Lightning protection grounding system suitable for loose coal gangue geology photovoltaic power station

By using lightning protection grounding system with galvanized flat steel and toner plus clay materials in photovoltaic power stations, combined with sensors and data analysis, real-time monitoring and dynamic optimization of loose coal gangue under geological conditions is achieved, and the grounding resistance and The problem of spontaneous combustion risk improves the safety and stability of the system.

CN118943774APending Publication Date: 2024-11-12CHINA WATER NORTHEASTERN INVESTIGATION DESIGN & RES +2
View PDF 0 Cites 2 Cited by

Patent Information

Application Number
CN202411363251.6
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-27
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing lightning protection grounding system is difficult to reduce the grounding resistance under loose coal gangue geological conditions, and lacks real-time monitoring and dynamic adjustment capabilities, which has led to the threat of the safety and stability of photovoltaic power plants, especially in the monitoring of spontaneous combustion risks.

Method used

A horizontal outdoor grounding mesh and vertical ground pole composed of galvanized flat steel is designed, combined with toner and clay resistance reduction materials, equipped with a variety of sensors for real-time data monitoring. The data processing center uses principal component analysis and ARIMA model to perform data. Preprocessing and prediction, real-time monitoring and early warning system automatically issues alarms, and uses Q learning algorithms for intelligent optimization and control.

Benefits of technology

It effectively reduces grounding resistance, improves lightning protection effect, realizes timely early warning and prevention of spontaneous combustion risks, enhances the overall safety and reliability of photovoltaic power stations, and reduces failure rate and maintenance costs.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118943774A_ABST
    Figure CN118943774A_ABST
Patent Text Reader

Abstract

The invention relates to the field of mine area photovoltaic power station lightning protection, and discloses a lightning protection grounding system suitable for a loose coal gangue geology photovoltaic power station, and the system comprises an outdoor horizontal grounding grid which is composed of galvanized flat steel; the plurality of vertical grounding electrodes are formed by galvanized steel pipes; the carbon powder and clay resistance reducing material is laid around the outdoor horizontal grounding grid; a plurality of sensors distributed at different positions of the photovoltaic power station and used for monitoring temperature, humidity, CO concentration and grounding resistance; the data processing center comprises a wireless transmission device, a data preprocessing unit, a data storage facility and a data analysis platform; the real-time monitoring and early warning system comprises a display device and an early warning signaling mechanism. And the intelligent optimization control module dynamically adjusts grounding system parameters and environment control measures according to the monitoring data. By reducing the grounding resistance, safe operation of the photovoltaic power station under the condition of thunder and lightning or short circuit can be ensured, the failure rate is reduced, and the reliability of equipment is improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of lightning protection for photovoltaic power stations in mining areas, and in particular to a lightning protection grounding system suitable for photovoltaic power stations in loose coal gangue geology. Background Art

[0002] With the rapid development of new energy, photovoltaic power generation has become an important means to solve energy crises and environmental problems worldwide. However, photovoltaic power stations are usually located in open areas and face multiple risks such as lightning strikes, environmental factors and spontaneous combustion. These risks pose a serious threat to the safety and stability of photovoltaic power generation systems, especially under loose coal gangue geological conditions, where traditional lightning protection and grounding systems face many technical difficulties.

[0003] The existing lightning protection grounding system mainly relies on a simple grounding grid and grounding electrode structure, but under loose coal gangue geological conditions, the grounding resistance is difficult to effectively reduce. This high grounding resistance not only reduces the lightning protection effect, but may also cause equipment to suffer overvoltage damage when struck by lightning, increasing the instability of the system. In addition, the traditional grounding system lacks intelligent monitoring and dynamic adjustment capabilities, and cannot respond to changes in the environment and equipment status in real time, resulting in low maintenance efficiency and delayed fault response.

[0004] Traditional monitoring methods rely on manual inspections and regular maintenance, and cannot achieve real-time monitoring of photovoltaic power stations. This method not only consumes a lot of manpower and resources, but also has monitoring blind spots, making it difficult to timely discover and deal with potential safety hazards. In particular, for the monitoring of spontaneous combustion risks, traditional systems are difficult to provide effective early warnings, and the fire risk caused by spontaneous combustion of coal gangue seriously threatens the safe operation of photovoltaic power stations.

[0005] In terms of intelligent optimization, existing technologies usually use static configurations and lack the ability to dynamically adjust based on real-time data. This fixed system design is difficult to cope with complex and changing environmental conditions and cannot ensure that the grounding system can maintain optimal performance under different conditions. At the same time, traditional systems lack the ability to comprehensively analyze and predict grounding resistance and environmental parameters, and cannot achieve intelligent prevention and response.

[0006] In summary, the existing technology has significant defects in grounding resistance reduction, real-time monitoring, dynamic adjustment and intelligent optimization of lightning protection grounding systems, and it is difficult to meet the safe operation requirements of photovoltaic power stations in loose coal gangue geology. Therefore, an innovative lightning protection grounding system that can comprehensively solve the above problems is urgently needed to improve the overall safety, reliability and operation efficiency of photovoltaic power stations. Summary of the invention

[0007] In view of the shortcomings of the prior art, the present invention provides a lightning protection and grounding system suitable for loose coal gangue geological photovoltaic power stations, which can not only provide lightning protection and grounding protection, but also monitor the risk of spontaneous combustion of coal gangue mountains in real time.

