect, and the electric quantity loss comprises power attenuation caused by dirt and dust shielding of the photovoltaic module, photovoltaic module series connection adaptation loss, MPPT loss, direct current line loss from a group string to a junction box, photovoltaic array temperature rise loss, junction box parallel connection mismatch loss and the like;
firstly, a mismatch loss model of the photovoltaic array with the NxL x M structure is obtained by using a hybrid modeling method, wherein the mismatch loss model comprises the following steps:
according to the power attenuation nominal power of the photovoltaic module, setting module attenuation rate thresholds of which the attenuation is not more than 2.5% and 3% respectively after the photovoltaic module runs for 1 year, and the attenuation is not more than 0.7% annually and is not more than 20% in the 25-year life period; considering the stain and dust shielding loss of the photovoltaic module, and cleaning when the power difference of the module reaches 5%; under the stable illumination condition, the difference of the group string current values is within 5%, the group string mismatch loss is not more than 1%, the group string average MPPT deviation loss is not more than 2%, the average direct current line loss is not more than 1.5%, and the group string parallel mismatch loss is not more than 2%;
the string problem positioning is carried out according to the string threshold condition, the instant process of system electricity limiting or inverter working state adjustment is intercepted, and the fault judgment can be completed in a short period by combining the characteristic of 'voltage increase and current difference increase' of the fault string and the 'factor decomposition' method, so that the accuracy and the sensitivity are obviously improved, as shown in figure 2;
in addition, in order to perform accurate string position, infrared image mode is adopted to perform string fault identification and detection, including but not limited to string non-power generation, component surface damage, diode fault, poor consistency, broken grid, unfilled corner, fragments, hidden cracks, vegetation shielding, dust, bird droppings and the like;
performing accurate fault identification on the shot image by adopting an image processing technology; firstly, carrying out group string segmentation, automatically removing invalid information from a video by an image recognition algorithm, segmenting an image into each group string, calculating average temperature of all the group strings, and finding out a different group string;
the gradient image segmentation step of the preliminary separation set string and the background is as follows: firstly, acquiring a vertical gradient image according to a photovoltaic power station shooting image;
graImage(x，y)＝I(x，y+1)-I(x，y)
then thresholding the photovoltaic vertical image using a maximum inter-class variance method (Otsu algorithm);
graInv＝Otsu(graImage)
then reversing the thresholded gradient image to reserve a photovoltaic array region with smaller temperature difference and remove a background region with larger temperature difference;
graInv＝1-graOtsu
finally, optimizing a background area possibly contained in a part with smaller temperature difference, defining all pixel points with temperature values larger than the ambient temperature T in the temperature set storage image by utilizing the characteristic that the temperature of the background area is obviously lower than that of the photovoltaic string area, sequencing from large to small, averaging elements in the set, setting 0.5 time of the average value as a temperature threshold value, and marking the image with the temperature value lower than the temperature threshold value as a background image;
secondly, carrying out component segmentation, identifying and segmenting each component, calculating the average temperature of all components in a picture, and finding out a differential component;
aiming at the components after pretreatment, which comprise a photovoltaic array area and a ground area with smaller temperature difference, taking the average value as a central reference point for the optimization result, taking k times of standard deviation as the lower limit (mu-k sigma) and the upper limit (mu+k sigma) of a threshold interval, and acquiring a corrected image recognition result;
graMod＝graInv，(x，y)∈[μ-kσ，μ+kσ]
optimizing the photovoltaic module area, counting the median value of the heights of the photovoltaic array areas to be used as the average height of the photovoltaic array area, then regarding the area with the difference value between the area height and the average height of the photovoltaic array exceeding a threshold value as an area to be adjusted, searching horizontal or vertical reference information, if the searching is successful, performing area cutting, otherwise, not cutting to avoid the condition of hot spot missing detection, as shown in figure 3;
