Coal mine production energy prediction method of physical-information fusion neural network

Abstract

A method for predicting coal mine production energy using a physical-information fusion neural network includes the following steps: establishing a coupled prediction model of coal mining energy consumption, gas emission, and mine water inflow using a physical-information neural network; establishing an energy-material correlation model for the core links of coal mine production; and predicting the energy demand and output of the coal mine production energy system based on the coal mine production plan. This invention proposes a physical-information-driven coal mine energy prediction method with coordinated energy-material processes in the core links. This method enables flexible load adjustment based on actual operating conditions, promotes the deep transformation of mines towards green, low-carbon, and intelligent operations, and provides scientific model support for achieving precise scheduling of coal mine energy and improving production efficiency.

Description

Technical Field

[0001] This invention relates to a method for predicting coal mine production energy using a physical-information fusion neural network, belonging to the field of coal mine production energy consumption and capacity prediction technology. Background Technology

[0002] As coal mining moves towards deeper levels, the evolution of the underground environment exhibits significant nonlinearity and large time lag. Changes in mining intensity do not instantaneously affect underground gas emissions and mine water inflow; instead, they have a response delay that varies with production dynamics. This results in critical safety measures such as ventilation and drainage operating in a passive, delayed, and inefficient mode. Traditional empirical models or purely data-driven methods struggle to describe the complex physical evolution logic. Under fluctuating production plans, the inability to accurately predict future energy consumption trends leads to excessive redundancy in meeting safety boundaries, limiting the flexible load adjustment of the production system based on actual conditions and creating a significant contradiction between safety and energy consumption.

[0003] Meanwhile, due to the lack of a refined forecasting method covering the entire chain of production, energy consumption, and production capacity, waste heat recovery in mining areas often operates in an inefficient and passive manner, making it impossible to predict heat generation potential based on production plans. This not only leads to a significant waste of geothermal resources but also makes it difficult for mining energy systems to achieve proactive and coordinated optimization of electricity and heat coupling, thus hindering the in-depth development of mines towards green, low-carbon, and intelligent transformation. Summary of the Invention

[0004] The purpose of this invention is to provide a method for predicting coal mine production energy using a physical-information fusion neural network. This method can flexibly adjust the load according to actual working conditions, promote the deep development of mines towards green, low-carbon, and intelligent transformation, and provide scientific model support for achieving precise scheduling of coal mine energy and improving production energy efficiency.

[0005] To achieve the above objectives, the present invention provides a method for predicting coal mine production energy using a physical-information fusion neural network, comprising the following steps:

[0006] S1. A coupled prediction model for coal mining energy consumption, gas emission, and mine water inflow is established using a Physics-Informed Neural Network (PINN).

[0007] S2. Establish an energy-material correlation model for the core links of coal mine production;

[0008] S3. Based on the coal mine production plan, predict the energy demand and output of the coal mine production energy system.

[0009] Furthermore, the specific process of S1 is as follows:

[0010] S1.1 Obtain historical coal mining energy consumption, gas emission, and mine water inflow data, as well as mine geological parameters and mining progress information;

[0011] S1.2. A simplified first-order differential equation model is established to determine the relationship between coal mining energy consumption, gas emission, and mine water inflow:

[0012] ;

[0013] ;

[0014] In the formula, , These represent gas emission rate and water inflow rate, respectively, in meters. 3 / min、m 3 / h; for Energy consumption during coal mining at any given time, in kW; , These represent the gas emission and water inflow per unit time under the influence of coal mining, both in cubic meters (m³). 3 ; , These are the influence coefficients of gas emission per unit time and water inflow under the influence of coal mining, respectively. , These represent the baseline gas emission and water inflow per unit time under non-mining conditions, both in cubic meters (m³). 3 ; , These are the time lag coefficients for baseline gas emission and water inflow under non-mining conditions per unit time, respectively.

[0015] in:

[0016] ;

[0017] ;

[0018] In the formula, , These represent the gas discharge rate from the goaf and the gas discharge rate from adjacent layers per unit time, respectively, in cubic meters per second (m³). 3 1.355 is the conversion factor; Permeability coefficient, in m / h; The water level of the aquifer is in meters (m). This refers to the drawdown of the water level, expressed in meters (m). , These are the radius of influence and the equivalent radius, respectively, in meters.

[0019] S1.3 To address the impact of nonlinear dynamic changes in data on prediction results, a time-sliding window for coal mining energy consumption is established as follows:

[0020] ;

[0021] In the formula, It is a sliding window matrix; The length of the window;

[0022] S1.4. The residual function equation of PI-TDNN is established as follows:

[0023] ;

[0024] In the formula, , , , These are the total residual, data residual, physical residual, and data smoothing residual, respectively. , , These are the weighting coefficients for data residuals, physical residuals, and data smoothing residuals, respectively.

[0025] Wherein: the equation for the data residual function is:

[0026] ;

[0027] In the formula, Time scale; It is a 2-norm; , These are the predicted value and the actual value, respectively.

[0028] The process of establishing the physical residual function equation is as follows:

[0029] The physical residual operator for gas emission is:

[0030] ;

[0031] In the formula, For residual operators; This is the predicted amount of gas emission, in cubic meters (m³). 3 / min;

[0032] The physical residual operator for water inflow is:

[0033] ;

[0034] In the formula, Forecast water inflow, unit: m 3 / h;

[0035] The physical residual function equation is:

[0036] ;

[0037] The equation for the predictive smoothing loss function is:

[0038] ;

[0039] In the formula, Let be the expectation of the function.

