Adaptive Optimization and Adjustment Method and Device for the Ventilation System of Mine Fans Operating with Mesh Hanging

Abstract

The present application provides an optimization and adjustment method and device for an adaptive mine fan running with a net for ventilation system, which relates to the technical field of mine ventilation. By collecting historical air quality parameters, operating parameters, environmental parameters, number of personnel and operation conditions, training an air prediction model to predict future air quality parameters, calculating the comprehensive air quality, obtaining the energy consumption of historical fans, calculating the correlation coefficient, mining key parameters from the operating parameters to calculate the predicted energy consumption, predicting the real-time comprehensive air quality, calculating the safety risk value by using the comprehensive air quality, environmental parameters, number of personnel and operation conditions, presetting an energy cost threshold and a safety risk threshold, calculating a weight adjustment value according to the predicted energy consumption and the safety risk value, obtaining the air quality target weight and the energy consumption target weight, constructing an objective function and constraint conditions in combination with the air quality target weight and the energy consumption target weight, and obtaining the optimal operating parameters of the fan, the energy efficiency and safety are greatly improved.

Description

Technical Field

[0001] The present application relates to the field of mine ventilation technology, and in particular to an optimization and adjustment method and device for an adaptive mine fan mesh operation ventilation system. Background Art

[0002] The mine fan hanging mesh operation ventilation system refers to the ventilation system used in the mine. The main purpose of this system is to ensure that there is enough air circulation in the mine to protect the health and safety of workers, while removing harmful gases and dust. The optimization and adjustment of the ventilation system is of great significance for energy saving and consumption reduction and improving the safety and production efficiency of mines.

[0003] Traditional mine ventilation methods usually include fixed-speed fan systems and adjustments based on simple control logic. The main characteristics of these systems include: fans run at a fixed speed and are not adjusted according to actual ventilation needs; ventilation volume adjustment often relies on operator experience for manual adjustment, lacks automation and optimization algorithm support; basic sensors and control systems are used to maintain the lowest level of safety standards rather than optimization.

[0004] In traditional systems, fans are usually designed to run at a fixed speed, that is, the fan runs at a fixed speed. This design is simple and stable, but it ignores the changes in conditions inside the mine, such as the mining progress of the working area, the number of miners, or seasonal changes. Because the fan runs at a fixed speed, the system fails to dynamically adjust power consumption according to the actual air quality needs, resulting in energy waste in many cases. For example, at night or during non-working hours, the ventilation demand of the mine may decrease, but the fan still runs at maximum capacity.

[0005] Fans running at fixed speeds do not adjust their output according to actual ventilation demand, resulting in unnecessary energy consumption and uneconomical use of electricity and resources. Fixed-speed systems may require frequent maintenance to maintain efficiency, and due to lack of optimization, long-term operating costs are higher than modern adaptive systems. Summary of the invention

[0006] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, one purpose of the present application is to propose an adaptive mine fan mesh operation ventilation system optimization adjustment method and device, which automatically adjusts the fan speed according to real-time data, greatly improving energy efficiency and safety.

[0007] One aspect of the present application provides an adaptive mine fan grid-operated ventilation system optimization adjustment method, comprising:

[0008] Step S100: collecting air quality parameters, fan operation parameters, environmental parameters, and the number of personnel and operation conditions in each ventilation area in the mine at historical times;

[0009] The specific method for collecting the air quality parameters, fan operation parameters, environmental parameters, and the number of personnel and operation conditions in each ventilation area in the mine at a historical time is as follows:

[0010] Step S110: Divide the mine into K ventilation areas according to the layout and ventilation requirements of the mine;

[0011] Step S120: deploying sensors in each ventilation area to collect air quality parameters and environmental parameters of each ventilation area, wherein the air quality parameters include gas concentration and dust concentration, and the environmental parameters include wind speed and pressure;

[0012] Step S130: Count the number of people in each ventilation area, monitor each fan, and collect its operating parameters, including: speed, power, and air volume;

[0013] Step S140: monitoring the working progress of each working surface to obtain the working status of each ventilation area;

[0014] Step S200: using the historical air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions to train the air prediction model, predict the air quality parameters inside the mine in the future, and calculate the comprehensive air quality;

[0015] The specific method of using the air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions in the historical time to train the air prediction model, predict the air quality parameters inside the mine in the future, and calculate the comprehensive air quality is:

[0016] Step S210: Select the LSTM model as the initial model, integrate the air quality parameters, environmental parameters, number of personnel in the ventilation area and operation conditions in the historical time according to the time series, and obtain the air quality parameter sequence {A 1 ,A 2 ,...,A b}、Environment parameter sequence {E 1 ,E 2 ,...,E b}、Sequence of number of personnel {P 1 ,P 2 ,...,P b} and the sequence of work situations {W 1 ,W 2 ,...,W b};

[0017] Step S220: Preset the sliding window length, sliding step length and prediction time step length, and use the sliding window method to obtain b training samples on the air quality parameter sequence, environmental parameter sequence, number of personnel sequence and operation situation sequence;

[0018] Step S230: using the air quality parameter sequence, environmental parameter sequence, personnel quantity sequence and operation status sequence of the historical time of the sliding window length as input data, predicting the air quality parameters of the future time of the prediction time step as output data;

[0019] Step S240: using mean square loss as the loss function and using the Adam optimization algorithm to optimize the model parameters, with the value of the loss function between the real air quality parameter and the predicted air quality parameter being minimized as the training goal. When the loss function reaches convergence, the training is completed and the air prediction model is obtained.

[0020] Step S250: Obtain air quality parameter A i The jth parameter a j The maximum value a max and the minimum value a min , calculate the standardized parameters

[0021] Step S260: performing weighted averaging on the standardized parameters to construct a calculation formula for comprehensive air quality;

[0022] The calculation formula of the comprehensive air quality is: Among them, ω j is the weight of the jth standardized parameter, J is the total number of air quality parameters;

[0023] Step S300: Obtain the energy consumption of the fan in historical time, calculate the correlation coefficient between the operating parameters and the energy consumption, mine D key parameters from all the operating parameters according to the correlation coefficient, and use the key parameters to calculate the predicted energy consumption of the fan;

[0024] The specific method of obtaining the energy consumption of the fan in historical time, calculating the correlation coefficient between the operating parameters and the energy consumption, mining D key parameters from all the operating parameters according to the correlation coefficient, and using the key parameters to calculate the predicted energy consumption of the fan is:

[0025] Step S310: defining energy consumption impact coefficient ECIF;

[0026] Step S320: Calculate the correlation coefficient between each operating parameter and the energy consumption of the fan;

