A method and system for coordinated control of a mine-use variable frequency air compressor and a nitrogen generator.

Abstract

This application relates to the field of control technology, specifically to a collaborative control method and system for a mining variable frequency air compressor and a nitrogen generator. The method includes: constructing an integrated predictive model to record the dynamic response characteristics between the frequency and exhaust pressure of the permanent magnet air compressor, the nonlinear relationship between nitrogen purity and flow rate of the membrane separation nitrogen generator unit under different inlet pressures, and the impedance characteristics of the connecting pipelines; optimizing the air compressor motor operating frequency control sequence and the opening sequence of the nitrogen generator unit's inlet regulating valve and product gas back pressure valve within each control cycle; setting an optimization objective function based on the tracking deviation of the output nitrogen pressure from the set value, the energy consumption weight corresponding to the efficiency factor of the permanent magnet motor under various speed conditions, and the energy loss caused by valve actions; and issuing the first instruction in the optimal control sequence as the current control instruction to both the explosion-proof permanent magnet variable frequency air compressor unit and the mobile membrane separation nitrogen generator unit.

Description

Technical Field

[0001] This application relates to the field of control technology, specifically to a method and system for the coordinated control of a mining variable frequency air compressor and a nitrogen generator. Background Technology

[0002] In high-risk working environments such as coal mining, nitrogen is widely used in critical safety aspects such as inerting for explosion protection, gas extraction, and roadway fire prevention. Mine nitrogen generation systems typically employ stationary air compressors in conjunction with independent nitrogen generators, which suffers from problems such as slow response, low energy efficiency, and difficulty in dynamically matching nitrogen output pressure and purity to actual underground needs. In recent years, with the development of permanent magnet variable frequency technology and membrane separation nitrogen generation technology, mobile, integrated variable frequency air compressor-nitrogen generator systems have gradually become a research hotspot. However, existing control systems mostly employ decentralized control strategies, lacking coordination between air compressor frequency regulation and nitrogen generator unit valve actions. This makes it difficult to balance nitrogen quality stability and optimal overall energy consumption when facing disturbances such as sudden changes in drilling conditions and fluctuations in gas load. Especially under complex geological conditions, factors such as coal seam hardness, borehole inclination angle, and drilling speed significantly affect nitrogen consumption patterns, further exacerbating the difficulty of system control. Therefore, further research is needed on the coordinated control technology of mine variable frequency air compressors and nitrogen generators. Summary of the Invention

[0003] This specification describes a method and system for the coordinated control of a mining variable frequency air compressor and a nitrogen generator through several embodiments.

[0004] Firstly, embodiments of this specification provide a method for the coordinated control of a mining variable frequency air compressor and a nitrogen generator, applied to a device comprising an explosion-proof permanent magnet variable frequency air compressor unit, a mobile membrane separation nitrogen generator unit, and a coordinated control unit. The method is executed by the coordinated control unit and includes the following steps:

[0005] An integrated prediction model is constructed, which records the dynamic response characteristics between the frequency and exhaust pressure of the permanent magnet air compressor, the nonlinear relationship between the nitrogen purity and flow rate of the membrane separation nitrogen generator under different inlet pressures, and the impedance characteristics of the connecting pipeline.

[0006] Within each control cycle, using the current device state as the initial condition, the control sequence of the air compressor motor operating frequency and the opening sequence of the nitrogen generator intake regulating valve and the product gas back pressure valve within the control cycle are optimized based on the integrated prediction model.

[0007] An optimization objective function is set, which is obtained based on the tracking deviation of the output nitrogen pressure to the set value, the energy consumption weight corresponding to the efficiency factor of the permanent magnet motor under various speed conditions, and the energy loss caused by valve action. The optimal control sequence is obtained by minimizing the optimization objective function. The control sequence includes a frequency control sequence and an opening sequence.

[0008] The first instruction in the optimal control sequence is sent as the current control instruction to the explosion-proof permanent magnet variable frequency air compressor unit and the mobile membrane separation nitrogen generation unit, respectively.

[0009] Secondly, embodiments of this specification provide a coordinated control system for a mining variable frequency air compressor and a nitrogen generator, including:

[0010] Explosion-proof permanent magnet variable frequency air compressor unit, used to provide a compressed air source with adjustable frequency drive;

[0011] A mobile membrane separation nitrogen generation unit includes an inlet regulating valve, a membrane separation component, and a product gas back pressure valve, used to separate compressed air into high-purity nitrogen and oxygen-enriched waste gas, and to control the nitrogen output pressure and flow rate by adjusting the inlet regulating valve and the product gas back pressure valve;

[0012] A collaborative control unit, communicatively connected to the explosion-proof permanent magnet variable frequency air compressor unit and the mobile membrane separation nitrogen generation unit, comprises:

[0013] The module is constructed to build an integrated prediction model. The integrated prediction model records the dynamic response characteristics between the frequency and exhaust pressure of the permanent magnet air compressor, the nonlinear relationship between the nitrogen purity and flow rate of the membrane separation nitrogen generator under different inlet pressures, and the impedance characteristics of the connecting pipeline.

[0014] The control module, within each control cycle, uses the current device state as the initial condition and optimizes the frequency control sequence of the air compressor motor and the opening sequence of the nitrogen generator intake regulating valve and the product gas back pressure valve within the control cycle based on the integrated prediction model.

[0015] The optimization module sets an optimization objective function, which is obtained based on the tracking deviation of the output nitrogen pressure to the set value, the energy consumption weight corresponding to the efficiency factor of the permanent magnet motor under various speed conditions, and the energy loss caused by valve action. The optimal control sequence is obtained by minimizing the optimization objective function. The control sequence includes a frequency control sequence and an opening sequence.

[0016] The execution module sends the first instruction in the optimal control sequence as the current control instruction to the explosion-proof permanent magnet variable frequency air compressor unit and the mobile membrane separation nitrogen generation unit respectively.

[0017] Thirdly, embodiments of this specification provide an electronic device, including a processor and a memory;

[0018] The processor is connected to the memory;

[0019] The memory is used to store executable program code;

[0020] The processor runs a program corresponding to the executable program code stored in the memory to perform the method described in any of the above aspects.

[0021] Fourthly, embodiments of this specification provide a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the methods described in any of the above aspects.

[0022] Fifthly, embodiments of this specification provide a computer program product, including a computer program that, when executed by a processor, implements the methods described in any of the above aspects.

[0023] The beneficial effects of the technical solutions provided in some embodiments of this specification include at least the following:

[0024] In several embodiments of this specification, a collaborative control method and system for a mining variable frequency air compressor and a nitrogen generator is provided. By constructing a collaborative control mechanism between the variable frequency drive of the air compressor and the membrane separation nitrogen generator unit, dynamic matching of nitrogen output pressure, flow rate, and purity is achieved, improving the operational stability of the mining nitrogen generator system. The air compressor speed and nitrogen generator valve opening are adjusted in real time according to drilling conditions, roadway environment, and gas demand, effectively avoiding nitrogen waste or insufficient supply problems caused by lagging adjustments in traditional control methods. Simultaneously, by introducing an energy efficiency optimization algorithm, energy consumption is reduced while ensuring nitrogen quality, decreasing equipment start-up and shutdown frequency, and extending the service life of key components.

