Early warning method in construction temporary warehouse electric power material supply

Abstract

The invention provides an early warning method in construction temporary warehouse electric power material supply, which comprises the following steps: establishing a three-dimensional electromagnetic field distribution model based on actual environment influence according to a relative position relationship between a highway construction temporary warehouse and a high-voltage transmission line, and obtaining electromagnetic environment theoretical distribution of each warehouse; in the temporary warehouse, electromagnetic sensors are arranged according to materials, highly sensitive to electromagnetic interference, of electronic components, and large-dynamic-range electromagnetic sensors are arranged according to materials, high in electromagnetic field induction, of metal materials; monitoring data collected by various electromagnetic sensors of the warehouse are transmitted back to a power grid dispatching center in real time through the low-power-consumption wide-area Internet of Things and are associated with warehouse material structure parameters, and a database is constructed; historical data of a power grid load and an electromagnetic environment are mined, an association rule of an electromagnetic interference characteristic and a power transmission line operation condition is extracted, and a collaborative prediction model of a multi-warehouse electromagnetic safety situation is established.

Description

Technical Field

[0001] The invention relates to the field of information technology, and in particular to an early warning method for supplying electric power materials in a temporary construction warehouse. Background Art

[0002] Under the special environment of highway construction, the supply management of power materials in temporary warehouses faces unprecedented challenges. Given the linear characteristics of the construction line, these warehouses are often scattered over a wide geographical area and are adjacent to high-voltage transmission lines, which makes them surrounded by strong electromagnetic fields. This electromagnetic environment not only poses a threat to the storage of power materials, but also increases the complexity of management due to the significant differences in the sensitivity of materials to electromagnetic interference. On the one hand, the performance of some power materials may be degraded due to electromagnetic interference; on the other hand, some materials need to be in a specific electromagnetic environment to maintain their optimal state. Therefore, in material management, the impact of the electromagnetic environment must be accurately considered to ensure that the materials are intact. At the same time, considering the wide distribution of warehouses and the dynamic changes in the construction environment, traditional manual inspections and static monitoring methods are obviously inadequate. How to build a dynamic multi-dimensional early warning method that can monitor the electromagnetic environment in real time and flexibly adjust the early warning strategy according to the characteristics of materials and construction progress under limited resources has become a research focus in the field of power material management. This method needs to be highly adaptable and intelligent, and can provide solid protection for material safety in the ever-changing construction site. In summary, the development of a dynamic multi-dimensional early warning method for power materials in highway construction environments is a technical problem that needs to be solved urgently, and innovative solutions are urgently needed to fill the existing technical gaps. Summary of the invention

[0003] The present invention provides an early warning method for the supply of power materials in a temporary construction warehouse, which mainly includes:

[0004] According to the relative position relationship between the temporary warehouses during highway construction and the high-voltage transmission lines, a three-dimensional electromagnetic field distribution model based on the actual environmental impact was established to obtain the theoretical distribution of the electromagnetic environment of each warehouse.

[0005] In the temporary warehouse, electromagnetic sensors are deployed for materials whose electronic components are highly sensitive to electromagnetic interference, and electromagnetic sensors with a large dynamic range are deployed for materials whose metal materials induce strong electromagnetic fields;

[0006] Through the low-power wide-area Internet of Things, the monitoring data collected by various electromagnetic sensors in the warehouse are transmitted back to the power grid dispatching center in real time, and associated with the warehouse material structure parameters to build a database;

[0007] Extracting electromagnetic interference thresholds of various materials from the database, integrating monitoring data with theoretical distribution, determining the distribution of electromagnetic field strength in the warehouse, and identifying the types of materials and specific areas with electromagnetic interference risks;

[0008] If the electromagnetic field intensity in a certain area is found to exceed the electromagnetic sensitivity threshold of the materials stored in the area, an early warning message will be generated, and protective facilities will be configured according to the actual electromagnetic field, and corresponding protective measures adjustment suggestions will be given;

[0009] If the overall electromagnetic environment of the warehouse deteriorates, the warning information will be sent to the power grid dispatching center to coordinate the dynamic adjustment of the operating parameters of the high-voltage transmission line to reduce the electromagnetic interference level generated by the transmission line to a safe range that all kinds of materials can withstand;

[0010] Mining historical data of power grid load and electromagnetic environment, extracting the correlation between electromagnetic interference characteristics and transmission line operating conditions, and establishing a collaborative prediction model for electromagnetic safety situation in multiple warehouses;

[0011] According to the prediction results of the prediction model, electromagnetic protection measures are adjusted through warehouse hardware facilities, and the storage area of ​​sensitive materials is dynamically optimized. At the same time, early warning information is fed back to the power grid dispatching center to coordinate and optimize the operation mode of the transmission line.

[0012] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0013] The present invention discloses an early warning method for the supply of power materials in a temporary construction warehouse. By real-time monitoring and analyzing the electromagnetic field intensity, the potential electromagnetic interference risk area is accurately located, and the sensitive materials are effectively prevented from being affected by electromagnetics, ensuring the integrity and normal operation of the materials. Combining the Internet of Things technology and intelligent algorithms, an alarm can be issued in advance, prompting managers to respond quickly, avoiding the risk of material damage, and enhancing the foresight and initiative of warehouse management. At the same time, the protection strategy is dynamically adjusted according to the real-time monitoring data, and a customized storage solution is provided according to the characteristics and electromagnetic sensitivity of different materials to ensure that the materials are in the optimal preservation state under a complex electromagnetic environment. In addition, the collaborative operation with the power grid dispatching center not only improves the operational stability of the power grid, but also optimizes the transmission line working mode according to the real-time monitoring data, reduces electromagnetic interference, realizes the harmonious coexistence of power facilities and warehouse material management, and promotes the optimal allocation of resources. By reducing material losses and maintenance costs, a double harvest of economic benefits and safety management is achieved, providing a stable logistical support for highway construction projects. Finally, the generated real-time data and analysis reports provide key information for decision makers, accelerate the optimization process of material allocation and warehouse layout, and greatly improve the efficiency and reliability of construction logistics. In summary, the present invention significantly enhances the electromagnetic environment safety of temporary warehouses near high-voltage transmission lines, and builds a solid defense line for the complete protection of sensitive materials. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 The present invention is a flow chart of an early warning method for supplying power materials to a temporary construction warehouse.

[0015] Figure 2 It is a schematic diagram of an early warning method for supplying electric power materials to a temporary construction warehouse according to the present invention.

[0016] Figure 3 It is another schematic diagram of an early warning method for supplying electric power materials to a temporary construction warehouse according to the present invention. DETAILED DESCRIPTION

[0017] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0018] like Figure 1-3 In this embodiment, an early warning method for supplying power materials in a temporary construction warehouse may specifically include:

[0019] S101. According to the relative position relationship between the temporary warehouses for highway construction and the high-voltage transmission lines, a three-dimensional electromagnetic field distribution model based on the actual environmental impact is established to obtain the theoretical distribution of the electromagnetic environment of each warehouse.

[0020] The three-dimensional coordinate data of the temporary warehouse for highway construction and the high-voltage transmission line are obtained, and the three-dimensional coordinate data includes the warehouse location, size and tower coordinates of the transmission line. The spatial distribution of the electromagnetic field source is determined according to the three-dimensional coordinate data, and the spatial distribution is determined by the voltage level, current load, phase line arrangement and tower structure of the transmission line. The finite element method is used to establish a three-dimensional electromagnetic field distribution model, and the three-dimensional electromagnetic field distribution model uses the transmission line parameters as boundary conditions. If there is terrain undulation, a digital terrain model is established; if there is atmospheric influence, an atmospheric propagation model is constructed. The distribution of electromagnetic field intensity in space is analyzed, and the electromagnetic field intensity distribution is obtained by combining the shielding and reflection effects of terrain undulation on electromagnetic wave propagation, and the influence of atmospheric conditions on electromagnetic wave attenuation. According to the specific location and building structure of each warehouse, the distribution of the electromagnetic field inside the warehouse is calculated, and the distribution is determined by the electromagnetic shielding coefficient and reflection coefficient of the warehouse wall material.