[0027] The calculation formula of the correlation coefficient is: Among them, s cIndicates the cth operating parameter, nh c represents the energy consumption of the fan under the cth operating parameter, C represents the number of operating parameter categories, and represent the mean values ​​of operating parameters and energy consumption respectively;

[0028] Step S330: defining importance weight coefficients;

[0029] The constraints satisfied by the importance weight coefficient are: τ c ∈[0,1], where τ c represents the importance weight coefficient of the cth operating parameter;

[0030] Step S340: Calculate the energy consumption impact coefficient ECIF according to the correlation coefficient and the importance weight coefficient;

[0031] The calculation formula of the energy consumption impact coefficient ECIF is: c =|PCC c (s,nh)×τ c , where PCC c (s,nh) is the correlation coefficient between the cth operating parameter and energy consumption, ECIF c is the energy consumption influence coefficient of the cth operating parameter;

[0032] Step S350: Preset the energy consumption impact coefficient threshold pcc, and set the D operating parameters S corresponding to the energy consumption impact coefficients that are greater than or equal to the energy consumption impact coefficient threshold pcc to be equal to the energy consumption impact coefficient threshold pcc. 1 ,s 2 ,...,s D}As a key parameter, it is used to establish a mathematical model for calculating the predicted energy consumption of the fan;

[0033] Step S360: Calculating the predicted energy consumption of the fan using key parameters according to the mathematical model of the predicted energy consumption of the fan;

[0034] The calculation formula for the predicted energy consumption of the fan is: τ d Represents the importance weight coefficient of the dth key parameter, s d Indicates the dth key parameter;

[0035] Step S400: predicting the real-time comprehensive air quality according to the air prediction model, and calculating the safety risk value of the mine using the comprehensive air quality, environmental parameters, the number of personnel in the ventilation area and the operation conditions;

[0036] The specific method of predicting the real-time comprehensive air quality according to the air prediction model and calculating the safety risk value of the mine by using the comprehensive air quality, environmental parameters, the number of personnel in the ventilation area and the working conditions is as follows:

[0037] Step S410: Collect the air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions at K time points in real time, and use the real-time air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions to predict the air quality parameters of the mine in the future time of the prediction time step, and calculate the real-time comprehensive air quality

[0038] Step S420: Calculate the personnel risk coefficient PRC according to the number of personnel and working conditions in the ventilation area;

[0039] The calculation formula of the personnel risk coefficient is: Among them, P k is the number of people collected for the kth time, W k is the operation status of the kth collection;

[0040] Step S430: Combine comprehensive air quality and personnel risk coefficient, and calculate the safety risk value SRV in the mine;

[0041] The calculation formula of the safety risk value is:

[0042] Step S500: preset an energy cost threshold and a safety risk threshold, calculate a weight adjustment value according to the predicted energy consumption and the safety risk value, and calculate the air quality target weight and the energy consumption target weight according to the target weight adjustment strategy and the weight adjustment value;

[0043] The specific method of calculating the air quality target weight and the energy consumption target weight according to the preset energy cost threshold and the safety risk threshold, and the weight adjustment value according to the target weight adjustment strategy and the weight adjustment value is as follows:

[0044] Step S510: Preset the energy cost threshold EC, obtain the current wind turbine operating parameters, and use the mathematical model of the wind turbine's predicted energy consumption to calculate the current wind turbine's predicted energy consumption NH. now , based on the energy cost threshold EC and the predicted energy consumption of the current wind turbine NH now The energy cost excess value ΔNH is calculated;

[0045] The energy cost excess value is calculated as follows: ΔNH = NH now -EC;

[0046] Step S520: Preset a security risk threshold SRV′, and calculate the difference between the security risk threshold and the security risk value to obtain a security risk difference ΔSRV;

[0047] The calculation formula of the safety risk difference is: ΔSRV=SRV-SRV′;

[0048] Step S530: constructing a target weight adjustment strategy for calculating weight adjustment values, wherein the weight adjustment values ​​include an air quality target weight adjustment value Δα and an energy consumption target weight adjustment value Δβ;

[0049] The function expression of the air quality target weight adjustment value is: Among them, α 1 A reference value representing the weight of the air quality target;

[0050] The function expression of the energy consumption target weight adjustment value is: Among them, β 1 Indicates the benchmark value of the energy consumption target weight;

[0051] Step S540: introducing the air inertia coefficient p and the energy consumption inertia coefficient q, smoothing the air quality target weight adjustment value Δα and the energy consumption target weight adjustment value Δβ to obtain smoothed weight adjustment values, wherein the weight adjustment values ​​include the air quality target weight adjustment value Δα′ and the energy consumption target weight adjustment value Δβ′;

[0052] The calculation formula of the smoothed air quality target weight adjustment value Δα′ is: Δα′=p×Δα+(1-p)×Δα;

[0053] The calculation formula of the smoothed energy consumption target weight adjustment value Δβ is: Δβ′=q×Δβ+(1-q)×Δβ;

[0054] Step S550: The smoothed air quality target weight adjustment value Δα′ and the energy consumption target weight adjustment value Δβ′ are normalized by a softmax method to calculate the air quality target weight α and the energy consumption target weight β;

[0055] The calculation formula of the air quality target weight α is:

[0056] The calculation formula of the energy consumption target weight β is:

[0057] Among them, α 0 and β 0 are the initial values ​​of the air quality target weight and the energy consumption target weight respectively;

[0058] Step S600: With the goal of minimizing predicted energy consumption and maximizing comprehensive air quality, an objective function and constraint conditions are constructed by combining air quality target weights and energy consumption target weights to obtain optimal operating parameters of the fan;

[0059] The specific method of minimizing predicted energy consumption and maximizing comprehensive air quality, combining air quality target weight and energy consumption target weight to construct objective function and constraint conditions, and obtaining the optimal operating parameters of the fan is as follows:

[0060] Step S610: define the decision variables as D key parameters of the wind turbine S = {s 1 ,s 2 ,...,s D}, the mathematical model of the predicted energy consumption of the fan is used as the energy consumption objective function fe(S), and the calculation formula of the comprehensive air quality is used as the air quality objective function fa(S);

[0061] Step S620: Calculate the maximum values ​​of the energy consumption objective function and the air quality objective function respectively, and use the predicted energy consumption and comprehensive air quality corresponding to the maximum values ​​as the negative ideal points fe(S)′ and fa(S)′ of the energy consumption objective function and the air quality objective function respectively;

[0062] Step S630: Calculate the minimum values ​​of the energy consumption objective function and the air quality objective function respectively, and use the predicted energy consumption and comprehensive air quality corresponding to the minimum values ​​as the ideal points fe(S) of the energy consumption objective function and the air quality objective function respectively. * and fa(S) * ;

[0063] Step S640: obtaining a normalized objective function according to the ideal point and the negative ideal point, including an energy consumption objective function ge(S) and an air quality objective function ga(S);

