A control method of a mine ultra-long distance reactive power compensation device

Abstract

This invention belongs to the field of mining power supply technology, specifically relating to a control method for a long-distance reactive power compensation device in mining. The method includes a central monitoring and coordination system that calculates the optimal reactive power output command for each reactive power compensation unit based on the overall network operating status and a pre-trained long-distance reactive power compensation algorithm model. The system then sends coordinated control commands containing the optimal reactive power output command to each local controller. A multi-objective optimization function is constructed through the central monitoring and coordination system, and the optimal reactive power output is solved using a pre-trained LSTM (Long Short-Term Memory) neural network model. The model is trained on historical data from all mining power transmission conditions, enabling it to accurately adapt to the characteristics of underground load fluctuations and operating condition changes. It can dynamically adjust the reactive power output of each compensation unit according to the overall network operating status, thus avoiding the increased active power loss caused by long-distance reactive power transmission and reducing frequent switching of compensation equipment through output smoothing constraints, thereby extending the equipment's service life.

Description

Technical Field

[0001] This invention belongs to the field of mining power supply technology, specifically relating to a control method for a long-distance reactive power compensation device for mining. Background Technology

[0002] In underground coal mining operations, the continuous extension of tunnels significantly increases the power supply distance of transmission lines. Ultra-long-distance transmission lines commonly suffer from large voltage drops, severe load fluctuations, and low power factors, seriously affecting the safe power supply to coal mines. Existing reactive power compensation methods in mines mostly employ centralized compensation at both ends of the line, which is difficult to adapt to the voltage distribution characteristics of long lines. This results in large voltage deviations along the line, making it impossible to maintain the voltage within acceptable range. Furthermore, the response to local load disturbances is delayed, easily causing voltage dips and spikes, leading to problems such as start-up and shutdown failures of mining equipment and insufficient motor output torque.

[0003] Meanwhile, the control algorithms of traditional compensation devices are mostly conventional optimization methods with fixed parameters. They do not combine the electrical characteristics of long mining lines to build an adaptation model, making it difficult to dynamically adjust reactive power output according to the overall network operation status. This can easily lead to long-distance transmission of reactive power and increase active power loss in the lines. Summary of the Invention

[0004] To address the aforementioned shortcomings of existing technologies, this invention provides a control method, terminal, and storage medium for a long-distance reactive power compensation device used in mining.

[0005] In a first aspect, the present invention provides a control method for a long-distance reactive power compensation device used in mining, comprising: S1. Determine the installation location of the reactive power compensation unit in the reactive power compensation device on ultra-long-distance transmission lines. The installation location is determined based on the electrical length of the transmission line, voltage distribution characteristics, and reactive power optimization configuration model. S2. At least two reactive power compensation units are arranged at the installation location. The reactive power compensation units are connected in series on different sections of the ultra-long-distance transmission line. Each reactive power compensation unit includes a combination module of thyristor-controlled reactor and thyristor-switched capacitor connected in parallel between the phase line and the ground line of the transmission line, a local measurement unit for real-time monitoring of local line voltage and current, and a local controller. S3. The voltage and current signals of the local line are collected in real time through the local measurement unit, and the collected measurement data is transmitted to the local controller. S4. Establish a data connection between the central monitoring and coordination system and the local controllers of each reactive power compensation unit through the communication network. The central monitoring and coordination system receives the measurement data of each reactive power compensation unit. S5. The central monitoring and coordination system calculates the optimal reactive power output command for each reactive power compensation unit based on the overall network operation status and the pre-trained long-distance reactive power compensation algorithm model, and sends the coordination control command containing the optimal reactive power output command to each local controller. S6. Based on the received coordination control commands, the local controller controls the conduction angle of the thyristor control reactor and the switching of the thyristor-switched capacitor to achieve reactive power compensation.

[0006] A further improvement to this technical solution is that the specific method for determining the installation location of the reactive power compensation unit in step S1 is as follows: S11. Collect the physical and operational basic parameters of the ultra-long-distance transmission line for mining, and calculate the electrical length of the line in conjunction with the benchmark values ​​of the mining power supply system. The calculation formula is as follows: ; in, The electrical length of the transmission line; This refers to the actual physical length of the transmission line; Resistance per unit length of the line; Reactance per unit length of the line; This serves as the reference impedance for the mine power supply system. , The rated voltage for ultra-long-distance transmission lines, This serves as the baseline capacity for mine power supply systems. S12. Real-time operating voltage at each monitoring point along the line is collected using a multi-point monitoring device. The voltage deviation rate at each point is calculated based on the line's rated voltage, and weak voltage points are identified. The calculation formula is as follows: ; in, The voltage deviation rate at the x-th monitoring point on the line; This represents the real-time voltage value at the x-th monitoring point on the line. This refers to the rated voltage of ultra-long-distance transmission lines, measured in volts. The monitoring points were marked as voltage weak points; S13. Construct a reactive power optimization configuration model with the dual objectives of minimizing voltage deviation and minimizing active power loss. Substitute the electrical length characteristic points and voltage weak points into the reactive power optimization configuration model to solve for the optimal installation location. The formula is: ; in, represents the optimal installation location set for the reactive power compensation unit; m represents the number of monitoring points in the ultra-long-distance transmission line. The objective function for the reactive power optimization configuration model; This is the weighting factor for the voltage deviation; This is the weighting coefficient for active power loss, and ; This refers to the total active power loss of ultra-long-distance transmission lines; This refers to the rated active power of the line.

[0007] Further improvements to this technical solution include the following specific method for arranging the reactive power compensation unit in step S2: S21. Based on the optimal installation location set obtained in step S1 At least two reactive power compensation units are arranged in different sections of the ultra-long-distance transmission line for mining, so that the reactive power compensation units are distributed in series along the line. Or at points with weak voltage, ensure that the electrical spacing between reactive power compensation units meets the following requirements: ; in, The electrical spacing between the two reactive power compensation units; These are the installation locations of the i-th and j-th reactive power compensation units, respectively. S22. At each installation location, the combined module of the thyristor-controlled reactor and the thyristor-switched capacitor in the reactive power compensation unit is connected in parallel between the phase line and the ground line of the transmission line, and the total capacity of the combined module is configured to meet the following requirements: ; in, The total reactive power capacity of a single reactive power compensation unit combined module; k is the mining compensation coefficient; This is the average power factor of the mining transmission line; S23. Install a local measurement unit and a local controller next to each reactive power compensation unit, connect the signal acquisition terminal of the local measurement unit to the transmission line, and establish electrical control connection and data transmission connection between the local controller and the combined module and the local measurement unit respectively.