[0021] Specifically, the three-dimensional coordinate data of the temporary warehouse for highway construction and the high-voltage transmission line are obtained, including the warehouse location and size and the tower coordinates of the transmission line. The spatial distribution of the electromagnetic field source is determined according to the voltage level, current load, phase line arrangement and tower structure of the transmission line. The finite element method is used to establish a three-dimensional electromagnetic field distribution model, and the transmission line parameters are input as boundary conditions.

[0022] A digital terrain model is established based on terrain elevation data, and an atmospheric propagation model is constructed using meteorological parameters such as atmospheric refractive index and humidity. These environmental factors are parameterized and input into the electromagnetic field distribution model. The distribution of electromagnetic field intensity in space is calculated by solving Maxwell's equations. The shielding and reflection effects of terrain undulations on electromagnetic wave propagation, as well as the influence of atmospheric conditions on electromagnetic wave attenuation, are considered.

[0023] According to the specific location and building structure of each warehouse, the distribution of electromagnetic fields inside the warehouse is calculated. According to the electromagnetic shielding coefficient and reflection coefficient of the warehouse wall material, the propagation attenuation and multipath effect of electromagnetic waves in the warehouse are calculated. Taking into account the secondary scattering of electromagnetic fields by equipment and items inside the warehouse, more accurate electromagnetic environment distribution data inside the warehouse is obtained.

[0024] Using 3D visualization technology, the calculated electromagnetic field strength data is converted into a 3D electromagnetic environment distribution map. Different colors and transparency are used to represent the changes in electromagnetic field strength, and the theoretical distribution of the electromagnetic environment of each warehouse is intuitively presented. Typical locations are selected for on-site electromagnetic field strength measurements, which are compared with the model calculation results to evaluate the model accuracy and perform necessary calibration. According to different construction stages and seasonal changes, the model parameters are adjusted to generate electromagnetic environment distribution maps under various scenarios, providing a comprehensive electromagnetic environment assessment.

[0025] When obtaining the three-dimensional coordinate data of the temporary warehouse for highway construction and the high-voltage transmission line, the GPS positioning system was used to accurately locate the warehouse location, and the warehouse dimensions were measured to be 20 meters long, 15 meters wide, and 6 meters high. The coordinates of the transmission line tower were obtained by a laser rangefinder, and the distance between adjacent towers was 300 meters. The voltage level of the transmission line is 500kV, the current load is 1000A, and the triangular arrangement is adopted. The tower type is a double-circuit straight tower. These parameters were input into the finite element software COMSOL Multiphysics to establish a three-dimensional electromagnetic field distribution model.

[0026] The terrain model was constructed using digital elevation model (DEM) data with a resolution of 30 meters. The atmospheric refractive index was obtained from the meteorological station as 1.000325 and the relative humidity was 60%. These data were used to construct an atmospheric propagation model, considering the propagation characteristics of electromagnetic waves in different media. The finite difference time domain method (FDTD) was used to solve Maxwell's equations and calculate the electromagnetic field intensity distribution. The shielding effect of terrain undulations on electromagnetic waves was considered in the calculation, and the reflection and diffraction of electromagnetic waves were simulated using a ray tracing algorithm.

[0027] For the warehouse building structure, the wall material is reinforced concrete, the electromagnetic shielding coefficient is 20dB, and the reflection coefficient is 0.8. The transmission line matrix method (TLM) is used to calculate the multipath propagation of electromagnetic waves in the warehouse, taking into account multiple reflections on the wall, ground and ceiling. The Monte Carlo simulation method is used to simulate the secondary scattering of electromagnetic fields by equipment and items inside the warehouse to generate more accurate electromagnetic environment distribution data inside the warehouse.

[0028] The OpenGL graphics library is used to achieve three-dimensional visualization, and the calculated electromagnetic field strength data is converted into a three-dimensional electromagnetic environment distribution map. The red, yellow and green gradients are used to represent the change of electromagnetic field strength from high to low, and the transparency range is set to 30%ˉ100%. Three typical locations of 50 meters, 100 meters and 200 meters away from the transmission line are selected for field electromagnetic field strength measurement. The model calculation results are compared with the spectrum analyzer to evaluate the model accuracy. According to the comparison results, the model parameters are optimized and calibrated by the least squares method. Considering the load changes during the construction period (daytime) and the non-construction period (nighttime), as well as the temperature and humidity changes in spring, summer, autumn and winter, the model parameters are adjusted to generate electromagnetic environment distribution maps under 8 different scenarios, providing a comprehensive electromagnetic environment assessment.

[0029] S102. In the temporary warehouse, electromagnetic sensors are installed for electronic components that are highly sensitive to electromagnetic interference; and electromagnetic sensors with a large dynamic range are installed for metal materials that induce strong electromagnetic fields.

[0030] A laser scanner is used to perform three-dimensional space scanning inside the warehouse to obtain point cloud data of the warehouse; based on the point cloud data, a spatial model of the warehouse is constructed through three-dimensional reconstruction software; for the electronic component area and the metal material area in the warehouse spatial model, the electromagnetic sensitivity is evaluated, and the layout point coordinates of high-sensitivity electromagnetic sensors and large dynamic range electromagnetic sensors are determined; based on the layout point coordinates, Hall effect sensors and capacitive sensors are laid out in the electronic component area, and Rogowski coil sensors and electrostatic field meters are laid out in the metal material area; sensor data of the Hall effect sensor, capacitive sensor, Rogowski coil sensor and electrostatic field meter are collected; based on the sensor data, a Kalman filter state equation and an observation equation are established; based on the state equation and the observation equation, an optimal estimate is obtained through iterative calculation; based on the optimal estimate and the layout point coordinates, a three-dimensional model of the electromagnetic field distribution in the warehouse is constructed; if electromagnetic interference exceeding a preset threshold is detected in the three-dimensional model of the electromagnetic field distribution, an alarm is triggered and the location information of the interference source is provided through a triangulation positioning algorithm.