[0064] The calculation formula of the normalized energy consumption objective function is:

[0065] The calculation formula of the normalized air quality objective function is:

[0066] Step S650: constructing a weighted comprehensive objective function according to the normalized objective function, the air quality objective weight α and the energy consumption objective weight β;

[0067] The functional expression of the weighted comprehensive objective function is: minf(S)=α×ga(S)+β×ge(S);

[0068] Step S660: setting constraints on the operating parameters of the fan according to the safety constraints of mine ventilation;

[0069] The constraints include: air volume balance constraint, pressure balance constraint, wind speed constraint, gas concentration constraint and equipment capacity constraint. The air volume balance constraint is expressed as The pressure balance constraint is expressed as ∑E yl = 0, the wind speed constraint is expressed as The gas concentration constraint is expressed as The key parameter capacity constraint is expressed as S∈[S min ,S max ],in, is the air volume, is the air volume, ∑E yl is the pressure E of each ventilation branch yl the sum of The wind speed E fs The minimum and maximum values ​​of is the gas concentration A ws The upper limit, S min , S max is the minimum and maximum value of the key parameter S;

[0070] Step S670: A multi-objective optimization model is constructed by weighted comprehensive objective functions and constraint conditions, and a multi-objective genetic algorithm is used to solve the multi-objective optimization model to obtain optimal operating parameters of the wind turbine.

[0071] One aspect of the present application provides an adaptive mine fan mesh operation ventilation system optimization and adjustment device, comprising:

[0072] The data collection and statistics module is used to collect the air quality parameters, fan operation parameters, environmental parameters, and the number of personnel and operation conditions in each ventilation area in the mine at a historical time;

[0073] The air quality prediction module is used to train the air prediction model using the historical air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions, predict the air quality parameters inside the mine in the future, and calculate the comprehensive air quality;

[0074] The predicted energy consumption calculation module is used to obtain the energy consumption of the fan in the historical time, calculate the correlation coefficient between the operating parameters and the energy consumption, mine D key parameters from all the operating parameters according to the correlation coefficient, and use the key parameters to calculate the predicted energy consumption of the fan;

[0075] Safety risk calculation module, used to predict the real-time comprehensive air quality according to the air prediction model, and calculate the safety risk value of the mine using the comprehensive air quality, environmental parameters, number of personnel in the ventilation area and operating conditions;

[0076] The weight dynamic adjustment module is used to preset energy cost thresholds and safety risk thresholds, calculate weight adjustment values ​​according to predicted energy consumption and safety risk values, and calculate air quality target weights and energy consumption target weights according to target weight adjustment strategies and weight adjustment values;

[0077] The target optimization constraint module is used to minimize the predicted energy consumption and maximize the comprehensive air quality. It combines the air quality target weight and the energy consumption target weight to construct the objective function and constraint conditions to obtain the optimal operating parameters of the fan.

[0078] One aspect of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the method for optimizing and adjusting an adaptive mine fan grid-operated ventilation system are implemented.

[0079] One aspect of the present application provides a readable storage medium storing a computer program suitable for loading by a processor to execute the steps in a method for optimizing and adjusting an adaptive mine fan grid-operated ventilation system.

[0080] The adaptive mine fan mesh operation ventilation system optimization adjustment method and device proposed in this application have the following advantages over the prior art:

[0081] This application innovatively uses the LSTM neural network and combines it with the sliding window method to build an air quality prediction model, taking into account the impact of historical air quality, environmental parameters, number of personnel and operating conditions on future air quality, and can accurately predict the trend of changes in mine air quality in the future.

[0082] This application proposes the concept of comprehensive air quality. By standardizing and weighted averaging various air quality parameters, the complex mine air conditions are quantified into a comprehensive indicator, which is convenient for real-time assessment of mine ventilation safety risks and provides constraints for fan optimization control.

[0083] This application innovatively defines the energy consumption impact coefficient ECIF, comprehensively considers the correlation and importance of various fan operating parameters and energy consumption, screens out key parameters that have a significant impact on energy consumption through the ECIF threshold, and simplifies the fan energy consumption prediction model.

[0084] This application dynamically adjusts the weights of the two optimization goals of energy consumption and air quality according to the excess of energy costs and safety risks. When energy consumption or risks exceed the standard, the weight is increased accordingly to guide the optimization direction, reflecting the adaptability and economy of fan control.

[0085] This application takes minimizing energy consumption and maximizing comprehensive air quality as optimization goals, takes air volume, pressure, wind speed, gas concentration, etc. as constraints, constructs a multi-objective optimization model, and uses a multi-objective genetic algorithm to solve it. The optimal solution for the fan operating parameters can be obtained to achieve a balance between ventilation safety and energy saving. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] Figure 1 A flow chart of the adaptive mine fan mesh operation ventilation system optimization adjustment method provided in this application;

[0087] Figure 2 Functional module diagram of the adaptive mine fan mesh operation ventilation system optimization and adjustment device provided in this application;

[0088] Figure 3 A schematic diagram of the structure of an electronic device provided in this application;

[0089] Figure 4 It is a schematic diagram of the structure of a readable storage medium provided by this application. DETAILED DESCRIPTION

[0090] In order to better understand the present application, various aspects of the present application will be described in more detail with reference to the accompanying drawings. It should be understood that these detailed descriptions are only descriptions of exemplary embodiments of the present application and do not limit the scope of the present application in any way. Throughout the specification, the same reference numerals refer to the same elements. The expression "and / or" includes any and all combinations of one or more of the associated listed items.

[0091] In the accompanying drawings, the size, dimensions and shapes of the elements have been slightly adjusted for ease of illustration. The drawings are for illustration only and are not strictly drawn to scale. As used herein, the terms "substantially", "approximately" and similar terms are used as terms of approximation, not as terms of degree, and are intended to illustrate the inherent deviations in measurements or calculations that will be recognized by those of ordinary skill in the art. In addition, in this application, the order in which the steps are described does not necessarily represent the order in which these processes occur in actual operation, unless otherwise specified or can be derived from the context.

[0092] It should also be understood that expressions such as "including", "comprising", "having", "containing" and / or "comprising" are open rather than closed expressions in this specification, which indicate the presence of the stated features, elements and / or components, but do not exclude the presence of one or more other features, elements, components and / or combinations thereof. In addition, when expressions such as "at least one of..." appear after a list of listed features, they modify the entire list of features rather than just the individual elements in the list. In addition, when describing embodiments of the present application, "may" is used to mean "one or more embodiments of the present application". And, the term "exemplary" is intended to refer to an example or illustration.

