A distributed photovoltaic power station intelligent safety operation and maintenance management method and system

Abstract

The application discloses a kind of distributed photovoltaic power station intelligent safe operation and maintenance management method and system, it is related to intelligent safe operation and maintenance technical field, by collecting photovoltaic group string operation data, feature parameter extraction is carried out, and according to the feature parameter extracted, disturbance risk identification is carried out, to mark risk photovoltaic group string, and calculate the potential leakage probability of risk photovoltaic group string, further analyze the degree of electrical insulation performance degradation of risk photovoltaic group string, assess the risk level of risk photovoltaic group string, then trend aggregation analysis is carried out to risk photovoltaic group string of first risk level and second risk level, to identify spatial clustering risk, trigger early warning mechanism, accurately quantify the potential leakage risk accumulation process, avoid inducing failure due to microcrack, waterlogging, aging and other hidden dangers are not discovered in time, improve the forward-looking early warning and regional linkage capability of intelligent operation and maintenance system, provide more efficient, more fine-grained security management support for photovoltaic power station.

Description

Technical Field

[0001] The present invention relates to the field of intelligent safety operation and maintenance technology, and specifically to an intelligent safety operation and maintenance management method and system for distributed photovoltaic power stations. Background Art

[0002] In distributed photovoltaic power stations, the string system constitutes the basic unit for collecting and transmitting electricity. The operating status of each string directly affects the power generation safety and stability of the entire site. During the operation of these strings, the long-term degradation of the "insulation status" has become one of the key hidden factors in current safety management. Especially in hot and humid environments with frequent rain and fog or high salt fog on the coast, the insulation protection layer of the components and the junction box can easily be gradually weakened due to problems such as material aging, micro-cracks, dust accumulation and moisture, eventually developing into potential leakage or breakdown accidents. Therefore, how to establish a dynamic identification and early warning mechanism for the "insulation degradation trend" at the string level without adding new hardware has become one of the core issues to ensure the safe operation of distributed photovoltaic power stations.

[0003] In the Chinese invention patent application with publication number CN118552055A, a distributed photovoltaic intelligent health evaluation method and system are proposed. By using a remote monitoring platform to obtain the operating big data of distributed photovoltaic power stations, unified monitoring and evaluation of power stations across the country can be achieved, improving management and operation efficiency; multiple indicators related to health are selected, and the quantitative value of each indicator is determined. In combination with an intelligent algorithm, dynamic weight allocation is performed on the influencing factors of the distributed photovoltaic power station to more accurately reflect the health status of the power station; and a multi-objective intelligent evaluation of the health of distributed photovoltaic power stations across the country is performed through a unified monitoring platform to generate an evaluation report.

[0004] The above methods can promptly identify and resolve problems, ensuring the safe and stable operation of power stations. However, in addition to these, in existing intelligent and safe operation and maintenance management methods for distributed photovoltaic power stations, the detection of string insulation performance mainly relies on "periodic insulation resistance testing" and "manual infrared / grounding inspection".

[0005] However, these two methods have defects: first, the detection frequency is low and the interval time is long, which makes it difficult to track the gradual change trend of the insulation status and easily misses the early hidden danger window; second, the insulation resistance test requires manual power-off operation, which is not suitable for frequent execution and is very likely to cause missed detection; third, the detection only reflects the status at a certain moment, and has poor dynamic response capabilities to sudden weather, drastic changes in climate humidity, etc.; fourth, there is a lack of modeling and analysis methods for the hidden leakage channels in the systematic structure of "component body-combiner box-ground wire coupling path", resulting in the existing distributed photovoltaic power station intelligent safety operation and maintenance management methods "unable to see, measure, and predict" the insulation degradation status, seriously affecting the intelligent scheduling and automatic prevention and control capabilities of the overall safety strategy, and also weakening the power generation efficiency of the power station, triggering inverter failures, increasing fire risks, and directly endangering the safety of people and equipment.

[0006] To this end, the present invention proposes a distributed photovoltaic power station intelligent safety operation and maintenance management method and system. Summary of the Invention

[0007] In response to the shortcomings of the existing technology, the present invention provides a distributed photovoltaic power station intelligent safety operation and maintenance management method and system. By collecting photovoltaic string operation data, characteristic parameters are extracted, and disturbance risk identification is performed based on the extracted characteristic parameters to mark risk photovoltaic strings and calculate the potential leakage probability of risk photovoltaic strings. , further analyze the degree of degradation of the electrical insulation performance of the risky photovoltaic strings, evaluate the risk level of the risky photovoltaic strings, and then further conduct trend aggregation analysis on the risky photovoltaic strings of the first risk level and the second risk level to identify spatial clustering risks, trigger the early warning mechanism, and accurately quantify the accumulation process of potential leakage risks, avoid failures caused by hidden dangers such as microcracks, water accumulation, and aging that are not discovered in time, improve the forward-looking warning and regional linkage capabilities of the intelligent operation and maintenance system, provide more efficient and fine-grained safety management support for photovoltaic power stations, and solve the problems in the above-mentioned background technology.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: a distributed photovoltaic power station intelligent safety operation and maintenance management method, comprising the following steps:

[0009] S1. Deploy smart sensor groups on photovoltaic strings of a distributed photovoltaic power station and use the smart sensor groups to collect photovoltaic string operation data in real time to construct a photovoltaic string operation data set S. Extract characteristic parameters based on the photovoltaic string operation data set S, and construct a characteristic parameter set F based on the extracted characteristic parameters.

[0010] S2. Based on the characteristic parameter set F, perform characteristic parameter coupling calculation to obtain the physical disturbance risk score , and the physical disturbance risk score a physical disturbance risk threshold value performing comparative analysis to mark out the risk photovoltaic string;

[0011] S3, for the risk photovoltaic string, according to the photovoltaic string operation data set S, the feature parameter set F and the physical disturbance risk score of the risk photovoltaic string , performing coupling calculation of physical disturbance and humidity parameter to obtain potential leakage probability , and further analyzing the electrical insulation performance degradation degree of the risk photovoltaic string to obtain leakage risk accumulation index LRAI;

[0012] S4, comparing the leakage risk accumulation index LRAI with the first leakage risk threshold value and the second leakage risk threshold value to evaluate the risk level of the risk photovoltaic string;

[0013] S5, according to the risk level evaluation result, constructing a risk photovoltaic string set, and performing trend aggregation analysis on the risk photovoltaic string set to obtain a trend aggregation factor STCI, identifying spatial aggregation risk and giving warning.

[0014] Preferably, S1 includes the following specific steps,

[0015] S11, taking each photovoltaic string of the distributed photovoltaic power station as a data acquisition unit, deploying an intelligent sensor group on each photovoltaic string to obtain photovoltaic string operation data, wherein the photovoltaic string operation data includes photovoltaic string output current value I, voltage V, photovoltaic module surface temperature Tsurf, air temperature Tair and relative humidity H;

[0016] The photovoltaic string refers to the smallest power generation operation and maintenance unit constructed by connecting multiple photovoltaic modules in direct current series mode.

[0017] The intelligent sensor group includes a bus current transformer, a bus voltage divider, a thermocouple temperature sensor and a humidity sensor.

[0018] S12, preprocessing the collected photovoltaic string operation data, including data cleaning, data smoothing and normalization processing, and constructing a photovoltaic string operation data set S according to the preprocessed photovoltaic string operation data.