then, performing fault identification, calculating the average temperature of each component, finding out hot spots in the component, recording the shape of the hot spots, and analyzing and identifying various faults and fouling types;
the K-means algorithm is improved, and the problems that the clustering effect and the time required by the clustering process are greatly influenced by an initial clustering center and the calculated amount is large and the clustering effect is low are solved; the core thought is to optimize the selection mode of the initial cluster and reduce the iterative calculation amount;
specifically, the first step searches for the sample pair with the farthest distance, sorts all samples according to any dimension, and searches for a pair of samples S1 and S2 with the farthest distance from both ends; secondly, taking two samples with the highest density in the same class set as S1 and S2 as initial clustering centers based on a distance criterion between each sample in the minimized unified class; thirdly, clustering the rest samples by combining a triangle inequality theorem, and determining the class of the sample to be clustered by comparing the sample center with the cluster with the nearest cluster center; finally, judging that if the stability of the original clustering center is higher than that of the new clustering center, replacing the clustered center with the original clustering center, otherwise, keeping the original clustering center;
according to the cluster analysis, the photovoltaic module area is measured and calculated, various typical hidden crack characteristics can be collected and analyzed, and thermal imaging and appearance comparison analysis results can be given to module infrared hot spot conditions caused by various different reasons, wherein the conditions comprise local shielding, dust or foreign matter shielding and the like; the fault condition is monitored by combining the total station equipment, the fault assembly and the fault equipment are accurately positioned, and the equipment state is accurately mastered.
Specifically, the fault types are divided into five categories:
(1) A battery piece in the assembly fails;
(2) Diode failure or bypass operating condition or junction box cold joint;
(3) Diode faults, bypass working states or junction box cold joints, surface stains of components, internal faults of components and the like exist in the components;
(4) The components are provided with surface stains, shadow shielding, damage to battery pieces in the components and the like;
(5) The whole series of faults generate heat, and the safety is burnt out or broken.
And in combination with the fault type and the analysis result, the system automatically gives out an alarm and pushes according to the level of maintenance difficulty, and an operation and maintenance person goes to the site for treatment according to fault positioning, as shown in fig. 4.
Further, the intelligent internet of things safety supervision system of the photovoltaic power station is built, a long-term quality control mechanism from an engineering construction period to an operation period can be realized for a photovoltaic power generation enterprise, multiple means such as performance detection, energy efficiency analysis, fault diagnosis, performance management and operation and maintenance of core equipment, intelligent analysis technology research and development and application are adopted, powerful technology and management guarantee are provided for the photovoltaic power generation enterprise, meanwhile, problems found by subsequent nodes can be fed back to the preamble node, a gateway moves forward and the aim of quality control virtuous circle is achieved, and finally the safe, efficient, economic and stable operation of the photovoltaic power station is realized.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (1)
1. The intelligent internet-of-things safety supervision method and system for the photovoltaic power station are characterized in that operation information of main equipment of the photovoltaic power station is stably collected and displayed in real time, so that the condition of power generation of the power station is achieved, and the intelligent internet-of-things safety supervision method and system specifically comprise the following steps:
1. the following information is monitored in real time: meteorological resource data including irradiance, ambient temperature, component back plate temperature, wind speed, wind direction, etc.; generating capacity data including daily generating capacity, monthly generating capacity, annual generating capacity, real-time power;
2. the operation management of the power station can be continuously optimized through the power station data analysis, the temperature rise loss analysis, the PR value analysis of each array and each string and the equivalent utilization hours of the inverter and the string are carried out, the conversion efficiency and the energy efficiency analysis are further carried out, and the power generation efficiency and the electric quantity output of the whole life cycle of the power station are maintained and improved;