[0008] Further improvements to this technical solution include the following specific method for acquiring and transmitting measurement data in step S3: S31. Set the local measurement unit to the mine monitoring working mode and collect the phase voltage, line voltage, phase current and line current signals of the local line in real time through the voltage transformer and current transformer. S32. The collected raw voltage and current signals are filtered and denoised to remove harmonic interference generated by electrical equipment in the coal mine. The filtering formula is as follows: ; ; in, Δt represents the effective values ​​of voltage and current after filtering at time t; N is the width of the filtering window; Δt is the acquisition time interval. These are the voltage and current values ​​from historical sampling points; S33. The filtered voltage and current measurement data are sent to the local controller in real time through the intrinsically safe data transmission interface for mining applications. The data is verified during transmission using the following verification formula: ; Where CRC stands for Cyclic Redundancy Check; ⊕ represents the XOR operation. is the kth measurement data byte; n is the number of bytes in a single frame of data.

[0009] Further improvements to this technical solution include the following specific method for establishing a data connection and receiving measurement data in step S4: S41. Select the power fiber optic private network as the main communication network and the underground wireless private network of the coal mine as the backup communication network. Establish bidirectional data connections between the central monitoring and coordination system and the local controllers of each reactive power compensation unit. S42. Configure a redundancy backup and link detection module in the communication network to detect the transmission success rate of the main communication network in real time. The calculation formula is as follows: ; in, The data transmission success rate of the main communication network; The number of measurement data packets successfully transmitted; The total number of measurement data packets sent; when η < 0.95, the system automatically switches to the backup communication network. S43. The central monitoring and coordination system receives measurement data uploaded by each local controller through the communication network, performs time synchronization and normalization processing on the multi-unit data, and the time synchronization error meets the requirements. ,in The normalization formula for the time synchronization error of multi-unit measurement data is: ; ; in, These are the normalized voltage and current values; This is the rated current of the line.

[0010] Further improvements to this technical solution include the following specific method for calculating the optimal reactive power output command and issuing the coordinated control command in step S5: S51. The central monitoring and coordination system constructs a multi-objective optimization function based on the normalized network-wide measurement dataset, with the objectives of voltage stability, loss reduction, and power output smoothness. The formula is as follows: ; Where J is the value of the multi-objective optimization function; n is the number of reactive power compensation units; Let be the real-time voltage at the installation point of the i-th reactive power compensation unit; The weighting coefficients are dimensionless and ; This represents the total active power loss of the line. The reactive power output of the i-th unit at adjacent time points; S52. Substitute the multi-objective optimization function into the pre-trained LSTM (Long Short-Term Memory) neural network model for solution. This model takes the overall network operating state as input and the optimal reactive power output as output. The solution formula is as follows: ; in, This represents the reactive power output value of the i-th unit predicted by the model. Let t be the feature vector of the entire network's operating state at time t; θ represents the normalized total active power loss; θ is the model pre-training parameter set, including weights and biases. S53. The model predictions are corrected based on the operational constraints of the mine power transmission line to obtain the optimal reactive power output command for each unit. The correction formula is as follows: ; in, This is the optimal reactive power output command for the i-th reactive power compensation unit; The maximum and minimum reactive power output limits for the i-th unit are respectively set. The optimal reactive power output command is then encapsulated into a coordination control command and sent to each local controller through the communication network.

[0011] Further improvements to this technical solution include the following specific method for constructing and training the pre-trained LSTM long short-term memory neural network model in step S52: S521. Collect historical operating data of ultra-long-distance transmission lines used in mining under all operating conditions, filter out effective data including voltage, current, active power loss, and reactive power output under different mining loads, different fault states, and different ambient temperatures, construct the original dataset for the model, and divide it proportionally. The division formula is as follows: ; in, The original dataset for the model has a sample size of M; The training set for the model accounts for [percentage]. ; This is the model validation set, accounting for [percentage]. ; This is the model test set, accounting for [percentage]. ,and ; S522. Construct an LSTM (Long Short-Term Memory) neural network structure containing an input layer, three LSTM hidden layers, a fully connected layer, and an output layer. The number of nodes in the input layer and the feature vector of the entire network's operating state are considered. The dimension is consistently m, and the number of nodes in the LSTM hidden layer is set sequentially as follows: , , The number of output layer nodes is the same as the number of reactive power compensation units, n. The root mean square error is used as the loss function for model training, and the loss formula is: ; in, This represents the root mean square error loss value of the model. The number of samples in the training set; This represents the actual optimal reactive power output value of the i-th reactive power compensation unit in the k-th training sample. This is the model's predicted reactive power output for the k-th training sample; S523. The adaptive moment estimation optimization algorithm is used to iteratively train the model, and the initial learning rate of the model is set. ; The weight decay coefficient; training batch size. Iterate training until the loss value on the validation set no longer decreases for 10 consecutive rounds and the loss value on the test set also decreases. A convergent pre-trained LSTM long short-term memory neural network model is obtained, and the model pre-trained parameter set θ is solidified into the algorithm module of the central monitoring and coordination system.

[0012] Further improvements to this technical solution include the following specific method for implementing reactive power compensation in step S6: S61. The local controller receives the coordination control command issued by the central monitoring and coordination system and parses out the optimal reactive power output command. Based on the output characteristics of the thyristor-controlled reactor and the thyristor-switched capacitors, the target conduction angle of the thyristor-controlled reactor and the target number of switching groups of the thyristor-switched capacitors are calculated. The formula for calculating the conduction angle is: ; in, The target conduction angle for the thyristor-controlled reactor; The target reactive power output of the thyristor-controlled reactor; This is the equivalent reactance of the thyristor-controlled reactor; S62. The local controller sends a trigger pulse signal to the thyristor-controlled reactor to adjust its thyristor conduction angle to the target conduction angle. Simultaneously, a switching control signal is sent to the thyristor to switch the capacitors, switching the corresponding number of capacitor banks. The switching logic satisfies... , where z is the target number of thyristor-switched capacitor groups; This is for rounding up; The reactive power output is for the purpose of switching capacitors with thyristors; This refers to the rated reactive power of a single capacitor bank. S63. The local controller collects the compensated local line voltage and current data in real time through the local measurement unit, calculates the actual reactive power compensation output, and the verification formula is: ; in, The actual reactive power compensation output of the i-th unit; The current value of the local line after compensation; To compensate for the power factor angle of the local line, when When the reactive power compensation has achieved the target effect, the compensation control is completed.

[0013] In a second aspect, the present invention provides a terminal, comprising: Processor, memory, among which, This memory is used to store computer programs. The processor is used to retrieve and run the computer program from memory, causing the terminal to perform the terminal method described above.

[0014] Thirdly, the present invention provides a computer storage medium storing instructions that, when executed on a computer, cause the computer to perform the methods described in the above aspects.

[0015] The beneficial effects of this invention are as follows: Based on the electrical length and voltage distribution characteristics of the transmission line and the dual-objective reactive power optimization configuration model, the installation location of the reactive power compensation unit is determined. Combined with the standard electrical spacing, the distributed compensation units are arranged to replace the traditional centralized compensation method at both ends. This effectively reduces the voltage deviation along the line and maintains the line voltage within the qualified range. From a layout perspective, this solves the problem of large voltage drop on long lines and avoids start-up and shutdown failures and insufficient motor output of mining equipment due to abnormal voltage, thus ensuring the stable operation of coal mine mining equipment.