[0031] Specifically, a laser scanner is used to perform a three-dimensional spatial scan of the interior of the warehouse to generate point cloud data, and a warehouse space model is constructed through three-dimensional reconstruction software. Electronic components and metal materials are classified, their electromagnetic sensitivity is evaluated, and the layout coordinates of high-sensitivity electromagnetic sensors and large dynamic range electromagnetic sensors are determined. In the electronic component area, a Hall effect sensor with a sensitivity of 1nT is deployed to measure weak magnetic fields, and a capacitive sensor with a measurement range of 0.1V / m to 100V / m is used to detect low-intensity electric fields. The sampling frequency is set to 1kHz, and the accuracy requirement is 0.1% full scale. The spectrum analysis of the collected high-precision electromagnetic field data is performed to identify the electromagnetic interference characteristics of different frequency bands. For the metal material area, a Rogowski coil sensor with a measurement range of 0.1mT to 1T is installed to measure strong magnetic fields, and an electrostatic field meter with a range of 1kV / m to 100kV / m is used to measure high-intensity electric fields. The sampling frequency is set to 10kHz, and the accuracy requirement is 1% full scale. Perform time domain analysis on the acquired wide-range electromagnetic field data to identify the instantaneous change characteristics of the electromagnetic field intensity. Collect all sensor data, establish the Kalman filter state equation x(k)=Ax(k-1)+w(k) and observation equation z(k)=Hx(k)+v(k), where A is the state transfer matrix, describing how the system state changes from time step k-1 to k, x(k) is the state vector at time step k, x(k-1) represents the state vector at the previous time step -1, z(k) is the observation vector at time step k, H is the observation matrix, describing the relationship between the system state and the observation, w(k) is the process noise, which is the random error introduced in the state transfer process, and v(k) is the observation noise, which is the random error introduced in the measurement process. Set the noise covariance matrix Q and R, and obtain the optimal estimate through iterative calculation. Construct a three-dimensional model of the electromagnetic field distribution in the warehouse based on the sensor location information and the filtered measurement data. The distribution of electromagnetic field intensity is represented by heat map. When electromagnetic interference exceeding the preset threshold is detected, an alarm is triggered and the location information of the interference source is provided through the triangulation positioning algorithm. The FARO Focus S350 laser scanner is used to perform a three-dimensional spatial scan of the interior of a warehouse of 60m×40m×10m. The scanning accuracy is set to 2mm@10m, which means that the scanning accuracy at a distance of 10 meters is 2mm, generating point cloud data containing about 500 million points. The point cloud registration and noise reduction are performed by Autodesk ReCap software to build a warehouse space model accurate to the centimeter level. According to the list of materials, electronic components are divided into three categories: high sensitivity, such as integrated circuits, medium sensitivity, such as resistors and capacitors, and low sensitivity, such as connectors. Metal materials are divided into two categories: strong magnetism, such as iron products, and weak magnetism, such as aluminum products. The electromagnetic field simulation software ANSYS Maxwell is used to evaluate the electromagnetic sensitivity of various materials and determine the layout coordinates of 50 high-sensitivity electromagnetic sensors and 30 large dynamic range electromagnetic sensors.In the electronic component area, Honeywell HMC1001 magnetic sensor (sensitivity 1nT) and Teledyne LeCroy AP015 electric field probe are arranged, with a range of 0.1V / m-100V / m. The sampling frequency is set to 1kHz, and the 16-bit ADC ensures 0.1% full-scale accuracy. Fast Fourier transform (FFT) is used to perform spectrum analysis on the collected electromagnetic field data to identify electromagnetic interference with characteristic frequencies such as 50Hz and 400Hz. For the metal material area, GMW Associates 42B Rogowski coil is installed, with a range of 0.1mT-1T and Monroe 247 electrostatic field meter, with a range of 1kV / m-100kV / m. The sampling frequency is 10kHz, and the 12-bit ADC ensures 1% full-scale accuracy. Wavelet transform is used to perform time-frequency analysis on wide-range electromagnetic field data to identify the instantaneous change characteristics of electromagnetic field intensity. All sensor data are collected by National Instruments cDAQ-9188 data acquisition unit to establish the Kalman filter model. The state transfer matrix A and the observation matrix H are set based on the electromagnetic field propagation characteristics, and the noise covariance matrices Q and R are determined by the sensor specifications and measured data. The Kalman filter algorithm is implemented using MATLAB, and the optimal estimate is obtained by iterative calculation. Combining the sensor position information and the filtered measurement data, a three-dimensional interpolation algorithm is used to construct an electromagnetic field distribution model with a grid resolution of 0.5m×0.5m×0.5m in the warehouse. The electromagnetic field intensity heat map is generated using ParaView software, and the color from blue to red indicates that the field strength is from weak to strong. When electromagnetic interference exceeding the preset threshold is detected, such as electric field strength>10V / m or magnetic field strength>0.1mT, an audible and visual alarm is triggered, and the triangulation positioning algorithm implemented by the least squares method provides the location information of the interference source, and the positioning accuracy is better than 1m.

[0032] S103. Through the low-power wide-area Internet of Things, the monitoring data collected by various electromagnetic sensors in the warehouse are transmitted back to the power grid dispatching center in real time, and are associated with the warehouse material structure parameters to build a database.

[0033] The original data of the electromagnetic sensor collected by the LoRa node device is obtained, and the difference between adjacent sampling points is calculated using the DPCM algorithm based on the original data. For the difference information, an encrypted data packet is generated using the AES-128 encryption algorithm, and the encrypted data packet is transmitted to the power grid dispatching center through the LoRaWAN network. The encrypted data packet is decrypted using a preset key to obtain the original monitoring data. A database is constructed, including obtaining material structure parameter information, and converting the original monitoring data and the material structure parameter information into data in JSON format. If the data in JSON format is structured material parameter information, it is stored in a MySQL database; if the data in JSON format is semi-structured monitoring data, it is stored in a MongoDB database.

[0034] Specifically, LoRaWAN gateways and LoRa node devices are deployed in the warehouse, and a star network topology is adopted to connect various electromagnetic sensors to the LoRa node. Low-power wide-area data transmission is achieved through the LoRaWAN protocol. The working frequency band of the node device is set to 470-510MHz, and the transmission power is 14dBm to ensure coverage of the entire warehouse area. The raw data collected by the sensor is preprocessed and compressed, and the DPCM (differential pulse code modulation) algorithm is used to reduce the amount of data. The DPCM algorithm calculates the difference between adjacent sampling points and only transmits the difference information to achieve data compression. The compressed data is encrypted using the AES-128 encryption algorithm to ensure transmission security. The encrypted data packets are transmitted to the power grid dispatching center in real time through the LoRaWAN network, and the transmission cycle is set to 5 minutes. The power grid dispatching center receives and parses the data packets from each LoRa node, decrypts them using the preset key, and restores the original monitoring data. Perform data quality checks to eliminate abnormal values, such as data that exceeds the sensor range. Obtain material structure parameter information from the warehouse management system through the RESTfulAPI interface, including material type, electromagnetic shielding performance, etc. The monitoring data and material parameters are uniformly converted into JSON format to prepare for database storage. A heterogeneous database is constructed using MySQL and MongoDB databases. A relational table is created in MySQL to store structured material parameter information, and a collection is created in MongoDB to store semi-structured monitoring data. Indexes are created to optimize query performance, such as creating a B-tree index for material ID in MySQL and a hash index for timestamp in MongoDB. Data association between MySQL and MongoDB is achieved through foreign key associations. Using database view technology, a unified view containing monitoring data and corresponding material parameters is created to support fast association queries. A Semtech SX1301 multi-channel LoRaWAN gateway and 50 LoRa node devices equipped with SX1276 chips are deployed in a 100m×50m×10m warehouse, using a star network topology. 20 Hall effect magnetic sensors and 30 capacitive electric field sensors are connected to the LoRa node, and the operating frequency band is set to 470MHz, the transmission power is 14dBm, and the sensitivity is -137dBm to achieve full warehouse coverage. Each node collects data once every 5 minutes, a total of 200 bytes. The DPCM algorithm is used to compress the data, and the compression ratio reaches 3:1. The difference between the current value Xn and the previous value Xn-1, ΔXn=Xn-Xn-1, represents the data, and only ΔXn is transmitted. The compressed data is encrypted using the AES-128 algorithm, with a key length of 128 bits, a packet length of 128 bits, and an encryption mode of CBC. The encrypted data packet is transmitted through the LoRaWAN Class A mode, and the uplink SF (spreading factor) is set to 7-12, which can be adaptively adjusted. The power grid dispatching center receives the data packet, decrypts it using the preset AES-128 key, and restores the original data.Perform quality checks on the data and remove abnormal values ​​that exceed ±5% of the sensor range. Obtain material structure parameters from the warehouse management system through the RESTful API (port 8080, authentication method OAuth2.0), including material ID, type, electromagnetic shielding performance, etc. Convert the monitoring data and material parameters into JSON format. The monitoring data structure is:

[0035] {"timestamp":1617235200,"sensor_id":"MAG001","value":0.05}, the material parameter structure is {"material_id":"M001","type":"metal","shielding_factor":30}. Create a material parameter table in the MySQL8.0 database, with the primary key being material_id, and create a B+ tree index for material_id. Create a monitoring data set in the MongoDB4.4 database, and create a hash index for the timestamp field. Associate MySQL and MongoDB data through the foreign key material_id. Create a view view_monitoring_data to connect monitoring data and material parameters, and support compound queries such as "SELECT * FROM view_monitoring_data WHERE timestamp BETWEEN? AND? AND shielding_factor>?", with a query time of less than 100ms.

[0036] S104. Extracting electromagnetic interference thresholds of various types of materials from the database, integrating the monitoring data with the theoretical distribution, determining the distribution of electromagnetic field strength in the warehouse, and identifying the types of materials and specific areas with electromagnetic interference risks.

[0037] The electromagnetic interference threshold data of various materials are obtained from the database, and the electromagnetic interference threshold table is established according to the material type and sensitivity. The electromagnetic interference threshold table includes the electric field strength threshold and the magnetic field strength threshold. Real-time monitoring data in the warehouse is obtained. If the real-time monitoring data is discrete monitoring point data, the ordinary kriging method is used to perform spatial interpolation on the discrete monitoring point data to obtain continuous electromagnetic field intensity distribution data. The continuous electromagnetic field intensity distribution data is fused with the theoretical distribution by the Markov chain Monte Carlo method to obtain the fused electromagnetic field intensity distribution. The fused electromagnetic field intensity distribution is compared with the electromagnetic interference threshold table, and the C4.5 decision tree algorithm is used to identify the area exceeding the threshold. The minimum leaf node sample number of the C4.5 decision tree algorithm is the preset sample value, and the maximum depth is the preset depth value. The sliding window method is used to update the historical data, and the electromagnetic interference threshold in the electromagnetic interference threshold table is adjusted according to the updated historical data. The time window of the sliding window method is the preset window value.