[0008] To achieve the above objectives, the present invention is implemented through the following technical solutions: A lightning protection grounding system suitable for a photovoltaic power station in loose coal gangue geology, comprising:

[0009] Outdoor horizontal grounding grid, made of galvanized flat steel;

[0010] Multiple vertical grounding electrodes made of galvanized steel pipes;

[0011] Carbon powder plus clay resistance reduction material laid around the outdoor horizontal grounding grid;

[0012] Multiple sensors distributed in different locations of the PV power plant to monitor temperature, humidity, CO concentration and ground resistance;

[0013] Data processing center, including wireless transmission devices, data pre-processing units, data storage facilities and data analysis platforms;

[0014] Real-time monitoring and early warning system, including display equipment and early warning signaling mechanism;

[0015] Intelligent optimization control module dynamically adjusts grounding system parameters and environmental control measures based on monitoring data.

[0016] Preferably, the system further comprises an equipment downconductor, and the equipment downconductor is made of galvanized flat steel.

[0017] Preferably, the specifications of the galvanized flat steel of the outdoor horizontal grounding grid are 60mm±10mm in width and 6mm±1mm in thickness.

[0018] Preferably, the outdoor horizontal grounding grid is buried at a depth of 50-70 cm below the ground, and carbon powder and clay are laid around the grounding body with a laying thickness of 25-35 cm.

[0019] Preferably, the vertical grounding electrode is a galvanized steel pipe with a diameter of 45-55 mm and a length of 2400-2600 mm, which is vertically buried underground and installed one every 8-12 meters.

[0020] Preferably, the sensors include a temperature sensor, a humidity sensor, a CO concentration sensor and a ground resistance sensor, and the sensors are arranged at different key positions of the photovoltaic power station to collect data once a minute.

[0021] Preferably, the data analysis platform of the data processing center uses principal component analysis to perform dimensionality reduction processing on the data, and the specific steps include:

[0022] Compute the covariance matrix of the data;

[0023] Perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors;

[0024] Select the eigenvectors corresponding to the first k largest eigenvalues ​​to form a feature matrix;

[0025] Project the original data onto the feature matrix to obtain the reduced-dimensional data;

[0026] The reduced-dimensional data is then used for further analysis and modeling.

[0027] Preferably, the data analysis platform of the data processing center uses the ARIMA model to predict the ground resistance, and the specific steps include:

[0028] Collect historical ground resistance data and construct a time series dataset;

[0029] Determine the order of the ARIMA model through the autocorrelation function and partial autocorrelation function graphs;

[0030] Use the training data set to fit the ARIMA model and obtain the model parameters;

[0031] Use the trained ARIMA model to perform short-term prediction of ground resistance;

[0032] The ARIMA model formula is:

[0033]

[0034] in, is the predicted grounding resistance, R(t-1), R(t-2), …, R(tp) are the grounding resistance values ​​of the first p time steps, φ1, φ2, …, φ p are the model parameters of the AR part, ∈(t-1), ∈(tq) are the error terms of the first q time steps, θ1, θ q is the model parameter of the MA part

[0035] Preferably, the real-time monitoring and early warning system automatically issues an alarm when the ground resistance or spontaneous combustion risk score exceeds a preset threshold, specifically including:

[0036] The preset threshold value of the ground resistance is not greater than 0.5Ω;

[0037] The spontaneous combustion risk score is predicted by a multivariate linear regression model, and the specific steps include:

[0038] Collect environmental parameter data such as temperature, humidity, and CO concentration;

[0039] Use the multivariate linear regression model to train the data set and determine the model coefficient β;

[0040] Real-time calculation of spontaneous combustion risk score based on the model formula:

[0041]

[0042] in, is the predicted spontaneous combustion risk score, x i For different environmental parameters, β i is the corresponding model coefficient;

[0043] When the spontaneous combustion risk score exceeds the preset threshold, the system automatically issues a warning signal.

[0044] Preferably, the intelligent optimization control module uses a Q learning algorithm to optimize and adjust the grounding system, and the specific steps include:

[0045] Define the state space S, including ground resistance value and environmental parameter value;

[0046] Define action space A, including adjusting the number of grounding electrodes and changing the layout of galvanized flat steel;

[0047] Define a reward function R to give positive and negative rewards according to the change of ground resistance;

[0048] Use Q-learning algorithm to gradually optimize the grounding system design and obtain the optimal grounding system configuration;

[0049] The Q learning algorithm formula is:

[0050] Q(s,a)=r+γmax a′ Q(s′,a′)

[0051] Among them, Q(s,a) is the value of taking action a in state s, r is the immediate reward, γ is the discount factor, and a′ is the possible action in the next state s′.