[0093] Unless otherwise specified, all words (including engineering terms and scientific and technological terms) used in this article have the same meaning as those commonly understood by ordinary technicians in the field to which this application belongs. It should also be understood that, unless clearly stated in this application, words defined in common dictionaries should be interpreted as having the same meaning as their meaning in the context of the relevant technology, and should not be interpreted in an idealized or overly formal sense.

[0094] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0095] Example 1

[0096] like Figure 1 As shown, the adaptive mine fan mesh operation ventilation system optimization adjustment method provided by this application includes:

[0097] Step S100: collecting air quality parameters, fan operation parameters, environmental parameters, and the number of personnel and operation conditions in each ventilation area in the mine at historical times;

[0098] The air quality parameters refer to the physical or chemical index parameters related to the air quality in each ventilation area in the mine.

[0099] The operating parameters of the fan refer to the machine parameters when the fan is running.

[0100] The operating conditions refer to the work progress in each ventilation area within the mine, such as the progress of the project.

[0101] The specific method for collecting the air quality parameters, fan operation parameters, environmental parameters, and the number of personnel and operation conditions in each ventilation area in the mine at a historical time is as follows:

[0102] Step S110: Divide the mine into K ventilation areas according to the layout and ventilation requirements of the mine;

[0103] The ventilation area includes an air inlet and an air return outlet.

[0104] Step S120: deploying sensors in each ventilation area to collect air quality parameters and environmental parameters of each ventilation area, wherein the air quality parameters include gas concentration and dust concentration, and the environmental parameters include wind speed and pressure;

[0105] Step S130: Count the number of people in each ventilation area, monitor each fan, and collect its operating parameters, including: speed, power, and air volume;

[0106] Step S140: monitoring the working progress of each working surface to obtain the working status of each ventilation area;

[0107] Step S200: using the historical air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions to train the air prediction model, predict the air quality parameters inside the mine in the future, and calculate the comprehensive air quality;

[0108] The specific method of using the air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions in the historical time to train the air prediction model, predict the air quality parameters inside the mine in the future, and calculate the comprehensive air quality is:

[0109] Step S210: Select the LSTM model as the initial model, integrate the air quality parameters, environmental parameters, number of personnel in the ventilation area and operation conditions in the historical time according to the time series, and obtain the air quality parameter sequence {A 1 ,A 2 ,...,A b}、Environment parameter sequence {E 1 ,E 2 ,...,E b}、Sequence of number of personnel {P 1 ,P 2 ,...,P b} and the sequence of work situations {W 1 ,W 2 ,...,W b};

[0110] Step S220: Preset the sliding window length, sliding step length and prediction time step length, and use the sliding window method to obtain b training samples on the air quality parameter sequence, environmental parameter sequence, number of personnel sequence and operation situation sequence;

[0111] Step S230: using the air quality parameter sequence, environmental parameter sequence, number of personnel sequence and operation status sequence of the historical time of the sliding window length as input data, predicting the air quality parameters of the future time of the prediction time step as output data;

[0112] Step S240: using mean square loss as the loss function and using the Adam optimization algorithm to optimize the model parameters, with the value of the loss function between the real air quality parameter and the predicted air quality parameter being minimized as the training goal. When the loss function reaches convergence, the training is completed and the air prediction model is obtained.

[0113] Step S250: Obtain air quality parameter A i The jth parameter a j The maximum value a max and the minimum value a min , calculate the standardized parameters

[0114] Step S260: performing weighted averaging on the standardized parameters to construct a calculation formula for comprehensive air quality;

[0115] The calculation formula of the comprehensive air quality is: Among them, ω j is the weight of the jth standardized parameter, J is the total number of air quality parameters;

[0116] The weight of the normalization parameter ω j The setting is based on the weight of each parameter when it is actually used to assess air quality.

[0117] Step S300: Obtain the energy consumption of the fan in historical time, calculate the correlation coefficient between the operating parameters and the energy consumption, mine D key parameters from all the operating parameters according to the correlation coefficient, and use the key parameters to calculate the predicted energy consumption of the fan;

[0118] The specific method of obtaining the energy consumption of the fan in historical time, calculating the correlation coefficient between the operating parameters and the energy consumption, mining D key parameters from all the operating parameters according to the correlation coefficient, and using the key parameters to calculate the predicted energy consumption of the fan is:

[0119] Step S310: defining energy consumption impact coefficient ECIF;

[0120] The energy consumption impact coefficient is used to measure the impact of each operating parameter on the energy consumption of the fan, and the value range is [0, 1]. The larger the value, the greater the impact of the operating parameter on the energy consumption.

[0121] Step S320: Calculate the correlation coefficient between each operating parameter and the energy consumption of the fan;

[0122] The calculation formula of the correlation coefficient is: Among them, s c Indicates the cth operating parameter, nh c represents the energy consumption of the fan under the cth operating parameter, C represents the number of operating parameter categories, and represent the mean values ​​of operating parameters and energy consumption respectively;

[0123] The energy consumption of the fan under the cth operating parameter is obtained based on the statistics of the consumed electric energy.

[0124] PCC(s,nh) is the Pearson correlation coefficient between operating parameters and energy consumption, and its value range is [-1, 1]. The larger the absolute value of PCC(s,nh), the stronger the correlation.

[0125] Step S330: defining importance weight coefficients;

[0126] The importance weight coefficient is a coefficient used to judge the importance of each operating parameter, and is assigned according to the physical meaning of the operating parameter and engineering experience.

[0127] The constraints satisfied by the importance weight coefficient are: τ c ∈[0,1], where τ c represents the importance weight coefficient of the cth operating parameter;

[0128] Step S340: Calculate the energy consumption impact coefficient ECIF according to the correlation coefficient and the importance weight coefficient;

[0129] The calculation formula of the energy consumption impact coefficient ECIF is: c =|PCC c (s,nh)×τ c , where PCC c (s,nh) is the correlation coefficient between the cth operating parameter and energy consumption, ECIF c is the energy consumption influence coefficient of the cth operating parameter;

[0130] Step S350: Preset the energy consumption impact coefficient threshold pcc, and set the D operating parameters S corresponding to the energy consumption impact coefficients that are greater than or equal to the energy consumption impact coefficient threshold pcc to be equal to the energy consumption impact coefficient threshold pcc. 1 ,s 2 ,...,s D}As a key parameter, it is used to establish a mathematical model for calculating the predicted energy consumption of the fan;

[0131] Step S360: Calculating the predicted energy consumption of the fan using key parameters according to the mathematical model of the predicted energy consumption of the fan;

[0132] The calculation formula for the predicted energy consumption of the fan is: τ d Represents the importance weight coefficient of the dth key parameter, s d Indicates the dth key parameter;

[0133] Step S400: predicting the real-time comprehensive air quality according to the air prediction model, and calculating the safety risk value of the mine using the comprehensive air quality, environmental parameters, the number of personnel in the ventilation area and the operation conditions;

[0134] The safety risk value is an evaluation index for comprehensively assessing the safety value in a mine based on the air quality, environmental parameters, the number of personnel in the ventilation area, and the operating conditions in the mine.

