Method and system for detecting abnormal state of photovoltaic power station equipment

Abstract

The invention discloses a photovoltaic power station equipment abnormal state detection method and system, and relates to the technical field of photovoltaic power station detection, and the method comprises the steps: obtaining photovoltaic module operation data, environment temperature data and historical operation data, and generating a monitoring data set; and generating a correction factor based on the real-time illumination intensity data and the historical data, performing environment classification by combining the environment temperature and the real-time illumination intensity, and matching a corresponding basic threshold. And calculating the temperature deviation degree between the real-time temperature and the historical temperature mean value, dynamically adjusting a basic threshold value in combination with a correction factor, and screening potential abnormal data points. And taking a component corresponding to the potential abnormal data point as a target component, adjusting a data acquisition neighborhood range according to real-time illumination intensity change, and calculating a temperature slope and a power change rate of the target component. And determining adjacent components of the target component, calculating a hot spot effect degree mean value and a standard deviation, and when the mean value exceeds an abnormal data screening threshold value and the standard deviation is lower than a preset threshold value, judging that systematic abnormality occurs.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power station detection, and particularly to a method and system for detecting abnormal states of photovoltaic power station equipment. Background Art

[0002] In the actual operation of a photovoltaic power station, the detection of abnormal states of photovoltaic modules is a key link to ensure power generation efficiency and equipment safety. The operating environment of a photovoltaic power station has significant dynamic change characteristics, including seasonal temperature fluctuations, sudden changes in light intensity caused by short-term weather, and efficiency decay and aging differences of modules with the operation duration.

[0003] Currently, traditional methods for detecting abnormal conditions of photovoltaic power station equipment mostly use fixed threshold judgment or simple statistical analysis. These methods often do not fully consider the influence of environmental factors (such as light intensity and environmental temperature) on equipment operating parameters, resulting in easy misjudgment or missed judgment in different environments such as high temperature and strong light, low temperature and weak light. Summary of the Invention

[0004] To solve the technical problem of insufficient environmental adaptability of existing methods for detecting abnormal conditions of photovoltaic power station equipment, the present invention provides a method and system for detecting abnormal states of photovoltaic power station equipment.

[0005] The technical solution adopted by the present invention is as follows: In a first aspect of the present application, a method for detecting abnormal states of photovoltaic power station equipment is provided, including the following steps: S1: Obtain the operation data, environmental temperature data, and historical operation data of the photovoltaic module to generate a monitoring data set; wherein, the operation data includes the real-time temperature data, real-time power data, and real-time light intensity data of the photovoltaic module; the historical operation data includes the historical temperature data, historical power output data, and corresponding historical light intensity data of the photovoltaic module since it was put into use.

[0006] S2: Generate a correction factor based on the real-time light intensity data and historical data; classify the current environment based on the environmental temperature data and real-time light intensity data to obtain multiple environment categories, and match the basic threshold corresponding to each environment category from a pre-stored environmental category threshold library.

[0007] S3: Calculate the temperature deviation degree between the real-time temperature data and the average value of the historical temperature data of the photovoltaic module; dynamically adjust the basic threshold based on the temperature deviation degree and the correction factor to generate an abnormal data screening threshold; screen out potential abnormal data points from the monitoring data set based on the abnormal data screening threshold.

[0008] S4: Using the component corresponding to the potential abnormal data point as the target component, adjust the data acquisition neighborhood range according to the change in real-time light intensity data. Within the adjusted data acquisition neighborhood range, calculate the temperature slope and power change rate of the target component.

[0009] S5: Determine the neighboring components of the target component within the adjusted data acquisition neighborhood range, calculate the mean and standard deviation of the hot spot effect degree of the neighboring components. When the mean exceeds the abnormal data screening threshold and the standard deviation is lower than the preset fluctuation dynamic threshold, it is determined as a systematic anomaly.

[0010] Preferably, the generation of the correction factor based on real-time light intensity data and historical data includes the following: Normalize the real-time light intensity data based on the historical minimum light intensity data and historical maximum light intensity data of the current season to obtain the normalized value of the real-time light intensity data; based on the historical power output data and the corresponding historical light intensity data, construct a photovoltaic component efficiency decay model through polynomial fitting to determine the component aging coefficient reflecting the aging degree of the photovoltaic component; combine the normalized value of the real-time light intensity data with the component aging coefficient to generate the correction factor.