[0038] Specifically, the electromagnetic interference thresholds of various materials are extracted from the preset database, the structured threshold data are obtained from the MySQL database using SQL statements, and the unstructured threshold data are extracted from the MongoDB database using an aggregation pipeline. According to the type and sensitivity of the materials, an electromagnetic interference threshold table is established, including the electric field strength threshold and the magnetic field strength threshold. The threshold data is standardized, and the thresholds of different types of materials are converted into a standard normal distribution using the Z-score method to ensure that the thresholds are comparable. Real-time monitoring data in the warehouse is obtained, and the discrete monitoring point data are spatially interpolated using the ordinary kriging method to generate continuous electromagnetic field intensity distribution data. The theoretical model is fitted, and the best fitting result among the spherical model, exponential model or Gaussian model is selected. The interpolation accuracy is evaluated using the cross-validation method, and the root mean square error (RMSE) and the average kriging variance are calculated. The uncertainty analysis of the interpolation results is performed to generate a standard error map to provide input for subsequent Bayesian inference. The monitoring data is fused with the theoretical distribution through the Markov Chain Monte Carlo (MCMC) method, the prior probability of the electromagnetic field intensity distribution is updated, and the posterior probability distribution is obtained. The Metropol is-Hast ings algorithm is used for parameter sampling, and the burning period is set to 1000 iterations and the total number of iterations is 10000. The mean, variance and 95% confidence interval of the posterior distribution are calculated to quantify the uncertainty of the fusion results. The fused electromagnetic field intensity distribution map and uncertainty distribution map are generated. The fused electromagnetic field intensity distribution is compared with the standardized electromagnetic interference threshold table, and the C4.5 decision tree algorithm is used to identify the areas exceeding the threshold and the corresponding material types. The minimum number of leaf node samples of the decision tree is set to 5, the maximum depth is set to 10, and the Gini coefficient is used as the splitting criterion. According to the output results of the decision tree, the risk level is divided into three levels: low, medium and high, and a risk heat map is generated for visual display. Dynamic threshold adjustments are made, and the sliding window method is used every week to update historical data and adjust the electromagnetic interference threshold to ensure the accuracy and timeliness of risk identification. In the warehouse management system, SQL statements are used

[0039] "SELECT material_type, em_field_type, threshold_value FROM em_thresholds WHERE sens it ivity_level>3" extracts the electromagnetic interference threshold of highly sensitive materials from the MySQL database and passes it through the MongoDB aggregation pipeline

[0040] [{$match:{sens it ivity:{$gt:3}}},{$group:{_id:"$material_type",avg_th reshold:{$avg:"$threshold_value"}}}] Obtain unstructured threshold data. Apply Z-score standardization to the extracted threshold data, such as converting the electric field strength threshold of 5V / m for electronic components to a standard score of 1.2. Use ordinary kriging to spatially interpolate the data of 50 monitoring points, select the spherical semivariogram model, with an effective range of 20 meters, a nugget value of 0.05, and a sill value of 0.8. The interpolation accuracy is evaluated by leave-one-out cross-validation, and the RMSE is 0.3V / m and the average kriging variance is 0.25. Generate standard errors with an error range of 0.1-0.5V / m. Use the Metropol is-Hast ings algorithm for MCMC sampling, and select the normal distribution N(μ,σ^2) for the proposal distribution, where μ is the current state and σ=0.1. The burning period was set to 1000 iterations and the total iterations to 10000. The mean of the posterior distribution was calculated to be 6.2V / m, the variance was 0.4, and the 95% confidence interval was [5.8V / m, 6.6V / m]. The fused electromagnetic field intensity distribution map was generated, with an intensity range of 2-8V / m and a resolution of 0.5m×0.5m. The C4.5 decision tree algorithm was applied, with the minimum number of leaf node samples set to 5, the maximum depth set to 10, and the Gini coefficient used as the splitting criterion. According to the output of the decision tree, the risk level was divided into three levels: low (<4V / m), medium (4-6V / m), and high (>6V / m), and a risk heat map was generated. The historical data was updated using a 30-day sliding window every week, and the electromagnetic interference threshold was dynamically adjusted in combination with the "IF average field strength > historical 90% quantile THEN increase the threshold by 10%" rule in the preset knowledge base. Finally, the risk area coordinates (x:15m, y:25m, z:2m) and the corresponding high-risk material type "precision electronic instruments" were output.

[0041] S105. If it is found that the electromagnetic field intensity in a certain area exceeds the electromagnetic sensitivity threshold of the materials stored in the area, an early warning message is generated, and protective facilities are configured according to the actual electromagnetic field, and corresponding protective measures adjustment suggestions are given.

[0042] A K-means clustering algorithm is used to divide the warehouse space into regions. The K-means clustering algorithm sets the number of clusters to a preset value, and uses Euclidean distance as a similarity measure to obtain an electromagnetic environment zoning map. According to the electromagnetic environment zoning map, a C4.5 decision tree algorithm is used to compare the electromagnetic field intensity of each region with a preset electromagnetic sensitivity threshold of stored materials to determine whether there is an over-threshold situation. If the judgment result shows that the electromagnetic field intensity of a certain area exceeds the sensitivity threshold, an early warning is triggered, and a JSON format early warning information including the location of the exceeded area, the electromagnetic field intensity value, and the type of material is generated. Based on the JSON format early warning information, the existing electromagnetic protection facility information in the area is obtained, and a protective measure adjustment suggestion is generated. According to the protective measure adjustment suggestion, a cost-benefit analysis is performed on the protective measures, the return on investment is calculated, and a priority list is generated by arranging them in descending order according to the return on investment.

[0043] Specifically, based on real-time monitoring data, the K-means clustering algorithm is used to divide the warehouse space into regions, and regions with similar electromagnetic field strength characteristics are classified into one category to obtain an electromagnetic environment zoning map. The number of clusters K is set to 5, the Euclidean distance is used as the similarity measure, and the upper limit of the number of iterations is 100. The partitioning results are evaluated by the silhouette coefficient, and the partitioning scheme with the largest silhouette coefficient is selected. A partitioning result heat map is generated, and different colors are used to represent the electromagnetic field intensity level of each region. The electromagnetic sensitivity threshold of the stored materials in each region is queried from the database, and the C4.5 decision tree algorithm is used to compare the electromagnetic field intensity with the sensitivity threshold to determine whether there is an over-threshold situation. The maximum depth of the decision tree is set to 5, the minimum number of leaf node samples is set to 10, and the information gain ratio is used as the splitting criterion. A decision tree visualization diagram is generated to show the judgment process. The judgment results are superimposed on the partition heat map, and the over-threshold area is highlighted with a special mark. If the judgment result shows that the electromagnetic field intensity in a certain area exceeds the threshold, an early warning is triggered, and a JSON format early warning information containing information such as the location of the over-standard area, the electromagnetic field intensity value, and the type of material is generated. The early warning information structure is