[0135] The specific method of predicting the real-time comprehensive air quality according to the air prediction model and calculating the safety risk value of the mine by using the comprehensive air quality, environmental parameters, the number of personnel in the ventilation area and the working conditions is as follows:

[0136] Step S410: Collect the air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions at K time points in real time, and use the real-time air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions to predict the air quality parameters of the mine in the future time of the prediction time step, and calculate the real-time comprehensive air quality

[0137] Step S420: Calculate the personnel risk coefficient PRC according to the number of personnel and working conditions in the ventilation area;

[0138] The calculation formula of the personnel risk coefficient is: Among them, P k is the number of people collected for the kth time, W k is the operation status of the kth collection;

[0139] The value range of the personnel risk coefficient PRC is [0, 1], and the larger the value, the higher the personnel risk;

[0140] Step S430: Combine comprehensive air quality and personnel risk coefficient, and calculate the safety risk value SRV in the mine;

[0141] The calculation formula of the safety risk value is:

[0142] Step S500: preset an energy cost threshold and a safety risk threshold, calculate a weight adjustment value according to the predicted energy consumption and the safety risk value, and calculate the air quality target weight and the energy consumption target weight according to the target weight adjustment strategy and the weight adjustment value;

[0143] The energy cost threshold refers to the cost standard for energy consumption specified for each project, and is preset according to different projects and different conditions.

[0144] The specific method of calculating the air quality target weight and the energy consumption target weight according to the preset energy cost threshold and the safety risk threshold, and the weight adjustment value according to the target weight adjustment strategy and the weight adjustment value is as follows:

[0145] Step S510: Preset the energy cost threshold EC, obtain the current wind turbine operating parameters, and use the mathematical model of the wind turbine's predicted energy consumption to calculate the current wind turbine's predicted energy consumption NH. now , based on the energy cost threshold EC and the predicted energy consumption of the current wind turbine NH now The energy cost excess value ΔNH is calculated;

[0146] The energy cost excess value is calculated as follows: ΔNH = NH now -EC;

[0147] Step S520: Preset a security risk threshold SRV′, and calculate the difference between the security risk threshold and the security risk value to obtain a security risk difference ΔSRV;

[0148] The calculation formula of the safety risk difference is: ΔSRV=SRV-SRV′;

[0149] Step S530: constructing a target weight adjustment strategy for calculating weight adjustment values, wherein the weight adjustment values ​​include an air quality target weight adjustment value Δα and an energy consumption target weight adjustment value Δβ;

[0150] The function expression of the air quality target weight adjustment value is: Among them, α 1 A reference value representing the weight of the air quality target;

[0151] The function expression of the energy consumption target weight adjustment value is: Among them, β 1 Indicates the benchmark value of the energy consumption target weight;

[0152] Step S540: introducing the air inertia coefficient p and the energy consumption inertia coefficient q, smoothing the air quality target weight adjustment value Δα and the energy consumption target weight adjustment value Δβ to obtain smoothed weight adjustment values, wherein the weight adjustment values ​​include the air quality target weight adjustment value Δα′ and the energy consumption target weight adjustment value Δβ′;

[0153] The calculation formula of the smoothed air quality target weight adjustment value Δα′ is: Δα′=p×Δα+(1-p)×Δα;

[0154] The calculation formula of the smoothed energy consumption target weight adjustment value Δβ is: Δβ′=q×Δβ+(1-q)×Δβ;

[0155] Step S550: The smoothed air quality target weight adjustment value Δα′ and the energy consumption target weight adjustment value Δβ′ are normalized by a softmax method to calculate the air quality target weight α and the energy consumption target weight β;

[0156] The calculation formula of the air quality target weight α is:

[0157] The calculation formula of the energy consumption target weight β is:

[0158] Among them, α 0 and β 0 are the initial values ​​of the air quality target weight and the energy consumption target weight respectively;

[0159] Step S600: With the goal of minimizing predicted energy consumption and maximizing comprehensive air quality, an objective function and constraint conditions are constructed by combining air quality target weights and energy consumption target weights to obtain optimal operating parameters of the fan;

[0160] The specific method of minimizing predicted energy consumption and maximizing comprehensive air quality, combining air quality target weight and energy consumption target weight to construct objective function and constraint conditions, and obtaining the optimal operating parameters of the fan is as follows:

[0161] Step S610: define the decision variables as D key parameters of the wind turbine S = {s 1 ,s 2 ,...,s D}, the mathematical model of the predicted energy consumption of the fan is used as the energy consumption objective function fe(S), and the calculation formula of the comprehensive air quality is used as the air quality objective function fa(S);

[0162] Step S620: Calculate the maximum values ​​of the energy consumption objective function and the air quality objective function respectively, and use the predicted energy consumption and comprehensive air quality corresponding to the maximum values ​​as the negative ideal points fe(S)′ and fa(S)′ of the energy consumption objective function and the air quality objective function respectively;

[0163] The energy consumption is highest and the air quality is worst at the negative ideal point.

[0164] Step S630: Calculate the minimum values ​​of the energy consumption objective function and the air quality objective function respectively, and use the predicted energy consumption and comprehensive air quality corresponding to the minimum values ​​as the ideal points fe(S) of the energy consumption objective function and the air quality objective function respectively. * and fa(S) * ;

[0165] At the ideal point, energy consumption is lowest and air quality is best.

[0166] Step S640: obtaining a normalized objective function according to the ideal point and the negative ideal point, including an energy consumption objective function ge(S) and an air quality objective function ga(S);

[0167] The calculation formula of the normalized energy consumption objective function is:

[0168] The calculation formula of the normalized air quality objective function is:

[0169] Step S650: constructing a weighted comprehensive objective function according to the normalized objective function, the air quality objective weight α and the energy consumption objective weight β;

[0170] The functional expression of the weighted comprehensive objective function is: minf(S)=α×ga(S)+β×ge(S);

[0171] Step S660: setting constraints on the operating parameters of the fan according to the safety constraints of mine ventilation;

[0172] The constraints include: air volume balance constraint, pressure balance constraint, wind speed constraint, gas concentration constraint and equipment capacity constraint. The air volume balance constraint is expressed as The pressure balance constraint is expressed as ΣE yl = 0, the wind speed constraint is expressed as The gas concentration constraint is expressed as The key parameter capacity constraint is expressed as S∈[S min ,S max ],in, is the air volume, is the air volume, ∑E yl is the pressure E of each ventilation branch yl the sum of The wind speed E fs The minimum and maximum values ​​of is the gas concentration A ws The upper limit, S min , S max is the minimum and maximum value of the key parameter S;

[0173] Step S670: A multi-objective optimization model is constructed by weighted comprehensive objective functions and constraint conditions, and a multi-objective genetic algorithm is used to solve the multi-objective optimization model to obtain optimal operating parameters of the wind turbine.