3. according to the equipment monitoring condition, performance management and operation maintenance are carried out on core equipment such as a photovoltaic module, an inverter, a combiner box and the like, potential faults of the power station are analyzed and alarmed in real time, and potential risks are prevented;
the first step comprises the following steps:
collecting meteorological data in real time, converging meteorological resource indexes and marking to reflect actual solar resource conditions of the photovoltaic power station in a statistical period; the method is characterized by adopting indexes such as average wind speed, average air temperature, relative humidity, total radiation of a horizontal plane, total radiation of an inclined plane, sunshine hours and the like;
cleaning the collected related data, and automatically removing impurity data according to a preset algorithm by a data combination system for processing and collecting the related data according to various impurities such as format errors, data anomalies, data missing, duplication, contradiction, logic relation confusion and the like; in particular, the reasons for the lack of data are manifold, which makes the system lack a lot of useful information, while uncertainty in the data may lead to unreliable output, by taking regression methods to replace the missing values, mainly by building a suitable piecewise difference function on the known data, the missing values being replaced by using this function to calculate an approximation;
interference data inaccurate in scene description still exists in the middle of the simply cleaned data, and the noise data can influence the convergence speed of the data, so that noise is removed by adopting a normal distribution method;
according to the normal distribution formula,wherein σ can be expressed as a standard deviation of the dataset, μ represents a mean of the dataset, and x represents data of the dataset; noise data can be understood as small probability data relative to normal data; the normal distribution has the following characteristics: the probability that x falls outside (mu-3 sigma, mu+3 sigma) is less than three thousandths; according to this feature, points three times the standard deviation of the data set can be assumed to be noise data exclusion by calculating the standard deviation of the data set;
the influence of continuous overcast and rainy weather, sand and dust weather, solar radiation and the like on power generation and safety factors is analyzed by monitoring meteorological conditions, and the influence of weather changes on a power station is studied mainly from the time dimension according to collected meteorological data such as wind, temperature, humidity, pressure, rain and the like;
generating data:
the data acquisition device is used for acquiring related data of a power station related photovoltaic module, a combiner, an inverter, a box transformer and the like in real time, establishing a photovoltaic module power generation model, and acquiring the radiation quantity H, the environment temperature T and the module backboard temperature T according to the radiation quantity T m Component operating voltage V m And current I m Judging whether the real-time working state of the photovoltaic module is abnormal or not; the ideal working temperature of the photovoltaic power generation assembly is about 25 ℃, and when the temperature rises by 1 ℃, the output power is reduced, and the generated energy is correspondingly reduced;
photovoltaic module working current and irradiance H, environment temperature T and module backboard temperature T m The equal correlation factor correspondence function is as follows:
establishing an equation of component voltage and current:
V m (T)＝V m0 +p×β(T-25)-I m ΔR s (T)
the current change influence factor is calculated as follows:
ΔR s (T)＝p×0.1264×(T-25)
according to the voltage and the current, the overall power of the photovoltaic module is calculated as follows:
P m ＝I m ×V m
according to the power station performance evaluation index, the power generation performance of the whole power station is evaluated by adopting the equivalent utilization hours and the overall efficiency of the photovoltaic power station system;
equivalent utilization hours Y p Means that in the statistical period, the power generation capacity of the power station is converted into the whole power station
The number of power generation hours under installed full load operating conditions, also referred to as the equivalent full load power generation hours; units: h, performing H;
wherein E is p The unit is generated energy: KWh, P 0 The unit KWP is the installed power (peak watt power) of the power station;
calculating the ratio of the actual power generation amount to the theoretical power generation amount in the statistical period, and converting the overall efficiency (PR value) of the photovoltaic power station system into:
