A photovoltaic power station operation fault detection system based on data collection and analysis

Abstract

The present application belongs to the field of photovoltaic fault detection, and relates to data analysis technology, and is used for solving the problem that the prior art cannot generate targeted operation and maintenance decisions in combination with overall operation state evaluation results, in particular to a photovoltaic power station operation fault detection system based on data collection and analysis, which comprises a regional detection module, an operation and maintenance evaluation module and an operation and maintenance analysis module connected in sequence, and the regional detection module, the operation and maintenance evaluation module and the operation and maintenance analysis module are all in communication connection with a database; the regional detection module is used for performing regional detection analysis on the photovoltaic power station; the present application realizes comprehensive detection and intelligent operation and maintenance of the operation state of the photovoltaic power station, through regional division and multi-parameter collection, the system can accurately locate the fault position and type, and the periodic evaluation mechanism enables the system to capture the cumulative abnormal trend, and overall, the system significantly improves the operation reliability of the photovoltaic power station and provides strong support for the intelligent development of the photovoltaic industry.

Description

TECHNICAL FIELD

[0001] The application belongs to the field of photovoltaic fault detection, and relates to a data analysis technique, in particular to a photovoltaic power station operation fault detection system based on data collection and analysis. BACKGROUND

[0002] Traditional photovoltaic power station operation and maintenance mainly relies on manual inspection and regular maintenance, which is low in efficiency, high in cost and difficult to find hidden faults, and the photovoltaic power station operation fault detection system collects photovoltaic power station operation data comprehensively and in real time, uses big data, Internet of Things and artificial intelligence technology, and constructs an intelligent and automatic fault detection and diagnosis platform.

[0003] The patent for invention with publication number CN118944593B discloses a photovoltaic power station fault detection method based on a knowledge graph, which realizes the conversion of heterogeneous time series data into structured graph data by constructing a knowledge graph, constructs a graph neural network model according to the knowledge graph, learns node features, generates node embedding representation, establishes a fault detection model, and realizes fault identification through link prediction technology, so that the system can identify potential faults in the early stage, reduce photovoltaic power station downtime, and improve operation efficiency; however, the method cannot evaluate and analyze the overall operation state according to periodic detection results, and cannot generate targeted operation and maintenance decisions combined with the overall operation state evaluation results, resulting in low photovoltaic power station operation and maintenance efficiency, and hidden risks accumulated by various detection parameters in a period of time cannot be fed back.

[0004] In view of the above technical problems, the present application provides a solution. SUMMARY

[0005] The application aims to provide a photovoltaic power station operation fault detection system based on data collection and analysis, which can solve the problem that the prior art cannot generate targeted operation and maintenance decisions combined with overall operation state evaluation results.

[0006] The technical problem to be solved by the application is how to provide a photovoltaic power station operation fault detection system based on data collection and analysis, which can generate targeted operation and maintenance decisions combined with overall operation state evaluation results.

[0007] The object of the application can be achieved by the following technical solutions.

[0008] A photovoltaic power station operation fault detection system based on data collection and analysis, comprising a regional detection module, an operation and maintenance evaluation module and an operation and maintenance analysis module connected in sequence, wherein the regional detection module, the operation and maintenance evaluation module and the operation and maintenance analysis module are in communication connection with a database.

[0009] The region detection module is used for regional detection analysis of the photovoltaic power station: the photovoltaic power station is divided into detection regions i, i=1, 2, …, n, n is a positive integer, sensors are arranged according to the equipment in the detection region and parameters e, e=1, 2, …, m, m is a positive integer, are generated, a detection period is generated, a plurality of detection time points with equal time intervals are set in the detection period, fault detection is performed at the detection time points, and the detection time points are marked as normal time points or abnormal time points;

[0010] The operation and maintenance evaluation module is used for overall operation and maintenance evaluation analysis of the photovoltaic power station: the abnormal performance value and the fault performance value of the detection period are obtained, the sum of the abnormal performance value and the fault performance value is marked as an operation and maintenance demand value, and whether the overall operation state of the photovoltaic power station in the detection period meets the requirements is determined through the operation and maintenance demand value;

[0011] The operation and maintenance analysis module is used for operation and maintenance decision analysis of the photovoltaic power station.