[0174] The above steps construct a multi-objective optimization model, comprehensively consider the two objectives of fan energy consumption and comprehensive mine air quality, introduce a dynamic weight adjustment mechanism, and achieve coordinated optimization control of energy saving and safety of the ventilation system.

[0175] Example 2

[0176] like Figure 2 As shown, the adaptive mine fan mesh operation ventilation system optimization and adjustment device provided by this application includes:

[0177] The data collection and statistics module is used to collect the air quality parameters, fan operation parameters, environmental parameters, and the number of personnel and operation conditions in each ventilation area in the mine at a historical time;

[0178] The air quality prediction module is used to train the air prediction model using the historical air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions, predict the air quality parameters inside the mine in the future, and calculate the comprehensive air quality;

[0179] The predicted energy consumption calculation module is used to obtain the energy consumption of the fan in the historical time, calculate the correlation coefficient between the operating parameters and the energy consumption, mine D key parameters from all the operating parameters according to the correlation coefficient, and use the key parameters to calculate the predicted energy consumption of the fan;

[0180] Safety risk calculation module, used to predict the real-time comprehensive air quality according to the air prediction model, and calculate the safety risk value of the mine using the comprehensive air quality, environmental parameters, number of personnel in the ventilation area and operating conditions;

[0181] The weight dynamic adjustment module is used to preset energy cost thresholds and safety risk thresholds, calculate weight adjustment values ​​according to predicted energy consumption and safety risk values, and calculate air quality target weights and energy consumption target weights according to target weight adjustment strategies and weight adjustment values;

[0182] The target optimization constraint module is used to minimize the predicted energy consumption and maximize the comprehensive air quality. It combines the air quality target weight and the energy consumption target weight to construct the objective function and constraint conditions to obtain the optimal operating parameters of the fan.

[0183] Example 3

[0184] Figure 3 1 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present application. Figure 3As shown, according to another aspect of the present application, an electronic device is also provided. The electronic device may include one or more processors and one or more memories. The memories store computer readable codes, and when the computer readable codes are executed by one or more processors, the above-mentioned adaptive mine fan hanging network operation ventilation system optimization adjustment method can be executed.

[0185] The method or system according to the embodiment of the present application can also be used by Figure 3 The electronic device architecture shown in FIG. Figure 3 As shown, the electronic device may include a bus, one or more CPUs, a read-only memory (ROM), a random access memory (RAM), a communication port connected to a network, an input / output component, a hard disk, and the like. The storage device in the electronic device, such as a ROM or a hard disk, may store the adaptive mine fan mesh operation ventilation system optimization and adjustment method provided in the present application. The adaptive mine fan mesh operation ventilation system optimization and adjustment method may, for example, include: collecting air quality parameters, fan operating parameters, environmental parameters, and the number of personnel and operating conditions in each ventilation area in the mine at historical times; using the air quality parameters, environmental parameters, number of personnel and operating conditions in the ventilation area at historical times to train an air prediction model, predict the air quality parameters inside the mine at future times, and calculate the comprehensive air quality; obtain the energy consumption of the fan at historical times, calculate the correlation coefficient between the operating parameters and the energy consumption, and mine D key parameters from all operating parameters according to the correlation coefficient, and use the relevant The predicted energy consumption of the fan is obtained by calculating the key parameters; the real-time comprehensive air quality is predicted according to the air prediction model, and the safety risk value of the mine is calculated using the comprehensive air quality, environmental parameters, number of people in the ventilation area, and operating conditions; energy cost thresholds and safety risk thresholds are preset, and weight adjustment values ​​are calculated according to the predicted energy consumption and safety risk values; the air quality target weight and energy consumption target weight are calculated according to the target weight adjustment strategy and weight adjustment value; with the goal of minimizing the predicted energy consumption and maximizing the comprehensive air quality, the objective function and constraints are constructed in combination with the air quality target weight and the energy consumption target weight to obtain the optimal operating parameters of the fan. Furthermore, the electronic device may also include a user interface. Of course, Figure 3 The architecture shown is only exemplary and can be omitted according to actual needs when implementing different devices. Figure 3 One or more components of an electronic device are shown.

[0186] Example 4

[0187] Figure 4 Schematic diagram of a readable storage medium structure provided by an embodiment of the present application. Figure 4As shown, it is a readable storage medium according to an embodiment of the present application. Computer-readable instructions are stored on the computer-readable storage medium. When the computer-readable instructions are executed by the processor, the adaptive mine fan hanging network operation ventilation system optimization adjustment method according to the embodiment of the present application described with reference to the above figures can be executed. The storage medium includes, for example, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory (cache). Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0188] In addition, according to the implementation mode of the present application, the process described in the above reference flowchart can be implemented as a computer software program. For example, the present application provides a non-transitory machine-readable storage medium, which stores machine-readable instructions, and the machine-readable instructions can be executed by a processor to execute instructions corresponding to the method steps provided in the present application, such as: collecting air quality parameters, operating parameters of fans, environmental parameters, and the number of personnel and operating conditions in ventilation areas of each ventilation area in the mine at historical times; using the air quality parameters, environmental parameters, number of personnel and operating conditions in ventilation areas at historical times to train an air prediction model, predict the air quality parameters inside the mine at future times, and calculate the comprehensive air quality; obtain the energy consumption of fans at historical times, and calculate the correlation coefficient between operating parameters and energy consumption. number, mine D key parameters from all operating parameters according to the correlation coefficient, and use the key parameters to calculate the predicted energy consumption of the fan; predict the real-time comprehensive air quality according to the air prediction model, and use the comprehensive air quality, environmental parameters, the number of people in the ventilation area and the operating conditions to calculate the safety risk value of the mine; preset the energy cost threshold and the safety risk threshold, calculate the weight adjustment value according to the predicted energy consumption and the safety risk value, and calculate the air quality target weight and the energy consumption target weight according to the target weight adjustment strategy and the weight adjustment value; with the goal of minimizing the predicted energy consumption and maximizing the comprehensive air quality, the objective function and constraints are constructed in combination with the air quality target weight and the energy consumption target weight to obtain the optimal operating parameters of the fan. When the computer program is executed by the central processing unit (CPU), the above functions defined in the method of the present application are executed.