[0025] Other features and advantages of various embodiments of this specification will be further revealed in the following detailed description and accompanying drawings. Attached Figure Description

[0026] To more clearly illustrate the technical solutions in the embodiments of this specification, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this specification. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0027] Figure 1 This is a schematic diagram of the collaborative control provided in this manual.

[0028] Figure 2This is a schematic diagram of the collaborative control method provided in this specification.

[0029] Figure 3 This is a schematic diagram of the method for constructing an integrated prediction model provided in this manual.

[0030] Figure 4 This is a schematic diagram of the process for optimizing the control cycle based on an integrated predictive model, as provided in this specification.

[0031] Figure 5 This is a schematic diagram of the method for obtaining feedforward compensation provided in this specification.

[0032] Figure 6 This is a schematic diagram of the collaborative control unit provided in this manual.

[0033] Figure 7 This is a schematic diagram of the electronic device provided in this manual.

[0034] Among them: 10, Cooperative control unit; 20, Explosion-proof permanent magnet variable frequency air compressor unit; 30, Mobile membrane separation nitrogen generation unit; 31, Inlet regulating valve; 32, Product air back pressure valve; 101, Construction module; 102, Control module; 103, Optimization module; 104, Execution module; 1100, Electronic equipment; 1101, Processor; 1102, Communication bus; 1103, User interface; 1104, Network interface; 1105, Memory. Detailed Implementation

[0035] The technical solutions of the embodiments of this specification will be explained and described below with reference to the accompanying drawings. However, the following embodiments are only preferred embodiments of this specification and not all of them. Other embodiments obtained by those skilled in the art based on the embodiments in the implementation methods without creative effort are all within the protection scope of this specification.

[0036] The terms "first," "second," "third," etc., in the description, claims, and accompanying drawings are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such processes, methods, products, or apparatus.

[0037] In the following description, terms such as “inner,” “outer,” “upper,” “lower,” “left,” and “right” are used only to facilitate the description of the embodiments and to simplify the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this specification.

[0038] All data involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data comply with the relevant laws, regulations and standards of the relevant countries and regions.

[0039] Before introducing the technical solutions described in this manual, the application scenarios and related technologies of the technical solutions will be introduced.

[0040] Coal mines are typical Class I explosive gas environments (primarily methane), and all electrical equipment, including motors driving air compressors and nitrogen generators, must meet stringent explosion-proof standards. In coal mining, nitrogen, as an inert gas, plays a crucial safety and technological role in several key stages. Its application spans mine construction, coal seam mining, gas control, and fire prevention, significantly contributing to ensuring underground operational safety and improving mining efficiency. During new mine development or roadway extension, nitrogen is often used for local inerting to prevent gas accumulation near the face from exploding upon contact with an ignition source. Injecting high-purity nitrogen into the goaf before face advancement or during mining effectively inhibits spontaneous combustion of residual coal, reduces oxygen concentration in the goaf, and achieves active fire prevention. In high-gas or outburst-prone mines, nitrogen can be used to displace or dilute combustible gases in gas pipelines, ensuring the safe operation of the extraction system; it can also be used in "nitrogen injection for gas displacement" technology to improve gas desorption efficiency. When coal spontaneously combusts or fires occur underground, injecting nitrogen to quickly reduce the oxygen concentration in the fire zone, usually controlling it below 5%, is an important means of fire prevention and extinguishing.

[0041] To ensure safety and effectiveness, the preparation of nitrogen for mining must meet the following core requirements: For fire suppression and extinguishing applications, nitrogen purity must be ≥97% (volume fraction), with ≥99% required for some high-risk scenarios. For inerting and explosion-proof applications, ≥95% purity is generally required, but dynamic adjustments based on oxygen concentration monitoring are necessary. Nitrogen injection pressure is typically 0.5–1.2 MPa, and must be designed according to injection distance, pipeline resistance, and the volume of the target area.

[0042] Equipment for nitrogen production using membrane separation is compact, quick to start, and easy to maintain, making it suitable for mobile or small- to medium-sized mines. Nitrogen plays an irreplaceable role in the entire lifecycle safety management of coal mines. Its efficient, reliable, and compliant production and application rely on the deep integration of mining processes, explosion-proof standards, and gas engineering, making it an important component of modern intelligent mine safety systems.

[0043] However, most current control systems employ a distributed control strategy, with the frequency converter of the air compressor and the valve operation of the nitrogen generator operating independently, lacking an effective coordination mechanism. This makes it difficult for the system to simultaneously ensure the stability of nitrogen purity and pressure when dealing with dynamic disturbances such as sudden changes in drilling conditions and fluctuations in gas load.

[0044] Therefore, this manual provides a method and system for the coordinated control of a mine-use variable frequency air compressor and a nitrogen generator. Please refer to the appendix. Figure 1 By changing the independent operation mode of the air compressor and nitrogen generation processes, a permanent magnet variable frequency air compressor and a membrane separation nitrogen generation unit are integrated, and a collaborative control architecture based on adaptive operating conditions is constructed on this basis. By real-time acquisition of multi-dimensional operating parameters such as drilling speed, coal seam hardness, nitrogen injection pipeline pressure, flow rate, and nitrogen purity, combined with the dynamic changes in downhole gas load, the air compressor's speed (output frequency) and exhaust pressure, as well as the opening of key regulating valves in the nitrogen generation unit, are jointly optimized and controlled in a closed-loop manner. This linkage mechanism enables efficient matching of compressed air supply and nitrogen generation processes at the energy and material flow levels. It not only effectively avoids decreased nitrogen generation efficiency or purity fluctuations caused by over- or under-supply of air compressors, but also quickly maintains the pressure stability and purity consistency of nitrogen output under disturbances such as sudden changes in drilling conditions, changes in roadway resistance, or sudden gas demand. At the same time, while meeting the requirements for safety inerting or fire prevention, it reduces ineffective energy consumption, reduces mechanical wear caused by frequent start-ups and shutdowns of equipment, extends the service life of key components, and improves the deployment flexibility and operational reliability of the whole machine in narrow, high-humidity, and high-dust underground environments.

[0045] This manual first provides a method for the coordinated control of a mine-use variable frequency air compressor and a nitrogen generator. Please refer to the appendix. Figure 2 The method, applied in an apparatus comprising an explosion-proof permanent magnet variable frequency air compressor unit 20, a mobile membrane separation nitrogen generator unit 30, and a collaborative control unit 10, is executed by the collaborative control unit 10 and includes the following steps:

[0046] Step S1) Construct an integrated prediction model, which records the dynamic response characteristics between the frequency and exhaust pressure of the permanent magnet air compressor, the nonlinear relationship between the nitrogen purity and flow rate of the membrane separation nitrogen generator under different inlet pressures, and the impedance characteristics of the connecting pipeline.