[0012] Further, the specific process of fault detection at the detection time point includes: collecting the value of parameter e in detection region i at the detection time point and marking it as a collection value CJie, calling the standard value BZie corresponding to parameter e, marking the absolute value of the difference between the collection value CJie and the standard value BZie as the detection value JCie of parameter e, and marking the detection region as a normal region or an abnormal region through the detection value JCie.

[0013] Further, the specific process of marking the detection region as a normal region or an abnormal region includes: calling the detection threshold JCed of parameter e through the database, comparing the detection value JCie of each parameter e in the detection region i with the corresponding detection threshold JCed: if all detection values JCie are less than the corresponding detection threshold JCed, it is determined that the fault detection result of the detection region meets the requirements, and the corresponding detection region is marked as a normal region; otherwise, it is determined that the fault detection result of the detection region does not meet the requirements, the corresponding detection region is marked as an abnormal region, a fault handling signal is generated, and the fault handling signal is sent to the mobile terminal of the management personnel.

[0014] Further, the specific process of marking the detection time point as a normal time point or an abnormal time point includes: if all detection regions are marked as normal regions, the corresponding detection time point is marked as a normal time point; otherwise, the corresponding detection time point is marked as an abnormal time point.

[0015] Further, the acquisition process of the abnormal performance value and the fault performance value comprises: marking the ratio of the number of abnormal regions to the number of normal regions at the detection time point as an abnormal coefficient, marking the maximum value of the abnormal coefficients at all detection time points in the detection period as the abnormal performance value, and marking the ratio of the number of marked abnormal time points to the number of marked normal time points in the detection period as the fault performance value.

[0016] Further, the specific process of determining whether the overall operation state of the photovoltaic power station in the detection period meets the requirements comprises: calling the operation and maintenance demand threshold value through the database, comparing the operation and maintenance demand value with the operation and maintenance demand threshold value, if the operation and maintenance demand value is less than the operation and maintenance demand threshold value, determining that the overall operation state of the photovoltaic power station in the detection period meets the requirements and does not have the operation and maintenance feature, generating an operation and maintenance analysis signal and sending the operation and maintenance analysis signal to the operation and maintenance analysis module, and if the operation and maintenance demand value is greater than or equal to the operation and maintenance demand threshold value, determining that the overall operation state of the photovoltaic power station in the detection period does not meet the requirements and has the operation and maintenance feature, generating an operation and maintenance analysis signal and sending the operation and maintenance analysis signal to the operation and maintenance analysis module.

[0017] Further, the specific process of the operation and maintenance analysis module performing operation and maintenance decision analysis on the photovoltaic power station comprises: acquiring a decision coefficient of the detection period, acquiring a decision threshold value through the database, comparing the decision coefficient with the decision threshold value, if the decision coefficient is less than the decision threshold value, generating a comprehensive maintenance signal and sending the comprehensive maintenance signal to the mobile terminal of the management personnel, and if the decision coefficient is greater than or equal to the decision threshold value, marking the L1 parameters e with the maximum value of the over-standard performance value as optimization objects, generating a key optimization signal and sending the key optimization signal and the optimization objects to the mobile terminal of the management personnel.

[0018] Further, the acquisition process of the decision coefficient of the detection period comprises: marking the parameters e with the detection value JCie at the abnormal time point not less than the corresponding detection threshold value JCed as analysis objects, marking the ratio of the detection value JCie to the detection threshold value JCed of the analysis objects at the abnormal time point as the over-standard value of the analysis objects, marking the maximum value of the over-standard values of all parameters e as the over-standard performance value, and performing variance calculation on the over-standard performance values of all parameters e to obtain the decision coefficient.