[0189] The methods, apparatuses, and devices of the present application may be implemented in many ways. For example, the methods, apparatuses, and devices of the present application may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of steps for the method is for illustration only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specified. In addition, in some embodiments, the present application may also be implemented as programs recorded in a recording medium, which include machine-readable instructions for implementing the method according to the present application. Therefore, the present application also covers recording media storing programs for executing the method according to the present application.

[0190] In addition, the parts of the above-mentioned technical solutions provided in the embodiments of the present application that are consistent with the implementation principles of the corresponding technical solutions in the prior art are not described in detail to avoid excessive redundancy.

[0191] The specific implementation modes as described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation mode of the present invention and is not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. Adaptive mine fan mesh operation ventilation system optimization adjustment method, characterized in that: include: Collect the air quality parameters, fan operation parameters, environmental parameters, and the number of personnel and working conditions in each ventilation area in the mine at a historical time; The air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions at historical times are used to train the air prediction model, predict the air quality parameters inside the mine at future times, and calculate the comprehensive air quality; Obtain the energy consumption of the fan in historical time, calculate the correlation coefficient between the operating parameters and the energy consumption, mine D key parameters from all the operating parameters according to the correlation coefficient, and use the key parameters to calculate the predicted energy consumption of the fan; Predict the real-time comprehensive air quality based on the air prediction model, and calculate the safety risk value of the mine using the comprehensive air quality, environmental parameters, number of personnel in the ventilation area and operating conditions; Preset energy cost thresholds and safety risk thresholds, calculate weight adjustment values ​​based on predicted energy consumption and safety risk values, and calculate air quality target weights and energy consumption target weights based on target weight adjustment strategies and weight adjustment values; With the goal of minimizing predicted energy consumption and maximizing comprehensive air quality, the objective function and constraint conditions are constructed by combining the air quality target weight and energy consumption target weight to obtain the optimal operating parameters of the fan; The specific method of predicting the real-time comprehensive air quality according to the air prediction model and calculating the safety risk value of the mine by using the comprehensive air quality, environmental parameters, the number of personnel in the ventilation area and the working conditions is as follows: Collect air quality parameters, environmental parameters, number of personnel in ventilation areas and working conditions at K time points in real time, and use the real-time air quality parameters, environmental parameters, number of personnel in ventilation areas and working conditions to predict the air quality parameters of the mine in the future time of the prediction time step, and calculate the real-time comprehensive air quality Calculate the personnel risk factor PRC based on the number of personnel and working conditions in the ventilation area; The calculation formula of the personnel risk coefficient is: Among them, P k is the number of people collected for the kth time, W k is the operation status of the kth collection; Combined with comprehensive air quality and personnel risk coefficient, and calculate the safety risk value SRV in the mine; The calculation formula of the safety risk value is:

2. The adaptive mine fan grid-operated ventilation system optimization and adjustment method according to claim 1 is characterized in that: The specific method for collecting the air quality parameters, fan operation parameters, environmental parameters, and the number of personnel and operation conditions in each ventilation area in the mine at a historical time is as follows: The mine will be divided into K ventilation zones according to the mine layout and ventilation requirements; Deploy sensors in each ventilation area to collect air quality parameters and environmental parameters in each ventilation area. The air quality parameters include gas concentration and dust concentration, and the environmental parameters include wind speed and pressure. Count the number of people in each ventilation area, monitor each fan, and collect its operating parameters, including speed, power, and air volume; Monitor the working progress of each working surface to obtain the operating status of each ventilation area.

3. The adaptive mine fan grid-operated ventilation system optimization and adjustment method according to claim 2 is characterized in that: The specific method of using the air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions in the historical time to train the air prediction model, predict the air quality parameters inside the mine in the future, and calculate the comprehensive air quality is: The LSTM model is selected as the initial model, and the air quality parameters, environmental parameters, number of personnel in the ventilation area, and operation conditions in the historical time are integrated according to the time series to obtain the air quality parameter sequence {A 1 ,A 2 ,...,A b }、Environment parameter sequence {E 1 ,E 2 ,...,E b }、Sequence of number of personnel {P 1 ,P 2 ,...,P b } and the sequence of work situations {W 1 ,W 2 ,...,W b }; The sliding window length, sliding step and prediction time step are preset, and b training samples are obtained on the air quality parameter sequence, environmental parameter sequence, number of personnel sequence and operation situation sequence using the sliding window method; The air quality parameter sequence, environmental parameter sequence, number of personnel sequence and operation status sequence of the historical time of the sliding window length are used as input data, and the air quality parameters of the future time of the prediction time step are predicted as output data; The mean square loss is used as the loss function, and the Adam optimization algorithm is used to optimize the model parameters. The training goal is to minimize the value of the loss function between the real air quality parameters and the predicted air quality parameters. When the loss function reaches convergence, the training is completed and the air prediction model is obtained. Get air quality parameter A i The jth parameter a j The maximum value a max and the minimum value a min , calculate the standardized parameters The standardized parameters are weighted averaged to construct a calculation formula for comprehensive air quality; The calculation formula of the comprehensive air quality is: Among them, ω j is the weight of the jth standardized parameter, and J is the total number of air quality parameters.

4. The adaptive mine fan grid-operated ventilation system optimization and adjustment method according to claim 3 is characterized in that: The specific method of obtaining the energy consumption of the fan in historical time, calculating the correlation coefficient between the operating parameters and the energy consumption, mining D key parameters from all the operating parameters according to the correlation coefficient, and using the key parameters to calculate the predicted energy consumption of the fan is: Define the energy consumption impact factor ECIF; Calculate the correlation coefficient between each operating parameter and the energy consumption of the fan; The calculation formula of the correlation coefficient is: Among them, s c Indicates the cth operating parameter, nh c represents the energy consumption of the fan under the cth operating parameter, C represents the number of operating parameter categories, and represent the mean values ​​of operating parameters and energy consumption respectively; Define importance weight coefficients; The constraints satisfied by the importance weight coefficient are: τ c ∈[0,1], where τ c represents the importance weight coefficient of the cth operating parameter; The energy consumption impact coefficient ECIF is calculated based on the correlation coefficient and importance weight coefficient; The calculation formula of the energy consumption impact coefficient ECIF is: c =|PCC c (s,nh)|×τ c , where PCC c (s,nh) is the correlation coefficient between the cth operating parameter and energy consumption, ECIF c is the energy consumption influence coefficient of the cth operating parameter; The energy consumption impact coefficient threshold pcc is preset, and the D operating parameters S corresponding to the energy consumption impact coefficients that are greater than or equal to the energy consumption impact coefficient threshold are set to {s1, s2, ..., s D }As a key parameter, it is used to establish a mathematical model for calculating the predicted energy consumption of the fan; According to the mathematical model of the predicted energy consumption of the fan, the predicted energy consumption of the fan is calculated using key parameters; The calculation formula for the predicted energy consumption of the fan is: τ d Represents the importance weight coefficient of the dth key parameter, s d Represents the dth key parameter.