[0019] Preferably, S1 further includes the following specific steps,

[0020] S13, according to the photovoltaic string operation data set S, performing feature parameter extraction to obtain current fluctuation index DL, voltage edge drift index Dv, capacitance coupling residual index Dr and condensation risk index JL;

[0021] The current fluctuation index DL refers to the volatility of the PV string output current value. By taking the difference between the PV string output current values ​​I at adjacent time points, the current change rate per unit time is obtained, a current change rate time series is constructed, and the standard deviation of the current change rate time series is calculated as the current fluctuation index.

[0022] The voltage edge drift index Dv refers to the deviation of the waveform slope of the rising or falling edge of the PV string voltage waveform relative to the standard PV string voltage waveform;

[0023] The capacitive coupling residual index Dr refers to the total amount of fitting residuals between the actual recovery curve of the PV string and the standard RC model when the voltage recovers from a low level to a steady state during the operation of the PV string;

[0024] The condensation risk index JL refers to the relative critical proximity between the surface temperature Tsurf of the PV module and the air dew point temperature, where the air dew point temperature refers to the critical temperature at which water vapor in the air condenses into liquid water;

[0025] S14. Construct a characteristic parameter set F based on the obtained current fluctuation index DL, voltage edge drift index Dv, capacitive coupling residual index Dr, and condensation risk index JL.

[0026] Preferably, the specific steps of S2 include:

[0027] S21. Perform dimensionless processing on the characteristic parameters in the characteristic parameter set F to eliminate the physical dimension, and analyze the risk intensity level of the photovoltaic string under the condition of coupling multiple characteristic parameters based on the dimensionless processed characteristic parameters to obtain the physical disturbance risk score. , where the physical disturbance risk score The specific way to obtain it is:

[0028] ;

[0029] Where, 、 and They represent the current fluctuation index DL, voltage edge drift index Dv and capacitive coupling residual index Dr of the PV string at the current time point t, respectively, and ln represents the natural logarithmic constant;

[0030] S22. Collect the operating data of several photovoltaic strings when they are in a healthy state, so as to calculate the physical disturbance risk scores of several photovoltaic strings when they are in a healthy state. , and score the risk of all physical disturbances in a healthy state Perform statistical distribution analysis and select the 95th percentile physical disturbance risk score from the statistical distribution analysis results as a physical disturbance risk threshold value ;

[0031] S23, comparing the physical disturbance risk threshold value with the physical disturbance risk score to evaluate the disturbance risk state of the photovoltaic string, if the physical disturbance risk score is greater than or equal to the physical disturbance risk threshold value , it is determined that the photovoltaic string is in an abnormal enhancement state, at which time the photovoltaic string is marked as a risk photovoltaic string, if the physical disturbance risk score is less than the physical disturbance risk threshold value , it is determined that the photovoltaic string is in a normal state and does not need to be processed.

[0032] Preferably, the S3 specific steps include,

[0033] S31, for the marked risk photovoltaic string, based on the photovoltaic string operation data set S, the characteristic parameter set F and the physical disturbance risk score , the probability of potential leakage of the risk photovoltaic string under the influence of the current physical disturbance and environmental humidity is comprehensively analyzed to obtain the potential leakage probability , wherein the potential leakage probability is specifically represented as:

[0034] ;

[0035] In the formula, is a leakage trend coupling coefficient, exp represents an exponential function, is the relative humidity of the risk photovoltaic string at the current time point t, is the dew risk index of the risk photovoltaic string at the current time point t.

[0036] Preferably, the S3 specific steps further include,

[0037] S32, set a time sampling window , and based on the photovoltaic string operation data set S, obtain the potential leakage probability of each data collection time point in the time sampling window , and use a sliding integral method to analyze the electrical insulation performance degradation degree of the risk photovoltaic string to obtain a leakage risk accumulation index LRAI, wherein the leakage risk accumulation index LRAI is specifically obtained as:

[0038] ;

[0039] In the formula, represents the potential leakage probability of the risk photovoltaic string at the data collection time point a potential leakage probability at the time, denotes an integral variable, denotes a historical time window length, denotes a decay factor.

[0040] Preferably, the S4 specific steps include,

[0041] S41, presetting a first leakage risk threshold and a second leakage risk threshold , and comparing and analyzing the leakage risk accumulation index LRAI with the first leakage risk threshold and the second leakage risk threshold to evaluate the risk level of the risk photovoltaic string, and the specific evaluation contents are as follows:

[0042] If the leakage risk accumulation index LRAI is less than or equal to the first leakage risk threshold , it is judged that the risk level of the risk photovoltaic string is the first risk level, at which time the normal photovoltaic power station operation mode is maintained, and the data monitoring frequency is maintained normal;

[0043] If the leakage risk accumulation index LRAI is greater than the first leakage risk threshold , and less than or equal to the second leakage risk threshold , it is judged that the risk level of the risk photovoltaic string is the second risk level, at which time the risk photovoltaic string has abnormal fluctuations, and the early warning mechanism needs to be triggered, the early warning label is generated, and the early warning label is sent to the safety monitoring platform, and the data monitoring frequency is adjusted from 30 minutes once to 10 minutes once;

[0044] If the leakage risk accumulation index LRAI is greater than or equal to the second leakage risk threshold , it is judged that the risk level of the risk photovoltaic string is the third risk level, at which time the photovoltaic string isolation instruction is immediately generated, the isolation switch corresponding to the photovoltaic string is closed to interrupt the connection between the photovoltaic string and the main circuit, and the isolation log and the execution report are generated, and the isolation log and the execution report are continuously sent to the safety monitoring platform, and an alarm is issued until the safety monitoring platform management personnel responds.

[0045] Preferably, the S5 specific steps include,

[0046] S51, collecting the risk photovoltaic strings in the first risk level and the second risk level, constructing a risk photovoltaic string set, and extracting the leakage risk accumulation index LRAI of each risk photovoltaic string in the risk photovoltaic string set, and performing data average calculation to obtain the leakage risk accumulation index average ;

[0047] S52, calculate the difference between the leakage risk accumulation index LRAI of each risk photovoltaic string and the average value of the leakage risk accumulation index, and divide the difference by the average value of the leakage risk accumulation index plus a non-zero infinitesimal constant ε to obtain the trend bias rate BIAS of each risk photovoltaic string.

[0048] Preferably, the specific steps of S5 further comprise,

[0049] S53, according to the trend bias rate BIAS of each risk photovoltaic string and the average value of the trend bias rate, using the variance calculation formula, obtain the trend bias rate STCI of the set of risk photovoltaic strings, i.e. the trend concentration factor STCI.

[0050] S54, extract the historical photovoltaic string operation data of the set of risk photovoltaic strings to continuously calculate the trend concentration factor STCI of the set of risk photovoltaic strings over a period of time, construct a trend concentration factor time series, and according to the trend concentration factor time series, obtain the historical mean and historical standard deviation of the trend concentration factor STCI, and obtain the dynamic trend risk threshold value through the standard deviation boundary model.

[0051] S55, compare the dynamic trend risk threshold value with the trend concentration factor STCI to evaluate the degradation trend fluctuation risk among the risk photovoltaic strings, and the specific evaluation content is as follows:

[0052] If the trend concentration factor STCI is greater than or equal to the dynamic trend risk threshold value , it is determined that the degradation trend fluctuation among the risk photovoltaic strings is in an abnormal range, and the degradation trend among the risk photovoltaic strings is synchronized to enhance, and there is a spatial aggregation risk. At this time, the risk photovoltaic strings in the set of risk photovoltaic strings whose trend bias rate is greater than 0 and higher than the average value of the trend bias rate at multiple consecutive time points are screened out, and whether the risk photovoltaic strings belong to a physically adjacent area is determined according to a photovoltaic power station equipment distribution map. If they belong to a physically adjacent area, it indicates that the risk photovoltaic strings in the physically adjacent area have a regional potential leakage risk, and an early warning mechanism is triggered immediately to generate a manual maintenance task and execute a voltage reduction operation strategy. If they do not belong to a physically adjacent area, no processing is required.