[0011] Preferably, the classification of the current environment based on ambient temperature data and real-time light intensity data results in multiple environment categories including the following: When the ambient temperature data is higher than the preset high temperature threshold and the real-time light intensity data is higher than the preset strong light threshold, it is classified as a high temperature and strong light scenario; when the ambient temperature data is lower than the preset low temperature threshold and the real-time light intensity data is lower than the preset weak light threshold, it is classified as a low temperature and weak light scenario; when the change rate of the real-time light intensity data within a preset time period is greater than the preset fluctuation threshold and the ambient temperature data is within the preset temperature range, it is classified as a cloudy and fluctuating scenario.

[0012] Preferably, the calculation of the temperature deviation degree between the real-time temperature data and the mean of the historical temperature data of the photovoltaic component includes the following: Calculate the absolute value of the difference between the real-time temperature data and the mean within the same light intensity interval of the historical temperature data as the temperature deviation degree.

[0013] Preferably, the dynamic adjustment of the basic threshold based on the temperature deviation degree and the correction factor to generate the abnormal data screening threshold includes the following: For the basic threshold corresponding to each matched environment category, set the first weight coefficient corresponding to the normalized value of the real-time light intensity data, the second weight coefficient corresponding to the component aging coefficient, and the third weight coefficient corresponding to the temperature deviation degree. Multiply the normalized value of the real-time light intensity data by the first weight coefficient, the component aging coefficient by the second weight coefficient, and the temperature deviation degree by the third weight coefficient to obtain their respective weighted values; sum the weighted values to obtain the adjustment coefficient; If the adjustment coefficient is greater than zero, then the adjusted threshold is obtained by adding the product of the adjustment coefficient and the preset positive adjustment ratio to the basic threshold; if the adjustment coefficient is less than zero, then the adjusted threshold is obtained by subtracting the product of the absolute value of the adjustment coefficient and the preset negative adjustment ratio from the basic threshold. The adjusted threshold is the abnormal data screening threshold; among them, the first weight coefficient, the second weight coefficient, the third weight coefficient, the positive adjustment ratio, and the negative adjustment ratio are all preset constants.

[0014] Preferably, taking the component corresponding to the potential abnormal data point as the target component, adjusting the data acquisition neighborhood range according to the change of the real-time light intensity data, and calculating the temperature slope and power change rate of the target component within the adjusted data acquisition neighborhood range includes the following: Taking the photovoltaic component corresponding to the potential abnormal data point as the target component, and calculating the change rate of the corresponding light intensity in real time; when the change rate of the light intensity is greater than or equal to the preset threshold, reducing the data acquisition neighborhood range centered on the target component; when the change rate of the light intensity is less than the preset threshold, restoring the default data acquisition neighborhood range. Based on the adjusted data acquisition neighborhood range, extracting the temperature data and power data of the target component within the adjusted data acquisition neighborhood range, and calculating the temperature slope and power change rate of the target component respectively based on the temperature data and power data.

[0015] Preferably, calculating the mean and standard deviation of the hot spot effect degree of the adjacent components includes the following: Within the adjusted data acquisition neighborhood range, obtaining the temperature data and power data of the adjacent components of each target component; respectively calculating the temperature slope and power change rate of each adjacent component; calculating the hot spot effect degree of each adjacent component according to the temperature slope, power change rate of each adjacent component and the preset hot spot effect degree calculation model; counting the hot spot effect degrees of all adjacent components, and calculating their mean and standard deviation.

[0016] The second aspect of the present application provides a photovoltaic power station equipment abnormal state detection system, which is applied to the above-mentioned photovoltaic power station equipment abnormal state detection method, and includes: A data acquisition module, which is used to acquire the operation data, ambient temperature data and historical operation data of the photovoltaic components, and generate a monitoring data set; among them, the operation data includes the real-time temperature data, real-time power data and real-time light intensity data of the photovoltaic components; the historical operation data includes the historical temperature data, historical power output data and corresponding historical light intensity data of the photovoltaic components since they were put into use.

[0017] Correction factor and threshold matching module, which is used to generate a correction factor based on real-time light intensity data and historical data; classify the current environment based on environmental temperature data and real-time light intensity data to obtain multiple environmental categories, and match the basic threshold corresponding to each environmental category from a pre-stored environmental category threshold library.

[0018] Threshold adjustment and abnormal data screening module, which is used to calculate the temperature deviation degree between real-time temperature data and the average value of the historical temperature data of the photovoltaic module; dynamically adjust the basic threshold based on the temperature deviation degree and the correction factor to generate an abnormal data screening threshold; screen out potential abnormal data points from the monitoring data set based on the abnormal data screening threshold.

[0019] Target component parameter calculation module, which is used to take the component corresponding to the potential abnormal data point as the target component, adjust the data acquisition neighborhood range according to the change of real-time light intensity data, and calculate the temperature slope and power change rate of the target component within the adjusted data acquisition neighborhood range.