[0052] The invention provides a lightning protection grounding system suitable for a photovoltaic power station in loose coal gangue geology.

[0053] It has the following beneficial effects:

[0054] 1. The present invention can ensure the safe operation of photovoltaic power stations in the event of lightning or short circuits by reducing grounding resistance, reduce failure rates, and increase equipment reliability. The optimized grounding system can maintain a stable grounding resistance under extreme weather conditions to ensure the stable operation of the photovoltaic system. By reducing electrical shocks caused by poor grounding, the service life of photovoltaic equipment can be extended and maintenance costs can be reduced.

[0055] 2. The present invention uses the down conductor to quickly ground the electrical equipment when the lightning current passes through, which reduces the damage to the equipment caused by lightning and improves the lightning protection effect. At the same time, galvanized flat steel is used as the down conductor material. Due to its good corrosion resistance, it can provide longer-term protection in harsh outdoor environments, reduce maintenance costs, and extend the service life of the system.

[0056] 3. The present invention can instantly detect potential abnormal conditions and performance degradation of the system through real-time monitoring and early warning systems, and issue early warnings, thereby allowing maintenance personnel to intervene and repair in a timely manner. This timely problem diagnosis and processing significantly reduces equipment failure rates and maintenance costs, extends the service life of equipment, and improves overall operation and maintenance efficiency.

[0057] 4. The present invention combines the spontaneous combustion risk scoring model with environmental monitoring to effectively prevent the risk of spontaneous combustion caused by environmental factors, especially in areas where flammable materials such as gangue are stored. Through accurate risk assessment and timely early warning mechanisms, the photovoltaic power station's ability to prevent disasters such as fires is enhanced, greatly improving the overall safety and reliability of the site. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is one of the schematic diagrams of the lightning protection grounding system of the present invention;

[0059] Figure 2 This is the second schematic diagram of the lightning protection grounding system of the present invention;

[0060] Figure 3 It is a system logic flow chart of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings of the present invention specification to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Please see attached Figure 1 -Attached Figure 3 The embodiment of the present invention provides a lightning protection grounding system suitable for a photovoltaic power station in loose coal gangue geology, including an outdoor horizontal grounding grid, a vertical grounding electrode and measures to reduce the grounding resistance.

[0063] First of all, the grounding resistance of the grounding device should generally meet the following requirements:

[0064]

[0065] Where:

[0066] R-maximum ground resistance considering seasonal changes, Ω;

[0067] I- The short-circuit current flowing through the grounding device used for calculation, U.

[0068] The maximum single-phase short-circuit current is considered according to the thermal stability current of the equipment. The single-phase short-circuit current occurring on the 220kV side is considered to be 25kA. After considering the power frequency shunt coefficient of the main transformer neutral point, line lightning conductor and other facilities, it is taken as 60%. According to the above formula, the grounding resistance R should be less than or equal to 0.13Ω.

[0069] Since the maximum short-circuit current occurs on the 220kV side, according to the "Grounding Design Specifications for AC Electrical Installations" (GB / T50065-2011): e =t m +t f +t0, short circuit duration time t on 220kV side e Take 0.6s, so the grounding body cross section is calculated according to the 220kV short-circuit current. According to the geological survey report of the reference mining area, the main grounding grid adopts steel grounding.

[0070] according to For thermal stability calculation, the effective cross-section of the main grounding grid should be no less than 262.25mm2, and the effective cross-section of the equipment down conductor should be no less than 376.64mm2. Taking into account the corrosiveness of the grounding material, the main grounding grid is made of galvanized flat steel with a specification of 60*6, and the end of the 4mm2 special grounding cord of the photovoltaic module is reliably connected to the outdoor horizontal grounding grid. The grounding device of the box-type step-up transformer is reliably connected to the outdoor grounding device, and a vertical grounding electrode is added. The vertical grounding electrode adopts a 50mm, L=2500mm galvanized steel pipe, and the equipment down conductor adopts a 60×8mm (>376.64mm 2 ) galvanized flat steel. Since the electrical equipment is mainly installed outdoors, the grounding resistance is guaranteed to be less than 4 ohms. To ensure personal safety, all electrical equipment is equipped with grounding devices, and the housing of the electrical equipment is reliably grounded. The grounding resistance must meet the requirements of relevant national standards. According to past experience, it is difficult to reduce the grounding resistance of the substation to less than 0.13Ω. Therefore, the grounding resistance is not greater than 0.5Ω.

[0071] At the same time, in order to ensure the safety of equipment and personnel, it is necessary to ensure that the step potential difference within the station area is within a safe range.

[0072] The step potential difference is the potential difference between the two feet of a human body in a walking state when the ground fault current flows through the grounding device. It is defined as the potential difference between two points on the ground with a horizontal distance of 1.0m.

[0073] Step potential difference U s and geometric correction factor K S, correction factor K, soil resistivity P, average stray current per unit conductor length of the grounding system, step potential difference U s for:

[0074]

[0075] L s =0.75L c +0.85L R

[0076] in:

[0077] I G - is the ground fault current of the grounding grid

[0078] L s - is the effective length of the grounding system conductor buried in the ground.