[0019] The present application has the following advantages:

[0020] The application realizes comprehensive detection and intelligent operation and maintenance of the operation state of the photovoltaic power station, through regional division and multi-parameter acquisition, the system can accurately locate the fault position and type, the periodic evaluation mechanism enables the system to capture the cumulative abnormal trend, instead of relying on single time point data, the quantitative operation and maintenance demand value provides an objective basis for operation and maintenance decision, avoids the subjectivity and hysteresis of human judgment, the targeted operation and maintenance suggestion helps to improve the maintenance efficiency and reduce the operation and maintenance cost, as a whole, the system significantly improves the operation reliability and economic benefit of the photovoltaic power station, and provides strong support for the intelligent development of the photovoltaic industry;

[0021] The application can realize accurate quantitative detection of parameters in each detection area of the photovoltaic power station, by comparing the collected value with the standard value, the detection value is calculated, which provides an objective basis for subsequent judgment of the area state, this method avoids the error caused by human subjective judgment, improves the accuracy and reliability of fault detection, at the same time, since the numerical detection method is adopted, the detection results of different parameters and different areas are comparable, which is convenient for unified evaluation and analysis;

[0022] The application realizes quantitative evaluation of the operation state of the photovoltaic power station, thus, the system can accurately reflect the abnormal and fault conditions of the photovoltaic power station in the detection period, and provide reliable data support for subsequent operation and maintenance decision, this quantitative evaluation method avoids the deviation of subjective judgment, improves the accuracy and reliability of fault detection, at the same time, by separating the calculation of abnormal performance and fault performance, the system can more comprehensively reflect the operation state of the photovoltaic power station, which helps the operation and maintenance personnel to more accurately identify and handle potential problems;

[0023] 4、The application realizes accurate evaluation and targeted operation and maintenance decision of the operation state of the photovoltaic power station, by introducing the comparison mechanism of decision coefficient and decision threshold, the system can automatically judge whether comprehensive maintenance or key optimization is needed according to the actual operation condition, when key optimization is needed, the parameter with the highest over-standard performance value is identified as the optimization object, so that the operation and maintenance work can be concentrated on the most need to improve aspect, this method not only improves the accuracy and efficiency of operation and maintenance, but also effectively reduces the operation and maintenance cost and prolongs the service life of the photovoltaic power station, at the same time, by sending the operation and maintenance information directly to the mobile terminal of the management personnel, quick response and timely processing are realized, which maximizes the downtime and power generation loss of the photovoltaic power station. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to make the technical solutions of the embodiments of the present application or the prior art clearer, the accompanying drawings needed in the embodiments or prior art description will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort on the basis of these drawings.

[0025] Figure 1 System block diagram of the embodiment one of the present application;

[0026] Figure 2 Method flow chart of the embodiment two of the present application. DETAILED DESCRIPTION

[0027] The technical solutions of the present application will be described clearly and completely below in combination with embodiments. Obviously, the described embodiments are only some embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present application.

[0028] In the conventional operation and maintenance process of the existing photovoltaic power station, the mode of relying on manual inspection and regular maintenance has problems of low efficiency and high cost, especially it is difficult to identify hidden faults. Although the fault detection method based on knowledge graph can realize early fault identification through graph neural network, it lacks global evaluation ability for periodic detection data, and cannot generate differentiated operation and maintenance strategies combined with dynamic indicators such as abnormal time point distribution, regional abnormal proportion and parameter exceeding degree, so that the system cannot effectively balance maintenance resource allocation and hidden risk control, causing operation and maintenance response lag and parameter abnormality accumulation.

[0029] For example, in a photovoltaic power station using a traditional detection method, the system can only determine the equipment state based on isolated data at a single time point, and cannot establish a dynamic evaluation model through indicators such as the number of abnormal regions at multiple time points in the detection period, the degree of continuous deviation of parameter detection values from thresholds, etc. When some detection regions have slight parameter exceeding at consecutive multiple time points, the system cannot identify the growth trend of the abnormal coefficient of the region, nor can it associate the difference in abnormal coefficients between different regions with the operation and maintenance priority. At the same time, since no correlation analysis mechanism of the abnormal time point density and the parameter exceeding degree in the detection period is established, the operation and maintenance personnel cannot determine whether to implement comprehensive maintenance or optimize specific parameters, resulting in waste of maintenance resources or failure to eliminate key parameter risks in time.