[0020] Systematic abnormality determination module, which is used to determine the neighboring components of the target component within the adjusted data acquisition neighborhood range, calculate the mean and standard deviation of the hot spot effect degree of the neighboring components, and when the mean exceeds the abnormal data screening threshold and the standard deviation is lower than the preset fluctuation dynamic threshold, it is determined as a systematic abnormality.

[0021] The beneficial effects of the present invention are at least one of the following: By classifying the environment through environmental temperature and light intensity, and combining the dynamic threshold adjustment of the correction factor and the temperature deviation degree, the detection threshold can adaptively change according to real-time environmental characteristics and component aging status, effectively reducing the false positive rate and false negative rate in different environmental scenarios.

[0022] Adjusting the data acquisition neighborhood range according to the change of real-time light intensity data can more accurately collect data of the target component under different light conditions. When the light intensity changes, the data acquisition neighborhood range is timely reduced or restored, so that the collected data can better reflect the true operating state of the target component, which helps to discover potential abnormal situations.

[0023] By calculating the mean and standard deviation of the hot spot effect degree of the neighboring components, and combining the abnormal data screening threshold and the fluctuation dynamic threshold for systematic abnormality determination. This method based on the correlation analysis of neighboring components can identify abnormal situations from the perspective of the cluster, effectively distinguish accidental abnormalities of individual components and potential problems of the entire system, and helps to discover and handle systematic abnormalities that may affect the operation of the entire photovoltaic power station in advance. Description of the Drawings

[0024] Figure 1 Schematic flowchart of the method according to the first embodiment of the present invention; Figure 2 System block diagram of the second embodiment of the present invention. Detailed implementation manners

[0025] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0026] Currently, traditional abnormal detection methods for photovoltaic power station equipment mostly use fixed threshold judgment or simple statistical analysis. These methods often do not fully consider the influence of environmental factors (such as light intensity, environmental temperature) on equipment operation parameters, resulting in the technical problem of insufficient environmental adaptability in existing abnormal detection methods for photovoltaic power station equipment.

[0027] To solve the above technical problems, the first embodiment provides a method for detecting the abnormal state of photovoltaic power station equipment, as Figure 1 shown, including the following steps: S1: Obtain the operation data, environmental temperature data, and historical operation data of the photovoltaic module to generate a monitoring data set; wherein, the operation data includes the real-time temperature data, real-time power data, and real-time light intensity data of the photovoltaic module; the historical operation data includes the historical temperature data, historical power output data, and corresponding historical light intensity data of the photovoltaic module since it was put into use.

[0028] It should be noted that the abnormal state of the photovoltaic module needs to be comprehensively determined through multi-dimensional data (real-time operation parameters, historical performance data, environmental variables), and single data cannot fully reflect the equipment state. Therefore, it is necessary to construct a monitoring data set containing real-time and historical data.

[0029] For reference, the surface temperature of the photovoltaic module is collected in real time by an integrated thermocouple sensor or an infrared temperature sensor, and the sampling frequency is 1 time per minute; the power data is obtained through the built-in power module of the inverter, including the DC-side and AC-side powers, and the time stamp is recorded synchronously; the light intensity is measured by the total radiation sensor installed in the power station; the environmental temperature data comes from the temperature sensor of the weather station, and the distance from the position of the component temperature sensor is not more than 5 meters to avoid interference from local heat island effects.

[0030] Exemplarily, the historical operation data is stored in a distributed database, indexed by "component number + time stamp", and includes all temperature, power, and corresponding light intensity data since the component was put into operation, and the storage period is more than 10 years. In the detailed implementation manners, the historical operation data can be preprocessed, abnormal values (such as data points with power suddenly changing to 0 or exceeding 120% of the rated value) can be removed, and the sliding average method (window size 10 minutes) can be used to smooth the noise.

[0031] Build a multi-dimensional monitoring data set that includes real-time and historical data, which can provide multi-dimensional data support for environmental classification, threshold adjustment, and abnormal feature extraction, and avoid misjudgment caused by data loss or noise.

[0032] S2: Generate a correction factor based on real-time light intensity data and historical data; classify the current environment based on environmental temperature data and real-time light intensity data to obtain multiple environmental categories, and match the basic threshold corresponding to each environmental category from the pre-stored environmental category threshold library.

[0033] It should be noted that the performance of photovoltaic modules is significantly affected by light intensity and aging degree. Fixed thresholds cannot adapt to dynamic environments and individual differences, and adaptive adjustment of thresholds needs to be achieved through correction factors and environmental classification.