[0044] {"warning_id":"W001","area":"A3","em_strength":8.5,"threshold":7.0,"material_type":"Precision electronic components","timestamp":"2023-04-0110:30:00"}. According to the degree of exceeding the threshold, the warning level is divided into low, medium and high levels, corresponding to yellow, orange and red warnings respectively. High-level warnings are automatically pushed to the mobile devices of relevant managers. The existing electromagnetic protection facilities information in the area is extracted from the protection facility database, and the Mamdani fuzzy inference system is used to generate protection measures adjustment suggestions based on the protection rules in the preset knowledge base. The input variables are set as "exceeding the threshold degree" and "existing protection level", and the output variable is "protection measures strength". Define a fuzzy rule set, such as "IF exceeding the threshold degree = high AND existing protection level = low THEN protection measures strength = strong". Defuzzification is performed through the centroid method to obtain the specific protection measures strength value. According to the strength value, the corresponding measures are selected from the protection measures library, such as replacement of shielding materials, optimization of grounding system, etc. A cost-benefit analysis of the protective measures was conducted, and the return on investment (ROI) was calculated. A priority list was generated by arranging the measures in descending order of ROI. In a warehouse space of 100m×50m×10m, the electromagnetic field intensity data of 500 monitoring points were collected, and the K-means clustering algorithm was used for regional division. The number of clusters K was set to 5, the Euclidean distance was used as the similarity measure, and the maximum number of iterations was 100. After 50 iterations, the cluster converged and 5 cluster centers were obtained, which were located at (20,15,3), (40,30,5), (60,10,2), (80,40,7) and (90,25,4), respectively, in meters. The calculated silhouette coefficient was 0.72, indicating that the clustering effect was good. A heat map was generated, and the five areas with high to low electromagnetic field intensity were represented by red, orange, yellow, green and blue. The electromagnetic sensitivity thresholds of materials in each area are queried from the preset database. For example, the threshold for the precision electronic component area is 5V / m, and the threshold for the general electronic equipment area is 10V / m. The C4.5 decision tree algorithm is used to compare the electromagnetic field strength with the threshold, and the maximum depth is set to 5, the minimum number of leaf node samples is set to 10, and the information gain ratio threshold is set to 0.1. A decision tree is generated, with the root node being "electromagnetic field strength" and the leaf nodes being "exceeding threshold" or "not exceeding threshold". The judgment result shows that the electromagnetic field strength in the area at (40,30,5) is 8.5V / m, which exceeds the threshold of 5V / m in this area. Trigger an early warning and generate an early warning message in JSON format:

[0045] {"warning_id":"W001","area":"A2","em_strength":8.5,"threshold":5.0,"material_type":"Precision electronic components","timestamp":"2023-04-0110:30:00","level":"High"}. The high-level warning is pushed to the mobile device of the manager through the WebSocket protocol. From the protection facility database, it is known that the area currently has fine metal material shielding including copper, aluminum, steel, etc., with a shielding effectiveness of 60dB. The Mamdani fuzzy inference system is used to generate protection measures suggestions, and the fuzzy set of the input variable "exceeding the threshold degree" is set to {low, medium, high}, and the membership function uses the Gaussian function; the fuzzy set of "existing protection level" is set to {weak, medium, strong}, and the membership function uses the trapezoidal function. The fuzzy set of the output variable "protection measure strength" is {fine-tuning, strengthening, reconstruction}, and the membership function uses the trigonometric function. Define 9 fuzzy rules, such as "IF threshold exceeded = high AND existing protection level = medium THEN protection measure strength = enhanced". Defuzzification is performed using the centroid method to obtain a protection measure strength value of 0.75. Select "Replace with 80dB shielding effectiveness metal shield" from the preset protection measure library, with an estimated cost of 50,000 yuan, an expected benefit of 80,000 yuan, and a calculated ROI of 60%. This measure is listed as the highest priority protection recommendation.

[0046] S106. If the overall electromagnetic environment of the warehouse deteriorates, the warning information will be sent to the power grid dispatching center to coordinate the dynamic adjustment of the operating parameters of the high-voltage transmission line and reduce the electromagnetic interference level generated by the transmission line to a safe range that all kinds of materials can withstand.

[0047] The electromagnetic environment data of the warehouse monitored by the preset distributed sensor network is obtained, and the temporal and spatial variation trend of the electromagnetic field intensity is calculated by a sliding window algorithm based on the data to obtain the electromagnetic field intensity variation data. A quantitative evaluation is performed on the electromagnetic field intensity variation data. If the average value of the electromagnetic field intensity increases by a preset range or the peak value exceeds a preset multiple of the safety standard, it is judged that the electromagnetic environment has deteriorated and an early warning data packet is generated. The early warning data packet is encrypted by the SSL / TLS protocol to obtain an encrypted early warning data packet, and the encrypted early warning data packet is sent to the power grid dispatching center. The power grid dispatching center receives the encrypted early warning data packet, uses the weighted least squares method to estimate the state of the power system, and determines the key transmission lines and their operating parameters that affect the electromagnetic environment of the warehouse. For the operating parameters of the key transmission lines, a non-dominated sorting genetic algorithm is used for multi-objective optimization; based on the optimized transmission line operating parameters, the transmission lines are dynamically adjusted.

[0048] Specifically, the overall electromagnetic environment of the warehouse is monitored in real time through a preset distributed sensor network, and the temporal and spatial variation trend of the electromagnetic field intensity is calculated using a sliding window algorithm. The window size is set to 60 minutes and the sliding step is 5 minutes. The degree of deterioration of the electromagnetic environment is quantitatively evaluated, and the threshold for triggering the warning is set to an increase of 20% in the average electromagnetic field intensity or a peak value exceeding 1.5 times the safety standard. If the judgment result shows that the electromagnetic environment has deteriorated as a whole, an early warning data packet containing information such as the warehouse location, electromagnetic field intensity distribution, and material type is generated. According to the degree of deterioration, the early warning information is divided into three priorities: low, medium, and high, and high priority information will be processed first. The early warning information is encrypted through the SSL / TLS protocol to ensure communication security, and the encrypted data packet is sent to the power grid dispatching center. After receiving the early warning information, the power grid dispatching center uses the weighted least squares method to estimate the power system state, and combines the real-time operation data of the transmission line to calculate the key transmission lines and their operating parameters that affect the electromagnetic environment of the warehouse. The degree of influence of each key transmission line is quantitatively evaluated, and its contribution rate to the electromagnetic environment of the warehouse is calculated. Considering the constraints of the power grid operation, the feasibility of parameter adjustment is evaluated. According to the calculation results, the non-dominated sorting genetic algorithm II (NSGA-II) is used to perform multi-objective optimization and dynamic adjustment of the transmission line operation parameters. The optimization objectives include minimizing the electromagnetic interference level and maximizing the stability of power grid operation. After each parameter adjustment, the adjustment effect is verified through the sensor network in the warehouse, and the results are fed back to the optimization algorithm. At the same time, a long short-term memory network (LSTM) is used to construct a dynamic relationship model between the electromagnetic environment and the transmission line parameters, and continuous learning and updating are used to improve the accuracy and efficiency of future adjustments. 50 electromagnetic field sensors are deployed in a warehouse of 100m×50m×10m with a sampling frequency of 1Hz. A sliding window algorithm is used with a window size of 60 minutes and a step size of 5 minutes to calculate the change in electromagnetic field intensity. The warning threshold is set to a 20% increase in the average value or a peak value exceeding 5V / m. When the electromagnetic environment is detected to be deteriorating, such as the average field strength in the window from 10:00-11:00 increases from 2.5V / m to 3.2V / m, an early warning is triggered, and a warning data packet in JSON format is generated as follows:

[0049] {"location":[30.5,104.1],"em_strength":{"avg":3.2,"peak":4.8},"material_types":["electronics","metals"]}, the priority is set to high. Use TLS1.3 protocol with a key length of 256 bits to encrypt the warning information. After the power grid dispatch center receives and decrypts the data, it applies the weighted least squares method for state estimation. The weight matrix W is set to a diagonal matrix, and the diagonal elements are the inverse of the measurement accuracy. Iterate the calculation 5 times, set the convergence threshold to 0.001, and obtain the state estimation values ​​of the four key transmission lines. Calculate the contribution rate of each line to the electromagnetic environment of the warehouse, such as line 1 accounts for 40%, line 2 accounts for 30%, line 3 accounts for 20%, and line 4 accounts for 10%. Considering the voltage stability constraint, the load power factor is not less than 0.85. Use the NSGA-II algorithm to optimize the transmission line parameters, with a population size of 100, an iteration number of 50, a crossover probability of 0.9, and a mutation probability of 0.1. The optimization goals are to minimize electromagnetic interference (weight 0.6) and maximize grid stability (weight 0.4). After each parameter adjustment, the sensor network verifies the effect, such as the field strength is reduced to 2.8V / m. At the same time, a dynamic relationship model is established using an LSTM network. The input layer contains the voltage and current parameters of four transmission lines, the hidden layer has 64 neurons, and the output layer is the predicted electromagnetic field strength. The model is trained using historical data from the past 30 days and updated every 24 hours, with a prediction accuracy of 92%.