the performance ratio can be influenced by different climate areas or seasons due to different environmental temperatures, and PR (power plant) caused by different temperatures does not belong to the quality problem of the power station; to exclude the influence of temperature, the standard performance ratio PR can be used stc Evaluation of photovoltaic plants, the standard Performance ratio is the performance of correcting the temperature conditions to standard test conditions (25 ℃ C.)Ratio of; for temperature correction, a temperature correction coefficient C is introduced i ：
C i ＝1+δ i ×(T cell -25)
Wherein delta is the power temperature coefficient of the photovoltaic module, and Tcell is the average working junction temperature of the battery in the evaluation period; according to the types of photovoltaic modules of a power station, taking the duty ratio of only the reserved power generation amount of the photovoltaic modules of different types as the duty ratio of the rated power of the modules, calculating the rated power of the modules, and obtaining the standard performance ratio PR by using the temperature correction coefficient stc The calculation formula is as follows:
obtaining a curve graph of standard performance ratio with respect to irradiance change of sunlight under different weather conditions;
the core device in the third step performs performance management and operation and maintenance, including the following contents:
the method can be used for basic evaluation of the operation condition of the power station according to the calculated related data analysis of the power generation capacity of the photovoltaic power station; however, the situation of insufficient generated energy can still be met in the running process of the power station, besides the equivalent utilization hours and the efficiency analysis, the electric quantity loss is also a very important aspect, and the electric quantity loss comprises power attenuation caused by dirt and dust shielding of the photovoltaic module, photovoltaic module series connection adaptation loss, MPPT loss, direct current line loss from a group string to a junction box, photovoltaic array temperature rise loss, junction box parallel connection mismatch loss and the like;
firstly, a mismatch loss model of the photovoltaic array with the NxL x M structure is obtained by using a hybrid modeling method, wherein the mismatch loss model comprises the following steps:
according to the power attenuation nominal power of the photovoltaic module, setting module attenuation rate thresholds of which the attenuation is not more than 2.5% and 3% respectively after the photovoltaic module runs for 1 year, and the attenuation is not more than 0.7% annually and is not more than 20% in the 25-year life period; considering the stain and dust shielding loss of the photovoltaic module, and cleaning when the power difference of the module reaches 5%; under the stable illumination condition, the difference of the group string current values is within 5%, the group string mismatch loss is not more than 1%, the group string average MPPT deviation loss is not more than 2%, the average direct current line loss is not more than 1.5%, and the group string parallel mismatch loss is not more than 2%;
the string problem positioning is carried out according to the string threshold condition, the instant process of system electricity limiting or inverter working state adjustment is intercepted, and the fault judgment can be completed in a short period by combining the characteristic of 'the current difference is increased when the voltage is increased' of the fault string and the 'factor decomposition' method, so that the accuracy and the sensitivity are obviously improved;
in addition, in order to perform accurate string position, infrared image mode is adopted to perform string fault identification and detection, including but not limited to string non-power generation, component surface damage, diode fault, poor consistency, broken grid, unfilled corner, fragments, hidden cracks, vegetation shielding, dust, bird droppings and the like;
performing accurate fault identification on the shot image by adopting an image processing technology; firstly, carrying out group string segmentation, automatically removing invalid information from a video by an image recognition algorithm, segmenting an image into each group string, calculating average temperature of all the group strings, and finding out a different group string;
the gradient image segmentation step of the preliminary separation set string and the background is as follows: firstly, acquiring a vertical gradient image according to a photovoltaic power station shooting image;
graImage(x，y)＝I(x，y+1)-I(x，y)
then thresholding the photovoltaic vertical image using a maximum inter-class variance method (Otsu algorithm);
graInv＝Otxu(graImage)
then reversing the thresholded gradient image to reserve a photovoltaic array region with smaller temperature difference and remove a background region with larger temperature difference;