[0030] If the above problems are not addressed, abnormal patterns and parameter correlation features in periodic monitoring data cannot be effectively extracted. System operation and maintenance decisions will rely on empirical judgment for a long time, making it difficult to avoid accelerated component performance degradation caused by persistent anomalies in local parameters. The accumulation of latent faults may trigger a chain reaction in multiple regions, increasing the risk of overall power plant shutdown. At the same time, repetitive maintenance operations will significantly increase labor and material costs, ultimately affecting the stability and economic benefits of power plant operation.

[0031] Example 1: As Figure 1 As shown, a photovoltaic power plant operation fault detection system based on data acquisition and analysis includes a regional detection module, an operation and maintenance assessment module, and an operation and maintenance analysis module connected in sequence. The regional detection module, the operation and maintenance assessment module, and the operation and maintenance analysis module are all connected to a database.

[0032] The regional detection module is used for regional detection and analysis of photovoltaic power plants. It divides the photovoltaic power plant into detection regions i, i = 1, 2, ..., n, where n is a positive integer. Sensors are deployed according to the equipment within each detection region, and parameters e, e = 1, 2, ..., m, where m is a positive integer, are generated. A detection cycle is generated, and several equally timed detection points are set within the detection cycle. At each detection point, the value of parameter e within detection region i is collected and marked as the collected value CJie. The corresponding standard value BZie for parameter e is retrieved. The absolute value of the difference between the collected value CJie and the standard value BZie is marked as the detection value JCie for parameter e. The detection threshold JC for parameter e is retrieved from the database. The system compares the detection values ​​JCie of all parameters e within detection area i with the corresponding detection threshold JCed. If all detection values ​​JCie are less than the corresponding detection threshold JCed, the fault detection result of the detection area is deemed to meet the requirements, and the corresponding detection area is marked as a normal area. Otherwise, the fault detection result of the detection area is deemed to not meet the requirements, and the corresponding detection area is marked as an abnormal area. A fault handling signal is generated and sent to the mobile terminal of the management personnel. If all detection areas are marked as normal areas, the corresponding detection time point is marked as a normal time point. Otherwise, the corresponding detection time point is marked as an abnormal time point.

[0033] The data acquisition value CJie is obtained in real time by sensors deployed within detection area i, while the standard value BZie is pre-stored in a database based on equipment specifications or historical operating data. The detection value JCie is calculated using absolute value operations to eliminate the influence of positive and negative deviations on the detection results. The detection threshold JCed is set according to different parameter types and equipment tolerance; for example, the current parameter threshold is set to ±5% of the rated value, and the voltage parameter threshold is set to ±3%. Detection area i is divided into n independent areas, with m sensors installed in each area to ensure that the data acquisition coverage density meets the detection accuracy requirements.

[0034] Specifically, after triggering the sensor to collect data at the detection time point, the system automatically retrieves the standard value of the corresponding parameter for comparison. The difference between the collected value and the standard value is quantified by the absolute value to form a comparable detection value. When the detection value exceeds the preset threshold value, it is determined that the device state corresponding to the parameter is abnormal. By comparing the threshold value of all parameters in the region one by one, the comprehensiveness of the abnormal detection is ensured. For example, in the detection region i = 1, the collected value CJ11 of parameter e = 1 is 215V, the standard value BZ11 is 220V, and the detection value JC11 = |215-220| = 5V. If the detection threshold JC1d is 6V, it is determined that the parameter is normal; if the detection threshold JC1d is 4V, the abnormality is triggered. This process replaces manual experience judgment with quantitative calculation, improving the objectivity and response speed of fault detection.