[0053] If the trend concentration factor STCI is less than the dynamic trend risk threshold value , it is determined that the degradation trend fluctuation among the risk photovoltaic strings is in a normal range, and no processing is required.

[0054] ​​​​​Preferably, a distributed photovoltaic power station intelligent safe operation and maintenance management system comprises a data acquisition and feature extraction module, a disturbance analysis module, a potential leakage probability calculation module, a risk assessment module and a spatial aggregation analysis module.

[0055] The data acquisition and feature extraction module is used for deploying an intelligent sensor group on a photovoltaic string of the distributed photovoltaic power station, and collecting photovoltaic string operation data in real time using the intelligent sensor group to construct a photovoltaic string operation data set S, and extracting feature parameters according to the photovoltaic string operation data set S, and constructing a feature parameter set F according to the extracted feature parameters.

[0056] The disturbance analysis module is used for performing feature parameter coupling calculation according to the feature parameter set F to obtain a physical disturbance risk score , and performing comparative analysis on the physical disturbance risk score and a physical disturbance risk threshold value to mark out a risk photovoltaic string

[0057] The potential leakage probability calculation module is used for, for the risk photovoltaic string, performing coupling calculation of the physical disturbance and humidity parameters according to the photovoltaic string operation data set S, the feature parameter set F and the physical disturbance risk score of the risk photovoltaic string to obtain a potential leakage probability , and further analyzing the electrical insulation performance degradation degree of the risk photovoltaic string to obtain a leakage risk accumulation index LRAI.

[0058] The risk assessment module is used for performing comparative analysis on the leakage risk accumulation index LRAI and a first leakage risk threshold value and a second leakage risk threshold value to assess the risk grade of the risk photovoltaic string.

[0059] The spatial aggregation analysis module is used for constructing a risk photovoltaic string set according to the risk grade assessment result, and performing trend aggregation analysis on the risk photovoltaic string set to obtain a trend aggregation factor STCI, identifying a spatial aggregation risk and performing early warning.

[0060] The present application provides a distributed photovoltaic power station intelligent safe operation and maintenance management method and system, which has the following beneficial effects:

[0061] (1) Through the construction of "potential leakage probability" and "leakage risk accumulation index LRAI", the humidity, condensation trend, capacitive coupling residual and other easily ignored parameters are introduced into the quantitative modeling of insulation performance degradation. Compared with the traditional method of relying on "periodic insulation resistance detection" or "manual inspection", this method can dynamically obtain risk indicators during the operation of photovoltaic modules, capture the gradual evolution characteristics of "insulation trend", identify potential but not yet prominent hidden dangers, especially in rainy, humid, coastal and other humid environments, which can significantly improve the early identification ability of micro-cracks, water vapor erosion, packaging aging and other problems, solve the pain points of traditional methods such as "low detection frequency, poor timeliness and high misjudgment risk", and improve the forward-looking and intelligent level of operation and maintenance.

[0062] (2) By comparing the leakage risk accumulation index LRAI with the trend deviation degree of photovoltaic string, "trend deviation rate BIAS" and "trend aggregation factor STCI" are proposed to identify the "degradation trend space aggregation" phenomenon among photovoltaic modules. When multiple physically adjacent photovoltaic strings show a synchronous trend of high leakage risk accumulation index LRAI, such as batch defects of junction boxes, regional water vapor aggregation, abnormal potential path of component string connection and other problems, it may cause "implicit regional risk aggregation". Without damaging the on-site structure and without external instruments, the trend data analysis can complete the partition hidden danger identification, which is a powerful supplement to "component individual risk assessment".

[0063] (3) By comparing the leakage risk accumulation index LRAI with the dynamic threshold, three-level risk grade determination is completed, and the trend aggregation factor STCI is further used to identify "abnormal space aggregation" events. Finally, the system triggers specific strategies including "early warning reporting", "depression operation", "string isolation" and the like, so as to realize the closed-loop control from "risk identification" to "safety disposal". Compared with the traditional early warning method, this method introduces the trend evolution dimension and spatial distribution evaluation mechanism, which can actively adjust the inspection frequency, pressure control logic and repair task issuing granularity according to the risk level and trend direction, so that the safety strategy is no longer static or artificially set, but dynamically adapted with data evolution, effectively improving the self-adaptation ability and fault rapid suppression efficiency of the photovoltaic power station intelligent operation and maintenance system, and enhancing the long-term safety and stability of the overall power station. BRIEF DESCRIPTION OF DRAWINGS

[0064] Figure 1 It is a distributed photovoltaic power station intelligent safety operation and maintenance management method flow diagram;

[0065] Figure 2 It is a distributed photovoltaic power station intelligent safety operation and maintenance management system block diagram;

[0066] Figure 3A flowchart of a pre-process of operation data collection and characteristic parameter extraction of a photovoltaic string according to the present application is shown in Fig. 1.

[0067] Figure 4 A flowchart of a risk level evaluation process of a risk photovoltaic string according to the present application is shown in Fig. 4. DETAILED DESCRIPTION

[0068] The technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of protection of the present application.

[0069] Embodiment 1

[0070] Referring to Fig. 1, Figure 1 the present application provides an intelligent safe operation and maintenance management method for a distributed photovoltaic power station, which comprises the following steps,

[0071] S1, deploying an intelligent sensor group on a photovoltaic string of a distributed photovoltaic power station, and using the intelligent sensor group to collect photovoltaic string operation data in real time to construct a photovoltaic string operation data set S, and extracting characteristic parameters according to the photovoltaic string operation data set S, and constructing a characteristic parameter set F according to the extracted characteristic parameters;

[0072] S2, performing coupling calculation of the characteristic parameters according to the characteristic parameter set F to obtain a physical disturbance risk score and comparing the physical disturbance risk score with a physical disturbance risk threshold value to mark out a risk photovoltaic string;

[0073] S3, for the risk photovoltaic string, performing coupling calculation of the physical disturbance and the humidity parameter according to the photovoltaic string operation data set S, the characteristic parameter set F and the physical disturbance risk score of the risk photovoltaic string to obtain a potential leakage probability and further analyzing the electrical insulation performance degradation degree of the risk photovoltaic string to obtain a leakage risk accumulation index LRAI;

[0074] S4, comparing the leakage risk accumulation index LRAI with a first leakage risk threshold value and a second leakage risk threshold value to evaluate the risk level of the risk photovoltaic string;

[0075] S5, constructing a risk photovoltaic string set according to the risk level evaluation result, and performing trend aggregation analysis on the risk photovoltaic string set to obtain a trend aggregation factor STCI, identifying a spatial aggregation risk, and performing early warning.

[0076] In the embodiment, by constructing a whole-process closed loop process from data acquisition, disturbance risk identification, trend evolution tracking to spatial aggregation early warning, the technical short board of "can't see, can't measure and can't predict" in the existing distributed photovoltaic power station insulation monitoring means is effectively broken. Compared with the traditional mode relying on manual detection, the method can dynamically identify the insulation degradation trend based on the component operation data, accurately quantify the leakage risk accumulation process, avoid inducing faults due to hidden dangers such as microcracks, water accumulation and aging, and especially through the calculation of the trend aggregation factor, the regional synchronous degradation phenomenon can be accurately identified, the transformation from single-point risk identification to systematic risk control is realized, the forward-looking early warning and regional linkage ability of the intelligent operation and maintenance system is significantly improved, and more efficient and finer safety management support is provided for the photovoltaic power station.