graInv＝1-graOtsu
finally, optimizing a background area possibly contained in a part with smaller temperature difference, defining all pixel points with temperature values larger than the ambient temperature T in the temperature set storage image by utilizing the characteristic that the temperature of the background area is obviously lower than that of the photovoltaic string area, sequencing from large to small, averaging elements in the set, setting 0.5 time of the average value as a temperature threshold value, and marking the image with the temperature value lower than the temperature threshold value as a background image;
secondly, carrying out component segmentation, identifying and segmenting each component, calculating the average temperature of all components in a picture, and finding out a differential component;
aiming at the components after pretreatment, which comprise a photovoltaic array area and a ground area with smaller temperature difference, taking the average value as a central reference point for the optimization result, taking k times of standard deviation as the lower limit (mu-k sigma) and the upper limit (mu+k sigma) of a threshold interval, and acquiring a corrected image recognition result;
graMod＝graInv，(x，y)∈[μ-kσ，μ+kσ]
optimizing the photovoltaic assembly area, counting the median value of the heights of all the photovoltaic array areas, taking the median value as the average height of the photovoltaic array area, taking the area with the difference value between the area height and the average height of the photovoltaic array exceeding a threshold value as an area to be adjusted, searching horizontal or vertical reference information, if the searching is successful, carrying out area cutting, otherwise, not cutting to avoid the condition of hot spot missing detection;
then, performing fault identification, calculating the average temperature of each component, finding out hot spots in the component, recording the shape of the hot spots, and analyzing and identifying various faults and fouling types;
the K-means algorithm is improved, and the problems that the clustering effect and the time required by the clustering process are greatly influenced by an initial clustering center and the calculated amount is large and the clustering effect is low are solved; the core thought is to optimize the selection mode of the initial cluster and reduce the iterative calculation amount;
specifically, the first step searches for the sample pair with the farthest distance, sorts all samples according to any dimension, and searches for a pair of samples S1 and S2 with the farthest distance from both ends; secondly, taking two samples with the highest density in the same class set as S1 and S2 as initial clustering centers based on a distance criterion between each sample in the minimized unified class; thirdly, clustering the rest samples by combining a triangle inequality theorem, and determining the class of the sample to be clustered by comparing the sample center with the cluster with the nearest cluster center; finally, judging that if the stability of the original clustering center is higher than that of the new clustering center, replacing the clustered center with the original clustering center, otherwise, keeping the original clustering center;
according to the cluster analysis, the photovoltaic module area is measured and calculated, various typical hidden crack characteristics can be collected and analyzed, and thermal imaging and appearance comparison analysis results can be given to module infrared hot spot conditions caused by various different reasons, wherein the conditions comprise local shielding, dust or foreign matter shielding and the like; the fault condition is monitored by combining the total station equipment, the fault assembly and the fault equipment are accurately positioned, and the equipment state is accurately mastered.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310350880.4A CN116452042A (en) | 2023-04-04 | 2023-04-04 | Intelligent Internet of things safety supervision method and system for photovoltaic power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310350880.4A CN116452042A (en) | 2023-04-04 | 2023-04-04 | Intelligent Internet of things safety supervision method and system for photovoltaic power station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116452042A true CN116452042A (en) | 2023-07-18 |
Family
ID=87131416
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310350880.4A Pending CN116452042A (en) | 2023-04-04 | 2023-04-04 | Intelligent Internet of things safety supervision method and system for photovoltaic power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116452042A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117013606A (en) * | 2023-08-14 | 2023-11-07 | 欧米勒电气有限公司 | Intelligent energy storage control system for photovoltaic power generation based on artificial intelligence |
| CN117151696A (en) * | 2023-10-27 | 2023-12-01 | 中科华辰(山东)实业股份有限公司 | Photovoltaic operation and maintenance management system |