[0079] Gravel and other materials with a resistivity of not less than 5000Ω.m are laid as high resistance layers, and carbon powder and clay are laid around the horizontal grounding body. After calculation, after laying a 30cm thick insulating operation floor, the grounding resistance is reduced, and finally the step potential difference in the station meets the safety requirements.

[0080] Therefore, in this embodiment, the lightning protection grounding system is constructed as follows:

[0081] Construction of outdoor horizontal grounding grid: A new outdoor horizontal grounding grid made of galvanized flat steel is built in the photovoltaic field. The specifications of the galvanized flat steel are 60mm wide and 6mm thick. This specification of flat steel can ensure sufficient cross-sectional area to meet the requirements of thermal stability calculation. Calculation formula It ensures that under short-circuit conditions, the grounding grid can withstand the current passing through it without being damaged due to excessive temperature rise.

[0082] Installation of vertical grounding electrodes: Vertical grounding electrodes are added on the basis of outdoor horizontal grounding grid to improve the effectiveness of the grounding system. Vertical grounding electrodes use galvanized steel pipes with a diameter of 50mm and a length of 2500mm. These steel pipes are buried vertically underground and connected to the horizontal grounding grid, thus forming a three-dimensional grounding system, increasing the grounding area and reducing the grounding resistance.

[0083] Measures to reduce grounding resistance: In order to further reduce grounding resistance, carbon powder and clay are laid around the horizontal grounding body. Carbon powder has good conductivity, while clay can keep the soil moist. The combination of the two can significantly reduce grounding resistance.

[0084] The reduction of grounding resistance helps to quickly and effectively introduce lightning current into the ground when lightning strikes, reduce overvoltage of equipment, and avoid equipment damage and instability of power system caused by lightning strikes. By rationally designing the shape, size and material of the grounding grid, and adding auxiliary conductive materials, the grounding resistance can be effectively reduced. At the same time, in the case of a short circuit, the grounding grid must be able to withstand huge currents without overheating, otherwise it may cause damage to the grounding grid material. Thermal stability calculation ensures that the temperature of the grounding grid will not exceed the safety limit within the predetermined short circuit duration.

[0085] The present invention can ensure the safe operation of the photovoltaic power station under lightning or short circuit conditions by reducing the grounding resistance, reduce the failure rate, and increase the reliability of the equipment. The optimized grounding system can maintain a stable grounding resistance under extreme weather conditions to ensure the stable operation of the photovoltaic system. By reducing the electrical shock caused by poor grounding, the service life of the photovoltaic equipment can be extended and the maintenance cost can be reduced.

[0086] As an implementation mode of the present invention, the system further comprises an equipment down conductor, and the equipment down conductor is made of galvanized flat steel.

[0087] The equipment down conductor is an important component that connects the electrical equipment housing to the grounding system. In this embodiment, the down conductor is made of galvanized flat steel, and its specifications need to be greater than or equal to 60mm×8mm to meet the effective cross-sectional area of ​​not less than 376.64mm 2 This design ensures that the downconductor can safely carry the high currents that may be experienced in extreme situations, such as direct lightning currents.

[0088] Galvanized flat steel is the material of choice for down conductors, as it not only has good electrical conductivity, but the zinc coating also provides additional corrosion protection, extending the service life of the system, especially in outdoor environments, facing wind, sun and humid conditions.

[0089] As a connection channel between electrical equipment and the grounding grid, the down conductor must be able to conduct current efficiently. Due to its large cross-sectional area, galvanized flat steel can provide low resistance, thereby efficiently conducting current to the grounding grid. Down conductors may experience a dramatic temperature increase during a lightning strike. Galvanized flat steel has sufficient thermal stability and mechanical strength to withstand high temperatures and physical shocks in a short period of time, ensuring the integrity of the system.

[0090] The present invention enables electrical equipment to be quickly grounded when lightning current passes through by adding a down conductor to the equipment, thereby reducing damage to the equipment caused by lightning and improving the effect of lightning protection. At the same time, galvanized flat steel is used as the down conductor material. Due to its good corrosion resistance, it can provide longer-term protection in harsh outdoor environments, reduce maintenance costs, and extend the service life of the system. In addition, when a lightning strike or electrical failure occurs, the down conductor can ensure that excessive current quickly flows into the ground, reducing the risk of electric shock, thereby ensuring personal safety.

[0091] Furthermore, the lightning protection grounding system of the present invention includes, in addition to the grounding grid structure, a plurality of sensors, a data processing center, a real-time monitoring and early warning system, and an intelligent optimization control module. These components work together to improve the efficiency and response speed of the system and ensure the safe operation of the photovoltaic power station in the event of lightning or other electrical faults.

[0092] Specifically, the lightning protection and grounding system of the present invention integrates a variety of sensors to ensure comprehensive monitoring of key environmental parameters of photovoltaic power stations. Specifically including:

[0093] Temperature Sensor:

[0094] Layout location: Installed on the back of photovoltaic panels, near substations and other heat-sensitive areas.