[0034] In a possible implementation manner, the generating a correction factor based on real-time light intensity data and historical data includes the following: Normalize the real-time light intensity data based on the historical minimum light intensity data and historical maximum light intensity data of the current season to obtain the normalized value of the real-time light intensity data; construct a photovoltaic module efficiency decay model through polynomial fitting based on historical power output data and corresponding historical light intensity data, and determine the component aging coefficient reflecting the aging degree of the photovoltaic module; combine the normalized value of the real-time light intensity data with the component aging coefficient to generate a correction factor.

[0035] Exemplarily, divide the historical light intensity data by the current season (spring / summer / autumn / winter), and calculate the minimum historical light intensity data within this season and the historical maximum light intensity data .

[0036] Normalization formula: , where is the real-time light intensity data, represents the normalized value of the real-time light intensity data, and the range is [0,1].

[0037] Exemplarily, normalize the historical power data and the corresponding light intensity data (normalize the power to a percentage of the rated power), and use quadratic polynomial fitting , where is the fitting coefficient.

[0038] Exemplarily, the aging coefficient is defined as the slope change rate of the fitting curve in the t-th year, reflecting the attenuation degree of the component efficiency over time. The correction factor is a vector , for subsequent threshold adjustment. The correction factor combines the illumination normalization value and the aging coefficient to form a comprehensive representation of the environment and individual characteristics.

[0039] In a possible implementation, classify the current environment based on the ambient temperature data and the real-time illumination intensity data to obtain multiple environment categories including the following: When the ambient temperature data is higher than the preset high-temperature threshold and the real-time illumination intensity data is higher than the preset strong-light threshold, it is classified as a high-temperature and strong-light scenario; when the ambient temperature data is lower than the preset low-temperature threshold and the real-time illumination intensity data is lower than the preset weak-light threshold, it is classified as a low-temperature and weak-light scenario; when the change rate of the real-time illumination intensity data within a preset time period is greater than the preset fluctuation threshold and the ambient temperature data is within a preset temperature range, it is classified as a cloudy and fluctuating scenario.

[0040] Exemplarily, high-temperature and strong-light scenario: the ambient temperature data T > 40 °C and the real-time illumination intensity data > 1000 W / m 2 ; where T represents the ambient temperature data.

[0041] Low-temperature and weak-light scenario: the ambient temperature data T < -10 °C and the real-time illumination intensity data < 200 W / m 2 ; Cloudy and fluctuating scenario: the real-time illumination intensity data The change rate within 5 minutes > 100 W / m / min and the ambient temperature data 10 °C ≤ T ≤ 30 °C. Where T represents the ambient temperature data.

[0042] Exemplarily, in the basic threshold library, store the basic thresholds for different environment categories, for example: The basic threshold for temperature anomaly in the high-temperature and strong-light scenario is 75 °C (the safety upper limit of the component surface temperature); The basic threshold for power anomaly in the low-temperature and weak-light scenario is 15% of the rated power. The threshold library is stored in the system configuration file and supports offline update. The environment is divided into three typical scenarios: high-temperature and strong-light, low-temperature and weak-light, and cloudy and fluctuating, and the corresponding basic thresholds are pre-stored (such as paying attention to the temperature safety upper limit in the high-temperature scenario and the power lower limit in the weak-light scenario), which solves the "one-size-fits-all" problem of traditional fixed thresholds in extreme environments. For example, dynamically increase the sensitivity to temperature anomalies in high-temperature and strong-light conditions, and reduce the misjudgment of power fluctuations in low-temperature and weak-light conditions, making the detection threshold more compatible with the environmental characteristics.

[0043] S3: Calculate the temperature deviation degree between the real-time temperature data and the average value of the historical temperature data of the photovoltaic module; based on the temperature deviation degree and the correction factor, dynamically adjust the basic threshold to generate an abnormal data screening threshold; based on the abnormal data screening threshold, screen out potential abnormal data points from the monitoring data set.

[0044] It should be noted that the temperature deviation degree between the real-time temperature data and the average value of the historical temperature data of the photovoltaic module reflects the abnormal trend of the current operating state. By dynamically adjusting the threshold in combination with the correction factor, misjudgment of the fixed threshold under complex working conditions can be reduced.

[0045] In a possible implementation manner, calculating the temperature deviation degree between the real-time temperature data and the average value of the historical temperature data of the photovoltaic module includes the following: calculating the absolute value of the difference between the real-time temperature data and the average value within the same light intensity interval of the historical temperature data as the temperature deviation degree.

[0046] Exemplarily, for temperature deviation degree calculation: divide the light intensity into 5 intervals: [0, 200], (200, 500], (500, 800], (800, 1000], (1000, +∞) W / m², for the real-time temperature data T real , find the historical temperature average value μ within the corresponding light intensity interval T , the temperature deviation degree: .