[0077] Embodiment 2

[0078] Please refer to Figure 1 and Figure 3 , in detail: S1 specific steps include,

[0079] S11, taking each photovoltaic string of the distributed photovoltaic power station as a data acquisition unit, deploying an intelligent sensor group on each photovoltaic string to obtain photovoltaic string operation data, wherein the photovoltaic string operation data includes photovoltaic string output current value I, voltage V, photovoltaic component surface temperature Tsurf, air temperature Tair and relative humidity H;

[0080] The photovoltaic string refers to the smallest power generation operation unit constructed by connecting multiple photovoltaic components in a direct current series mode;

[0081] The intelligent sensor group includes a combiner box current transformer, a combiner box voltage divider, a thermocouple temperature sensor and a humidity sensor;

[0082] The photovoltaic string output current value I is acquired by using the combiner box current transformer, the voltage V is acquired by using the combiner box voltage divider, the photovoltaic component surface temperature Tsurf and the air temperature Tair are acquired by using the thermocouple temperature sensor, and the relative humidity H is acquired by using the humidity sensor;

[0083] S12, preprocessing the collected photovoltaic string operation data, including data cleaning, data smoothing and normalization processing, and constructing a photovoltaic string operation data set S according to the preprocessed photovoltaic string operation data.

[0084] S13, according to the photovoltaic string operation data set S, performing feature parameter extraction to obtain a current fluctuation index DL, a voltage edge drift index Dv, a capacitance coupling residual index Dr and a dew risk index JL;

[0085] The current fluctuation index DL refers to the change rate of the short-circuit current over time, which is obtained by subtracting the photovoltaic string output current value I at the previous data collection time point from the photovoltaic string output current value I at a certain data collection time point and dividing by the data sampling time interval;

[0086] The voltage edge drift index Dv refers to the offset amplitude of the rising edge or falling edge of the photovoltaic string voltage waveform relative to the standard photovoltaic string voltage waveform, which is used to reflect whether the component potential establishment speed is abnormal.

[0087] The capacitance coupling residual index Dr refers to the total fitting residual amount between the actual recovery curve of the photovoltaic string and the standard RC model when the voltage recovers from low level to steady state during the operation of the photovoltaic string, which is used to reflect the asymmetry, degradation or charge leakage behavior of the capacitance coupling path between the components in the string. The standard RC model refers to the voltage recovery model under ideal conditions, i.e. without performance degradation and without additional loss.

[0088] The voltage recovers from low level to steady state refers to the dynamic voltage recovery process in which the system gradually recovers to its normal stable working voltage after the voltage temporarily drops or is in a low voltage state due to some reasons such as shading, load sudden drop and fast switching, etc.

[0089] The dew risk index JL refers to the relative critical closeness between the surface temperature Tsurf of the photovoltaic module and the air dew point temperature. The air dew point temperature refers to the critical temperature at which water vapor in the air condenses into liquid water. Liquid water can form a conductive water film path in the backboard microcrack, poor sealing of the junction box, and aged welding area, thereby causing safety hazards in the photovoltaic power plant.

[0090] The air dew point temperature is calculated by using the photovoltaic module surface temperature Tsurf and relative humidity H, and combining the Magnus formula. The Magnus formula is an empirical formula for estimating the relationship between water vapor saturation pressure and temperature and humidity.

[0091] S14, constructing a feature parameter set F according to the obtained current fluctuation index DL, voltage edge drift index Dv, capacitance coupling residual index Dr and dew risk index JL.

[0092] In the embodiment, by deploying a group of intelligent sensors in each photovoltaic string, basic operation data including short-circuit current, voltage, temperature and humidity are collected, and on this basis, a set of refined feature parameters F is constructed, including current fluctuation index DL, voltage edge drift index Dv, capacitance coupling residual index Dr and dew risk index JL. This method breaks through the passive mode of traditional photovoltaic insulation state evaluation which relies on manual infrared detection or regular resistance measurement. This method not only can accurately capture the operation dynamics at the component level, but also can complete the pre-judgment through the feature offset trend before the component occurs potential aging, micro-cracking or encapsulation degradation. Especially, the introduction of dew risk index can effectively identify environmental induced hidden dangers such as backboard water vapor penetration. Overall, the embodiment improves the response sensitivity to early signals of insulation degradation, lays a high-precision foundation for subsequent potential leakage modeling and trend identification, and strengthens the foresight and technical effectiveness of system-level safety warning.

[0093] Embodiment 3

[0094] Please refer to Figure 1 and Figure 4 , specifically: S2 specific steps include,

[0095] S21, the feature parameters in the feature parameter set F are dimensionless processed to eliminate the physical dimension, and the risk intensity level of the photovoltaic string under the coupling of multiple feature parameters is analyzed according to the dimensionless processed feature parameters, so as to obtain a physical disturbance risk score , wherein the physical disturbance risk score The specific acquisition method is:

[0096] ;

[0097] In the formula, , and respectively represent the current fluctuation index DL, the voltage edge drift index Dv and the capacitance coupling residual index Dr of the photovoltaic string at the current time point t, and ln represents the natural logarithm constant;

[0098] Formula derivation process and physical meaning: the formula combines the three dimensionless characteristic parameters, including current fluctuation index DL, voltage edge drift index Dv and capacitance coupling residual index Dr, through square operation to construct the disturbance intensity term, which is equivalent to the square sum of Euclidean norm, reflecting the overall disturbance intensity, and then uses the power function to power the constructed disturbance intensity term to obtain the disturbance amplification term, then adds the constant term 1+ to avoid zero input, and finally, logarithmic transformation is performed on the whole to enhance the scale discrimination degree and compress the extreme value fluctuation to form the final physical disturbance risk score. The formula integrates disturbance signal, non-linear enhancement and logarithmic mapping mechanism to construct a quantifiable and evaluable physical disturbance risk score, which effectively supports subsequent risk level division, early warning identification and trend aggregation analysis, and has clear physical basis and mathematical completeness.

[0099] S22, collecting a plurality of sets of photovoltaic string operating data of the photovoltaic strings in a healthy state to calculate a plurality of physical disturbance risk scores of the photovoltaic strings in the healthy state , and performing statistical distribution analysis on all the physical disturbance risk scores in the healthy state , and selecting the 95th percentile of the physical disturbance risk score from the statistical distribution analysis result as the physical disturbance risk threshold ;

[0100] Statistical distribution analysis refers to using the quantile extraction method to quantitatively describe the overall volatility and boundary characteristics of the sample, i.e. the physical disturbance risk score , so as to extract the upper limit tolerance value of the physical disturbance risk;

[0101] S23, comparing the physical disturbance risk threshold with the physical disturbance risk score to evaluate the disturbance risk state of the photovoltaic string. If the physical disturbance risk score is greater than or equal to the physical disturbance risk threshold , it is determined that the photovoltaic string is in an abnormal enhancement state, and the photovoltaic string is marked as a risk photovoltaic string. If the physical disturbance risk score is less than the physical disturbance risk threshold , it is determined that the photovoltaic string is in a normal state and does not need to be processed.