[0095] Function: Monitor the temperature of equipment and environment. The data is used to analyze the equipment operation status and environmental impact, and prevent equipment failure or fire caused by overheating.

[0096] Humidity Sensor:

[0097] Layout location: Installed on the ground surface near the grounding grid and in the room of electrical equipment.

[0098] Function: Monitor air humidity, as humidity directly affects grounding resistance and the insulation performance of electrical equipment. Humidity data is essential to maintaining the effectiveness of the grounding system.

[0099] CO concentration sensor:

[0100] Layout location: Especially placed in and around coal gangue storage areas, which are prone to spontaneous combustion.

[0101] Function: Real-time monitoring of carbon monoxide (CO) concentration as a warning indicator of spontaneous combustion, helping to detect fire risks early, especially in areas where coal gangue may spontaneously combust.

[0102] Ground resistance sensor:

[0103] Layout location: Installed at multiple key nodes of the grounding grid, especially the entry point and remote point of the grounding grid.

[0104] Function: Continuously monitor the change of ground resistance, the data is essential for evaluating the health and performance of the entire grounding system. The resistance measurement results help to adjust the grounding configuration or perform necessary maintenance work in time to ensure system performance.

[0105] These sensors transmit data to the data processing center in real time through wireless technology, ensuring the safe operation of the photovoltaic power station and effectively preventing failures and disasters. This intelligent monitoring system not only enhances the operation and maintenance capabilities of the photovoltaic station, but also greatly improves the response efficiency and safety management level.

[0106] The data processing center of the present invention includes a data analysis platform, which performs dimensionality reduction processing on the collected multi-source data by implementing principal component analysis (PCA). This process is intended to improve data processing efficiency and more accurately identify key variables, thereby optimizing monitoring and control strategies. The following are specific implementation steps:

[0107] 1. Data preprocessing:

[0108] Before conducting principal component analysis, the data is first standardized. All data are scaled to a form with zero mean and unit variance to ensure that data of different measurements are comparable and prevent differences in data measurement from affecting the analysis results.

[0109] 2. Calculate the covariance matrix of the data:

[0110] The covariance matrix between the variables is calculated using the standardized data. The covariance matrix describes the linear correlation between the variables, with the diagonal elements representing the variance of each variable and the off-diagonal elements representing the covariance between different variables.

[0111] 3. Perform eigenvalue decomposition:

[0112] Perform eigenvalue decomposition on the covariance matrix to obtain a set of eigenvalues ​​and corresponding eigenvectors. The eigenvalues ​​reflect the importance of each component in the data, while the eigenvectors indicate the direction of these principal components.

[0113] 4. Select the main components:

[0114] According to the size of the eigenvalue, the eigenvectors corresponding to the first k largest eigenvalues ​​are selected, and these eigenvectors constitute the characteristic matrix. The number of eigenvectors k selected depends on the cumulative contribution rate, and the principal component with a cumulative contribution rate of more than 85% is usually selected.

[0115] 5. Data Projection:

[0116] Project the original data set onto the selected eigenvectors, that is, use the feature matrix to transform the high-dimensional data into a low-dimensional space. This step is completed by matrix multiplication, and the result is a reduced-dimensional data set, where each row represents the coordinates of an observation in the new low-dimensional space.

[0117] 6. Utilization of dimensionality reduction data:

[0118] Use the reduced-dimensional data for further data analysis and modeling. Reduced-dimensional data is easier to visualize, cluster, and perform regression analysis due to its lower dimension. At the same time, the reduced data dimension also helps improve the training efficiency and prediction accuracy of subsequent machine learning models.

[0119] Data processed by PCA dimensionality reduction is more suitable for rapid response and decision support of monitoring systems because it simplifies the complexity of the problem. For example, in a real-time monitoring system, the dimensionality-reduced data can be used to quickly detect abnormal conditions, and the early warning system can quickly identify changes beyond the normal range based on the model, thereby issuing an alarm in a timely manner.

[0120] The data analysis platform of the data processing center of the present invention uses the ARIMA (Autoregressive Integrated Moving Average) model to predict the ground resistance data collected from the sensor. This process analyzes historical data, establishes a time series model, and performs short-term predictions, thereby helping to foresee the future trend of ground resistance changes and take preventive measures in advance.

[0121] The specific implementation steps are as follows:

[0122] 1. Collect historical ground resistance data and construct a time series dataset:

[0123] The ground resistance data over a long period of time is collected from the ground resistance sensor to construct a time series data set. These data points are arranged in time order, and each data point represents the ground resistance value of one time step.

[0124] 2. Data preprocessing:

[0125] Perform preliminary processing on time series data, including removing outliers, filling missing values, and performing data stationarity tests. ADF (Augmented Dickey-Fuller) test is usually used for stationarity test. If the data is not stationary, perform difference operation to make it stationary.

[0126] 3. Determine the order of the ARIMA model through the autocorrelation function and partial autocorrelation function graph:

[0127] Plot the autocorrelation function (ACF) and partial autocorrelation function (PACF) graphs, and determine the orders (p and q values) of the AR and MA parts by observing the truncation and tailing phenomena in the ACF and PACF graphs.