[0047] The integrated predictive model reflects the dynamic coupling relationships between key subsystems in a mine-use variable frequency air compressor with integrated nitrogen compression. Specifically, the integrated predictive model first models the operating characteristics of the permanent magnet variable frequency air compressor, focusing on capturing the dynamic response process between its output frequency and exhaust pressure. For example, when the air compressor frequency increases from 30 Hz to 45 Hz in a step, due to factors such as motor acceleration, gas compression inertia, and cooling system delay, the exhaust pressure does not reach a steady-state value instantaneously, but rather exhibits a transition process with a certain time constant and overshoot characteristics. This dynamic characteristic is recorded by the integrated predictive model, supporting feedforward compensation for subsequent control commands.

[0048] An integrated predictive model describes the nonlinear output behavior of a membrane separation nitrogen generator unit under different inlet pressure conditions. For example, data from a mobile membrane separation nitrogen generator unit 30 of the same model and specifications, measured under laboratory conditions, shows that as the inlet pressure increases from 0.6 MPa to 0.9 MPa, the nitrogen purity increases from 95% to 98.5%, but the flow rate increase tends to saturate and even slightly decreases due to excessive pressure differential across the membrane module. This nonlinear relationship between purity and flow rate needs to be obtained through fitting measured data. Furthermore, the integrated predictive model also incorporates the fluid resistance characteristics of the pipeline connecting the air compressor outlet to the nitrogen generator module inlet, including the effects of pipe diameter, length, number of bends, and local resistance coefficient on airflow pressure drop and response delay. For example, in the device, a 20-meter-long Φ25mm high-pressure hose at a flow rate of 80 Nm³ / h... 3 At a pressure of approximately 0.12 MPa, a steady-state pressure drop of about 1.5 seconds is generated, introducing an airflow transmission delay of about 1.5 seconds. If this impedance effect is ignored, the actual intake pressure of the nitrogen generator unit will be lower than expected, thus affecting the nitrogen quality. By integrating the dynamic response of the air compressor, the nonlinear mapping of nitrogen generation, and pipeline impedance into an integrated predictive model, the interaction results of each link can be predicted before control decisions are made, providing support for subsequent synergistic optimization.

[0049] For details, please refer to the appendix. Figure 3 Methods for constructing ensemble prediction models include:

[0050] Step S11) Under laboratory conditions, a step frequency response test is performed on the explosion-proof permanent magnet variable frequency air compressor unit 20. Dynamic data of the exhaust pressure changing over time is collected and aligned with the frequency data along the time axis to obtain test data. In a controlled laboratory environment, a series of step frequency commands are applied to the air compressor, such as a sudden increase from 35 Hz to 45 Hz. Simultaneously, the response curve of its exhaust pressure evolving over time is collected at high frequency, and the pressure data and frequency commands are strictly aligned with the timestamps to form a complete set of input-output test datasets. These data clearly reflect the dynamic response of the air compressor during acceleration, pressure stabilization, and unloading processes, including inertial delay, overshoot, and settling time. For example, in the test of a 75kW mining permanent magnet air compressor, the exhaust pressure takes about 2.3 seconds to reach 90% steady-state value under a 45Hz step input, and there is an overshoot of about 5%, which is used for subsequent modeling.

[0051] Step S12) Fit the test data to obtain the transfer function between frequency and exhaust pressure, and establish a dynamic response model based on the transfer function. Use the least squares method or frequency domain fitting to obtain a low-order transfer function to describe the dynamic mapping relationship from frequency command to exhaust pressure, thereby establishing the dynamic response model of the air compressor.

[0052] Step S13) Under laboratory conditions, when the membrane separation nitrogen generation unit is in steady-state operation, adjust the inlet pressure and simultaneously measure the nitrogen outlet purity and flow rate to establish the mapping relationship between the inlet pressure and nitrogen purity and flow rate, and establish an embedded model in the form of piecewise function, polynomial regression or table lookup interpolation.

[0053] For the membrane separation nitrogen generation unit, under the premise of ensuring thermal and gas flow steady-state conditions, the upstream gas supply pressure was adjusted, for example, gradually increasing from 0.6 MPa to 1.0 MPa, while simultaneously recording the purity (which can be inferred from a high-precision oxygen analyzer) and volumetric flow rate at the nitrogen outlet. Experiments showed that in the 0.7-0.9 MPa range, the purity linearly increased from 95.2% to 98.1%, while the flow rate increase gradually slowed down, exhibiting obvious nonlinear saturation characteristics. A piecewise polynomial regression method was used: a quadratic polynomial was used to fit the purity-pressure curve in the 0.6-0.8 MPa range, while a first-order piecewise function with an inflection point was used in the 0.8-1.0 MPa range. Simultaneously, interpolation using a lookup table was employed for the flow rate to preserve measured details. This allows for real-time prediction of nitrogen generation performance based on the inlet gas pressure, providing support for coordinated control.

[0054] Step S14) Divide the connecting pipeline into multiple segments. Based on the geometric parameters and gas flow equation of each segment, calculate the pressure drop of the segment at different flow rates. Simplify the pressure drop into the impedance coefficient of the segment. Establish the impedance characteristic model of the connecting pipeline based on the impedance coefficient.

[0055] For the high-pressure pipeline connecting the air compressor and the nitrogen generator module, it is divided into several physical sections along the flow direction, such as straight pipe sections, elbow sections, and quick-connect joint sections. Each section's pressure drop at different flow rates is calculated based on its inner diameter, length, local resistance coefficient, and gas properties (such as air density and viscosity), using the Darcy-Weisbach equation and the Colebrook formula. For example, an 8-meter-long rubber hose with an inner diameter of 20mm generates approximately 0.08MPa of pressure loss at a flow rate of 60Nm³ / h, while a 90° elbow effectively increases the resistance of a straight pipe by 0.5 meters. The pressure loss is simplified to a resistance coefficient proportional to the square of the flow rate, used to quickly estimate the pressure drop caused by the pipeline under any operating condition.

[0056] Step S15) The dynamic response model, embedded model, and impedance characteristic model are combined to construct an integrated prediction model. Coupled and integrated within a unified time and state space framework, a complete integrated prediction model is constructed. The integrated prediction model can take the air compressor frequency command as input, sequentially deduce the exhaust pressure, the actual intake pressure after pipeline attenuation, and then predict the nitrogen purity and flow output, forming a closed-loop, calculable causal chain.

[0057] Step S2) Within each control cycle, using the current device state as the initial condition, optimize the air compressor motor operating frequency control sequence and the opening sequence of the nitrogen generator unit's inlet regulating valve 31 and product gas back pressure valve 32 based on the integrated prediction model. Based on the current device state and the established integrated prediction model, proactively plan the optimal action sequence of the air compressor motor operating frequency and the key valves (inlet regulating valve 31 and product gas back pressure valve 32) of the nitrogen generator unit for a future period, thereby achieving optimal energy efficiency while meeting safe gas supply requirements. For details, please refer to the appendix. Figure 4 ,include:

[0058] Step S21) Divide each control cycle into N optimization steps, and use the air compressor frequency within the next N optimization steps as the decision variable to form a frequency control sequence to be optimized. At the beginning of each control cycle, for example, once every 2 seconds, first divide the time window of the cycle into N discrete optimization steps (e.g., N=10, 0.2 seconds per step), and set the air compressor operating frequency in the next N steps as the decision variable to form a frequency control sequence of length N.