[0050] S107. Mine the historical data of power grid load and electromagnetic environment, extract the correlation between electromagnetic interference characteristics and transmission line operating conditions, and establish a collaborative prediction model for the electromagnetic safety situation of multiple warehouses.

[0051] Obtain historical data of power grid monitoring and historical data of warehouse electromagnetic environment monitoring, including power grid load, transmission line operating parameters, and warehouse electromagnetic field strength. According to the historical data of power grid monitoring and the historical data of warehouse electromagnetic environment monitoring, the moving median method is used to process outliers, and the interpolation method is used to process missing values ​​to obtain cleaned data. The cleaned data is standardized by the minimum-maximum normalization method to determine the standardized data. The electromagnetic interference signal in the standardized data is decomposed into 5 layers of multi-scale using Daubechies wavelet to obtain time domain features and frequency domain features. According to the time domain features and the frequency domain features, the principal component analysis method is used to reduce the feature dimension, and it is determined whether the cumulative contribution rate reaches the preset range. If it reaches the preset range, the electromagnetic interference feature vector is determined. For the electromagnetic interference feature vector and the transmission line operating parameters, the Apriori algorithm is used to analyze the correlation relationship. Set the minimum support and the minimum confidence, and determine whether the support and confidence meet the conditions. If the conditions are met, a strong correlation rule is determined to obtain the correlation relationship between electromagnetic interference and the transmission line operating conditions. A graph convolutional network is constructed according to the association model, and the graph convolutional network includes a two-layer GCN structure, and the activation function of the GCN structure is ReLU. The graph convolutional network is trained using the Adam optimizer to obtain a multi-warehouse electromagnetic safety situation collaborative prediction model. The prediction error is calculated according to the prediction result, and it is determined whether the prediction error exceeds a preset threshold. If it exceeds the preset threshold, the warning threshold is adjusted to obtain a dynamic warning threshold.

[0052] Specifically, historical data including grid load, transmission line operation parameters, warehouse electromagnetic field strength, etc. are extracted from the power grid monitoring system and the warehouse electromagnetic environment monitoring system. Outliers are processed by moving median method and missing values ​​are processed by interpolation method to achieve data cleaning. The minimum-maximum normalization method is used for standardization processing to unify data of different dimensions into the [0,1] interval. Multi-source heterogeneous data are aligned by timestamp to form a structured multidimensional time series data set to ensure data consistency and integrity. The Daubechies wavelet is used to perform a 5-layer multi-scale decomposition of the electromagnetic interference signal to extract time domain and frequency domain features. The time domain features include statistical quantities such as mean, variance, skewness, and kurtosis, and the frequency domain features include the energy ratio of each frequency band and the main harmonic components. The principal component analysis method is combined to reduce the feature dimension, retain the principal components with a cumulative contribution rate of 95%, and obtain the feature vector of electromagnetic interference. The extracted features are interpreted in physical meaning, such as the mean reflects the interference intensity, the variance represents the degree of fluctuation, and the frequency band energy ratio reflects the interference spectrum characteristics. The Apriori algorithm is used to analyze the correlation between electromagnetic interference characteristics and transmission line operating conditions, and the minimum support is set to 0.05 and the minimum confidence is set to 0.7. Considering the time lag effect, the correlation rules under different time scales of 0-24 hours are analyzed. The support and confidence are calculated, and the strongly correlated rules are screened out to build the association model between electromagnetic interference and transmission line operating conditions. The association rules are quantitatively evaluated, and the l ift value and Kulczynski metric are calculated to provide the basis for weight initialization for the subsequent graph neural network. A collaborative prediction model of electromagnetic safety situation of multiple warehouses is constructed based on graph convolutional network (GCN). Each warehouse is regarded as a node in the graph, and the transmission line is regarded as an edge. The node features include the electromagnetic environment parameters of the warehouse, and the edge features include the operating parameters of the transmission line. A two-layer GCN structure is designed, with a hidden layer dimension of 64 and ReLU as the activation function. Information interaction and collaborative prediction between multiple warehouses are realized through message passing. The mean square error is used as the loss function, and the Adam optimizer is used for model training. The learning rate is set to 0.001 and the number of training rounds is 200. The mean absolute error (MAE) and root mean square error (RMSE) were selected as performance evaluation indicators. The prediction results were visualized using the Matplotlib library, and the warning threshold was dynamically adjusted according to the prediction error to improve the practicality and adaptability of the model. There are 5 warehouses in a certain power grid area. One year of 15-minute sampling interval data was extracted from the power grid monitoring system, including parameters such as power grid load, voltage and current of 10 transmission lines, and electromagnetic field intensity data was obtained from the warehouse electromagnetic environment monitoring system. The 11-point moving median method was used to handle outliers, and 342 outliers were detected and corrected. The linear interpolation method was used to handle 567 missing values. The data was mapped to the [0,1] interval through minimum-maximum normalization, such as normalizing the 50Hz electromagnetic field intensity from 0-10V / m.The multi-source data were aligned using timestamps to form a 35040×87 dimensional data matrix. The db4 wavelet was applied to the electromagnetic interference signal for 5-layer decomposition, and 12 time domain features were extracted, such as a mean of 3.2V / m, a variance of 0.8, and 20 frequency domain features, such as a 50Hz component accounting for 85%. Dimensionality reduction was performed through principal component analysis, and 14 principal components were retained, with a cumulative contribution rate of 95.3%. The Apriori algorithm set the minimum support of 0.05 and the minimum confidence of 0.7, and found 78 strong association rules, such as "Line 1 current increased by 10% → 2 hours later, the electromagnetic field strength of warehouse A increased by 8%" (support 0.06, confidence 0.75). The l ift value of 1.8 and the Kulczynski metric of 0.72 were calculated to verify the significance of the rules. A graph structure with 5 nodes and 10 edges was constructed, with 32 node feature dimensions (including electromagnetic field strength, temperature, etc.) and 16 edge feature dimensions (including line voltage, current, etc.). Design a two-layer GCN with 64 hidden layers and ReLU activation. Use the mean square error loss function, Adam optimizer learning rate 0.001, batch size 32, and 200 rounds of training. On the test set, the performance of MAE is 0.15V / m and RMSE is 0.22V / m. Use Matplotlib to draw a comparison chart between the predicted results and the actual values, set the dynamic warning threshold to 1.2 times the predicted value, and realize real-time monitoring and warning of electromagnetic safety situation.

[0053] S108. According to the prediction results of the prediction model, the electromagnetic protection measures are adjusted through the warehouse hardware facilities, the storage area of ​​sensitive materials is dynamically optimized, and the early warning information is fed back to the power grid dispatching center to coordinate and optimize the operation mode of the transmission line.

[0054] Obtain the prediction results of the electromagnetic field intensity distribution in the warehouse and the electromagnetic sensitivity data of the materials, and calculate the optimal storage plan for the materials based on the prediction results and sensitivity data. Use PLC to adjust the working parameters of the electromagnetic shielding equipment in the warehouse, and the working parameters include the angle of the shielding plate and the thickness of the absorbing material. Use electromagnetic field sensors to monitor the shielding effect in real time, and form a closed-loop feedback based on the monitoring results; if the monitoring results show that the shielding effect does not meet the standards, the PLC is triggered to adjust the control parameters based on the feedback data. Send the early warning information to the power grid dispatching center through the IEC61850 protocol, and the early warning information includes the predicted electromagnetic exceeding the standard area, time and degree. The power grid dispatching center receives the early warning information and uses the NSGA-II algorithm to generate an optimized operation plan for the transmission line. The optimized operation plan includes line load distribution and reactive compensation device adjustment parameters.