5. The adaptive mine fan grid-operated ventilation system optimization and adjustment method according to claim 4 is characterized in that: The specific method of calculating the air quality target weight and the energy consumption target weight according to the preset energy cost threshold and the safety risk threshold, and the weight adjustment value according to the target weight adjustment strategy and the weight adjustment value is as follows: The energy cost threshold EC is preset, the operating parameters of the current fan are obtained, and the predicted energy consumption NH of the current fan is calculated using the mathematical model of the predicted energy consumption of the fan. now , based on the energy cost threshold EC and the predicted energy consumption of the current wind turbine NH now The energy cost excess value ΔNH is calculated; The energy cost excess value is calculated as follows: ΔNH = NH now -EC; A security risk threshold SRV′ is preset, and a security risk difference ΔSRV is obtained by performing a difference calculation between the security risk threshold and the security risk value; The calculation formula of the safety risk difference is: ΔSRV=SRV-SRV′; Constructing a target weight adjustment strategy for calculating weight adjustment values, wherein the weight adjustment values ​​include an air quality target weight adjustment value Δα and an energy consumption target weight adjustment value Δβ; The function expression of the air quality target weight adjustment value is: Among them, α1 represents the reference value of the air quality target weight; The function expression of the energy consumption target weight adjustment value is: Among them, β1 represents the baseline value of the energy consumption target weight; Introducing the air inertia coefficient p and the energy consumption inertia coefficient q, smoothing the air quality target weight adjustment value Δα and the energy consumption target weight adjustment value Δβ, and obtaining smoothed weight adjustment values, wherein the weight adjustment values ​​include the air quality target weight adjustment value Δα′ and the energy consumption target weight adjustment value Δβ′; The calculation formula of the smoothed air quality target weight adjustment value Δα′ is: Δα′=p×Δα+(1-p)×Δα; The calculation formula of the smoothed energy consumption target weight adjustment value Δβ is: Δβ′=q×Δβ+(1-q)×Δβ; The smoothed air quality target weight adjustment value Δα′ and energy consumption target weight adjustment value Δβ′ are normalized by softmax method to calculate the air quality target weight α and energy consumption target weight β; The calculation formula of the air quality target weight α is: The calculation formula of the energy consumption target weight β is: Among them, α0 and β0 are the initial values ​​of the air quality target weight and energy consumption target weight, respectively.

6. The adaptive mine fan grid-operated ventilation system optimization and adjustment method according to claim 5 is characterized in that: The specific method of minimizing predicted energy consumption and maximizing comprehensive air quality, combining air quality target weight and energy consumption target weight to construct objective function and constraint conditions, and obtaining the optimal operating parameters of the fan is as follows: Define the decision variables as D key parameters of the wind turbine S = {s1, s2, ..., s D }, the mathematical model of the predicted energy consumption of the fan is used as the energy consumption objective function fe(S), and the calculation formula of the comprehensive air quality is used as the air quality objective function fa(S); Calculate the maximum values ​​of the energy consumption objective function and the air quality objective function respectively, and use the predicted energy consumption and comprehensive air quality corresponding to the maximum values ​​as the negative ideal points fe(S)′ and fa(S)′ of the energy consumption objective function and the air quality objective function respectively; Calculate the minimum values ​​of the energy consumption objective function and the air quality objective function respectively, and take the predicted energy consumption and comprehensive air quality corresponding to the minimum values ​​as the ideal points fe(S) of the energy consumption objective function and the air quality objective function respectively. * and fa(S) * ; The normalized objective function is obtained according to the ideal point and the negative ideal point, including the energy consumption objective function ge(S) and the air quality objective function ga(S); According to the normalized objective function, the air quality target weight α and the energy consumption target weight β, a weighted comprehensive objective function is constructed; The functional expression of the weighted comprehensive objective function is: minf(S)=α×ga(S)+β×ge(S); According to the safety constraints of mine ventilation, set the constraints of fan operating parameters; The constraints include: air volume balance constraint, pressure balance constraint, wind speed constraint, gas concentration constraint and equipment capacity constraint. The air volume balance constraint is expressed as The pressure balance constraint is expressed as ∑E yl = 0, the wind speed constraint is expressed as The gas concentration constraint is expressed as The key parameter capacity constraint is expressed as S∈[S min ,S max ],in, is the air volume, is the air volume, ∑E yl is the pressure E of each ventilation branch yl the sum of The wind speed E fs The minimum and maximum values ​​of is the gas concentration A ws The upper limit, S min , S max is the minimum and maximum value of the key parameter S; The multi-objective optimization model is composed of weighted comprehensive objective function and constraint conditions. The multi-objective genetic algorithm is used to solve the multi-objective optimization model to obtain the optimal operating parameters of the wind turbine.

7. An adaptive mine fan mesh-operated ventilation system optimization and adjustment device, which realizes the adaptive mine fan mesh-operated ventilation system optimization and adjustment method as claimed in any one of claims 1 to 6, characterized in that: include: The data collection and statistics module is used to collect the air quality parameters, fan operation parameters, environmental parameters, and the number of personnel and operation conditions in each ventilation area in the mine at a historical time; The air quality prediction module is used to train the air prediction model using the historical air quality parameters, environmental parameters, number of personnel in the ventilation area and working conditions, predict the air quality parameters inside the mine in the future, and calculate the comprehensive air quality; The predicted energy consumption calculation module is used to obtain the energy consumption of the fan in the historical time, calculate the correlation coefficient between the operating parameters and the energy consumption, mine D key parameters from all the operating parameters according to the correlation coefficient, and use the key parameters to calculate the predicted energy consumption of the fan; Safety risk calculation module, used to predict the real-time comprehensive air quality according to the air prediction model, and calculate the safety risk value of the mine using the comprehensive air quality, environmental parameters, number of personnel in the ventilation area and operating conditions; The weight dynamic adjustment module is used to preset energy cost thresholds and safety risk thresholds, calculate weight adjustment values ​​according to predicted energy consumption and safety risk values, and calculate air quality target weights and energy consumption target weights according to target weight adjustment strategies and weight adjustment values; The target optimization constraint module is used to minimize the predicted energy consumption and maximize the comprehensive air quality. It combines the air quality target weight and the energy consumption target weight to construct the objective function and constraint conditions to obtain the optimal operating parameters of the fan.

8. An electronic device, characterized in that: It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the adaptive mine fan grid-operated ventilation system optimization and adjustment method as described in any one of claims 1 to 6 are implemented.

9. A readable storage medium, characterized in that: The readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor to execute the steps in the adaptive mine fan grid-operated ventilation system optimization and adjustment method as described in any one of claims 1 to 6.

Images