[0059] Step S22) Based on the current device state, the integrated prediction model, and the frequency control sequence to be optimized, recursively predict the inlet pressure, nitrogen output pressure, purity, and flow rate of the inner membrane separation nitrogen generation unit for the next N optimization steps. The sequence is not directly output but is used as a candidate solution in the optimization search space. Subsequently, using the current measured device state (including current exhaust pressure, pipeline pressure, nitrogen purity, valve opening, and motor speed, etc.) as initial conditions, and combined with the integrated prediction model, recursively simulate each candidate frequency sequence: from step 1 to step N, predict how the air compressor exhaust pressure changes with frequency, how the actual inlet pressure after pipeline impedance attenuation acts on the membrane separation module, and further deduce the nitrogen output pressure, purity, and flow rate at each moment. For example, in a certain optimization, if the frequency sequence is rapidly increased to 48Hz in the first part, the model predicts that the intake pressure can reach 0.85MPa in step 3, corresponding to a nitrogen purity of about 97.8%. However, if the frequency drops sharply in the following steps, the purity may drop to 96.2% in step 6, triggering a safety lower limit warning.

[0060] Step S23) In each recursive prediction, the efficiency factor of the permanent magnet motor at the corresponding frequency is calculated simultaneously, and converted into equivalent power consumption cost according to the preset energy consumption weight. Simultaneously with the recursive prediction, the operating efficiency factor of the permanent magnet synchronous motor at each frequency point is calculated. The operating efficiency factor is derived from the motor's factory efficiency MAP or measured energy consumption curve. For example, at 40 Hz and 80% load, the motor efficiency is 94.5%, while at a low frequency of 25 Hz under light load, the efficiency may drop to 86%. Combining the current electricity price or unit energy consumption cost, the power consumption at each time step is converted into equivalent power consumption cost and assigned a preset weighting coefficient, allowing it to be calculated in the same objective function as the gas supply performance index.

[0061] Step S24) The opening sequence of the inlet regulating valve 31 and the product gas back pressure valve 32 is included in the decision variables. To further enhance control freedom, the system also includes the opening sequence of the inlet regulating valve 31 and the product gas back pressure valve 32 in the decision variables. The former is used to fine-tune the gas flow rate and pressure stability entering the membrane module, while the latter affects the pressure difference across the membrane by adjusting the product gas side back pressure, thereby actively controlling the separation efficiency. For example, appropriately closing the back pressure valve can increase the pressure on the non-permeable side of the membrane module, enhance the oxygen stripping effect, and help maintain high purity at lower inlet pressures, but it will increase system resistance and needs to be adjusted in coordination with the air compressor frequency.

[0062] Step S25) Using a preset optimization algorithm, obtain the decision value of the decision variable that minimizes the weighted sum of the nitrogen pressure tracking difference and the equivalent power consumption cost. Construct a comprehensive objective function, which is typically the weighted sum of the squared tracking errors between the nitrogen pressure and the setpoint, and the total equivalent power consumption cost. By calling a preset optimization algorithm, such as Sequential Quadratic Programming (SQP), interior-point method, or real-time iterative dynamic programming, solve for the joint decision sequence of frequency and valve opening that minimizes the objective function, while satisfying a series of physical and safety constraints.

[0063] Step S26) optimizes constraints including the air compressor frequency change rate limit, motor power limit, valve opening range, and change rate. The air compressor frequency change rate must not exceed ±5Hz / s to prevent mechanical shock; the motor output power must not exceed the rated value (e.g., 75kW); and the valve opening must be within the range of 0%-100% with each step change not exceeding 10% to avoid actuator wear or airflow oscillation. For example, in a typical drilling sudden change scenario, the system detects a sudden increase in air demand. Within 0.5 seconds, the optimizer plans a smooth transition sequence of first slightly increasing the frequency to 46Hz while slowly opening the intake valve. This avoids pressure overshoot and controls the single-cycle power consumption within 103% of the baseline value, significantly better than the 118% energy consumption level under traditional PID control. This achieves forward-looking, coordinated, and constraint-satisfied optimal control of multiple actuators, enabling the mobile mining nitrogen generation system to maintain both air supply quality and operational economy under complex disturbances, providing highly reliable and low-energy nitrogen supply for safe underground operations.

[0064] Step S3) Set the optimization objective function. The optimization objective function is obtained based on the tracking deviation of the output nitrogen pressure to the set value, the energy consumption weight corresponding to the efficiency factor of the permanent magnet motor under various speed conditions, and the energy loss caused by valve action. The optimal control sequence is obtained by minimizing the optimization objective function. The control sequence includes a frequency control sequence and an opening sequence.

[0065] A multi-objective optimization objective function that balances gas supply performance and system energy efficiency is constructed, and the optimal control sequence is solved based on this objective function. The objective function does not pursue the extreme value of a single index, but comprehensively considers the tracking accuracy of nitrogen output pressure to the process setpoint, the electrical energy consumption converted from the operating efficiency of the permanent magnet motor at different speeds, and the additional energy loss caused by frequent or large-amplitude movements of the regulating valve, thereby achieving a fine balance between safety, stability and energy saving.

[0066] Specifically, the first term of the objective function focuses on ensuring gas supply quality, namely, the tracking deviation between the nitrogen output pressure and the preset target value (e.g., 0.8 MPa, used for nitrogen injection for fire prevention in goaf areas). This deviation is typically quantified using the squared error form (e.g., L2 norm) to emphasize the penalty effect of large deviations. For example, if a sudden increase in drilling speed leads to a surge in gas consumption, and the pressure drops to 0.72 MPa, the deviation reaches 0.08 MPa. The squared term will significantly increase the objective function value, prompting the optimizer to prioritize increasing the air compressor frequency or adjusting valves to quickly restore pressure.

[0067] The second aspect reflects a refined modeling of motor energy consumption. Unlike simply using power or current as a proxy for energy consumption, this approach introduces an "efficiency factor" derived from measured values ​​or manufacturer-provided efficiency maps of permanent magnet synchronous motors. This factor reflects the input electrical energy corresponding to a unit output power under a specific combination of speed and load rate. For example, a 75kW explosion-proof permanent magnet motor has an efficiency of 95.2% at 45Hz and 85% load, but its efficiency drops to 88.7% at 30Hz and 50% load. The system maps the predicted motor operating point in each optimization step to the corresponding efficiency factor, calculates the equivalent power consumption based on the predicted power, multiplies it by a preset energy consumption weighting coefficient (e.g., λ1=0.6), and incorporates it into the objective function. This naturally favors the motor operating in its high-efficiency range during the optimization process, avoiding uneconomical conditions such as "low-frequency inefficiency" or "high-frequency overload."

[0068] The third aspect focuses on the implicit energy consumption and equipment wear caused by valve actuation. Although the valve itself does not directly consume a large amount of electrical energy, changes in its opening degree alter the pipeline resistance characteristics, indirectly affecting the air compressor load. Simultaneously, frequent or drastic valve adjustments accelerate actuator wear and induce airflow oscillations, increasing the risk of system instability. Therefore, the objective function introduces a penalty term for valve actuation, typically represented by the absolute value or sum of squares of the opening degree change between adjacent steps, and assigned a small but not negligible weight (e.g., λ² = 0.1). For example, if the intake regulating valve 31 continuously and significantly opens and closes within 5 optimization steps (e.g., from 40%->70%->30%), the penalty term will increase significantly, guiding the optimizer to choose a smoother, more gradual regulation strategy.