[0102] In the embodiment, by introducing a physical disturbance risk score, the current, voltage and capacitance behaviors exhibited in the operation of the photovoltaic string are comprehensively evaluated, and a dynamic 95% quantile risk threshold is constructed using historical samples in the healthy state, thereby realizing sensitive capture and determination of early features of insulation degradation. Compared with the traditional method of relying on artificial insulation resistance testing, the present application can continuously and non-invasively identify the cumulative trend of weak disturbance, effectively avoiding the problems of low detection frequency and slow response. At the same time, by uniformly processing the physical dimension, the comparability and data adaptability between different indicators are improved, so that the identification mechanism has stronger generalization ability and field adaptability, which helps to improve the early identification efficiency of the insulation degradation trend of the photovoltaic power station, provides accurate basis for subsequent risk warning and photovoltaic string grading disposal, and strengthens the active perception and dynamic response capability of the intelligent operation and maintenance system.

[0103] Embodiment 4

[0104] Please refer to Figure 1 and Figure 4 , in detail: the S3 specific steps include,

[0105] S31, for the marked risk photovoltaic string, according to the photovoltaic string operation data set S, the feature parameter set F and the physical disturbance risk score , comprehensively analyze the probability of potential leakage of the risk photovoltaic string under the influence of the current physical disturbance and environmental humidity, to obtain the potential leakage probability , wherein the potential leakage probability The specific form is:

[0106] ;

[0107] In the formula, represents the leakage trend coupling coefficient, exp represents the exponential function, represents the relative humidity of the risk photovoltaic string at the current time point t, represents the dew risk index of the risk photovoltaic string at the current time point t.

[0108] The leakage trend coupling coefficient represents the nonlinear coupling adjustment factor for adjusting the growth amplitude of the potential leakage probability under the joint action of the physical disturbance risk score , the relative humidity and the dew risk index , the greater the value of the leakage trend coupling coefficient , the more sensitive the photovoltaic string is to external disturbance conditions, and the stronger the risk amplification trend, which is used to reflect the sensitivity of the photovoltaic string to the leakage response of the coupling condition, wherein the leakage trend coupling coefficient The specific value is obtained by using a least square method in combination with historical operation data of the photovoltaic string;

[0109] Formula derivation process and physical meaning: first, the formula introduces an electron breakdown probability model as a physical modeling inspiration, and the core structure of the formula is an exponential transition expression form. This structure is analogous to the Weibull-type nonlinear mutation mechanism in the electron breakdown probability model. When the physical disturbance continues to increase and the environmental conditions approach the critical state, the leakage risk does not increase linearly, but rapidly approaches 1 in an explosive jump way. Therefore, an exponential function is used for processing. The exponential function has a risk performance form of gentle before the critical point and rapid acceleration after the critical point.

[0110] Wherein, the physical disturbance risk score represents the abnormal electrical dynamics of the photovoltaic string in the running process, and the physical disturbance risk score is stronger, the more intense the potential change is, and the easier the latent discharge is triggered.

[0111] represents the humidity term. The higher the humidity is, the more likely the insulating surface or gap is to form a conductive bridge due to water vapor accumulation, is a wetness amplification factor, which reflects the surface water film form critical trend, The smaller it is, the closer the component surface temperature is to the air dew point, and the more likely condensation is to occur.

[0112] represents the environmental factor adjustment term, which is a nonlinear function structure, ensuring that the true risk signal is released under the condition of "high humidity + thermal criticality", and a thermal-humidity linkage evaluation model with physical response sensitivity and risk filtering capability is constructed

[0113] represents the equivalent leakage excitation factor, which is a disturbance, humidity and wetness coupling term, indicating that if the electrical fluctuation of the photovoltaic string is abnormal, the humidity is too high, and the component surface is close to the condensation critical point at a certain moment, the system is in a highly sensitive state, and it is easy to cause potential leakage path to form, thereby causing grounding fault, arc discharge or potential imbalance.

[0114] The specific examples are as follows:

[0115] Assume that the parameters are as shown in Table 1:

[0116]

[0117] Table 1

[0118] According to Table 1, the potential leakage probability is calculated :

[0119] ;

[0120] S3 specific steps also include,

[0121] S32, set the time sampling window{ , t}, and according to the photovoltaic string operation data set S, obtain the potential leakage probability of each data collection time point in the time sampling window{ , t} And use the sliding integral method to analyze the electrical insulation performance degradation degree of the risk photovoltaic string, so as to obtain the leakage risk accumulation index LRAI, wherein the specific acquisition method of the leakage risk accumulation index LRAI is:

[0122] ;

[0123] In the formula, Indicates the potential leakage probability of the risk photovoltaic string at the data collection time point , Indicates the integral variable, Indicates the length of the historical time window, Indicates the attenuation factor, wherein the specific value of the attenuation factor Is determined by.

[0124] In the insulation performance degradation process of the photovoltaic module, the electrical insulation performance degradation is not instantaneous, but a long-term progressive degradation process affected by environmental load, component aging and micro-leakage accumulation. Therefore, when evaluating the current insulation degradation degree of a photovoltaic string, it should not only depend on the potential leakage probability at a certain time point But also needs to consider whether it continues to present a high risk leakage situation in a period of time.

[0125] Formula derivation process and physical meaning: at any current time point t, the potential leakage probability of each historical time point in the historical time window{ , t} is reviewed, and its distance from the current time point t is arranged and accumulated according to the physical attenuation influence of the time interval t- , so as to obtain the potential leakage accumulation level in the past period of time , wherein is an exponential decay function. In the operation and maintenance process of the photovoltaic string, the insulation performance will not suddenly deteriorate, but will gradually develop with the continuous accumulation of environmental pressure, such as humidity, thermal stress and electrical breakdown trend. However, the influence of potential abnormality occurring at different historical time on the current state is not equal, so an exponential decay function is used to represent the physical evolution law that the influence of historical leakage probability on the current time decreases over time. Through the exponential decay function, the potential abnormal behavior closer to the current time in the historical time window can be evaluated, thereby forming a time integral index that more truly reflects the insulation degradation trend of the string, and avoiding misjudgment caused by long-term interference of long-term disturbance.

[0126] In the embodiment, by introducing the potential leakage probability and the sliding integral mechanism, dynamic quantitative evaluation of the electrical insulation performance of the risk photovoltaic string is realized. This method not only combines easily ignored factors such as environmental humidity and dewing trend, but also sets a time window and a decay factor to analyze the trend accumulation of the risk evolution process in different time periods, effectively depicting the accumulative change path of potential hidden dangers. Compared with the existing method which only relies on manual patrol or single-point resistance measurement, this method has stronger continuity, sensitivity and early warning preposition, and can identify early signs of potential leakage risk before the system surface has no explicit abnormality, significantly improving the active identification and operation response capability of "structural hidden degradation", and providing core support for improving the intelligent safety protection capability of distributed photovoltaic power stations in complex climate and aging environment.

[0127] Embodiment 5

[0128] Please refer to Figure 1 and Figure 4 , in detail: the S4 specific steps include,

[0129] S41, presetting a first leakage risk threshold and a second leakage risk threshold , and comparing the leakage risk accumulation index LRAI with the first leakage risk threshold and the second leakage risk threshold to evaluate the risk level of the risk photovoltaic string. The specific evaluation content is as follows:

[0130] If the leakage risk accumulation index LRAI is less than or equal to the first leakage risk threshold , it is judged that the risk level of the risk photovoltaic string is the first risk level, at which time the normal photovoltaic power station operation mode is maintained, and the data monitoring frequency is maintained normal;

[0131] If the leakage risk accumulation index LRAI is greater than the first leakage risk threshold and less than or equal to the second leakage risk threshold If the risk level of the risk photovoltaic string is determined as the second risk level, the risk photovoltaic string has abnormal fluctuations, and a pre-warning mechanism needs to be triggered, a pre-warning label is generated, and the pre-warning label is sent to the safety monitoring platform, and the data monitoring frequency is adjusted from 30 minutes to 10 minutes once.