[0047] In a possible implementation manner, dynamically adjusting the basic threshold based on the temperature deviation degree and the correction factor to generate an abnormal data screening threshold includes the following: For the basic threshold corresponding to each matched environmental category, set the first weight coefficient corresponding to the normalized value of the real-time light intensity data, the second weight coefficient corresponding to the component aging coefficient, and the third weight coefficient corresponding to the temperature deviation degree. Multiply the normalized value of the real-time light intensity data by the first weight coefficient, the component aging coefficient by the second weight coefficient, and the temperature deviation degree by the third weight coefficient to obtain their respective weighted values; sum the weighted values to obtain the adjustment coefficient; If the adjustment coefficient is greater than zero, then add the product of the adjustment coefficient and the preset positive adjustment ratio to the basic threshold to obtain the adjusted threshold; if the adjustment coefficient is less than zero, then subtract the product of the absolute value of the adjustment coefficient and the preset negative adjustment ratio from the basic threshold to obtain the adjusted threshold; the adjusted threshold is the abnormal data screening threshold; wherein, the first weight coefficient, the second weight coefficient, the third weight coefficient, the positive adjustment ratio, and the negative adjustment ratio are all preset constants.

[0048] Exemplarily, preset weight coefficients: the first weight coefficient k1 = 0.5 (weight of the normalized value of the real-time light intensity data), the second weight coefficient k2 = 0.3 (weight of the component aging coefficient), the third weight coefficient k3 = 0.2 (weight of the temperature deviation degree); Adjustment coefficient Let the positive adjustment ratio be 10% and the negative adjustment ratio be 5%. The adjustment formula is: ; represents the base threshold, and the generated is used as the abnormal data screening threshold. represents the normalized value of the real-time light intensity data, represents the degree of temperature deviation.

[0049] A correction factor is generated through light intensity normalization (eliminating seasonal light differences) and component aging coefficient (quantifying efficiency decay), and the threshold is dynamically adjusted in combination with the degree of temperature deviation. For example, the temperature fluctuation detection sensitivity of aging components is automatically reduced to avoid false alarms caused by natural decay, enabling the detection system to identify sudden anomalies of new components and also adapt to the progressive degradation of old components.

[0050] S4: Using the component corresponding to the potential abnormal data point as the target component, adjust the data acquisition neighborhood range according to the change of the real-time light intensity data. Within the adjusted data acquisition neighborhood range, calculate the temperature slope and power change rate of the target component.

[0051] It should be noted that a sudden change in the real-time light intensity data will cause fluctuations in the temperature and power of the components within the data acquisition neighborhood range. A fixed acquisition range is likely to introduce noise, and the data acquisition neighborhood range needs to be dynamically adjusted according to the light stability.

[0052] In a possible implementation manner, the step of using the component corresponding to the potential abnormal data point as the target component, adjusting the data acquisition neighborhood range according to the change of the real-time light intensity data, and calculating the temperature slope and power change rate of the target component within the adjusted data acquisition neighborhood range includes the following: Taking the photovoltaic component corresponding to the potential abnormal data point as the target component, and calculating the corresponding light intensity change rate in real time; when the light intensity change rate is greater than or equal to the preset threshold, narrowing the data acquisition neighborhood range centered on the target component; when the light intensity change rate is less than the preset threshold, restoring the default data acquisition neighborhood range; Based on the adjusted data acquisition neighborhood range, extracting the temperature data and power data of the target component within the adjusted data acquisition neighborhood range, and respectively calculating the temperature slope and power change rate of the target component based on the temperature data and power data.

[0053] Exemplarily, the default data acquisition neighborhood range: a 3x3 matrix centered on the target component (a total of 9 components). The calculation of the light intensity change rate: , where t represents the current timestamp, used to mark the data acquisition moment; represents the real-time light intensity data at the current moment t, Represents the real-time light intensity data at the previous moment t-1, where minutes, the preset threshold v th =50W / m 2 / min. When When this is the case, the data acquisition neighborhood range is reduced to the target component itself (1x1) to avoid interference from sudden changes in light on other components within the data acquisition neighborhood range. When When this is the case, the default data acquisition neighborhood range is restored.

[0054] Exemplarily, the temperature slope: ; (unit: °C / minute).

[0055] Power change rate: ; ([[]] is the rated power of the component).

[0056] Among them, t represents the current timestamp, used to mark the data acquisition moment, represents the real-time temperature data of the photovoltaic component at the current moment t; represents the temperature data of the photovoltaic component 10 minutes before the current moment t; represents the power data of the photovoltaic component at the current moment t; represents the power data of the photovoltaic component 10 minutes before the current moment t.