[0069] The expression for the objective function to be optimized is:

[0070]

[0071] Among them, w p w represents the weighting coefficient for nitrogen pressure tracking error. p The higher the value, the greater the emphasis on precise pressure tracking of the set value, at the cost of increased energy consumption. p If the value is too small, pressure fluctuations may exceed the safety tolerance. nit To predict nitrogen pressure, Pset For the set value, λ1 represents the weighting coefficient of the energy consumption item, C ele c(f,T) represents the equivalent power consumption cost function based on motor speed and load, where f is the operating frequency of the permanent magnet inverter motor, and T is the motor output torque, reflecting the current load magnitude. Since motor efficiency is a non-linear function of f and T (usually obtained from an efficiency map provided by the manufacturer or measured data), C... ele c(f,T) is the energy cost converted from the input electrical power (considering efficiency) at the current operating point. λ2 represents the weighting coefficient of the valve action penalty term. Δu value This represents the change in valve opening between adjacent optimization steps.

[0072] Step S4) The first instruction in the optimal control sequence is sent as the current control instruction to the explosion-proof permanent magnet variable frequency air compressor unit 20 and the mobile membrane separation nitrogen generation unit 30 respectively.

[0073] After completing multi-step optimization within a control cycle, the system obtains a frequency control sequence (e.g., [46Hz, 47Hz, 47.5Hz, ...]) containing N time steps, along with corresponding opening sequences for the intake regulating valve 31 and the product air back pressure valve 32 (e.g., [52%, 54%, 55%, ...]). Although the entire sequence is optimized, only the first element, i.e., the instruction to be executed at the current moment, is used as the actual control output. The air compressor inverter receives the 46Hz frequency setpoint, and the valve controller synchronously adjusts the two regulating valves to 52% opening. The remaining subsequent instructions are calculated but not executed immediately. Instead, they are re-predicted and optimized based on the updated actual system state at the start of the next control cycle, generating a completely new control sequence. This replanning mechanism gives the device a stronger anti-interference capability.

[0074] For example, in a coal mine underground nitrogen injection fire suppression operation, when the working face advances, causing a sudden increase in the volume of the goaf and a 15% instantaneous increase in gas demand, a traditional fixed-frequency control system may experience a sudden drop in nitrogen pressure to 0.68 MPa (set value is 0.8 MPa) due to response lag, triggering a safety alarm. In this solution, after detecting the pressure drop trend, the device completes an optimization cycle within 2 seconds, generates a new control sequence, and immediately issues the first instruction: increasing the air compressor frequency from the current 42Hz to 45.5Hz, while slightly increasing the opening of the intake regulating valve 31 from 48% to 51%, and slightly closing the back pressure valve to maintain the membrane module pressure difference. After executing this instruction, the device stabilizes the pressure at 0.795 MPa within 4 seconds, and the motor always operates in the high-efficiency range without overload or frequent start-stop. Because only the first step is executed each time, even if subsequent drilling conditions change abruptly, such as gas outbursts suppressing gas consumption, the device can promptly correct the strategy in the next cycle, preventing the error from continuing.

[0075] On the other hand, in another implementation, within each control cycle, a feedforward control method is also executed to obtain a feedforward compensation amount, which is then added to the current control command. Please refer to the appendix. Figure 5 The feedforward control method includes the following steps:

[0076] Step S51) Collect operating data of the device under different working conditions to generate reference process data. The working conditions include coal seam hardness, borehole inclination angle, and drilling speed. The operating data records the nitrogen consumption pattern and its correlation with the device's input and output variables. Collecting operating data under different working conditions generates reference process data. The working conditions include key parameters such as coal seam hardness, borehole inclination angle, and drilling speed. These parameters directly affect the nitrogen consumption pattern and its correlation with the device's input and output variables. For example, in the mining of a high-hardness coal seam, due to increased drill bit wear, greater drilling pressure and higher rotational speed may be required, leading to a significant increase in nitrogen consumption. Therefore, accurately recording these changes helps in establishing a more accurate model.

[0077] Step S52) Based on the stored operational data, identify whether the current operation procedure matches a stored typical procedure. For example, in a coal mine underground nitrogen injection fire prevention and extinguishing project, the device has accumulated a large amount of data on nitrogen consumption patterns under different types of coal seams (soft, medium, hard) and different borehole angles (vertical, oblique). When a new mining task begins, the device automatically analyzes the current operating conditions and attempts to find the closest historical case for reference.

[0078] Step S53) When it is identified that the current operation matches a stored typical operation and is a repetitive operation, the nitrogen consumption pattern of the matching typical operation is retrieved, and the disturbance trend sequence within a preset time period is predicted. If the current operation successfully matches a stored typical operation and is a repetitive operation, the corresponding nitrogen consumption pattern can be retrieved, and the disturbance trend sequence within a preset time period can be predicted. For example, if the current working face is processing a medium-hard coal seam area that is very similar to a previous operation, based on historical records, it can be expected that in the next half hour, as the borehole depth increases, the nitrogen demand will gradually increase.

[0079] Step S54) Generate a feedforward compensation amount based on the disturbance trend sequence, and superimpose the feedforward compensation amount onto the current control command. If the forecast indicates that nitrogen demand will increase by 10% in the next half hour, the unit will adjust the air compressor's operating frequency or valve opening in advance to ensure timely fulfillment of this incremental demand. That is, in addition to executing the standard feedback control strategy, a certain proportion of energy supply or regulating valve position adjustment will be added as feedforward compensation to better cope with upcoming changes and avoid performance degradation or resource waste caused by hysteresis effects.

[0080] Methods for predicting the trend sequence of disturbances within a preset time period include:

[0081] Historical nitrogen consumption patterns are extracted from the matched typical process data and aligned with the current operation process along the time axis. The nitrogen consumption patterns include a time series of nitrogen consumption rates, and the time series is matched with a preset optimization step size.

[0082] Based on the nitrogen consumption mode, the current nitrogen output flow rate of the membrane separation nitrogen generation unit, and the control sequence, the sequence of nitrogen output pressure disturbance caused by changes in gas demand within a preset time period is deduced.

[0083] The disturbance sequence is smoothed and filtered to obtain the disturbance trend sequence within a preset time period.

[0084] Based on the precise alignment of historical typical process data with the current operational status, reproducible disturbance patterns are extracted from actual operational experience. Specifically, the corresponding historical nitrogen consumption patterns are retrieved from the matched typical process data. These patterns record the trajectory of nitrogen consumption rate per unit time under the same or similar operating conditions (e.g., coal seam hardness of 4, borehole inclination angle of 30°, drilling speed of 1.2 m / min) with high temporal resolution, forming a time series aligned with the optimization step size (e.g., 0.2 seconds per step). For example, in the historical record of a certain hard rock drilling operation, the nitrogen consumption rate began to increase by approximately 2 Nm³ / min starting 5 minutes after the drill bit entered the rock formation. 3 The slope of / h / min increases linearly and then stabilizes after 15 minutes; this complete dynamic feature is fully preserved in the database.