[0128] Statistical methods such as AIC (Akaike Information Criterion) and BIC (Bayesian Information Criterion) were used to further optimize the selection of the model order.

[0129] 4. Use the training data set to fit the ARIMA model and obtain the model parameters:

[0130] The processed time series data is divided into training set and test set, and the training set is used for model fitting.

[0131] The model parameters are estimated using the maximum likelihood estimation method to obtain the parameters φ and θ of the ARIMA model.

[0132] The ARIMA model formula is:

[0133]

[0134] in, is the predicted grounding resistance, R(t-1), R(t-2), …, R(tp) are the grounding resistance values ​​of the first p time steps, φ1, φ2, …, φ p are the model parameters of the AR part, ∈(t-1), ∈(tq) are the error terms of the first q time steps, θ1, θ q are the model parameters of the MA part.

[0135] 5. Model verification and adjustment:

[0136] The prediction accuracy of the model was verified using the test set, and the model performance was evaluated by calculating indicators such as mean square error (MSE) and root mean square error (RMSE).

[0137] Adjust the model parameters according to the validation results to ensure that the model has good predictive ability.

[0138] 6. Use the trained ARIMA model to make short-term predictions of ground resistance:

[0139] The ground resistance of several future time steps is predicted using the trained ARIMA model.

[0140] The predictions are compared with the actual measurements and the model is adjusted to improve the prediction accuracy.

[0141] The prediction results can be used to foresee the changing trend of ground resistance in advance, helping the operation and maintenance team to take preventive maintenance measures.

[0142] Through the above steps, the data processing center uses the ARIMA model to effectively predict the grounding resistance, helping the photovoltaic power station operation and maintenance team to foresee potential problems and take timely measures to ensure the stable operation and safety of the system.

[0143] The real-time monitoring and early warning system of the present invention automatically issues an alarm to ensure the safe operation of the photovoltaic power station by monitoring the ground resistance and spontaneous combustion risk score. The system uses multiple sensor data for real-time calculation and issues an early warning based on a preset threshold.

[0144] The specific implementation steps are as follows:

[0145] 1. Ground resistance monitoring and early warning:

[0146] Preset threshold: The system sets the preset safety threshold of ground resistance to no more than 0.5Ω. This threshold is determined according to national standards and actual operating experience to ensure the lightning protection effect and safety performance of the system.

[0147] Real-time monitoring: The ground resistance sensor monitors the ground resistance value in real time and transmits the data to the data processing center.

[0148] Threshold comparison: The real-time monitoring system compares the current ground resistance value with the preset threshold.

[0149] Alarm triggering: When the ground resistance value exceeds 0.5Ω, the system automatically issues an alarm to notify the operation and maintenance personnel to conduct inspection and maintenance.

[0150] 2. Spontaneous combustion risk score prediction and early warning:

[0151] Data collection: The system collects environmental parameter data such as temperature, humidity, CO concentration, etc. in real time. These data are collected through corresponding sensors and transmitted to the data processing center.

[0152] Model training: Use the multivariate linear regression model to train the collected data and determine the model coefficient β i :

[0153] Use historical data sets to perform regression analysis to determine the environmental parameters (x i ) on the risk of spontaneous combustion (β i ).

[0154] The formula of the multivariate linear regression model after training is:

[0155]

[0156] in, is the predicted spontaneous combustion risk score, x i For different environmental parameters, β w are the corresponding model coefficients.

[0157] Real-time calculation: Based on the current sensor data, the trained model is used to calculate the spontaneous combustion risk score in real time

[0158] Threshold comparison: The system sets a preset safety threshold for the spontaneous combustion risk score. When this threshold is exceeded, a high risk of spontaneous combustion is considered to exist.

[0159] Alarm trigger: When the spontaneous combustion risk score calculated in real time When the preset threshold is exceeded, the system automatically sends out a warning signal to notify relevant personnel to take preventive measures.

[0160] 3. Early warning signal transmission:

[0161] Multiple methods: The system transmits warning signals through multiple methods, including SMS, email and application notifications, to ensure that relevant personnel can receive alarm information in time.

[0162] Alarm level: The system sets different alarm levels according to the degree of exceeding the limit of ground resistance value and spontaneous combustion risk score, which are divided into low, medium and high alarms, so that operation and maintenance personnel can take corresponding actions according to the alarm level.

[0163] Low-level alarm: The ground resistance value is close to 0.5Ω or the spontaneous combustion risk score is slightly higher than the threshold. It is recommended that the operation and maintenance personnel conduct an inspection.

[0164] Intermediate alarm: The ground resistance value obviously exceeds 0.5Ω or the spontaneous combustion risk score is significantly higher than the threshold. It is recommended that the operation and maintenance personnel take maintenance measures as soon as possible.

[0165] Advanced alarm: The ground resistance value significantly exceeds 0.5Ω or the spontaneous combustion risk score is extremely high, requiring operation and maintenance personnel to take emergency measures immediately to prevent safety accidents.