[0055] Specifically, according to the prediction results of the prediction model, the working parameters of the electromagnetic shielding equipment in the warehouse are adjusted through the PLC (programmable logic controller), such as adjusting the angle of the shielding plate and changing the thickness of the absorbing material, to achieve dynamic adjustment of the electromagnetic protection measures. High-precision electromagnetic field sensors are used to monitor the shielding effect in real time to form a closed-loop feedback to ensure the effectiveness of the protection measures. The PLC continuously optimizes the control parameters based on the feedback data to maintain the best shielding effect. The automated logistics system in the warehouse is used to combine the electromagnetic field intensity distribution prediction results and the electromagnetic sensitivity data of the materials, and the genetic algorithm is used to calculate the optimal storage plan. The algorithm considers the importance and urgency of the materials and optimizes the handling order. After the automatic handling and rearrangement of sensitive materials, the adjusted electromagnetic environment is evaluated through the distributed sensor network to verify the optimization effect. If there is still a risk in the adjusted electromagnetic environment, a new round of optimization calculation and adjustment is triggered. The warning information is sent to the power grid dispatching and control center through the IEC61850 protocol, including detailed information such as the predicted electromagnetic exceeding area, time and degree. According to the severity of the warning, the information is divided into three levels: general, important and urgent, and different response measures are adopted respectively. For emergency warnings, the emergency plan is activated and the operating parameters of the relevant transmission lines are adjusted first. After receiving the warning information, the power grid dispatching center uses the NSGA-II (non-dominated sorting genetic algorithm II) algorithm to comprehensively consider factors such as power grid safety, economy and electromagnetic interference to generate an optimized operation plan for the transmission line. The corresponding adjustment operations are performed through remote control, such as changing the line load distribution and adjusting the reactive compensation device. After the optimization plan is implemented, the changes in the electromagnetic environment are continuously monitored and the adjustment effect is evaluated. According to the evaluation results, the optimization objectives and constraints are dynamically adjusted to achieve continuous improvement. At the same time, the adjusted power grid operation data is fed back to the warehouse management system to form a collaborative optimization closed loop between the warehouse and the power grid. In a 100m×50m×10m smart warehouse, the prediction model shows that the electromagnetic field strength in the northwest corner will exceed the standard by 20% in the next 4 hours. After receiving the warning information, the Siemens S7-1500PLC controls the angle of the 12 adjustable shielding plates in the northwest corner to adjust from 45° to 60°, and at the same time increases the thickness of the absorbing material from 2cm to 3cm. 10 high-precision electromagnetic field sensors (sensitivity 0.1V / m) monitor the shielding effect in real time, sampling every 30 seconds. The PLC adopts the PID control algorithm, with a proportional coefficient Kp=0.8, an integral time Ti=120s, and a differential time Td=30s, and continuously optimizes the control parameters to maintain the shielding effect above 30dB. The automated logistics system uses a genetic algorithm to calculate the optimal storage plan, with a population size of 100, a crossover probability of 0.8, a mutation probability of 0.1, and 500 iterations. The algorithm divides 1,000 pieces of materials into three categories according to electromagnetic sensitivity, and takes into account importance (level 1-5) and urgency (urgent use within 24 hours). The AGV car completes the rearrangement of materials in 30 minutes according to the optimized order.50 distributed sensors assess the adjusted electromagnetic environment, and Kriging interpolation is used to generate a new electromagnetic field distribution map.

[0056] The IEC61850 protocol encodes the warning information into MMS messages and sends them to the power grid dispatch control center through an encrypted VPN tunnel. The warnings are divided into three levels: general (exceeding the standard <10%), important (10%-30%), and emergency (>30%), which trigger 5 minutes, 2 minutes, and immediate responses respectively. The power grid dispatch center uses the NSGA-II algorithm to optimize the transmission line operation plan, with a population size of 200 and 1000 iterations. The optimization objectives include minimizing electromagnetic interference, network losses, and adjustment costs, and the constraints include voltage stability and N-1 safety verification. The remote control system executes the optimization plan, such as reducing the load of line 2 by 15% and adjusting the SVG reactive compensation by +20Mvar. The adjustment effect is evaluated every 5 minutes, and the weight coefficient is adjusted dynamically. Finally, the warehouse electromagnetic environment compliance rate is increased from 85% to 98%, and the power grid loss is reduced by 3%.

[0057] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. An early warning method for the supply of power materials in a temporary construction warehouse, characterized in that: The method comprises: According to the relative position relationship between the temporary warehouses during highway construction and the high-voltage transmission lines, a three-dimensional electromagnetic field distribution model based on the actual environmental impact was established to obtain the theoretical distribution of the electromagnetic environment of each warehouse. In the temporary warehouse, electromagnetic sensors are deployed for materials whose electronic components are highly sensitive to electromagnetic interference, and electromagnetic sensors with a large dynamic range are deployed for materials whose metal materials induce strong electromagnetic fields; Through the low-power wide-area Internet of Things, the monitoring data collected by various electromagnetic sensors in the warehouse are transmitted back to the power grid dispatching center in real time, and associated with the warehouse material structure parameters to build a database; Extracting electromagnetic interference thresholds of various materials from the database, integrating monitoring data with theoretical distribution, determining the distribution of electromagnetic field strength in the warehouse, and identifying the types of materials and specific areas with electromagnetic interference risks; If the electromagnetic field intensity in a certain area is found to exceed the electromagnetic sensitivity threshold of the materials stored in the area, an early warning message will be generated, and protective facilities will be configured according to the actual electromagnetic field, and corresponding protective measures adjustment suggestions will be given; If the overall electromagnetic environment of the warehouse deteriorates, the warning information will be sent to the power grid dispatching center to coordinate the dynamic adjustment of the operating parameters of the high-voltage transmission line to reduce the electromagnetic interference level generated by the transmission line to a safe range that all kinds of materials can withstand; Mining historical data of power grid load and electromagnetic environment, extracting the correlation between electromagnetic interference characteristics and transmission line operating conditions, and establishing a collaborative prediction model for electromagnetic safety situation in multiple warehouses; According to the prediction results of the prediction model, electromagnetic protection measures are adjusted through warehouse hardware facilities, and the storage area of ​​sensitive materials is dynamically optimized. At the same time, early warning information is fed back to the power grid dispatching center to coordinate and optimize the operation mode of the transmission line.

2. The method according to claim 1, wherein: According to the relative position relationship between the temporary warehouse for highway construction and the high-voltage transmission line, a three-dimensional electromagnetic field distribution model based on the actual environmental impact is established to obtain the theoretical distribution of the electromagnetic environment of each warehouse, including: Acquire three-dimensional coordinate data of a temporary warehouse for highway construction and a high-voltage transmission line, wherein the three-dimensional coordinate data includes the location and size of the warehouse and the tower coordinates of the transmission line; Determine the spatial distribution of the electromagnetic field source according to the three-dimensional coordinate data, wherein the spatial distribution is determined by the voltage level, current load, phase line arrangement and tower structure of the transmission line; A 3D electromagnetic field distribution model is established by using a finite element method, wherein the 3D electromagnetic field distribution model uses transmission line parameters as boundary conditions; If there is terrain undulation, a digital terrain model is established; If there is atmospheric influence, an atmospheric propagation model is constructed; Analyze the distribution of electromagnetic field intensity in space, which is obtained by combining the shielding and reflection effects of terrain undulations on electromagnetic wave propagation and the influence of atmospheric conditions on electromagnetic wave attenuation; According to the specific location and building structure of each warehouse, the distribution of the electromagnetic field inside the warehouse is calculated, and the distribution is determined by the electromagnetic shielding coefficient and reflection coefficient of the warehouse wall material.

3. The method according to claim 1, wherein: In the temporary warehouse, electromagnetic sensors are deployed for materials whose electronic components are highly sensitive to electromagnetic interference, and electromagnetic sensors with a large dynamic range are deployed for materials whose metal materials induce strong electromagnetic fields, including: For the interior of the warehouse, a laser scanner is used to perform three-dimensional space scanning to obtain the warehouse's point cloud data; Constructing a spatial model of the warehouse using three-dimensional reconstruction software based on the point cloud data; For the electronic component area and the metal material area in the warehouse space model, the electromagnetic sensitivity is evaluated, and the layout point coordinates of the high-sensitivity electromagnetic sensor and the large dynamic range electromagnetic sensor are determined; According to the layout point coordinates, Hall effect sensors and capacitive sensors are laid out in the electronic component area, and Rogowski coil sensors and electrostatic field meters are laid out in the metal material area; Collect sensor data from Hall effect sensors, capacitive sensors, Rogowski coil sensors, and electrostatic field meters; According to the sensor data, a Kalman filter state equation and an observation equation are established; According to the state equation and the observation equation, an optimal estimation value is obtained through iterative calculation; Based on the optimal estimated value and the layout point coordinates, construct a three-dimensional model of the electromagnetic field distribution in the warehouse; If electromagnetic interference exceeding a preset threshold is detected in the three-dimensional model of electromagnetic field distribution, an alarm is triggered and the location information of the interference source is provided through a triangulation positioning algorithm.