[0035] Among them, the detection threshold of the parameter is pre-stored in the database, and each parameter corresponds to an independent detection threshold. The detection threshold is set according to historical operation data or equipment specifications. The calculation of the detection value is based on the absolute difference between the collected value and the standard value. For example, when the collected value of a parameter is 25 and the standard value is 20, the detection value is 5. The detection values of all parameters in the detection region need to be compared with the corresponding detection threshold one by one. If the detection value of a parameter exceeds the threshold, the abnormality is directly triggered. The generation of the fault handling signal adopts an automatic triggering mechanism. For example, when the detection region is marked as an abnormal region, the system automatically generates a signal containing the abnormal region number and the parameter exceeding the standard, and sends it to the designated terminal through the preset interface.

[0036] Specifically, in actual application, a detection region of a photovoltaic power station can be set, for example, a region containing 10 photovoltaic components. For this detection region, 5 key parameters e are set for detection, including output voltage, output current, surface temperature, inclination angle and dust coverage rate. The detection threshold JCed of these 5 parameters is retrieved from the database, which is: output voltage threshold 300V, output current threshold 8A, surface temperature threshold 60℃, inclination angle threshold 5°, and dust coverage rate threshold 10%.

[0037] At the detection time point, the system collects the actual detection values JCie of the 5 parameters in the detection region, for example: output voltage 295V, output current 7.8A, surface temperature 58℃, inclination angle 3°, and dust coverage rate 8%. Compare these detection values with the corresponding detection thresholds, and find that all detection values are less than the respective thresholds. Therefore, the system determines that the fault detection result of the detection region meets the requirements, and marks the detection region as a normal region.

[0038] The operation and maintenance evaluation module is used for overall operation and maintenance evaluation analysis of the photovoltaic power station: the ratio of the number of abnormal regions to the number of normal regions at the detection time point is marked as an abnormal coefficient, the maximum value of the abnormal coefficients at all detection time points in the detection period is marked as an abnormal performance value, the ratio of the number of abnormal time points to the number of normal time points in the detection period is marked as a fault performance value, and the sum of the abnormal performance value and the fault performance value is marked as an operation and maintenance demand value. The operation and maintenance demand threshold is called through the database, and the operation and maintenance demand value is compared with the operation and maintenance demand threshold: if the operation and maintenance demand value is less than the operation and maintenance demand threshold, it is determined that the overall operation state of the photovoltaic power station in the detection period meets the requirements and does not have the operation and maintenance characteristics; if the operation and maintenance demand value is greater than or equal to the operation and maintenance demand threshold, it is determined that the overall operation state of the photovoltaic power station in the detection period does not meet the requirements and has the operation and maintenance characteristics, and an operation and maintenance analysis signal is generated and sent to the operation and maintenance analysis module.

[0039] The abnormal coefficient dynamically reflects the abnormality degree of a single detection time point through the ratio of the number of abnormal regions to the number of normal regions, the abnormal performance value captures the most serious abnormal state by selecting the maximum value of the abnormal coefficients in the detection period, and the fault performance value quantifies the persistence of fault occurrence through the ratio of the abnormal time points to the normal time points.

[0040] Specifically, in the detection period, the abnormal coefficient is calculated according to the number of abnormal regions and normal regions at each detection time point, the maximum value of the abnormal coefficient is used to represent the most serious abnormal situation in the period, and the ratio of the abnormal time points to the normal time points reflects the frequency of fault occurrence. The operation and maintenance demand value is obtained by adding the abnormal performance value and the fault performance value, which can consider the influence of abnormal peak value and fault persistence on the overall operation state. For example, if the maximum value of the abnormal coefficient in a detection period is 0.5, the ratio of the abnormal time points to the normal time points is 0.3, and the operation and maintenance demand value is 0.8, it can be determined whether operation and maintenance is needed by comparing with the preset threshold. This method quantifies the abnormality degree and fault frequency, improves the objectivity and accuracy of operation and maintenance evaluation, and provides a reliable basis for subsequent operation and maintenance decision.