[0085] The device then dynamically aligns the current operation's actual progress along the timeline with the historical sequence. For example, if drilling has been ongoing for 8 minutes and the real-time monitoring shows a drilling rate highly consistent with historical cases, the system uses the remaining portion of the historical sequence "after the 8th minute" (e.g., data for the next 10 minutes) as a reference benchmark for future nitrogen demand. Based on this, and combined with the actual output flow rate of the current membrane separation nitrogen generation unit, real-time feedback from the flow meter, and the planned frequency and valve control sequence within the current control cycle, the system uses material balance relationships to infer: if the expected nitrogen consumption rate at a future time is 65 Nm³... 3 / h, while the current control strategy can only provide 60Nm 3 If the gas demand exceeds the supply capacity, the system will experience a pressure drop of approximately 0.05 MPa per hour. This pressure disturbance caused by gas demand exceeding supply capacity is calculated point by point, forming a preliminary time series of the disturbance.

[0086] The original disturbance sequence may contain high-frequency noise or local abrupt changes, and directly using it for feedforward may cause unnecessary jitter in the actuator. Therefore, a smoothing filter is applied to this disturbance sequence, typically using a low-pass filter or a moving average window (such as a 5-step sliding window), to suppress high-frequency fluctuations while preserving the main trend characteristics. For example, after filtering, the 0.07MPa spike disturbance that originally appeared in step 12 is smoothed into a gradual change of 0.05-0.06MPa over three consecutive steps, which better matches the response characteristics of the physical system.

[0087] If a cumulative pressure drop of 0.12 MPa is predicted in steps 6-10, a feedforward component equivalent to increasing the frequency by 2.5 Hz will be added to the current control command in advance, and the intake valve opening will be finely adjusted by +3%, thereby enhancing the gas supply capacity before the disturbance actually occurs. In a field test of tunnel excavation in a coal mine, after introducing this feedforward mechanism, the standard deviation of nitrogen pressure fluctuation decreased from ±0.042 MPa to ±0.018 MPa in the face of repetitive drilling disturbances, while the air compressor energy consumption decreased by about 7%.

[0088] Specifically, the method for generating the feedforward compensation amount based on the disturbance trend sequence includes:

[0089] With the goal of minimizing the tracking deviation of the output nitrogen pressure from the set value, and with the tracking deviation being less than a preset deviation threshold as a constraint, the required inlet pressure compensation sequence is generated based on the disturbance trend sequence, the dynamic operating characteristics of the membrane separation nitrogen generation unit, and the control sequence. The dynamic operating characteristics include the nonlinear relationship between nitrogen purity and flow rate of the membrane separation nitrogen generation unit under different inlet pressures.

[0090] Based on the intake pressure compensation sequence, a corresponding feedforward compensation sequence is generated;

[0091] Extract the feedforward compensation amount corresponding to the current control cycle from the feedforward compensation amount sequence, and use it as the final generated feedforward compensation amount.

[0092] The process of generating feedforward compensation based on the disturbance trend sequence is a planning problem aimed at suppressing pressure deviation and constrained by the physical characteristics of the device. The optimization objective is to minimize the tracking deviation of the output nitrogen pressure from the setpoint, and this deviation is required to remain below a preset safety threshold (e.g., ±0.02 MPa) throughout the prediction time domain. This is a fundamental requirement for ensuring inerting effectiveness in coal mine nitrogen injection operations. Under this premise, by combining the obtained disturbance trend sequence—that is, the equivalent pressure drop caused by sudden increases in gas demand or changes in pipeline resistance in future optimization steps, the dynamic operating characteristics of the membrane separation nitrogen generation unit, especially the nonlinear mapping relationship between its inlet pressure and nitrogen flow rate / purity—and the baseline control sequence already generated within the current control cycle, a set of required inlet pressure compensation sequences is solved in reverse.

[0093] The physical limitations of the membrane separation unit must be fully considered. For example, a mobile membrane module can stably output 60 Nm³ / h of nitrogen with a purity of 97.5% at an inlet pressure of 0.75 MPa. If the flow rate needs to be increased to 68 Nm³ / h to cope with disturbances, simply increasing the frequency may not be effective. This is because if the inlet pressure is only increased to 0.80 MPa, the flow rate may only increase to 63 Nm³ / h, and the purity may slightly decrease due to the large membrane pressure difference. Therefore, it is necessary to accurately calculate the increase in inlet pressure ΔP_in(k) required to offset the 0.03 MPa pressure disturbance at step k based on the embedded nonlinear performance model. This can be achieved through table lookup interpolation or local linearization approximation to ensure that the compensated total inlet pressure meets the flow rate requirements without causing the purity to fall below the safe threshold of 97%.

[0094] After obtaining the intake pressure compensation sequence, it is further converted into an executable feedforward compensation sequence. Since the intake pressure is derived from the attenuation of the air compressor exhaust pressure through the pipeline impedance, and the pipeline pressure drop is proportional to the square of the flow rate, it is necessary to combine the current flow rate prediction value and the pipeline impedance model to back-calculate ΔP_in(k) into the additional exhaust pressure increment that the air compressor needs to provide. Then, based on the air compressor dynamic response model (such as the transfer function), it is converted into a frequency compensation quantity Δf(k). At the same time, in order to maintain the optimal pressure difference of the membrane module, the product air back pressure valve 32 may also need to be fine-tuned. This part is also included in the feedforward sequence in the form of an opening compensation quantity Δu_back(k).

[0095] Although the entire feedforward compensation sequence covers the next N optimization steps, according to the rolling time-domain control principle, only the first element corresponding to the current control cycle is extracted. That is, Δf(1) and Δu_valve(1) are used as the final feedforward compensation. The compensation is superimposed on the control command in real time. For example, in a typical coal roadway drilling operation, it is predicted that nitrogen consumption will increase by 12% in the next 5 seconds due to the drill bit cutting into the fault zone, and the disturbance trend sequence indicates that the pressure will drop by 0.045MPa. After the above reverse calculation, the frequency feedforward compensation is generated by +1.8Hz and the intake valve opening compensation by +2.5%. After superposition, the actual operating frequency of the air compressor increases from 44.2Hz to 46.0Hz, and the valve is synchronously fine-tuned, so that the pressure fluctuation is suppressed within ±0.015MPa and the purity is stable at 97.8%, which is better than the ±0.038MPa fluctuation without feedforward.

[0096] On the other hand, this specification provides a coordinated control system for a mine-use variable frequency air compressor and a nitrogen generator; please refer to the appendix. Figure 6 ,include:

[0097] Explosion-proof permanent magnet variable frequency air compressor unit 20 is used to provide a compressed air source with adjustable frequency drive;

[0098] The mobile membrane separation nitrogen generation unit 30 includes an inlet regulating valve 31, a membrane separation component, and a product gas back pressure valve 32, which is used to separate compressed air into high-purity nitrogen and oxygen-enriched waste gas, and to control the nitrogen output pressure and flow rate by adjusting the inlet regulating valve 31 and the product gas back pressure valve 32.