[0016] The local measurement unit adopts mining-adapted acquisition and filtering methods to filter out underground electrical harmonic interference, and combines cyclic redundancy check to achieve accurate transmission of measurement data. At the same time, it constructs a dual communication network with a dedicated power fiber optic network as the main network and an underground wireless network as a backup, coupled with link detection and automatic switching mechanisms, to meet the environmental requirements of explosion protection and electromagnetic interference in coal mines, ensuring the continuity and accuracy of measurement data and control command transmission, and providing a reliable data foundation for subsequent reactive power compensation calculations.

[0017] A multi-objective optimization function is constructed through a central monitoring and coordination system. The optimal reactive power output is solved by combining a pre-trained LSTM (Long Short-Term Memory) neural network model. The model is trained on historical data of all operating conditions of mine power transmission and can accurately adapt to the characteristics of underground load fluctuations and operating condition changes. It can dynamically adjust the reactive power output of each compensation unit according to the overall network operation status. This not only avoids the problem of increased active power loss caused by long-distance transmission of reactive power, but also reduces the frequent switching of compensation equipment through output smoothing constraints, thus extending the service life of the equipment.

[0018] The local controller precisely adjusts the conduction angle of the thyristor-controlled reactor and the number of thyristor-switched capacitor banks according to the central command, realizing fine-grained adjustment of reactive power compensation. At the same time, it verifies the actual output by collecting data after compensation in real time, ensuring that the compensation effect matches the optimal reactive power output command, forming a closed-loop compensation process of "calculation-control-verification". This effectively suppresses voltage dips and surges caused by local load disturbances, and improves the voltage stability and power factor of ultra-long-distance transmission lines for mining. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a schematic flowchart illustrating a method according to an embodiment of the present invention.

[0021] Figure 2 This is a schematic diagram of the structure of a terminal provided in an embodiment of the present invention. Detailed Implementation

[0022] To make the objectives, features, and advantages of this invention more apparent and understandable, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings of the specific embodiments. Obviously, the embodiments described below are only some embodiments of this invention, and not all embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention.

[0024] Figure 1This is a schematic flowchart illustrating the control method of a long-distance reactive power compensation device for mining provided by the present invention. The order of steps in this flowchart can be changed, and some steps can be omitted, depending on different requirements.

[0025] like Figure 1 As shown, the method includes: S1. Determine the installation location of the reactive power compensation unit in the reactive power compensation device on ultra-long-distance transmission lines. The installation location is determined based on the electrical length of the transmission line, voltage distribution characteristics, and reactive power optimization configuration model. S2. At least two reactive power compensation units are arranged at the installation location. The reactive power compensation units are connected in series on different sections of the ultra-long-distance transmission line. Each reactive power compensation unit includes a combination module of thyristor-controlled reactor and thyristor-switched capacitor connected in parallel between the phase line and the ground line of the transmission line, a local measurement unit for real-time monitoring of local line voltage and current, and a local controller. S3. The voltage and current signals of the local line are collected in real time through the local measurement unit, and the collected measurement data is transmitted to the local controller. S4. Establish a data connection between the central monitoring and coordination system and the local controllers of each reactive power compensation unit through the communication network. The central monitoring and coordination system receives the measurement data of each reactive power compensation unit. S5. The central monitoring and coordination system calculates the optimal reactive power output command for each reactive power compensation unit based on the overall network operation status and the pre-trained long-distance reactive power compensation algorithm model, and sends the coordination control command containing the optimal reactive power output command to each local controller. S6. Based on the received coordination control commands, the local controller controls the conduction angle of the thyristor control reactor and the switching of the thyristor-switched capacitor to achieve reactive power compensation.

[0026] To facilitate understanding of the present invention, the following description further illustrates the control method of the mine ultra-long distance reactive power compensation device provided by the present invention, based on the principle of the control method of the mine ultra-long distance reactive power compensation device of the present invention and in conjunction with the process of controlling the mine ultra-long distance reactive power compensation device in the embodiments.

[0027] First, the specific method for determining the installation location of the reactive power compensation unit in step S1 is as follows: S11. Collect the physical and operational basic parameters of the ultra-long-distance transmission line for mining, and calculate the electrical length of the line in conjunction with the benchmark values ​​of the mining power supply system. The calculation formula is as follows: ; in, The electrical length of the transmission line, in radians; The actual physical length of the transmission line is expressed in kilometers. The resistance per unit length of the line is expressed in ohms per kilometer. The reactance per unit length of the line is expressed in ohms per kilometer. This serves as the reference impedance for the mine power supply system. The unit is ohms. The rated voltage for ultra-long-distance transmission lines, This serves as the baseline capacity for mine power supply systems. S12. Real-time operating voltage at each monitoring point along the line is collected using a multi-point monitoring device. The voltage deviation rate at each point is calculated based on the line's rated voltage, and weak voltage points are identified. The calculation formula is as follows: ; in, The voltage deviation rate at the x-th monitoring point on the line; This represents the real-time voltage value at the x-th monitoring point on the line, in volts. This refers to the rated voltage of ultra-long-distance transmission lines, measured in volts. The monitoring points were marked as voltage weak points; S13. Construct a reactive power optimization configuration model with the dual objectives of minimizing voltage deviation and minimizing active power loss. Substitute the electrical length characteristic points and voltage weak points into the reactive power optimization configuration model to solve for the optimal installation location. The formula is: ; in, represents the optimal installation location set for reactive power compensation units, in kilometers; m represents the number of monitoring points in ultra-long-distance transmission lines. The objective function for the reactive power optimization configuration model; This is the weighting factor for the voltage deviation; This is the weighting coefficient for active power loss, and ; Total active power loss for ultra-long-distance transmission lines, expressed in watts; This refers to the rated active power of the line, measured in watts.

[0028] Using a mining line parameter tester, five test sections, each 1 kilometer long, were evenly selected along the ultra-long-distance transmission line. The resistance and reactance of each test section were measured, and the average value was taken as the resistance per unit length of the line. and reactance per unit length The actual physical length of the transmission line is obtained from the transmission line design drawings. (Unit: km); Extract the system rated voltage from the technical specifications of the coal mine power supply system. (Unit: kV) and base capacity (Unit: megavolt-amperes).

[0029] According to the definition formula of the reference impedance of the mining power supply system, first, the rated voltage... Convert the unit to kilovolts, and the base capacity. The unit is kept in megavolt-amperes, and the reference impedance is calculated. The formula is: ; For example, if the rated voltage of the mine power supply system kV, base capacity Megavolt-amperes, then the reference impedance ohm.

[0030] Collected and the calculated Substitute the values ​​into the electrical length calculation formula to solve for the electrical length of the transmission line. (Unit: radians), the formula is: ; For example, if the actual physical length of the line kilometer, resistance per unit length Ohms per kilometer, reactance per unit length Ohms per kilometer, reference impedance Ohm, then Electrical length radian.