[0057] In this example, the data window is the most recent 10 minutes, collected once per second, and the mean value is taken to calculate the temperature slope and power change rate of the target component.

[0058] Dynamically adjust the data acquisition neighborhood range according to the light intensity change rate (such as reducing to a single component during sudden light changes and expanding to 3x3 during stability), and combine dynamic characteristic parameters such as temperature slope and power change rate to effectively extract abnormal signals under different light conditions. For example, in a cloudy and fluctuating scenario, avoid interference from light on other components within the data acquisition neighborhood range, focus on the local overheating or sudden power drop characteristics of the target component, and improve the detection sensitivity of hotspot-like abnormalities.

[0059] S5: Determine the neighboring components of the target component within the adjusted data acquisition neighborhood range, calculate the mean and standard deviation of the hotspot effect degree of the neighboring components. When the mean exceeds the abnormal data screening threshold and the standard deviation is lower than the preset fluctuation dynamic threshold, it is determined as a systematic abnormality.

[0060] It should be noted that the abnormality of a single component may be individual noise. When the components within the data acquisition neighborhood range are generally abnormal and the fluctuation is small, it is more likely to be a systematic problem (such as local occlusion, circuit failure), and such abnormalities need to be identified through statistical analysis.

[0061] In a possible implementation, the calculation of the mean and standard deviation of the hot spot effect degree of adjacent components includes the following: Within the adjusted data acquisition neighborhood range, obtain the temperature data and power data of the adjacent components of each target component; calculate the temperature slope and power change rate of each adjacent component respectively; calculate the hot spot effect degree of each adjacent component according to the temperature slope, power change rate of each adjacent component and a preset hot spot effect degree calculation model; count the hot spot effect degrees of all adjacent components and calculate their mean and standard deviation.

[0062] Exemplarily, for all components within the adjusted data acquisition neighborhood range (the default is 3x3 or a reduced range), determine the adjacent relationship through a component layout coordinate file (storing the row and column positions of each component).

[0063] The hot spot effect degree is calculated through a hot spot effect model: .

[0064] Among them, the weight coefficient is determined according to hot spot mechanism experiments. The temperature slope reflects the local overheating trend, and the power change rate reflects the performance abnormality.

[0065] Statistical analysis and determination: Calculate the hot spot effect degree H of all adjacent components within the adjusted data acquisition neighborhood range to obtain the mean and the standard deviation . Preset the fluctuation dynamic threshold = 0.3. When the mean exceeds the abnormal data screening threshold and the standard deviation is lower than the preset fluctuation dynamic threshold, it is determined as a systematic abnormality (indicating that the components within the data acquisition neighborhood range are generally abnormal and have small fluctuations, rather than individual noise). This mechanism effectively filters out the accidental noise of a single component (such as an instantaneous sensor failure) and identifies the consistent abnormality of the components within the data acquisition neighborhood range.

[0066] It should be noted that the preset fluctuation dynamic threshold is a statistical threshold for measuring the discreteness of the hot spot effect degree of components within the data acquisition neighborhood range. The smaller its value, the more consistent the states of the components within the data acquisition neighborhood range. The preset fluctuation dynamic threshold is determined in the following way: Analyze the neighborhood standard deviation distribution during the normal operation period and the known fault period, and select the best segmentation point that can distinguish the two.

[0067] In summary, the monitoring data set generated by S1 provides input for S2 - S5. The environmental classification of S2 determines the base threshold. S3 dynamically adjusts the threshold by combining the correction factor and the degree of temperature deviation, forming the key basis for the determination of S5. S4 dynamically adjusts the data acquisition neighborhood range and calculates characteristic parameters (temperature slope, power change rate) based on the potential abnormal data points screened by S3, providing the core indicators for the calculation of the hot spot effect in S5. S5 completes the systematic anomaly determination through statistical analysis based on the data acquisition neighborhood range and characteristic parameters of S4, combined with the dynamic threshold of S3, forming a complete detection closed - loop.

[0068] Embodiment 2 provides a photovoltaic power station equipment abnormal state detection system, which is applied to the above - mentioned photovoltaic power station equipment abnormal state detection method, as Figure 2 shown, including: A data acquisition module, which is used to acquire the operation data, ambient temperature data and historical operation data of photovoltaic modules, and generate a monitoring data set; among them, the operation data includes the real - time temperature data, real - time power data and real - time light intensity data of photovoltaic modules; the historical operation data includes the historical temperature data, historical power output data and corresponding historical light intensity data of photovoltaic modules since they were put into use.