[0099] The collaborative control unit 10 is communicatively connected to the explosion-proof permanent magnet variable frequency air compressor unit 20 and the mobile membrane separation nitrogen generation unit 30. The collaborative control unit 10 includes:

[0100] Module 101 is used to construct an integrated prediction model. The integrated prediction model records the dynamic response characteristics between the frequency and exhaust pressure of the permanent magnet air compressor, the nonlinear relationship between the nitrogen purity and flow rate of the membrane separation nitrogen generator under different inlet pressures, and the impedance characteristics of the connecting pipeline.

[0101] In each control cycle, the control module 102 uses the current device state as the initial condition and optimizes the frequency control sequence of the air compressor motor and the opening sequence of the nitrogen generator inlet regulating valve 31 and the product gas back pressure valve 32 based on the integrated prediction model.

[0102] The optimization module 103 sets an optimization objective function, which is obtained based on the tracking deviation of the output nitrogen pressure to the set value, the energy consumption weight corresponding to the efficiency factor of the permanent magnet motor under various speed conditions, and the energy loss caused by valve action. The optimal control sequence is obtained by minimizing the optimization objective function. The control sequence includes a frequency control sequence and an opening sequence.

[0103] The execution module 104 sends the first instruction in the optimal control sequence as the current control instruction to the explosion-proof permanent magnet variable frequency air compressor unit 20 and the mobile membrane separation nitrogen generation unit 30 respectively.

[0104] Please see Figure 7 The diagram shown is a structural schematic of an electronic device provided in an embodiment of this specification.

[0105] like Figure 7 As shown, the electronic device 1100 may include: at least one processor 1101, at least one network interface 1104, a user interface 1103, a memory 1105, and at least one communication bus 1102. The communication bus 1102 can be used to connect and communicate with the various components mentioned above. The user interface 1103 may include buttons, and optionally may include standard wired or wireless interfaces. The network interface 1104 may include, but is not limited to, a Bluetooth module, an NFC module, or a Wi-Fi module. The processor 1101 may include one or more processing cores. The processor 1101 connects to various parts within the electronic device 1100 using various interfaces and lines, and performs various functions of the routing device and processes data by running or executing instructions, programs, code sets, or instruction sets stored in the memory 1105, and by calling data stored in the memory 1105. Optionally, the processor 1101 may be implemented using at least one hardware form of DSP, FPGA, or PLA. The processor 1101 may integrate one or more combinations of CPU, GPU, and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content that the display screen needs to show; and the modem is used for wireless communication.

[0106] It is understandable that the aforementioned modem may not be integrated into the processor 1101, but may be implemented using a separate chip.

[0107] The memory 1105 may include RAM or ROM. Optionally, the memory 1105 may include a non-transitory computer-readable medium. The memory 1105 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 1105 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 1105 may also be at least one storage device located remotely from the aforementioned processor 1101. As a computer storage medium, the memory 1105 may include an operating system, a network communication module, a user interface module, and application programs. The processor 1101 may be used to call the application programs stored in the memory 1105 and execute the methods in the above-described embodiments.

[0108] This specification also provides a computer-readable storage medium storing instructions that, when executed on a computer or processor, cause the computer or processor to perform multiple steps as described in the above embodiments. If the constituent modules of the above-described electronic device are implemented as software functional units and sold or used as independent products, they can be stored in the computer-readable storage medium.

[0109] This specification also provides a computer program product, including a computer program that, when executed by a processor, implements the multiple steps described in the above embodiments.

[0110] Where there is no conflict, the technical features in this embodiment and implementation scheme can be combined arbitrarily.

[0111] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes multiple computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this specification are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted through the computer-readable storage medium. The computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center integrating multiple available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., digital versatile discs (DVDs)), or semiconductor media (e.g., solid-state drives (SSDs)).

[0112] When implemented through hardware or firmware, the aforementioned method flow is programmed into the hardware circuit to obtain the corresponding hardware circuit structure and achieve the corresponding function. For example, a Programmable Logic Device (PLD) (such as a Field Programmable Gate Array (FPGA)) is such an integrated circuit, whose logic function is determined by the user programming the device. Designers can program a digital system onto a PLD themselves, eliminating the need for chip manufacturers to design and fabricate dedicated integrated circuit chips. Furthermore, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly implemented using "logic compiler" software, similar to the software compiler used in program development. The original code before compilation must also be written in a specific programming language, called a Hardware Description Language (HDL). There is not just one HDL, but many. Those skilled in the art should understand that by simply performing some logic programming on the method flow using one of the aforementioned hardware description languages ​​and programming it into an integrated circuit, the hardware circuit implementing the logic method flow can be easily obtained.

[0113] The embodiments described above are merely preferred embodiments of this specification and are not intended to limit the scope of this specification. Any modifications and improvements made by those skilled in the art to the technical solutions of this specification without departing from the spirit of this specification should fall within the protection scope defined by the claims of this specification.

Claims

1. A method for coordinated control of a mining variable frequency air compressor and a nitrogen generator, characterized in that, Applied to an apparatus comprising an explosion-proof permanent magnet variable frequency air compressor unit, a mobile membrane separation nitrogen generation unit, and a collaborative control unit, the method is executed by the collaborative control unit and includes the following steps: An integrated prediction model is constructed, which records the dynamic response characteristics between the frequency and exhaust pressure of the permanent magnet air compressor, the nonlinear relationship between the nitrogen purity and flow rate of the membrane separation nitrogen generator under different inlet pressures, and the impedance characteristics of the connecting pipeline. Within each control cycle, using the current device state as the initial condition, the control sequence of the air compressor motor operating frequency and the opening sequence of the nitrogen generator intake regulating valve and the product gas back pressure valve within the control cycle are optimized based on the integrated prediction model. An optimization objective function is set, which is obtained based on the tracking deviation of the output nitrogen pressure to the set value, the energy consumption weight corresponding to the efficiency factor of the permanent magnet motor under various speed conditions, and the energy loss caused by valve action. The optimal control sequence is obtained by minimizing the optimization objective function. The control sequence includes a frequency control sequence and an opening sequence. The first instruction in the optimal control sequence is sent as the current control instruction to the explosion-proof permanent magnet variable frequency air compressor unit and the mobile membrane separation nitrogen generation unit respectively; Within each control cycle, a feedforward control method is also executed to obtain a feedforward compensation amount, which is then added to the current control command. The steps of the feedforward control method are as follows: The data acquisition device operates under different conditions and generates reference process data. The operating conditions include coal seam hardness, borehole inclination angle and drilling speed. The operating data records the nitrogen consumption pattern and its correlation with the device's input and output variables. Based on the stored operational data, identify whether the current operation procedure matches a stored typical procedure; When the current operation is identified as matching a stored typical operation and being a repetitive operation, the nitrogen consumption pattern of the matching typical operation is retrieved, and the disturbance trend sequence within a preset time period is predicted. Generate a feedforward compensation amount based on the disturbance trend sequence, and then add the feedforward compensation amount to the current control command. Methods for predicting the trend sequence of disturbances within a preset time period include: Historical nitrogen consumption patterns are extracted from the matched typical process data and aligned with the current operation process along the time axis. The nitrogen consumption patterns include a time series of nitrogen consumption rates, and the time series is matched with a preset optimization step size. Based on the nitrogen consumption mode, the current nitrogen output flow rate of the membrane separation nitrogen generation unit, and the control sequence, the sequence of nitrogen output pressure disturbance caused by changes in gas demand within a preset time period is deduced. The disturbance sequence is smoothed and filtered to obtain the disturbance trend sequence within a preset time period.