[0031] S12. Implementation process of voltage weak point identification: Monitoring points are deployed along ultra-long-distance transmission lines at a density of one monitoring point every 500 meters. The total number of monitoring points (m) is determined based on the actual physical length of the line. Determine (e.g.) (At kilometer markers, m=10), each monitoring point is equipped with an intrinsically safe voltage monitoring sensor for mining applications. The sensor's measurement range is adapted to the rated voltage of the line. The measurement accuracy is no less than 0.2 grade.

[0032] The real-time operating voltage of each monitoring point is simultaneously collected through the centralized acquisition module of the multi-point monitoring device. (Unit: Volt), the sampling frequency is set to 100Hz, and the sampling is carried out continuously for 10 minutes, with 60,000 voltage samples obtained at each monitoring point.

[0033] The real-time voltage value of each monitoring point is obtained by averaging the voltage samples. Combined with the line's rated voltage Calculate the voltage deviation rate at each monitoring point. The formula is: ; Setting the voltage deviation rate threshold to 0.05 will satisfy... The monitoring points are marked as voltage weak points. For example, the line's rated voltage. Volts, the real-time voltage value at a certain monitoring point The voltage deviation rate at that monitoring point is calculated in volts. The monitoring point was determined to be a weak point in voltage.

[0034] A reactive power optimization configuration model is constructed with the dual objectives of minimizing voltage deviation and minimizing active power loss. The objective function is... The calculation formula is: ; in, This is the weighting factor for the voltage deviation. This is the weighting coefficient for active power loss, and In light of the core requirement of stable voltage in underground coal mine power supply, the following settings are made: =0.7, =0.3; The total active power loss (in watts) of an ultra-long-distance transmission line is calculated using line parameters and operating current, as shown in the formula: (I represents the real-time line current, in amperes); The rated active power of the line (unit: watts) is determined by the total rated power of the coal mining equipment.

[0035] By constructing a dual-objective reactive power optimization configuration model combining the electrical length and voltage distribution characteristics of transmission lines, the resulting optimal installation location set can accurately match voltage-weak areas and key electrical characteristic points of ultra-long-distance transmission lines in coal mines. This avoids the blindness of traditional installation methods and ensures that reactive power compensation units can achieve maximum compensation efficiency. Based on voltage deviation rate identification of voltage-weak points, reactive power compensation units are strategically placed at key locations to directly compensate and adjust areas with abnormal voltage, effectively reducing voltage deviation along the line and maintaining the line voltage within acceptable range. This prevents mining equipment from experiencing starting difficulties and insufficient output torque due to low voltage, ensuring continuous coal mining operations. Minimizing active power loss is included in the optimization objective. When determining installation locations, both voltage stability and energy consumption control are considered. Through the rational layout of reactive power compensation units, the additional active power loss caused by long-distance reactive power transmission is reduced, lowering the energy consumption cost of the coal mine power supply system and improving energy utilization efficiency.

[0036] Secondly, the specific method for arranging the reactive power compensation unit in step S2 is as follows: S21. Based on the optimal installation location set obtained in step S1 At least two reactive power compensation units are arranged in different sections of the ultra-long-distance transmission line for mining, so that the reactive power compensation units are distributed in series along the line. Or at points with weak voltage, ensure that the electrical spacing between reactive power compensation units meets the following requirements: ; in, The electrical distance between two reactive power compensation units, in radians; The installation locations of the i-th and j-th reactive power compensation units are shown in kilometers; verify whether the electrical clearance meets the requirements. ( The electrical length of the transmission line calculated in step S1 (in radians) is used. If it does not meet the requirements, the installation position is adjusted to ensure that the electrical spacing between adjacent compensation units meets the requirements and to avoid mutual interference. S22. At each installation location, the combined module of the thyristor-controlled reactor and the thyristor-switched capacitor in the reactive power compensation unit is connected in parallel between the phase line and the ground line of the transmission line, and the total capacity of the combined module is configured to meet the following requirements: ; in, The total reactive power capacity of a single reactive power compensation unit module is expressed in megavars; k is the mining compensation coefficient, with a value of 1.1~1.2 to adapt to the characteristics of underground loads. This is the average power factor of the mining transmission line; S23. Install a local measurement unit and a local controller next to each reactive power compensation unit. Connect the signal acquisition terminal of the local measurement unit to the transmission line. Establish electrical control connections and data transmission connections between the local controller and the combined module and the local measurement unit, respectively, to ensure that the control signal transmission delay meets the requirements. ,in This represents the control signal transmission delay between the local controller and the combined module, measured in milliseconds.

[0037] Construct a mine-use explosion-proof installation foundation at the marked installation location. The foundation is made of reinforced concrete and its dimensions are designed according to the external dimensions of the reactive power compensation unit. Cable connection holes and fixing bolt holes are reserved. The horizontal error of the top of the foundation does not exceed ±2mm to ensure that the reactive power compensation unit is installed stably and can adapt to the vibration environment in the coal mine.

[0038] The thyristor-controlled reactor (TCR) and thyristor-switched capacitor (TSC) combination module in the reactive power compensation unit are connected in parallel between the phase line and the ground line of the transmission line via a mining high-voltage cable. When wiring, a mining explosion-proof junction box is used, and the cable joints are insulated with an insulation resistance of not less than 500MΩ. After the wiring is completed, a withstand voltage test is performed. The test voltage is 1.5 times the rated voltage of the line, and the duration is 1 minute. If there is no breakdown or flashover, it is considered qualified.

[0039] TCR and TSC capacity allocation: based on the total reactive power capacity of the combined modules. The capacity ratio of TCR and TSC is allocated, typically setting the total capacity of TSC to 1.1 to 1.2 times the maximum adjustable capacity of TCR, achieving bidirectional fine-tuning of reactive power; TSC uses multiple capacitor banks of different capacities, configured in equal tolerance steps of Q, 2Q, and 4Q, with the total capacity meeting... ( (This is the maximum adjustable reactive power capacity of the TCR).

[0040] On the explosion-proof mounting base next to each reactive power compensation unit, the local measurement unit and local controller are fixed. The equipment is installed at a height that is convenient for maintenance personnel to operate, and the horizontal distance from the combined module does not exceed 1 meter to reduce interference caused by signal transmission distance. Both the local measurement unit and the local controller adopt an intrinsically safe design for mining and meet the explosion-proof requirements of underground coal mines.

[0041] The voltage signal acquisition terminal of the local measurement unit is connected to the phase line of the transmission line through a voltage transformer, and the current signal acquisition terminal is connected in series with the transmission line through a current transformer to ensure the accuracy of the acquired signals. The control output terminal of the local controller is electrically connected to the TCR thyristor trigger terminal and TSC switching switch control terminal in the combined module through a mining control cable, and the data transmission terminal is connected to the data output terminal of the local measurement unit.