[0069] A correction factor and threshold matching module, which is used to generate a correction factor based on the real - time light intensity data and historical data; classify the current environment based on the ambient temperature data and real - time light intensity data to obtain multiple environment categories, and match the base threshold corresponding to each environment category from the pre - stored environment category threshold library.

[0070] A threshold adjustment and abnormal data screening module, which is used to calculate the degree of temperature deviation between the real - time temperature data and the average value of the historical temperature data of the photovoltaic module; dynamically adjust the base threshold based on the degree of temperature deviation and the correction factor to generate an abnormal data screening threshold; screen out potential abnormal data points from the monitoring data set based on the abnormal data screening threshold.

[0071] A target component parameter calculation module, which is used to take the component corresponding to the potential abnormal data point as the target component, adjust the data acquisition neighborhood range according to the change of the real - time light intensity data, and calculate the temperature slope and power change rate of the target component within the adjusted data acquisition neighborhood range.

[0072] A systematic anomaly determination module, which is used to determine the neighboring components of the target component within the adjusted data acquisition neighborhood range, calculate the mean and standard deviation of the hot spot effect degree of the neighboring components, and when the mean exceeds the abnormal data screening threshold and the standard deviation is lower than the preset fluctuation dynamic threshold, it is determined as a systematic anomaly.

[0073] The above-described embodiments merely represent specific implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the patent for the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several variations and improvements can still be made, and these all fall within the protection scope of the present invention.

Claims

1. A method for detecting abnormal states of photovoltaic power station equipment, characterized in that, It includes the following steps: S1: Obtain the operation data, ambient temperature data, and historical operation data of the photovoltaic module to generate a monitoring data set. Among them, the operation data includes the real-time temperature data, real-time power data, and real-time light intensity data of the photovoltaic module; the historical operation data includes the historical temperature data, historical power output data, and corresponding historical light intensity data since the photovoltaic module was put into use. S2: Generate a correction factor based on the real-time light intensity data and historical data; classify the current environment based on the ambient temperature data and real-time light intensity data to obtain multiple environment categories, and match the basic threshold corresponding to each environment category from the pre-stored environment category threshold library. S3: Calculate the temperature deviation degree between the real-time temperature data and the average value of the historical temperature data of the photovoltaic module; dynamically adjust the basic threshold based on the temperature deviation degree and the correction factor to generate an abnormal data screening threshold; screen out potential abnormal data points from the monitoring data set based on the abnormal data screening threshold. S4: Use the component corresponding to the potential abnormal data point as the target component, adjust the data acquisition neighborhood range according to the change of the real-time light intensity data, and calculate the temperature slope and power change rate of the target component within the adjusted data acquisition neighborhood range. S5: Determine the neighboring components of the target component within the adjusted data acquisition neighborhood range, calculate the mean and standard deviation of the hot spot effect degree of the neighboring components. When the mean exceeds the abnormal data screening threshold and the standard deviation is lower than the preset fluctuation dynamic threshold, it is determined as a systematic anomaly.

2. The method for detecting abnormal states of photovoltaic power station equipment according to claim 1, wherein The generation of the correction factor based on the real-time light intensity data and historical data includes the following: Normalize the real-time light intensity data based on the historical minimum light intensity data and historical maximum light intensity data of the current season to obtain the normalized value of the real-time light intensity data; construct a photovoltaic module efficiency decay model through polynomial fitting based on the historical power output data and the corresponding historical light intensity data to determine the component aging coefficient reflecting the aging degree of the photovoltaic module; combine the normalized value of the real-time light intensity data and the component aging coefficient to generate a correction factor.

3. A method for detecting abnormal states of photovoltaic power station equipment according to claim 2, characterized in that, The classification of the current environment based on the ambient temperature data and real-time light intensity data to obtain multiple environment categories includes the following: When the ambient temperature data is higher than the preset high temperature threshold and the real-time light intensity data is higher than the preset strong light threshold, it is classified as a high temperature and strong light scenario. When the ambient temperature data is lower than the preset low temperature threshold and the real-time light intensity data is lower than the preset weak light threshold, it is classified as a low temperature and weak light scenario. When the change rate of the real-time light intensity data within the preset time period is greater than the preset fluctuation threshold and the ambient temperature data is within the preset temperature range, it is classified as a cloudy fluctuation scenario.

4. A method for detecting abnormal states of photovoltaic power station equipment according to claim 3, characterized in that, The calculation of the temperature deviation degree between the real-time temperature data and the average value of the historical temperature data of the photovoltaic module includes the following: Calculate the absolute value of the difference between the real-time temperature data and the average value of the historical temperature data within the same light intensity interval as the temperature deviation degree.