[0041] The operation and maintenance demand threshold is obtained by training historical operation data and stored in the preset threshold table of the database. The comparison of the operation and maintenance demand value and the operation and maintenance demand threshold adopts a numerical comparison algorithm, which realizes the judgment of numerical size relationship through computer program. The generation of the operation and maintenance analysis signal is executed by the communication module, and the signal transmission protocol adopts the MQTT Internet of Things communication protocol.

[0042] Specifically, the operation and maintenance requirement threshold is input to the comparison unit as a judgment basis through a database interface call. The operation and maintenance requirement value is obtained by adding the abnormal performance value and the fault performance value, and is input to the comparison unit for numerical comparison. When the operation and maintenance requirement value exceeds the threshold value, the comparison unit triggers a signal generation instruction, and the communication module generates an operation and maintenance analysis signal containing a timestamp and a power station number according to the instruction. For example, when the operation and maintenance requirement threshold is set to 0.8 and the operation and maintenance requirement value calculated in the detection period is 0.85, it is determined that the power station operation state does not meet the requirements, and an operation and maintenance analysis signal containing the power station ID and the detection period number is generated. The signal is transmitted to the operation and maintenance analysis module through the wireless network, triggering the subsequent decision analysis process, and realizing the automatic processing from state evaluation to operation and maintenance decision.

[0043] The operation and maintenance analysis module is used for operation and maintenance decision analysis of the photovoltaic power station: parameters e with abnormal time point detection values JCie not less than corresponding detection thresholds JCed are marked as analysis objects, a ratio of the detection value JCie of the analysis object at the abnormal time point to the detection threshold JCed is marked as an over-standard value of the analysis object, a maximum value of the over-standard values corresponding to all parameters e is marked as an over-standard performance value, a decision coefficient is obtained by performing variance calculation on the over-standard performance values of all parameters e, a decision threshold is obtained through a database, and the decision coefficient and the decision threshold are compared: if the decision coefficient is less than the decision threshold, a comprehensive maintenance signal is generated and sent to the mobile terminal of the management personnel; and if the decision coefficient is greater than or equal to the decision threshold, L1 parameters e with the maximum over-standard performance value are marked as optimization objects, a key optimization signal is generated and sent to the mobile terminal of the management personnel together with the optimization objects.

[0044] The decision coefficient reflects the over-standard fluctuation difference of different parameters through variance calculation, and the greater the variance, the more significant the difference in over-standard degree between parameters. The decision threshold is a critical point for switching maintenance strategies and is obtained by training historical operation and maintenance data. L1 is a preset positive integer for controlling the number of optimization objects, and its value is dynamically adjusted according to the size of the power station. The key optimization signal carries parameter identification information, enabling the maintenance personnel to quickly locate the key parameters.

[0045] Specifically, after the over-standard performance values of each parameter in the detection period are calculated, the variance operation is used to quantify the discreteness of the over-standard degree of the parameter group. When the variance value is lower than a preset threshold, it indicates that the over-standard fluctuation of the parameter group is small, and at this time, the comprehensive maintenance process is triggered to repair all parameters uniformly. When the variance value exceeds the threshold, it indicates that some parameters significantly deviate from the standard, and at this time, the system automatically extracts the parameters in the top L1 positions of the over-standard performance value ranking as optimization objects. For example, when L1 = 3 is set for a power station, the system will screen out the three parameters with the most serious over-standard to generate an optimization list. This mechanism realizes intelligent switching of the maintenance strategy through analysis of data discreteness, while optimizing the allocation of maintenance resources and ensuring system stability.

[0046] The parameter whose abnormal time point detection value is not less than the detection threshold value is marked as an analysis object, and in specific implementation, all parameters at the abnormal time point are traversed to filter out parameters exceeding or equal to the detection threshold value as the analysis object. The ratio of the detection value of the analysis object to the detection threshold value is marked as an over-standard value. For example, when the detection value is 1.5 times the detection threshold value, the over-standard value is 1.5. The maximum value of the over-standard value corresponding to all parameters is marked as an over-standard performance value. In specific implementation, the over-standard value of each parameter at all abnormal time points is counted, and the maximum value is taken as the over-standard performance value of the parameter. The variance of the over-standard performance values of all parameters is calculated, for example, by calculating the average of the squares of the deviations of the over-standard performance values from the average value, to obtain the decision coefficient in the form of variance.