[0042] Next, the specific method for collecting and transmitting measurement data in step S3 is as follows: S31. Set the local measurement unit to the mine monitoring working mode and collect the phase voltage, line voltage, phase current and line current signals of the local line in real time through voltage transformer and current transformer. The collection frequency meets f≥200Hz, where f is the signal collection frequency of the local measurement unit in Hertz, and the collection accuracy is not less than 0.2 level. S32. The collected raw voltage and current signals are filtered and denoised to remove harmonic interference generated by electrical equipment in the coal mine. The filtering formula is as follows: ; ; in, Δt represents the effective values ​​of voltage and current after filtering at time t, in volts and amperes respectively; N is the width of the filtering window, with a value of 5~10 to adapt to the disturbance characteristics of mining applications; Δt is the acquisition time interval. The unit is seconds; These are the voltage and current values ​​from historical sampling points; S33. The filtered voltage and current measurement data are sent to the local controller in real time through the intrinsically safe data transmission interface for mining applications. The data is verified during transmission using the following verification formula: ; Where CRC stands for Cyclic Redundancy Check; ⊕ represents the XOR operation. The k-th measurement data byte; n is the number of bytes in a single frame of data, ensuring that the measurement data transmission accuracy is ≥99.9%.

[0043] Instrument transformer selection and installation: Select mine-use explosion-proof voltage and current transformers. The voltage transformer ratio should be based on the rated voltage of the transmission line. Determine (e.g.) When the voltage is 10 kV, the transformation ratio is set to 10000:100. The transformation ratio of the current transformer is based on the rated current of the line. Determine (e.g.) =100 Amperes, the transformation ratio is set to 100:5); the voltage transformer is connected in parallel between the phase line and the ground line of the transmission line, and the current transformer is connected in series in the phase line of the transmission line. The secondary side of the transformer is connected to the signal acquisition terminal of the local measurement unit through a shielded cable. The cable shield is grounded to reduce electromagnetic interference.

[0044] In addition, the specific method for establishing a data connection and receiving measurement data in step S4 is as follows: S41. Select a dedicated power fiber optic network as the main communication network and a dedicated wireless network in the coal mine as the backup communication network. Establish bidirectional data connections between the central monitoring and coordination system and the local controllers of each reactive power compensation unit. The transmission rate of the main communication network shall meet V1≥100Mbps, where V1 is the transmission rate of the main communication network in megabits per second. The transmission rate of the backup communication network shall meet V2≥10Mbps, where V2 is the transmission rate of the backup communication network in megabits per second. S42. Configure a redundancy backup and link detection module in the communication network to detect the transmission success rate of the main communication network in real time. The calculation formula is as follows: ; in, The data transmission success rate of the main communication network; The number of measurement data packets successfully transmitted; The total number of measurement data packets sent; when η < 0.95, the system automatically switches to the backup communication network. S43. The central monitoring and coordination system receives measurement data uploaded by each local controller through the communication network, performs time synchronization and normalization processing on the multi-unit data, and the time synchronization error meets the requirements. ,in The time synchronization error of multi-unit measurement data, in milliseconds, is normalized using the following formula: ; ; in, These are the normalized voltage and current values; The rated current of the line is expressed in amperes, forming a unified measurement dataset for the entire network.

[0045] Flame-retardant power optical fiber for mining is selected as the transmission medium for the main communication network. It is laid along the power transmission line in accordance with the underground wiring specifications for coal mines. The fiber cores are 4 (2 cores for data transmission and 2 cores for backup). During the laying process, avoid close parallel laying with high-voltage cables, and the spacing should not be less than 0.5 meters to reduce electromagnetic interference. The backup communication network adopts an intrinsically safe wireless private network for mining, and selects a mining wireless communication module with a working frequency of 433MHz. Wireless repeaters are placed at roadway intersections, equipment chambers and other locations along the power transmission line. The repeater spacing does not exceed 500 meters to ensure full wireless signal coverage and no communication blind spots.

[0046] The communication interface of the central monitoring and coordination system is connected to the dedicated power fiber optic network via a fiber optic transceiver, and the transmission rate of the main communication network is configured. The communication protocol uses TCP / IP, with a fixed IP address range (e.g., 192.168.1.0 / 24), and each local controller is assigned a unique IP address. The intrinsically safe communication interface of the local controller is connected to the terminal node of the power fiber optic private network and the communication module of the wireless private network, respectively. The transmission rate of the backup communication network is configured as follows: The communication protocol is consistent with the main communication network to ensure data format compatibility.

[0047] After setup, use network testing tools (such as the ping command) to test the communication connectivity between the central monitoring and coordination system and each local controller. The ping response time of the main communication network should be ≤10ms and the packet loss rate should be 0; the ping response time of the backup communication network should be ≤50ms and the packet loss rate should be ≤0.1%, ensuring that both communication networks can achieve stable bidirectional data transmission.

[0048] A redundant backup module for the communication network is installed in the central monitoring and coordination system. This module monitors the operating status of the main communication network in real time and caches the coordination control commands to be sent and the measurement data received. The cache capacity is not less than 10MB to avoid data loss during network switching. The same redundant backup module is configured in each local controller to achieve bidirectional data caching.

[0049] If the statistically obtained transmission success rate η < 0.95, the redundant backup module immediately triggers a network switching command, switching the data transmission link from the main communication network (power fiber optic private network) to the backup communication network (coal mine underground wireless private network). The switching process is executed automatically, with a switching delay of ≤ 50ms. Simultaneously, a main communication network fault alarm signal is issued on the monitoring interface of the central monitoring and coordination system, prompting maintenance personnel to troubleshoot the fault. Once the main communication network is repaired, if the transmission success rate η ≥ 0.95 and remains stable for 30 seconds, it automatically switches back to the main communication network.

[0050] Then, the specific method for calculating the optimal reactive power output command and issuing the coordinated control command in step S5 is as follows: S51. The central monitoring and coordination system constructs a multi-objective optimization function based on the normalized network-wide measurement dataset, with the objectives of voltage stability, loss reduction, and power output smoothness. The formula is as follows: ; Where J is the value of the multi-objective optimization function; n is the number of reactive power compensation units; is the real-time voltage at the installation point of the i-th reactive power compensation unit, in volts; The weighting coefficients are dimensionless and ; Total active power loss of the line, in watts; The reactive power output of the i-th unit at adjacent time points is expressed in megavars. S52. Substitute the multi-objective optimization function into the pre-trained LSTM (Long Short-Term Memory) neural network model for solution. This model takes the overall network operating state as input and the optimal reactive power output as output. The solution formula is as follows: ; in, The reactive power output value of the i-th unit predicted by the model is expressed in megavars. Let t be the feature vector of the entire network's operating state at time t; θ represents the normalized total active power loss; θ is the model pre-training parameter set, including weights and biases. S53. The model predictions are corrected based on the operational constraints of the mine power transmission line to obtain the optimal reactive power output command for each unit. The correction formula is as follows: ; in, This is the optimal reactive power output command for the i-th reactive power compensation unit, in megavars; These are the maximum and minimum reactive power output limits for the i-th unit, respectively, in megavars. , To determine the maximum adjustable reactive power capacity of the TCR, the optimal reactive power output command is encapsulated into a coordination control command and sent to each local controller via the communication network.