[0132] If the leakage risk accumulation index LRAI is greater than or equal to the second leakage risk threshold , the risk level of the risk photovoltaic string is determined as the third risk level, and the photovoltaic string isolation instruction is immediately generated, the isolation switch corresponding to the photovoltaic string is closed to interrupt the connection between the photovoltaic string and the main circuit, and the isolation log and the execution report are generated, and the isolation log and the execution report are continuously sent to the safety monitoring platform, and an alarm is issued until the safety monitoring platform manager responds.

[0133] In the embodiment, by setting two leakage risk thresholds, a three-stage risk level division mechanism is constructed to realize fine-grained dynamic evaluation of the insulation degradation state of the photovoltaic string. Compared with the traditional method of relying only on single-point insulation resistance detection, it can identify "trend degradation" earlier rather than just responding to "faults". It has a significant advantage for chronic problems such as micro-cracks, moisture, and aging of the package. According to the evaluation results, the response strategy is automatically matched, such as dynamically adjusting the monitoring frequency, generating a pre-warning label, triggering an isolation instruction, etc. A closed-loop link from identification to disposal is formed, which improves the safety response capability of the distributed photovoltaic power station under complex weather conditions, avoids accidents caused by delayed response or inaccurate judgment, and balances the warning accuracy and operation stability. The problem of "can't see, can't measure, can't predict" mentioned in the background art is solved, and the monitoring granularity and control initiative of the insulation degradation process are enhanced.

[0134] Embodiment 6

[0135] Please refer to Figure 1 , in detail: the specific steps S5 include,

[0136] S51, the risk photovoltaic strings in the first risk level and the second risk level are collected to construct a risk photovoltaic string set, and the leakage risk accumulation index LRAI of each risk photovoltaic string in the risk photovoltaic string set is extracted for data average calculation to obtain the average value of the leakage risk accumulation index ;

[0137] S52, the difference between the leakage risk accumulation index LRAI of each risk photovoltaic string in the risk photovoltaic string set and the average value of the leakage risk accumulation index is calculated, and the difference is divided by the sum of the average value of the leakage risk accumulation index and a non-zero small constant ε to obtain the trend deviation rate of each risk photovoltaic string , wherein the trend deviation rate refers to the relative deviation of the leakage risk accumulation index LRAI of the risk photovoltaic string from the average value of the leakage risk accumulation index.

[0138] The specific step S5 further includes,

[0139] S53, according to the trend deviation rate of each risk photovoltaic string and the average value of the leakage risk accumulation index , using the variance calculation formula, the trend deviation rate of the risk photovoltaic string set variance, that is, the trend concentration factor STCI;

[0140] By calculating the trend deviation rate of each risk photovoltaic string variance, the synchronization and deviation of the trend performance between the risk photovoltaic strings can be reflected, so as to realize the quantitative characterization of the trend concentration, and the smaller the variance, the more concentrated the trend performance, the higher the spatial synchronization risk characteristics, which is suitable for subsequent clustering identification and risk attribution analysis, and ensures that the index has operability and discriminant value in engineering discrimination and dynamic evolution modeling.

[0141] S54, extracting the historical photovoltaic string operation data of the risk photovoltaic string set to continuously calculate the trend concentration factor STCI of the risk photovoltaic string set in a period of time, constructing a trend concentration factor time series, and according to the trend concentration factor time series, obtaining the historical mean and historical standard deviation of the trend concentration factor STCI, and through the standard deviation boundary model, obtaining the dynamic trend risk threshold ;

[0142] The trend concentration factor time series refers to a set sequence of the trend concentration factor STCI of the risk photovoltaic string set extracted in chronological order in continuous time;

[0143] The standard deviation boundary model is a dynamic threshold setting model constructed based on statistical distribution law, and its core idea is: in the trend concentration factor time series, the mean and standard deviation are calculated from the historical samples to construct the upper and lower boundaries reflecting the normal fluctuation range, and the dynamic threshold range for risk discrimination is defined;

[0144] S55, comparing and analyzing the dynamic trend risk threshold with the trend concentration factor STCI to evaluate the degradation trend fluctuation risk between the risk photovoltaic strings, and the specific evaluation content is as follows:

[0145] If the trend concentration factor STCI is greater than or equal to the dynamic trend risk threshold ​, then it is determined that the degradation trend fluctuation between the risk photovoltaic strings is in an abnormal range, the risk photovoltaic strings appear a phenomenon of synchronous enhancement of degradation trend, and there is a spatial aggregation risk, at this time, the trend deviation rate is greater than 0 and is higher than the trend deviation rate at multiple continuous time points The average value of the risk photovoltaic strings, and whether the risk photovoltaic strings belong to a physically adjacent region according to a photovoltaic power station equipment distribution map, if the risk photovoltaic strings belong to the physically adjacent region, it indicates that the risk photovoltaic strings in the physically adjacent region have a regional potential leakage risk, an early warning mechanism is triggered immediately, an artificial maintenance task is generated, and a voltage reduction operation strategy is executed, if the risk photovoltaic strings do not belong to the physically adjacent region, no processing is required.

[0146] The current fluctuation, voltage offset, and leakage probability of a single photovoltaic string may be only an occasional fluctuation or individual device aging, but when multiple geographically adjacent photovoltaic strings simultaneously present consistent trend deviation such as rising leakage probability and voltage drop in a similar time period, it may indicate that there is a systematic thermal imbalance, aging of the same batch of components, and environmental coupling risks such as regional condensation in the system. In a specific example, a certain distributed photovoltaic power station collects data showing that the trend aggregation factor STCI of 30 photovoltaic strings in area A simultaneously rises from 0.03 to 0.09 from early morning to 10 am, at this time, the voltage curve appears slight fluctuation, but none of them touches the single-point alarm threshold, the system automatically tracks the trend deviation rate BIAS of these photovoltaic strings in time sequence, and calculates the trend aggregation factor STCI in the time window, when the trend aggregation factor STCI exceeds the dynamic trend risk threshold , it is determined that the photovoltaic strings in area A have a "trend synchronous degradation", that is, it is determined as a potential condensation type group risk, then the region is identified to have a large cold-warm temperature difference at night, the box body sealing is aging, and there is a situation of repeated retention of moisture, then the ventilation device is forcibly opened to drain moisture, and the maintenance personnel are warned to perform artificial maintenance;

[0147] If the trend aggregation factor STCI is less than the dynamic trend risk threshold , it is determined that the degradation trend fluctuation between the risk photovoltaic strings is in a normal range, and no processing is required.

[0148] In the embodiment, the trend deviation rate BIAS is constructed The trend consistency enhancement of the risk group strings in the photovoltaic power station is effectively identified by the trend consistency factor STCI, which makes up for the defects of the traditional insulation risk assessment focusing on single point state and being difficult to find systematic degradation synergy. Compared with the existing method relying on periodic detection and manual inspection, the scheme can realize intelligent identification driven by trend evolution, automatically trigger regional hidden danger warning, improve early perception ability and response timeliness, and at the same time, the device distribution information is introduced to judge the physical proximity, improve the strategy accuracy, effectively avoid false alarm or misplacement, significantly enhance the dynamic tracking ability of the system to the implicit degradation paths such as component aging, moisture erosion and potential unevenness, promote the photovoltaic power station from "periodic inspection" to "trend-driven active prevention and control", and ensure the operation safety and maintenance economy of large-scale power stations.