[0047] Specifically, in the detection period, first, parameters whose detection values at all abnormal time points exceed or equal to the detection threshold value are identified and marked as analysis objects. For each analysis object, the ratio of its detection value at the abnormal time point to the corresponding detection threshold value is calculated to obtain an over-standard value. The over-standard value of each parameter at all abnormal time points is counted, and the maximum value is extracted as the over-standard performance value of the parameter. After collecting the over-standard performance values of all parameters, the variance of these values is calculated, and the variance result is the decision coefficient. Through variance calculation, the dispersion degree of the over-standard performance values of different parameters can be reflected, and the greater the variance, the more obvious the fluctuation difference between parameters. When the decision coefficient is less than the decision threshold value, it indicates that the fluctuation difference between parameters is small, and comprehensive maintenance is required; when the decision coefficient is greater than or equal to the decision threshold value, it indicates that the fluctuation of some parameters is significant, and the parameter with the maximum over-standard performance value needs to be optimized first. In this way, the fluctuation of parameters is analyzed through variance analysis, and the pertinence of the optimization maintenance strategy is improved.

[0048] Embodiment two: as shown in the following table, a photovoltaic power station operation fault detection method based on data acquisition analysis includes the following steps: Figure 2

[0049] Step one: regional detection analysis of the photovoltaic power station: generate a detection period, set a plurality of time intervals equal detection time points in the detection period, and obtain the detection value JCie of the parameter e in the detection region i at the detection time point;

[0050] Step two: overall operation and maintenance evaluation analysis of the photovoltaic power station: obtain the operation and maintenance demand value of the detection period, and determine whether the overall operation state of the photovoltaic power station in the detection period meets the requirements through the operation and maintenance demand value;

[0051] Step three: operation and maintenance decision analysis of the photovoltaic power station: obtain the decision coefficient of the detection period, and generate a targeted operation and maintenance decision signal through the decision coefficient.

[0052] ​The application discloses a photovoltaic power station operation fault detection system based on data collection and analysis.

[0053] The above merely illustrates and describes the structure of the application, and those skilled in the art can make various modifications, supplements or substitutions to the described specific embodiments or adopt similar ways to replace, as long as the modifications, supplements or substitutions do not deviate from the structure of the application or exceed the range defined by the claims, and the modifications, supplements or substitutions should belong to the protection range of the application.

[0054] In the description of the present specification, the description referring to the terms "one embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in connection with the embodiment or example are contained in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0055] The preferred embodiments of the application disclosed above are only used to help explain the application. The preferred embodiments do not describe all the details and limit the application to the specific embodiments. Obviously, according to the content of the present specification, many modifications and changes can be made. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the application, so that those skilled in the art can well understand and utilize the application. The application is limited by the claims and the entire range and equivalents thereof.