[0051] Furthermore, the specific method for constructing and training the pre-trained LSTM long short-term memory neural network model in step S52 is as follows: S521. Collect historical operating data of ultra-long-distance transmission lines used in mining under all operating conditions, filter out effective data including voltage, current, active power loss, and reactive power output under different mining loads, different fault states, and different ambient temperatures, construct the original dataset for the model, and divide it proportionally. The division formula is as follows: ; in, The original dataset for the model has a sample size of M; The training set for the model accounts for [percentage]. ; This is the model validation set, accounting for [percentage]. ; This is the model test set, accounting for [percentage]. ,and ; S522. Construct an LSTM (Long Short-Term Memory) neural network structure containing an input layer, three LSTM hidden layers, a fully connected layer, and an output layer. The number of nodes in the input layer and the feature vector of the entire network's operating state are considered. The dimension is consistently m, and the number of nodes in the LSTM hidden layer is set sequentially as follows: , , The number of output layer nodes is the same as the number of reactive power compensation units, n. The root mean square error is used as the loss function for model training, and the loss formula is: ; in, This represents the root mean square error loss value of the model. The number of samples in the training set; is the actual optimal reactive power output value of the i-th reactive power compensation unit in the k-th training sample, in megavars; This is the model's predicted reactive power output for the kth training sample, in megavars. S523. The adaptive moment estimation optimization algorithm is used to iteratively train the model, and the initial learning rate of the model is set. ; This is the weight decay coefficient. Training batch size Iterate training until the loss value on the validation set no longer decreases for 10 consecutive rounds and the loss value on the test set also decreases. A convergent pre-trained LSTM long short-term memory neural network model is obtained, and the model pre-trained parameter set θ is solidified into the algorithm module of the central monitoring and coordination system.

[0052] Historical operating data of ultra-long-distance power transmission lines used in mining were collected over the past two years, covering various scenarios such as light load, heavy load, start-up and shutdown of mining equipment, and line faults. Data dimensions included voltage, current, active power loss, and reactive power output, with a total sample size of M=100,000. After filtering the valid data and removing invalid samples such as voltage anomalies and current surges, M=95,000 valid samples were retained.

[0053] Network architecture design: Construct a neural network structure containing an input layer, three LSTM hidden layers, a fully connected layer, and an output layer. Input layer: Number of nodes m = 2n + 1 (n is the number of compensation units), and feature vectors Consistent dimensions; LSTM hidden layer: The number of nodes is set sequentially as follows (All dimensions are dimensionless), each layer contains a forget gate, an input gate, an output gate, and a cell state, enabling long-term time-dependent feature extraction; Fully connected layer: 32 nodes, ReLU activation function is used; Output layer: The number of nodes is the same as the number of reactive power compensation units, n. The activation function is a linear function, and the output is the predicted value of reactive power output. .

[0054] Each unit The command is encapsulated as a coordinated control instruction. The instruction format includes a timestamp, compensation unit number, and optimal reactive power output value. It is then sent to each local controller through the communication network built by S4, ensuring that the transmission delay is ≤20ms.

[0055] Finally, the specific method for the control module to achieve reactive power compensation in step S6 is as follows: S61. The local controller receives the coordination control command issued by the central monitoring and coordination system and parses out the optimal reactive power output command. Based on the output characteristics of the thyristor-controlled reactor and the thyristor-switched capacitors, the target conduction angle of the thyristor-controlled reactor and the target number of switching groups of the thyristor-switched capacitors are calculated. The formula for calculating the conduction angle is: ; in, The target conduction angle of the thyristor-controlled reactor, in degrees; The target reactive power output of the thyristor-controlled reactor is expressed in megavars. This is the equivalent reactance of the thyristor-controlled reactor, expressed in ohms. S62. The local controller sends a trigger pulse signal to the thyristor-controlled reactor to adjust its thyristor conduction angle to the target conduction angle. Adjust the step size to meet the requirements. Where Δα is the conduction angle adjustment step size in degrees; simultaneously, a switching control signal is sent to the thyristor to switch the capacitors, switching the corresponding number of capacitor banks, and the switching logic satisfies , where z is the target number of thyristor-switched capacitor groups; This is for rounding up; The reactive power output of the target capacitor switching device for thyristors, measured in megavars; This refers to the rated reactive power of a single capacitor bank, expressed in megavars. S63. The local controller collects the compensated local line voltage and current data in real time through the local measurement unit, calculates the actual reactive power compensation output, and the verification formula is: ; in, The actual reactive power compensation output of the i-th unit is expressed in megavars. The current value of the local line after compensation is expressed in amperes. The power factor angle of the local line after compensation, in degrees, when When the reactive power compensation has achieved the target effect, the compensation control is completed.

[0056] TCR and TSC target output allocation: Based on the combined characteristics of the thyristor-controlled reactor (TCR) and thyristor-switched capacitor (TSC), the optimal reactive power output command is assigned. The target reactive power allocated to TCR (Unit: megavar, inductive reactive power is negative, capacitive reactive power is positive) and the target reactive power output of TSC. (Unit: megavar, only capacitive reactive power is positive), the allocation principle is: priority is given to providing fixed capacitive reactive power through TSC, and the remaining reactive power demand is dynamically adjusted by TCR, that is... .

[0057] Target conduction angle calculation: based on the equivalent reactance of the TCR (Unit: Ohms, determined by the TCR equipment parameter manual) and target reactive power output Calculate the target conduction angle of the TCR. (Unit: degree).

[0058] TCR conduction angle adjustment: The trigger pulse generation module of the local controller adjusts the conduction angle according to the target conduction angle. and conduction angle adjustment step size (satisfies 0.1°) The value range is 0.5°. A corresponding thyristor trigger pulse signal is generated, with a pulse width of 10μs and a trigger voltage of 15V. The trigger pulse signal is sent to the thyristor trigger terminal of the TCR via a mining control cable, and the conduction angle is gradually adjusted from the current value to the target conduction angle according to the adjustment step size. The adjustment process is smooth, avoiding sudden changes in reactive power output.

[0059] TSC Switching Control: The switching control module of the local controller generates a switching control signal for the TSC based on the target number of switching groups z. The control signal is active high (24V) and cut off low (0V). The control signal is sent to the switching switch (mining vacuum contactor) of the TSC through the mine explosion-proof junction box. The corresponding number of capacitor groups are switched according to the principle of "switching first and then switching". The switching interval is ≥20ms to avoid damage to the equipment due to excessive switching inrush current.

[0060] Regulation process monitoring: During the TCR conduction angle adjustment and TSC switching process, the local controller monitors the TCR operating current and TSC switching status in real time. If an abnormal TCR current (exceeding 1.1 times the rated current) or TSC switching failure is detected, the regulation is stopped immediately and a fault alarm signal is issued. At the same time, the fault information is uploaded to the central monitoring and coordination system.