[0149] Embodiment 7

[0150] Please refer to Figure 2 , specifically: a distributed photovoltaic power station intelligent safety operation and maintenance management system, comprising a data acquisition and feature extraction module, a perturbation analysis module, a potential leakage probability calculation module, a risk assessment module and a spatial aggregation analysis module;

[0151] The data acquisition and feature extraction module is used for deploying an intelligent sensor group on the photovoltaic string of the distributed photovoltaic power station, and using the intelligent sensor group to acquire photovoltaic string operation data in real time to construct a photovoltaic string operation data set S, and extracting feature parameters according to the photovoltaic string operation data set S, and constructing a feature parameter set F according to the extracted feature parameters;

[0152] The perturbation analysis module is used for performing feature parameter coupling calculation according to the feature parameter set F to obtain a physical perturbation risk score , and comparing the physical perturbation risk score with a physical perturbation risk threshold to mark out a risk photovoltaic string

[0153] The potential leakage probability calculation module is used for, for the risk photovoltaic string, performing coupling calculation of the physical perturbation and the humidity parameter according to the photovoltaic string operation data set S, the feature parameter set F and the physical perturbation risk score of the risk photovoltaic string to obtain a potential leakage probability , and further analyzing the electrical insulation performance degradation degree of the risk photovoltaic string to obtain a leakage risk accumulation index LRAI;

[0154] The risk assessment module is used for comparing the leakage risk accumulation index LRAI with a first leakage risk threshold and a second leakage risk threshold A comparative analysis is performed to evaluate the risk level of the risk photovoltaic string;

[0155] The spatial aggregation analysis module is configured to construct a risk photovoltaic string set according to the risk level evaluation result, and perform a trend aggregation analysis on the risk photovoltaic string set to obtain a trend aggregation factor STCI, identify a spatial aggregation risk, and perform early warning.

[0156] In the embodiments, by constructing a multi-module linked intelligent operation and maintenance system, in view of the problems that it is difficult for traditional distributed photovoltaic power stations to identify the insulation degradation trend in real time and monitor regional hidden danger aggregation, a closed-loop technical path from "data collection-risk scoring-trend identification-grade evaluation-aggregation determination" is proposed, the dynamic quantification of the component-level potential leakage trend, the spatial identification of the trend evolution and the graded response are realized, the system does not rely on traditional intermittent detection means, and has a continuous self-adaptive evaluation capability, which significantly improves the overall risk perception granularity of the photovoltaic power station and the timeliness and accuracy of hidden danger disposal, and provides effective support for building a more forward-looking intelligent safety protection system for distributed photovoltaic power stations.

[0157] Although the embodiments of the present application have been shown and described, it can be understood by those skilled in the art that various changes, modifications, replacements and variations can be made to the embodiments without departing from the principles and spirits of the present application, and the scope of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent and safe operation and maintenance management of a distributed photovoltaic power station, characterized by: The following steps are included: S1. Deploy smart sensor groups on photovoltaic strings of a distributed photovoltaic power station and use the smart sensor groups to collect photovoltaic string operation data in real time to construct a photovoltaic string operation data set S. Extract characteristic parameters based on the photovoltaic string operation data set S, and construct a characteristic parameter set F based on the extracted characteristic parameters. S2. Based on the characteristic parameter set F, perform characteristic parameter coupling calculation to obtain the physical disturbance risk score , and the physical disturbance risk score and physical disturbance risk thresholds Conduct comparative analysis to identify risky PV strings; S3. For risky PV strings, the risk score of the physical disturbance of the risky PV strings is calculated based on the PV string operation data set S, the characteristic parameter set F and the risky PV strings. , perform coupled calculation of physical disturbance and humidity parameters to obtain the potential leakage probability , and further analyze the degree of degradation of the electrical insulation performance of the risky PV strings to obtain the leakage risk accumulation index LRAI; S4. Compare the leakage risk accumulation index LRAI with the first leakage risk threshold and the second leakage risk threshold Conduct comparative analysis to assess the risk level of risky PV strings; S5. Based on the risk level assessment results, construct a risky PV string set and perform trend aggregation analysis on the risky PV string set to obtain the trend aggregation factor (STCI), identify spatial aggregation risks, and issue early warnings.

2. The method for intelligent and safe operation and maintenance of a distributed photovoltaic power station according to claim 1, characterized in that: The specific steps of S1 include: S11, using each photovoltaic string of the distributed photovoltaic power station as a data acquisition unit, deploying an intelligent sensor group on each photovoltaic string to obtain photovoltaic string operation data, wherein the photovoltaic string operation data includes the photovoltaic string output current value I, voltage V, photovoltaic module surface temperature Tsurf, air temperature Tair and relative humidity H; A photovoltaic string refers to the smallest power generation and operation unit constructed by connecting multiple photovoltaic modules in a DC series manner; The intelligent sensor group includes a combiner box current transformer, a combiner box voltage divider, a thermocouple temperature sensor, and a humidity sensor; S12. Preprocessing the collected photovoltaic string operation data, including data cleaning, data smoothing and normalization, and constructing a photovoltaic string operation data set S based on the preprocessed photovoltaic string operation data.

3. The method for intelligent and safe operation and maintenance management of a distributed photovoltaic power station according to claim 2, characterized in that: The specific steps of S1 also include: S13. Extract characteristic parameters based on the photovoltaic string operation data set S to obtain a current fluctuation index DL, a voltage edge drift index Dv, a capacitive coupling residual index Dr, and a condensation risk index JL; The current fluctuation index DL refers to the volatility of the PV string output current value. By taking the difference between the PV string output current values ​​I at adjacent time points, the current change rate per unit time is obtained, a current change rate time series is constructed, and the standard deviation of the current change rate time series is calculated as the current fluctuation index. The voltage edge drift index Dv refers to the deviation of the waveform slope of the rising or falling edge of the PV string voltage waveform relative to the standard PV string voltage waveform; The capacitive coupling residual index Dr refers to the total amount of fitting residuals between the actual recovery curve of the PV string and the standard RC model when the voltage recovers from a low level to a steady state during the operation of the PV string; The condensation risk index JL refers to the relative critical proximity between the surface temperature Tsurf of the PV module and the air dew point temperature, where the air dew point temperature refers to the critical temperature at which water vapor in the air condenses into liquid water; S14. Construct a characteristic parameter set F based on the obtained current fluctuation index DL, voltage edge drift index Dv, capacitive coupling residual index Dr, and condensation risk index JL.

4. The method for intelligent and safe operation and maintenance of a distributed photovoltaic power station according to claim 3, characterized in that: The specific steps of S2 include: S21. Perform dimensionless processing on the characteristic parameters in the characteristic parameter set F to eliminate the physical dimension, and analyze the risk intensity level of the photovoltaic string under the condition of coupling multiple characteristic parameters based on the dimensionless processed characteristic parameters to obtain the physical disturbance risk score. , where the physical disturbance risk score The specific way to obtain it is: ； Where, 、 and They represent the current fluctuation index DL, voltage edge drift index Dv and capacitive coupling residual index Dr of the PV string at the current time point t, respectively, and ln represents the natural logarithmic constant; S22. Collect the operating data of several photovoltaic strings when they are in a healthy state, so as to calculate the physical disturbance risk scores of several photovoltaic strings when they are in a healthy state. , and score the risk of all physical disturbances in a healthy state Perform statistical distribution analysis and select the 95th percentile physical disturbance risk score from the statistical distribution analysis results As a physical disturbance risk threshold ; S23. Physical disturbance risk threshold and physical disturbance risk scoring Conduct comparative analysis to assess the disturbance risk status of PV strings. If the physical disturbance risk score Greater than or equal to the physical disturbance risk threshold , then the PV string is judged to be in an abnormally enhanced state, and the PV string is marked as a risky PV string. If the physical disturbance risk score Less than the physical disturbance risk threshold , it is determined that the PV string is in a normal state and no processing is required.