Claims

1. A photovoltaic power plant operation fault detection system based on data collection analysis, characterized in that, The method comprises a region detection module, an operation and maintenance evaluation module and an operation and maintenance analysis module connected in sequence, and the region detection module, the operation and maintenance evaluation module and the operation and maintenance analysis module are in communication connection with a database. The region detection module is used for performing regional detection analysis on the photovoltaic power station: the photovoltaic power station is divided into detection regions i, i=1, 2, …, n, n being a positive integer, sensors are arranged according to the equipment in the detection regions and parameters e, e=1, 2, …, m, m being a positive integer, are generated, a detection period is generated, a plurality of detection time points with equal time intervals are set in the detection period, fault detection is performed at the detection time points and the detection time points are marked as normal time points or abnormal time points; The operation and maintenance evaluation module is used for performing overall operation and maintenance evaluation analysis on the photovoltaic power station: abnormal performance values and fault performance values of the detection period are obtained, a sum value of the abnormal performance values and the fault performance values is marked as an operation and maintenance demand value, and whether the overall operation state of the photovoltaic power station in the detection period meets the requirements is determined through the operation and maintenance demand value; The operation and maintenance analysis module is used for performing operation and maintenance decision analysis on the photovoltaic power station; The process of obtaining the abnormal performance values and the fault performance values comprises: a ratio of the number of abnormal regions to the number of normal regions at the detection time points is marked as an abnormal coefficient, a maximum value of the abnormal coefficients of all the detection time points in the detection period is marked as the abnormal performance value, and a ratio of the number of marked abnormal time points to the number of marked normal time points in the detection period is marked as the fault performance value; The specific process of determining whether the overall operation state of the photovoltaic power station in the detection period meets the requirements comprises: an operation and maintenance demand threshold value is called through the database, the operation and maintenance demand value is compared with the operation and maintenance demand threshold value: if the operation and maintenance demand value is less than the operation and maintenance demand threshold value, it is determined that the overall operation state of the photovoltaic power station in the detection period meets the requirements and has no operation and maintenance characteristics; if the operation and maintenance demand value is greater than or equal to the operation and maintenance demand threshold value, it is determined that the overall operation state of the photovoltaic power station in the detection period does not meet the requirements and has operation and maintenance characteristics, an operation and maintenance analysis signal is generated and sent to the operation and maintenance analysis module; The specific process of the operation and maintenance analysis module performing operation and maintenance decision analysis on the photovoltaic power station comprises: a decision coefficient of the detection period is obtained, a decision threshold value is obtained through the database, the decision coefficient is compared with the decision threshold value: if the decision coefficient is less than the decision threshold value, a comprehensive maintenance signal is generated and sent to a mobile terminal of a management personnel; if the decision coefficient is greater than or equal to the decision threshold value, L1 parameters e with the largest over-standard performance value are marked as optimization objects, a key optimization signal and the optimization objects are generated and sent to the mobile terminal of the management personnel. The obtaining process of the decision coefficient of the detection period includes: marking the parameter e whose abnormal time point detection value JCie is not less than the corresponding detection threshold JCed as an analysis object, marking the ratio of the detection value JCie of the analysis object at the abnormal time point to the detection threshold JCed as an over-standard value of the analysis object, marking the maximum value of the over-standard values of all parameters e as an over-standard performance value, and calculating the variance of the over-standard performance values of all parameters e to obtain the decision coefficient.

2. The photovoltaic power plant operation fault detection system based on data collection analysis according to claim 1, characterized in that, The specific process of fault detection at the detection time point includes: collecting the value of the parameter e in the detection area i at the detection time point and marking it as a collection value CJie, calling the standard value BZie corresponding to the parameter e, marking the absolute value of the difference between the collection value CJie and the standard value BZie as the detection value JCie of the parameter e, and marking the detection area as a normal area or an abnormal area through the detection value JCie.

3. The photovoltaic power plant operation fault detection system based on data collection analysis according to claim 2, characterized in that, The specific process of marking the detection area as a normal area or an abnormal area includes: calling the detection threshold JCed of the parameter e through the database, comparing the detection value JCie of all parameters e in the detection area i with the corresponding detection threshold JCed respectively, if all detection values JCie are less than the corresponding detection threshold JCed, determining that the fault detection result of the detection area meets the requirements, marking the corresponding detection area as a normal area, otherwise, determining that the fault detection result of the detection area does not meet the requirements, marking the corresponding detection area as an abnormal area, generating a fault handling signal and sending the fault handling signal to the mobile terminal of the management personnel.

4. The photovoltaic power plant operation fault detection system based on data collection analysis according to claim 3, characterized in that, The specific process of marking the detection time point as a normal time point or an abnormal time point includes: if all detection areas are marked as normal areas, marking the corresponding detection time point as a normal time point, otherwise, marking the corresponding detection time point as an abnormal time point.

Images