[0061] Compensation effect determination: Set compensation accuracy threshold Significant scarcity, when satisfied If the reactive power compensation reaches the target effect, the compensation control is completed; if not, return to S61 to recalculate the target conduction angle and the number of switching groups, and execute the adjustment process again until the compensation accuracy requirements are met.

[0062] Figure 2 This is a schematic diagram of a terminal 300 provided in an embodiment of the present invention. The terminal 300 can be used to execute the control method of the long-distance reactive power compensation device for mining provided in an embodiment of the present invention.

[0063] The terminal 300 may include a processor 310, a memory 320, and a communication module 330. These components communicate via one or more buses. Those skilled in the art will understand that the server structure shown in the figure does not constitute a limitation of the present invention. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0064] The memory 320 can be used to store the execution instructions of the processor 310. The memory 320 can be implemented by any type of volatile or non-volatile memory terminal or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. When the execution instructions in the memory 320 are executed by the processor 310, the terminal 300 is able to perform some or all of the steps in the above method embodiments.

[0065] The processor 310 serves as the control center of the storage terminal, connecting various parts of the electronic terminal via various interfaces and lines. It executes software programs and / or modules stored in the memory 320, and calls data stored in the memory to perform various functions of the electronic terminal and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 310 may consist only of a central processing unit (CPU). In this embodiment of the invention, the CPU may have a single processing core or include multiple processing cores.

[0066] The communication module 330 is used to establish a communication channel, enabling the storage terminal to communicate with other terminals. It receives user data sent by other terminals or sends user data to other terminals.

[0067] The present invention also provides a computer storage medium, wherein the computer storage medium may store a program, which, when executed, may include some or all of the steps provided in the embodiments of the present invention. The storage medium may be a magnetic disk, an optical disk, read-only memory (ROM), or random access memory (RAM), etc.

[0068] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium such as a USB flash drive, mobile hard drive, read-only memory (ROM), random access memory (RAM), magnetic disk, or optical disk, or other media capable of storing program code. It includes several instructions to cause a computer terminal (which may be a personal computer, server, or a second terminal, network terminal, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention.

[0069] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the terminal embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0070] In the embodiments provided by this invention, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the system embodiments described above are merely illustrative. For instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between systems or modules may be electrical, mechanical, or other forms.

[0071] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0072] In addition, the functional modules in the various embodiments of the present invention can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0073] Although the present invention has been described in detail with reference to the accompanying drawings and preferred embodiments, the present invention is not limited thereto. Various equivalent modifications or substitutions can be made to the embodiments of the present invention by those skilled in the art without departing from the spirit and essence of the invention, and such modifications or substitutions should all be within the scope of the present invention. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should also be covered within the protection scope of the present invention.

Claims

1. A control method for a long-distance reactive power compensation device used in mining, characterized in that, include: S1. Determine the installation location of the reactive power compensation unit in the reactive power compensation device on ultra-long-distance transmission lines. The installation location is determined based on the electrical length of the transmission line, voltage distribution characteristics, and reactive power optimization configuration model. S2. At least two reactive power compensation units are arranged at the installation location. The reactive power compensation units are connected in series on different sections of the ultra-long-distance transmission line. Each reactive power compensation unit includes a combination module of thyristor-controlled reactor and thyristor-switched capacitor connected in parallel between the phase line and the ground line of the transmission line, a local measurement unit for real-time monitoring of local line voltage and current, and a local controller. S3. The voltage and current signals of the local line are collected in real time through the local measurement unit, and the collected measurement data is transmitted to the local controller. S4. Establish a data connection between the central monitoring and coordination system and the local controllers of each reactive power compensation unit through the communication network. The central monitoring and coordination system receives the measurement data of each reactive power compensation unit. S5. The central monitoring and coordination system calculates the optimal reactive power output command for each reactive power compensation unit based on the overall network operation status and the pre-trained long-distance reactive power compensation algorithm model, and sends the coordination control command containing the optimal reactive power output command to each local controller. S6. Based on the received coordination control commands, the local controller controls the conduction angle of the thyristor control reactor and the switching of the thyristor-switched capacitor to achieve reactive power compensation.

2. The control method for the long-distance reactive power compensation device for mining as described in claim 1, characterized in that, The specific method for determining the installation location of the reactive power compensation unit in step S1 is as follows: S11. Collect the physical and operational basic parameters of the ultra-long-distance transmission line for mining, and calculate the electrical length of the line in conjunction with the benchmark values ​​of the mining power supply system. The calculation formula is as follows: ； in, The electrical length of the transmission line; This refers to the actual physical length of the transmission line; Resistance per unit length of the line; Reactance per unit length of the line; This serves as the reference impedance for the mine power supply system. , The rated voltage for ultra-long-distance transmission lines, This serves as the baseline capacity for mine power supply systems. S12. Real-time operating voltage at each monitoring point along the line is collected using a multi-point monitoring device. The voltage deviation rate at each point is calculated based on the line's rated voltage, and weak voltage points are identified. The calculation formula is as follows: ； in, The voltage deviation rate at the x-th monitoring point on the line; This represents the real-time voltage value at the x-th monitoring point on the line. This refers to the rated voltage of ultra-long-distance transmission lines, measured in volts. The monitoring points were marked as voltage weak points; S13. Construct a reactive power optimization configuration model with the dual objectives of minimizing voltage deviation and minimizing active power loss. Substitute the electrical length characteristic points and voltage weak points into the reactive power optimization configuration model to solve for the optimal installation location. The formula is: ； in, represents the optimal installation location set for the reactive power compensation unit; m represents the number of monitoring points in the ultra-long-distance transmission line. The objective function for the reactive power optimization configuration model; This is the weighting factor for the voltage deviation; This is the weighting coefficient for active power loss, and ; This refers to the total active power loss of ultra-long-distance transmission lines; This refers to the rated active power of the line.

3. The control method for the long-distance reactive power compensation device for mining according to claim 2, characterized in that, The specific method for arranging the reactive power compensation unit in step S2 is as follows: S21. Based on the optimal installation location set obtained in step S1 At least two reactive power compensation units are arranged in different sections of the ultra-long-distance transmission line for mining, so that the reactive power compensation units are distributed in series along the line. Or at points with weak voltage, ensure that the electrical spacing between reactive power compensation units meets the following requirements: ； in, The electrical spacing between the two reactive power compensation units; These are the installation positions of the i-th and j-th reactive power compensation units, respectively. S22. At each installation location, the combined module of the thyristor-controlled reactor and the thyristor-switched capacitor in the reactive power compensation unit is connected in parallel between the phase line and the ground line of the transmission line, and the total capacity of the combined module is configured to meet the following requirements: ； in, The total reactive power capacity of a single reactive power compensation unit combined module; k is the mining compensation coefficient; This is the average power factor of the mining transmission line; S23. Install a local measurement unit and a local controller next to each reactive power compensation unit, connect the signal acquisition terminal of the local measurement unit to the transmission line, and establish electrical control connection and data transmission connection between the local controller and the combined module and the local measurement unit respectively.