2. The method for coordinated control of a mine-use variable frequency air compressor and a nitrogen generator according to claim 1, characterized in that, Methods for constructing ensemble prediction models include: Under laboratory conditions, the explosion-proof permanent magnet variable frequency air compressor unit was subjected to a step frequency response test. Dynamic data of the exhaust pressure changing with time was collected and aligned with the frequency data along the time axis to obtain test data. The test data is fitted to obtain the transfer function between frequency and exhaust pressure, and a dynamic response model is established based on the transfer function. Under laboratory conditions, when the membrane separation nitrogen generation unit is in steady-state operation, the inlet pressure is adjusted and the nitrogen outlet purity and flow rate are measured simultaneously to establish the mapping relationship between the inlet pressure and the nitrogen purity and flow rate, and to establish an embedded model in the form of piecewise function, polynomial regression or table lookup interpolation. The connecting pipeline is divided into multiple segments. Based on the geometric parameters and gas flow equation of each segment, the pressure drop of the segment under different flow rates is calculated. The pressure drop is simplified to the impedance coefficient of the segment. The impedance characteristic model of the connecting pipeline is established based on the impedance coefficient. An integrated prediction model is constructed by combining the dynamic response model, the embedded model, and the impedance characteristic model.

3. The method for coordinated control of a mine-use variable frequency air compressor and a nitrogen generator according to claim 1, characterized in that, The method for optimizing the air compressor motor operating frequency control sequence and the opening sequence of the nitrogen generator unit intake regulating valve and product gas back pressure valve within the control cycle based on the integrated prediction model includes: Each control cycle is divided into N optimization steps, and the air compressor frequency within the next N optimization steps is taken as the decision variable to form the frequency control sequence to be optimized. Based on the current device status, the integrated prediction model, and the frequency control sequence to be optimized, the inlet pressure, nitrogen output pressure, purity, and flow rate of the inner membrane separation nitrogen generation unit for the next N optimized steps are recursively predicted. In each recursive prediction, the efficiency factor of the permanent magnet motor at the corresponding frequency is calculated and converted into equivalent power consumption cost according to the preset energy consumption weight. The opening sequence of the intake regulating valve and the product air back pressure valve is included in the decision variables; Using a preset optimization algorithm, obtain the decision value of the decision variable that minimizes the weighted sum of nitrogen pressure tracking difference and equivalent power consumption cost. The optimized constraints include limits on the air compressor frequency change rate, upper limit on motor power, valve opening range, and change rate.

4. The method for coordinated control of a mine-use variable frequency air compressor and a nitrogen generator according to claim 1, characterized in that, The method for generating feedforward compensation based on the disturbance trend sequence includes: With the goal of minimizing the tracking deviation of the output nitrogen pressure from the set value, and with the tracking deviation being less than a preset deviation threshold as a constraint, the required inlet pressure compensation sequence is generated based on the disturbance trend sequence, the dynamic operating characteristics of the membrane separation nitrogen generation unit, and the control sequence. The dynamic operating characteristics include the nonlinear relationship between nitrogen purity and flow rate of the membrane separation nitrogen generation unit under different inlet pressures. Based on the intake pressure compensation sequence, a corresponding feedforward compensation sequence is generated; Extract the feedforward compensation amount corresponding to the current control cycle from the feedforward compensation amount sequence, and use it as the final generated feedforward compensation amount.

5. A coordinated control system for a mining variable frequency air compressor and a nitrogen generator, characterized in that, include: Explosion-proof permanent magnet variable frequency air compressor unit, used to provide a compressed air source with adjustable frequency drive; A mobile membrane separation nitrogen generation unit includes an inlet regulating valve, a membrane separation component, and a product gas back pressure valve, used to separate compressed air into high-purity nitrogen and oxygen-enriched waste gas, and to control the nitrogen output pressure and flow rate by adjusting the inlet regulating valve and the product gas back pressure valve; A collaborative control unit, communicatively connected to the explosion-proof permanent magnet variable frequency air compressor unit and the mobile membrane separation nitrogen generation unit, comprises: The module is constructed to build an integrated prediction model. The integrated prediction model records the dynamic response characteristics between the frequency and exhaust pressure of the permanent magnet air compressor, the nonlinear relationship between the nitrogen purity and flow rate of the membrane separation nitrogen generator under different inlet pressures, and the impedance characteristics of the connecting pipeline. The control module, within each control cycle, uses the current device state as the initial condition and optimizes the frequency control sequence of the air compressor motor and the opening sequence of the nitrogen generator intake regulating valve and the product gas back pressure valve within the control cycle based on the integrated prediction model. The optimization module sets an optimization objective function, which is obtained based on the tracking deviation of the output nitrogen pressure to the set value, the energy consumption weight corresponding to the efficiency factor of the permanent magnet motor under various speed conditions, and the energy loss caused by valve action. The optimal control sequence is obtained by minimizing the optimization objective function. The control sequence includes a frequency control sequence and an opening sequence. The execution module sends the first instruction in the optimal control sequence as the current control instruction to the explosion-proof permanent magnet variable frequency air compressor unit and the mobile membrane separation nitrogen generation unit respectively; Within each control cycle, a feedforward control method is also executed to obtain a feedforward compensation amount, which is then added to the current control command. The steps of the feedforward control method are as follows: The data acquisition device operates under different conditions and generates reference process data. The operating conditions include coal seam hardness, borehole inclination angle and drilling speed. The operating data records the nitrogen consumption pattern and its correlation with the device's input and output variables. Based on the stored operational data, identify whether the current operation procedure matches a stored typical procedure; When the current operation is identified as matching a stored typical operation and being a repetitive operation, the nitrogen consumption pattern of the matching typical operation is retrieved, and the disturbance trend sequence within a preset time period is predicted. Generate a feedforward compensation amount based on the disturbance trend sequence, and then add the feedforward compensation amount to the current control command. Methods for predicting the trend sequence of disturbances within a preset time period include: Historical nitrogen consumption patterns are extracted from the matched typical process data and aligned with the current operation process along the time axis. The nitrogen consumption patterns include a time series of nitrogen consumption rates, and the time series is matched with a preset optimization step size. Based on the nitrogen consumption mode, the current nitrogen output flow rate of the membrane separation nitrogen generation unit, and the control sequence, the sequence of nitrogen output pressure disturbance caused by changes in gas demand within a preset time period is deduced. The disturbance sequence is smoothed and filtered to obtain the disturbance trend sequence within a preset time period.

6. An electronic device, characterized in that, Including the processor and memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code stored in the memory to perform the method as described in any one of claims 1-4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-4.

8. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1-4.

Images