5. The method for intelligent and safe operation and maintenance of a distributed photovoltaic power station according to claim 4, characterized in that: The specific steps of S3 include: S31. For the marked risky PV strings, based on the PV string operation data set S, characteristic parameter set F and physical disturbance risk score , comprehensively analyze the probability of potential leakage of risk PV strings under the influence of current physical disturbance and environmental humidity to obtain the potential leakage probability , where the potential leakage probability The specific manifestations are: ； Where, represents the leakage trend coupling coefficient, exp represents the exponential function, represents the relative humidity of the risky PV string at the current time point t, Indicates the condensation risk index of the risky PV string at the current time point t.

6. A distributed photovoltaic power station intelligent safety operation and maintenance management method according to claim 5, characterized in that: The specific steps of S3 also include: S32, set time sampling window { , t}, and according to the photovoltaic string operation data set S, obtain the time sampling window { , the potential leakage probability at each data acquisition time point within t} The sliding integral method is used to analyze the degree of degradation of the electrical insulation performance of the risky PV strings to obtain the leakage risk accumulation index LRAI. The specific method for obtaining the leakage risk accumulation index LRAI is as follows: ； Where, Indicates the risk of PV strings at the data collection time point The potential leakage probability when represents the integration variable, Indicates the length of the historical time window, Represents the attenuation factor.

7. The method for intelligent and safe operation and maintenance of a distributed photovoltaic power station according to claim 6, characterized in that: The specific steps of S4 include: S41. Preset the first leakage risk threshold and the second leakage risk threshold and the leakage risk accumulation index LRAI and the first leakage risk threshold and the second leakage risk threshold A comparative analysis is conducted to assess the risk level of risky PV strings. The specific assessment contents are as follows: If the leakage risk accumulation index LRAI is less than or equal to the first leakage risk threshold , the risk level of the risky PV string is judged to be the first risk level. At this time, the normal operation mode of the PV power station is maintained, and the data monitoring frequency is maintained at normal level; If the leakage risk accumulation index LRAI is greater than the first leakage risk threshold , and is less than or equal to the second leakage risk threshold , the risk level of the risky PV string is determined to be the second risk level. At this time, there is abnormal fluctuation in the risky PV string, which needs to trigger the early warning mechanism, generate an early warning tag, and send the early warning tag to the safety monitoring platform. At the same time, the data monitoring frequency is adjusted from once every 30 minutes to once every 10 minutes. If the leakage risk accumulation index LRAI is greater than or equal to the second leakage risk threshold , the risk level of the risky PV string is determined to be the third risk level. At this time, a PV string isolation instruction is immediately generated, and the isolation switch corresponding to the PV string is closed to disconnect the PV string from the main circuit. An isolation log and an execution report are generated and continuously sent to the safety monitoring platform. An alarm is issued until the safety monitoring platform administrator responds.

8. The method for intelligent and safe operation and maintenance of a distributed photovoltaic power station according to claim 7, characterized in that: The specific steps of S5 include: S51, gather risky photovoltaic strings at the first risk level and the second risk level, construct a risky photovoltaic string set, extract the leakage risk accumulation index LRAI of each risky photovoltaic string in the risky photovoltaic string set, and perform data averaging to obtain the average value of the leakage risk accumulation index ; S52. Calculate the leakage risk accumulation index LRAI and the average value of the leakage risk accumulation index of each risky PV string in the risky PV string set and divide the difference by the average value of the leakage risk accumulation index The sum of the trend deviation rate BIAS of each risky PV string is obtained by adding the non-zero small constant ε.

9. The method for intelligent and safe operation and maintenance of a distributed photovoltaic power station according to claim 8, characterized in that: The specific steps of S5 also include: S53, based on the trend deviation rate of each risky PV string and the average value of leakage risk accumulation index , use the variance calculation formula to obtain the trend deviation rate of the risk photovoltaic string set Variance, that is, the trend clustering factor STCI; S54. Extract the historical photovoltaic string operation data of the risk photovoltaic string set to continuously calculate the trend aggregation factor STCI of the risk photovoltaic string set over a period of time, construct the trend aggregation factor time series, and obtain the historical mean and historical standard deviation of the trend aggregation factor STCI based on the trend aggregation factor time series, and obtain the dynamic trend risk threshold through the standard deviation boundary model. ; S55. Dynamic trend risk threshold A comparative analysis is conducted with the trend clustering factor (STCI) to assess the risk of degradation trend fluctuations among risky PV strings. The specific assessment contents are as follows: If the trend concentration factor STCI is greater than or equal to the dynamic trend risk threshold , it is determined that the degradation trend fluctuations between risky PV strings are in an abnormal range, and there is a phenomenon of synchronous enhancement of degradation trends between risky PV strings, and there is a spatial clustering risk. At this time, the trend deviation rate in the risky PV string set is screened out. Greater than 0 and higher than the trend deviation rate at multiple consecutive time points The system then determines the risky PV strings based on the average value and, based on the PV power station equipment distribution map, determines whether the risky PV strings belong to a physically adjacent area. If so, it indicates that the risky PV strings in the physically adjacent area have a regional potential leakage risk, immediately triggering an early warning mechanism, generating a manual maintenance task, and executing a voltage reduction operation strategy. If not, no action is required. If the trend concentration factor STCI is less than the dynamic trend risk threshold , it is determined that the degradation trend fluctuation between risky PV strings is within the normal range and no processing is required.

10. A distributed photovoltaic power station intelligent safety operation and maintenance management system, used to implement the distributed photovoltaic power station intelligent safety operation and maintenance management method according to any one of claims 1 to 9, characterized in that: It includes data acquisition and feature extraction module, disturbance analysis module, potential leakage probability calculation module, risk assessment module and spatial aggregation analysis module; The data acquisition and feature extraction module is used to deploy an intelligent sensor group on the photovoltaic strings of the distributed photovoltaic power station, and use the intelligent sensor group to collect photovoltaic string operation data in real time to construct a photovoltaic string operation data set S, and extract feature parameters based on the photovoltaic string operation data set S, and construct a feature parameter set F based on the extracted feature parameters; The disturbance analysis module is used to perform characteristic parameter coupling calculation based on the characteristic parameter set F to obtain the physical disturbance risk score. , and the physical disturbance risk score and physical disturbance risk thresholds Conduct comparative analysis to identify risky PV strings; The potential leakage probability calculation module is used for risky photovoltaic strings, based on the photovoltaic string operation data set S, characteristic parameter set F and the physical disturbance risk score of the risky photovoltaic strings. , perform coupled calculation of physical disturbance and humidity parameters to obtain the potential leakage probability , and further analyze the degree of degradation of the electrical insulation performance of the risky PV strings to obtain the leakage risk accumulation index LRAI; The risk assessment module is used to compare the leakage risk accumulation index LRAI with the first leakage risk threshold and the second leakage risk threshold Conduct comparative analysis to assess the risk level of risky PV strings; The spatial aggregation analysis module is used to construct a risky photovoltaic string set based on the risk level assessment results, and perform trend aggregation analysis on the risky photovoltaic string set to obtain the trend aggregation factor (STCI), identify spatial aggregation risks, and issue early warnings.

Images