[0166] 4. Alarm processing and recording:

[0167] Automatic recording: The triggering time, specific value and processing results of each alarm are automatically recorded by the system to facilitate future analysis and improvement of maintenance strategies.

[0168] Response measures: Operation and maintenance personnel will quickly formulate and implement corresponding response measures based on the alarm information and level, including adjusting the grounding system configuration, improving environmental ventilation, adding resistance-reducing materials, etc.

[0169] Feedback mechanism: After handling the alarm, the operation and maintenance personnel will feed back the processing results to the system. The system records and analyzes the feedback information to optimize future early warning mechanisms and maintenance plans.

[0170] Through the above steps, the real-time monitoring and early warning system of the present invention can efficiently and accurately monitor the grounding resistance and the risk of spontaneous combustion, and issue an alarm in time to ensure the safe and stable operation of the photovoltaic power station under various environmental conditions.

[0171] The intelligent optimization control module of the present invention dynamically optimizes and adjusts the grounding system by using a Q-learning algorithm. The algorithm continuously learns and adjusts the configuration of the grounding system to optimally respond to changes in the environment and electrical conditions, thereby keeping the grounding resistance within a safe range and improving the stability and reliability of the system.

[0172] The specific implementation steps are as follows:

[0173] 1. Define the state space S:

[0174] The state space S includes all the key parameters of the grounding system, including:

[0175] Current grounding resistance value R;

[0176] Environmental parameter values ​​(such as temperature R, humidity H, CO concentration C);

[0177] These parameters together describe the current state of the grounding system, and the state vector s is expressed as:

[0178] s=(R,R,H,C)

[0179] 2. Define the action space A:

[0180] Action space A includes the adjustments that can be made to the grounding system, including:

[0181] Adjust the number of grounding electrodes N;

[0182] Change the layout L of galvanized flat steel;

[0183] Increase or decrease the amount of drag-reducing material used M;

[0184] Action a is represented by:

[0185] a=(N,L,M)

[0186] 3. Define the reward function R:

[0187] The reward function R is used to evaluate the effect of each action and give positive and negative rewards according to the change in ground resistance, including:

[0188] If the adjusted grounding resistance is reduced and within the safe range (no more than 0.5Ω), a positive reward r will be given;

[0189] If the adjusted ground resistance does not decrease or exceeds the safe range, a negative reward -r is given;

[0190] The reward function formula is:

[0191]

[0192] Among them, R' is the adjusted grounding resistance value.

[0193] 4. Implementation of Q-learning algorithm:

[0194] Initialize Q value: Initialize the Q table. Each element Q(s,a) of the Q table represents the value of taking action a in state s, and the initial value is set to zero.

[0195] Strategy selection: In each state s, the greedy strategy is used to select action a, that is:

[0196] Randomly select actions with probability ∈ to explore new actions;

[0197] Select the current best action with probability 1-∈, using existing experience;

[0198] Execute action: According to the selected action a, adjust the grounding system configuration to obtain a new state s′ and immediate reward r.

[0199] Update Q-value: Update the Q-value using the following Q-learning update formula:

[0200] Q(s,a)=Q(s,a)+α[r+γmax a′ Q(s′,a′)-Q(s,a)]

[0201] Among them, Q(s,a) is the value of taking action a in state s, r is the immediate reward, γ is the discount factor used to weigh the impact of future rewards, α is the learning rate, which controls the step size of Q value update, and max a′ Q(s′,a′) is the maximum Q value of all possible actions in the next state s′.

[0202] Iterative learning: Repeat the above process until the Q table converges, that is, the Q value no longer changes significantly, indicating that the optimal configuration of the grounding system has been found.

[0203] 5. Get the optimal grounding system configuration:

[0204] After the Q-learning algorithm converges, the optimal action of the system in each state is the optimal grounding system configuration.

[0205] In actual operation, the optimal action a in the Q table is found according to the current state s, and the grounding system configuration is dynamically adjusted to keep the grounding resistance within a safe range.

[0206] Through continuous learning and optimization of the Q learning algorithm, the intelligent optimization control module can adjust the configuration of the grounding system in real time to ensure that the grounding resistance remains within a safe range while improving the adaptability and stability of the system. This method not only improves the reliability of the lightning protection grounding system, but also reduces maintenance costs and extends the service life of the equipment.

[0207] In general, the present invention integrates multiple sensors, data processing centers, real-time monitoring and early warning systems, and intelligent optimization control modules, which not only significantly reduces the grounding resistance and improves the efficiency of the lightning protection grounding system, but also realizes comprehensive real-time monitoring and dynamic optimization of photovoltaic power stations, improves the stability and reliability of the system, and effectively prevents the risk of spontaneous combustion, reduces equipment failures and maintenance costs, and ensures the safe operation of photovoltaic power stations under various environmental conditions.