| CN117761468A (en) * | 2024-02-22 | 2024-03-26 | 国网甘肃省电力公司张掖供电公司 | multi-parameter operation state monitoring method and system for new energy power station |
| CN117807546A (en) * | 2024-02-29 | 2024-04-02 | 山东德源电力科技股份有限公司 | Efficient data storage method and system for photovoltaic protocol converter |
| CN117852719A (en) * | 2024-01-15 | 2024-04-09 | 重庆双江航运发展有限公司 | Full-flow management method and system for engineering data |
| CN118228893A (en) * | 2024-05-22 | 2024-06-21 | 国网安徽省电力有限公司经济技术研究院 | Operation optimization method for AC/DC hybrid power distribution network |
-
2023
- 2023-04-04 CN CN202310350880.4A patent/CN116452042A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117013606A (en) * | 2023-08-14 | 2023-11-07 | 欧米勒电气有限公司 | Intelligent energy storage control system for photovoltaic power generation based on artificial intelligence |
| CN117013606B (en) * | 2023-08-14 | 2024-05-17 | 欧米勒电气有限公司 | Intelligent energy storage control system for photovoltaic power generation based on artificial intelligence |
| CN117151696A (en) * | 2023-10-27 | 2023-12-01 | 中科华辰(山东)实业股份有限公司 | Photovoltaic operation and maintenance management system |
| CN117151696B (en) * | 2023-10-27 | 2024-01-23 | 中科华辰(山东)实业股份有限公司 | Photovoltaic operation and maintenance management system |
| CN117852719A (en) * | 2024-01-15 | 2024-04-09 | 重庆双江航运发展有限公司 | Full-flow management method and system for engineering data |
| CN117761468A (en) * | 2024-02-22 | 2024-03-26 | 国网甘肃省电力公司张掖供电公司 | multi-parameter operation state monitoring method and system for new energy power station |
| CN117761468B (en) * | 2024-02-22 | 2024-05-24 | 国网甘肃省电力公司张掖供电公司 | Multi-parameter operation state monitoring method and system for new energy power station |
| CN117807546A (en) * | 2024-02-29 | 2024-04-02 | 山东德源电力科技股份有限公司 | Efficient data storage method and system for photovoltaic protocol converter |
| CN117807546B (en) * | 2024-02-29 | 2024-04-30 | 山东德源电力科技股份有限公司 | Efficient data storage method and system for photovoltaic protocol converter |
| CN118228893A (en) * | 2024-05-22 | 2024-06-21 | 国网安徽省电力有限公司经济技术研究院 | Operation optimization method for AC/DC hybrid power distribution network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116452042A (en) | Intelligent Internet of things safety supervision method and system for photovoltaic power station | |
| WO2024021548A1 (en) | Photovoltaic power generation intelligent operation and maintenance method and system, and storage medium | |
| CN108572011B (en) | Photovoltaic cell panel dust deposition state monitoring system based on machine vision and calculation method | |
| Haba | Monitoring solar panels using machine learning techniques | |
| Zhang et al. | A fault diagnosis method for photovoltaic module current mismatch based on numerical analysis and statistics | |
| CN111614317B (en) | IV curve scanning-based diagnosis method for shadow shielding of photovoltaic panel | |
| CN112653393B (en) | Control method and device for photovoltaic system IV diagnosis | |
| CN114669569B (en) | Big data-based automatic cleaning system for photovoltaic module | |
| CN115642877A (en) | Photovoltaic module abnormal shielding detection method and system based on deep learning | |
| CN118071033B (en) | Photovoltaic power generation efficiency analysis and evaluation method | |
| Yun et al. | Research on fault diagnosis of photovoltaic array based on random forest algorithm | |
| CN117634742A (en) | Distributed photovoltaic running state evaluation method | |
| CN112505518B (en) | Method, device and system for detecting dust accumulation of photovoltaic string | |
| Tella et al. | Deep learning system for defect classification of solar panel cells | |
| CN117332920A (en) | New energy station operation fault evolution analysis method | |
| Li et al. | Research and application of photovoltaic power station on-line hot spot detection operation and maintenance system based on unmanned aerial vehicle infrared and visible light detection | |
| CN116433217A (en) | Distributed photovoltaic power generation management method and system | |
| Zhang et al. | Inspection and classification system of photovoltaic module defects based on UAV and thermal imaging | |
| CN116089790A (en) | Calculation method and device for generating capacity loss of photovoltaic module and electronic equipment | |
| CN116131460A (en) | Photovoltaic Fang Zhenfa electric energy deviation anomaly analysis method | |
| US20240030866A1 (en) | System for monitoring under-performance of solar power plant | |
| Tang et al. | Module defect detection and diagnosis for intelligent maintenance of solar photovoltaic plants: Techniques, systems and perspectives | |
| CN116938134A (en) | Photovoltaic power station shielding monitoring method based on curve similarity | |
| CN115293525A (en) | Intelligent photovoltaic power station performance evaluation system | |
| CN111711417B (en) | Method for diagnosing abnormal power generation amount in 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 |