5. The method for detecting abnormal states of photovoltaic power station equipment according to claim 4, wherein, The dynamic adjustment of the basic threshold based on the temperature deviation degree and the correction factor to generate an abnormal data screening threshold includes the following: For each of the base thresholds corresponding to the matched environmental categories, set the first weight coefficient corresponding to the normalized value of the real-time light intensity data, the second weight coefficient corresponding to the component aging coefficient, and the third weight coefficient corresponding to the temperature deviation degree; Multiply the normalized value of the real-time light intensity data by the first weight coefficient, multiply the component aging coefficient by the second weight coefficient, and multiply the temperature deviation degree by the third weight coefficient to obtain their respective weighted values; sum the weighted values to obtain the adjustment coefficient; If the adjustment coefficient is greater than zero, add the product of the adjustment coefficient and the preset positive adjustment ratio to the base threshold to obtain the adjusted threshold; If the adjustment coefficient is less than zero, subtract the product of the absolute value of the adjustment coefficient and the preset negative adjustment ratio from the base threshold to obtain the adjusted threshold; the adjusted threshold is the abnormal data screening threshold; among them, the first weight coefficient, the second weight coefficient, the third weight coefficient, the positive adjustment ratio, and the negative adjustment ratio are all preset constants.

6. The method for detecting abnormal states of photovoltaic power station equipment according to claim 1, characterized in that, Taking the component corresponding to the potential abnormal data point as the target component, adjusting the data acquisition neighborhood range according to the change of the real-time light intensity data, and calculating the temperature slope and power change rate of the target component within the adjusted data acquisition neighborhood range includes the following content: Taking the photovoltaic component corresponding to the potential abnormal data point as the target component, and calculating the change rate of the corresponding light intensity in real time; when the change rate of the light intensity is greater than or equal to the preset threshold, narrowing the data acquisition neighborhood range centered on the target component; when the change rate of the light intensity is less than the preset threshold, restoring the default data acquisition neighborhood range; Based on the adjusted data acquisition neighborhood range, extract the temperature data and power data of the target component within the adjusted data acquisition neighborhood range, and calculate the temperature slope and power change rate of the target component respectively based on the temperature data and power data.

7. A method for detecting abnormal states of photovoltaic power station equipment according to claim 3, characterized in that, The calculation of the mean and standard deviation of the hot spot effect degree of the adjacent components includes the following content: Within the adjusted data acquisition neighborhood range, obtain the temperature data and power data of the adjacent components of each target component; calculate the temperature slope and power change rate of each adjacent component respectively; calculate the hot spot effect degree of each adjacent component according to the temperature slope, power change rate of each adjacent component and the preset hot spot effect degree calculation model; count the hot spot effect degrees of all adjacent components and calculate their mean and standard deviation.

8. A detection system for abnormal states of photovoltaic power station equipment, characterized in that, Applied to the photovoltaic power station equipment abnormal state detection method according to any one of claims 1-7, including: A data acquisition module, which is used to acquire the operation data, environmental temperature data and historical operation data of the photovoltaic components to generate a monitoring data set; among them, the operation data includes the real-time temperature data, real-time power data and real-time light intensity data of the photovoltaic components; the historical operation data includes the historical temperature data, historical power output data and corresponding historical light intensity data of the photovoltaic components since they were put into use; Correction factor and threshold matching module, which is used to generate a correction factor based on real-time light intensity data and historical data; classify the current environment based on environmental temperature data and real-time light intensity data to obtain multiple environmental categories, and match the basic threshold corresponding to each environmental category from the pre-stored environmental category threshold library; Threshold adjustment and anomaly screening module, which is used to calculate the temperature deviation degree between the real-time temperature data and the average value of the historical temperature data of the photovoltaic module; dynamically adjust the basic threshold based on the temperature deviation degree and the correction factor to generate an anomaly data screening threshold; screen out potential anomaly data points from the monitoring data set based on the anomaly data screening threshold; Target component parameter calculation module, which is used to take the component corresponding to the potential anomaly data point as the target component, adjust the data acquisition neighborhood range according to the change of real-time light intensity data, and calculate the temperature slope and power change rate of the target component within the adjusted data acquisition neighborhood range; Systematic anomaly determination module, which is used to determine the neighboring components of the target component within the adjusted data acquisition neighborhood range, calculate the mean and standard deviation of the hot spot effect degree of the neighboring components, and determine it as a systematic anomaly when the mean exceeds the anomaly data screening threshold and the standard deviation is lower than the preset fluctuation dynamic threshold.

Images