4. The method according to claim 1, wherein: The monitoring data collected by various electromagnetic sensors in the warehouse are transmitted back to the power grid dispatching center in real time through the low-power wide-area Internet of Things, and are associated with the warehouse material structure parameters to build a database, including: Obtain the original data of the electromagnetic sensor collected by the LoRa node device, and calculate the difference between adjacent sampling points using the DPCM algorithm based on the original data; For the difference information, an AES-128 encryption algorithm is used to generate an encrypted data packet, and the encrypted data packet is transmitted to the power grid dispatching center through the LoRaWAN network; Decrypting the encrypted data packet using a preset key to obtain original monitoring data; Building a database, including obtaining material structure parameter information, and converting the original monitoring data and the material structure parameter information into data in JSON format; If the data in the JSON format is structured material parameter information, it is stored in the MySQL database; If the data in JSON format is semi-structured monitoring data, it is stored in a MongoDB database.

5. The method according to claim 1, wherein: The electromagnetic interference thresholds of various materials are extracted from the database, the monitoring data is integrated with the theoretical distribution, the distribution of the electromagnetic field strength in the warehouse is determined, and the types and specific areas of materials with electromagnetic interference risks are identified, including: Acquire electromagnetic interference threshold data of various materials from the database, and establish the electromagnetic interference threshold table according to the material type and sensitivity, wherein the electromagnetic interference threshold table includes electric field strength threshold and magnetic field strength threshold; Acquire real-time monitoring data in the warehouse. If the real-time monitoring data is discrete monitoring point data, use ordinary kriging to perform spatial interpolation on the discrete monitoring point data to obtain continuous electromagnetic field intensity distribution data; The continuous electromagnetic field intensity distribution data is fused with the theoretical distribution by using a Markov chain Monte Carlo method to obtain a fused electromagnetic field intensity distribution; The fused electromagnetic field intensity distribution is compared with the electromagnetic interference threshold table, and the C4.5 decision tree algorithm is used to identify the area exceeding the threshold, wherein the minimum leaf node sample number of the C4.5 decision tree algorithm is a preset sample value, and the maximum depth is a preset depth value; The historical data is updated by a sliding window method, and the electromagnetic interference threshold in the electromagnetic interference threshold table is adjusted according to the updated historical data. The time window of the sliding window method is a preset window value.

6. The method according to claim 1, wherein: If the electromagnetic field strength in a certain area is found to exceed the electromagnetic sensitivity threshold of the materials stored in the area, an early warning message is generated, and protective facilities are configured according to the actual electromagnetic field, and corresponding protective measures adjustment suggestions are given, including: The warehouse space is divided into regions using a K-means clustering algorithm, wherein the K-means clustering algorithm sets the number of clusters to a preset value and uses the Euclidean distance as a similarity metric to obtain an electromagnetic environment partition map; According to the electromagnetic environment zoning map, the C4.5 decision tree algorithm is used to compare the electromagnetic field intensity of each area with the preset electromagnetic sensitivity threshold of the stored materials to determine whether there is an over-threshold situation; If the judgment result shows that the electromagnetic field strength in a certain area exceeds the sensitivity threshold, an early warning is triggered, and a JSON format early warning message is generated, including the location of the area exceeding the standard, the electromagnetic field strength value, and the material type; Based on the JSON format warning information, obtain the existing electromagnetic protection facility information in the area and generate protection measures adjustment suggestions; Based on the protective measures adjustment suggestions, a cost-benefit analysis is performed on the protective measures, the return on investment is calculated, and a priority list is generated by arranging the measures in descending order according to the return on investment.

7. The method according to claim 1, wherein: If the overall electromagnetic environment of the warehouse deteriorates, the warning information will be sent to the power grid dispatching center to coordinate the dynamic adjustment of the operating parameters of the high-voltage transmission line to reduce the electromagnetic interference level generated by the transmission line to a safe range that all kinds of materials can withstand, including: Obtaining warehouse electromagnetic environment data monitored by a preset distributed sensor network, and calculating the temporal and spatial variation trend of the electromagnetic field intensity using a sliding window algorithm based on the data to obtain electromagnetic field intensity variation data; A quantitative evaluation is performed on the electromagnetic field intensity change data. If the average electromagnetic field intensity increases by a preset range or the peak value exceeds a preset multiple of the safety standard, it is determined that the electromagnetic environment has deteriorated and an early warning data packet is generated; The early warning data packet is encrypted by the SSL / TLS protocol to obtain an encrypted early warning data packet, and the encrypted early warning data packet is sent to the power grid dispatching center; The power grid dispatching center receives the encrypted warning data packet, uses the weighted least squares method to estimate the power system state, and determines the key transmission lines and their operating parameters that affect the electromagnetic environment of the warehouse; A non-dominated sorting genetic algorithm is used to perform multi-objective optimization on the operating parameters of the key transmission line; Based on the optimized transmission line operating parameters, the transmission line is dynamically adjusted.

8. The method according to claim 1, wherein: The historical data of power grid load and electromagnetic environment are mined, the correlation between electromagnetic interference characteristics and transmission line operation conditions is extracted, and a collaborative prediction model of electromagnetic safety situation of multiple warehouses is established, including: Obtain historical data of power grid monitoring and warehouse electromagnetic environment monitoring, including power grid load, transmission line operating parameters and warehouse electromagnetic field strength; Based on the historical data of power grid monitoring and the historical data of warehouse electromagnetic environment monitoring, the moving median method is used to deal with abnormal values, and the interpolation method is used to deal with missing values ​​to obtain cleaned data; The cleaned data is standardized using a minimum-maximum normalization method to determine standardized data; The electromagnetic interference signal in the standardized data is subjected to a 5-layer multi-scale decomposition using Daubechies wavelet to obtain time domain features and frequency domain features; Using principal component analysis to reduce feature dimensions according to the time domain features and the frequency domain features, determining whether the cumulative contribution rate reaches a preset range, and if so, determining an electromagnetic interference feature vector; Apriori algorithm is used to analyze the correlation between the electromagnetic interference feature vector and the transmission line operation parameter; Set the minimum support and minimum confidence, and judge whether the support and confidence meet the conditions. If they meet the conditions, determine the strong correlation rule and obtain the correlation relationship between electromagnetic interference and transmission line operation conditions; Constructing a graph convolutional network according to the association model, wherein the graph convolutional network includes a two-layer GCN structure, and the activation function of the GCN structure is ReLU; The graph convolutional network is trained using the Adam optimizer to obtain a collaborative prediction model for electromagnetic safety situation in multiple warehouses. The prediction error is calculated according to the prediction result, and it is determined whether the prediction error exceeds a preset threshold. If it exceeds the preset threshold, the warning threshold is adjusted to obtain a dynamic warning threshold.

9. The method according to claim 1, wherein: According to the prediction results of the prediction model, the electromagnetic protection measures are adjusted through the warehouse hardware facilities, the storage area of ​​sensitive materials is dynamically optimized, and the early warning information is fed back to the power grid dispatching center to coordinate and optimize the operation mode of the transmission line, including: Obtain the prediction results of the electromagnetic field intensity distribution in the warehouse and the electromagnetic sensitivity data of the materials, and calculate the optimal storage plan for the materials based on the prediction results and sensitivity data; Adjusting the working parameters of the electromagnetic shielding equipment in the warehouse by PLC, wherein the working parameters include the angle of the shielding plate and the thickness of the absorbing material; Use electromagnetic field sensors to monitor the shielding effect in real time and form a closed-loop feedback based on the monitoring results; If the monitoring results show that the shielding effect does not meet the standard, the PLC will be triggered to adjust the control parameters according to the feedback data; Sending warning information to the power grid dispatching center via the IEC61850 protocol, wherein the warning information includes the predicted electromagnetic exceeding standard area, time and degree; The power grid dispatching center receives the warning information and generates an optimized operation plan for the transmission line using the NSGA-II algorithm. The optimized operation plan includes line load distribution and reactive power compensation device adjustment parameters.

Images