[0208] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A lightning protection and grounding system suitable for a photovoltaic power station in loose coal gangue geology, characterized in that: include: Outdoor horizontal grounding grid, made of galvanized flat steel; Multiple vertical grounding electrodes made of galvanized steel pipes; Carbon powder plus clay resistance reduction material laid around the outdoor horizontal grounding grid; Multiple sensors distributed in different locations of the PV power plant to monitor temperature, humidity, CO concentration and ground resistance; A data processing center, including a wireless transmission device, a data preprocessing unit, a data storage unit and a data analysis platform; Real-time monitoring and early warning system, including display equipment and early warning signaling mechanism; Intelligent optimization control module dynamically adjusts grounding system parameters and environmental control measures based on monitoring data.

2. According to claim 1, a lightning protection and grounding system suitable for a photovoltaic power station in loose coal gangue geology is characterized in that: The system also includes an equipment down conductor, which is made of galvanized flat steel.

3. The lightning protection grounding system suitable for a photovoltaic power station in loose coal gangue geology according to claim 1 is characterized in that: The specifications of the galvanized flat steel of the outdoor horizontal grounding grid are 60mm±10mm in width and 6mm±1mm in thickness.

4. The lightning protection and grounding system suitable for a photovoltaic power station in loose coal gangue geology according to claim 1 is characterized in that: The outdoor horizontal grounding grid is buried at a depth of 50-70 cm below the ground, and carbon powder and clay are laid around the grounding body with a laying thickness of 25-35 cm.

5. The lightning protection and grounding system suitable for a photovoltaic power station in loose coal gangue geology according to claim 1 is characterized in that: The vertical grounding pole is a galvanized steel pipe with a diameter of 45-55 mm and a length of 2400-2600 mm, which is vertically buried underground and installed one every 8-12 meters.

6. The lightning protection grounding system suitable for a photovoltaic power station in loose coal gangue geology according to claim 1 is characterized in that: The sensors include a temperature sensor, a humidity sensor, a CO concentration sensor and a ground resistance sensor, and the sensors are arranged at different key positions of the photovoltaic power station.

7. The lightning protection and grounding system suitable for a photovoltaic power station in loose coal gangue geology according to claim 1 is characterized in that: The data analysis platform of the data processing center uses principal component analysis to perform dimensionality reduction processing on the data, and the specific steps include: Compute the covariance matrix of the data; Perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors; Select the eigenvectors corresponding to the first k largest eigenvalues ​​to form a feature matrix; Project the original data onto the feature matrix to obtain the reduced-dimensional data; The reduced-dimensional data is then used for further analysis and modeling.

8. The lightning protection and grounding system suitable for a photovoltaic power station in loose coal gangue geology according to claim 1 is characterized in that: The data analysis platform of the data processing center uses the ARIMA model to predict ground resistance, and the specific steps include: Collect historical ground resistance data and construct a time series dataset; Determine the order of the ARIMA model through the autocorrelation function and partial autocorrelation function graphs; Use the training data set to fit the ARIMA model and obtain the model parameters; Use the trained ARIMA model to perform short-term prediction of ground resistance; The ARIMA model formula is: in, is the predicted grounding resistance, R(t-1), R(t-2), …, R(tp) are the grounding resistance values ​​of the first p time steps, φ1, φ2, …, φ p are the model parameters of the AR part, ∈(t-1), ∈(tq) are the error terms of the first q time steps, θ1, θ q are the model parameters of the MA part.

9. The lightning protection and grounding system suitable for a photovoltaic power station in loose coal gangue geology according to claim 1 is characterized in that: The real-time monitoring and early warning system automatically issues an alarm when the ground resistance or spontaneous combustion risk score exceeds a preset threshold, specifically including: The preset threshold value of the ground resistance is not greater than 0.5Ω; The spontaneous combustion risk score is predicted by a multivariate linear regression model, and the specific steps include: Collect environmental parameter data such as temperature, humidity, and CO concentration; Use the multivariate linear regression model to train the data set and determine the model coefficient β; Real-time calculation of spontaneous combustion risk score based on the model formula: in, is the predicted spontaneous combustion risk score, x i For different environmental parameters, β i is the corresponding model coefficient; When the spontaneous combustion risk score exceeds the preset threshold, the system automatically issues a warning signal.

10. The lightning protection and grounding system suitable for a photovoltaic power station in loose coal gangue geology according to claim 1 is characterized in that: The intelligent optimization control module uses a Q learning algorithm to optimize and adjust the grounding system. The specific steps include: Define the state space S, including ground resistance value and environmental parameter value; Define action space A, including adjusting the number of grounding electrodes and changing the layout of galvanized flat steel; Define a reward function R to give positive and negative rewards according to the change of ground resistance; Use Q-learning algorithm to gradually optimize the grounding system design and obtain the optimal grounding system configuration; The Q learning algorithm formula is: Q(s,a)=r+γmax a′ Q(s′,a′) Among them, Q(s,a) is the value of taking action a in state s, r is the immediate reward, γ is the discount factor, and a′ is the possible action in the next state s′.

Citation Information

Cited By

  • Comprehensive lightning protection method and system for large-scale river model

    CN119475833A