4. The control method for the long-distance reactive power compensation device for mining according to claim 3, characterized in that, The specific method for collecting and transmitting measurement data in step S3 is as follows: S31. Set the local measurement unit to the mine monitoring working mode and collect the phase voltage, line voltage, phase current and line current signals of the local line in real time through the voltage transformer and current transformer. S32. The collected raw voltage and current signals are filtered and denoised to remove harmonic interference generated by electrical equipment in the coal mine. The filtering formula is as follows: ； ； in, Δt represents the effective values ​​of voltage and current after filtering at time t; N is the width of the filtering window; Δt is the acquisition time interval. These are the voltage and current values ​​from historical sampling points; S33. The filtered voltage and current measurement data are sent to the local controller in real time through the intrinsically safe data transmission interface for mining applications. The data is verified during transmission using the following verification formula: ； Where CRC stands for Cyclic Redundancy Check; ⊕ represents the XOR operation. is the kth measurement data byte; n is the number of bytes in a single frame of data.

5. The control method for the long-distance reactive power compensation device for mining according to claim 4, characterized in that, The specific method for establishing a data connection and receiving measurement data in step S4 is as follows: S41. Select the power fiber optic private network as the main communication network and the underground wireless private network of the coal mine as the backup communication network. Establish bidirectional data connections between the central monitoring and coordination system and the local controllers of each reactive power compensation unit. S42. Configure a redundancy backup and link detection module in the communication network to detect the transmission success rate of the main communication network in real time. The calculation formula is as follows: ； in, The success rate of data transmission in the main communication network; The number of measurement data packets successfully transmitted; The total number of measurement data packets sent; when η < 0.95, the system automatically switches to the backup communication network. S43. The central monitoring and coordination system receives measurement data uploaded by each local controller through the communication network, performs time synchronization and normalization processing on the multi-unit data, and the time synchronization error meets the requirements. ,in The normalization formula for the time synchronization error of multi-unit measurement data is: ； ； in, These are the normalized voltage and current values; This is the rated current of the line.

6. The control method for the long-distance reactive power compensation device for mining according to claim 5, characterized in that, The specific method for calculating the optimal reactive power output command and issuing the coordinated control command in step S5 is as follows: S51. The central monitoring and coordination system constructs a multi-objective optimization function based on the normalized network-wide measurement dataset, with the objectives of voltage stability, loss reduction, and power output smoothness. The formula is as follows: ； Where J is the value of the multi-objective optimization function; n is the number of reactive power compensation units; Let be the real-time voltage at the installation point of the i-th reactive power compensation unit; The weighting coefficients are dimensionless and ; This represents the total active power loss of the line. The reactive power output of the i-th unit at adjacent time points; S52. Substitute the multi-objective optimization function into the pre-trained LSTM (Long Short-Term Memory) neural network model for solution. This model takes the overall network operating state as input and the optimal reactive power output as output. The solution formula is as follows: ； in, This represents the reactive power output value of the i-th unit predicted by the model. Let t be the feature vector of the entire network's operating state at time t; θ represents the normalized total active power loss; θ is the model pre-training parameter set, including weights and biases. S53. The model predictions are corrected based on the operational constraints of the mine power transmission line to obtain the optimal reactive power output command for each unit. The correction formula is as follows: ； in, This is the optimal reactive power output command for the i-th reactive power compensation unit; These are the maximum and minimum reactive power output limits for the i-th unit, respectively. The optimal reactive power output command is then encapsulated into a coordination control command and sent to each local controller via the communication network.

7. The control method for the long-distance reactive power compensation device for mining according to claim 6, characterized in that, The specific method for constructing and training the pre-trained LSTM long short-term memory neural network model in step S52 is as follows: S521. Collect historical operating data of ultra-long-distance transmission lines used in mining under all operating conditions, filter out effective data including voltage, current, active power loss, and reactive power output under different mining loads, different fault states, and different ambient temperatures, construct the original dataset for the model, and divide it proportionally. The division formula is as follows: ； in, The original dataset for the model has a sample size of M; The training set for the model accounts for [percentage]. ; This is the model validation set, accounting for [percentage]. ; This is the model test set, accounting for [percentage]. ,and ; S522. Construct an LSTM (Long Short-Term Memory) neural network structure containing an input layer, three LSTM hidden layers, a fully connected layer, and an output layer. The number of nodes in the input layer and the feature vector of the entire network's operating state are considered. The dimension is consistently m, and the number of nodes in the LSTM hidden layer is set sequentially as follows: , , The number of output layer nodes is the same as the number of reactive power compensation units, n. The root mean square error is used as the loss function for model training, and the loss formula is: ； in, This represents the root mean square error loss value of the model. The number of samples in the training set; This represents the actual optimal reactive power output value of the i-th reactive power compensation unit in the k-th training sample. This is the model's predicted reactive power output for the k-th training sample; S523. The adaptive moment estimation optimization algorithm is used to iteratively train the model, and the initial learning rate of the model is set. ; Weight decay coefficient; training batch size Iterative training continues until the loss value on the validation set no longer decreases for 10 consecutive rounds and the loss value on the test set also decreases. A convergent pre-trained LSTM long short-term memory neural network model is obtained, and the model pre-trained parameter set θ is solidified into the algorithm module of the central monitoring and coordination system.

8. The control method for the long-distance reactive power compensation device for mining according to claim 6, characterized in that, The specific method for implementing reactive power compensation by the control module in step S6 is as follows: S61. The local controller receives the coordination control command issued by the central monitoring and coordination system and parses out the optimal reactive power output command. Based on the output characteristics of the thyristor-controlled reactor and the thyristor-switched capacitors, the target conduction angle of the thyristor-controlled reactor and the target number of switching groups of the thyristor-switched capacitors are calculated. The formula for calculating the conduction angle is: ； in, The target conduction angle for the thyristor-controlled reactor; The target reactive power output of the thyristor-controlled reactor; This is the equivalent reactance of the thyristor-controlled reactor; S62. The local controller sends a trigger pulse signal to the thyristor-controlled reactor to adjust its thyristor conduction angle to the target conduction angle. Simultaneously, a switching control signal is sent to the thyristor to switch the capacitors, switching the corresponding number of capacitor banks. The switching logic satisfies... , where z is the target number of thyristor-switched capacitor groups; This is for rounding up; The reactive power output is for the purpose of switching capacitors with thyristors; This refers to the rated reactive power of a single capacitor bank. S63. The local controller collects the compensated local line voltage and current data in real time through the local measurement unit, calculates the actual reactive power compensation output, and the verification formula is: ； in, The actual reactive power compensation output of the i-th unit; The current value of the local line after compensation; To compensate for the power factor angle of the local line, when When the reactive power compensation has achieved the target effect, the compensation control is completed.

9. A terminal, characterized in that, include: processor; Memory used to store the processor's execution instructions; The processor is configured to perform the method of any one of claims 1-8.

10. A computer-readable storage medium storing a computer program, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-8.

Images