[0040] Furthermore, the core coal mine production processes in S2 include coal mining, transportation, ventilation, drainage, and underground coal and water storage. The specific energy-matter correlation model is established as follows:

[0041] S2.1 Energy consumption model for coal mining:

[0042] ;

[0043] In the formula, Energy consumption per unit of coal cutting, expressed in kWh / t; for Coal volume mined at any given time, in m³ 3 / min; This is the coal volume-to-mass conversion factor, in t / m³. 3 ;60 is the time conversion factor; For the efficiency of the coal mining machine;

[0044]

[0045] In the formula, The extraction height is expressed in meters (m). For thickness measurements, the unit is meters (m). The velocity is measured at all times, in m / min.

[0046] S2.2 Energy consumption model in the transportation process:

[0047] ;

[0048] In the formula, unit of time The operating power of the belt conveyor, measured in kW; for Time-of-use capacity, in meters 3 / s; This is the overall drag coefficient, expressed in units of 1 / s; unit of time The conveyor speed is measured in m / s. This refers to the total length of the belt, in meters (m).

[0049] S2.3, Energy consumption model for ventilation:

[0050] ;

[0051] In the formula, In order to be in The operating power of the ventilation fan at all times, in kW; In order to be in The air intake volume of the ventilation fan at all times, in m³. 3 / h; The total air pressure of the fan is expressed in Pa. To improve the operating efficiency of the ventilation fan;

[0052] S2.4 Energy consumption model for drainage process:

[0053] ;

[0054] In the formula, for The operating power of the drainage pump at any given time, in kW; Specific gravity of the medium, in kg / m³ 3 ; This is the acceleration due to gravity, expressed in N / kg. for The flow rate of the drainage pump at any time is expressed in m³ / s. 3 / h; The pump head is measured in meters (m). To improve the operating efficiency of the drainage pump;

[0055] S2.5, Coal Storage Bunker Model:

[0056] ;

[0057] In the formula, for Coal storage capacity in the coal bunker at any given time, in cubic meters (m³). 3 ;

[0058] S2.6, Water Storage Tank Model:

[0059] ;

[0060] In the formula, for The water storage capacity of the water tank at any given time is expressed in cubic meters (m³). 3 ; for Inflow rate at any given time, in meters (m³) 3 / h.

[0061] Furthermore, the prediction process in S3 is as follows:

[0062] S3.1, Set the coal mine production plan as follows: the planned daily coal mining volume is... The planned transport volume is Ventilation requirements are that the underground gas concentration is below the safe upper limit, and planned drainage is... ;

[0063] S3.2 The energy demand forecast for the coal mine energy system is as follows:

[0064] S3.2-1, Energy requirements for coal mining are:

[0065] ;

[0066] In the formula, This represents the total daily energy consumption for coal mining, expressed in kWh.

[0067] S3.2-2, Energy requirements for the transportation process are:

[0068] ;

[0069] In the formula, This represents the total daily energy consumption for transportation, expressed in kWh; it must meet the following requirements:

[0070]

[0071] In the formula, This represents the daily coal storage capacity in the coal bunker, in meters (m³). 3 ; This represents the maximum coal storage capacity of the coal bunker, expressed in cubic meters (m³). 3 ;

[0072] S3.2-3, Energy requirements for ventilation:

[0073] ;

[0074] In the formula, This represents the total daily ventilation energy consumption, expressed in kWh; it must meet the following requirements:

[0075] ;

[0076] ;

[0077] In the formula, Air volume required, unit is m³ 3 / h; 1.1 is the air leakage coefficient; 60 is the unit conversion coefficient; 0.909 is the ventilation safety redundancy conversion coefficient; for The methane concentration in the mine at any given time; for Predicted gas emission at any given time, in cubic meters (m³). 3 / min; The upper limit of safe gas concentration;

[0078] S3.2-4, Energy requirements for drainage:

[0079] ;

[0080] In the formula, The total daily energy consumption for wastewater drainage is expressed in kWh; among which, the following conditions must be met:

[0081] ;

[0082] In the formula, for Predicted inflow volume in real time, in meters. 3 / h.

[0083] ;

[0084] In the formula, The remaining water volume in the reservoir the previous day, in cubic meters (m³). 3 ; This represents the maximum water storage capacity of the reservoir, expressed in cubic meters (m³). 3 ;

[0085] S3.2-5, The total energy demand of the energy system is:

[0086] ;

[0087] In the formula, This represents the total daily system energy consumption, expressed in kWh.

[0088] S3.3 The energy output forecast of the coal mine energy system is as follows:

[0089] S3.3-1, Direct heat exchange output of inrush water is:

[0090] ;

[0091] In the formula, This represents the total heat exchange capacity of the daily inflow, expressed in kWh. The density of the inflow water is expressed in kg / m³. 3 ; This refers to the specific heat capacity of the gushing water, in units of... ; The heat exchange temperature difference is expressed in °C; 3600 is the time conversion factor.

[0092] S3.3-2, the product of exhaust air passing through ethylene glycol heat exchange is:

[0093] ;

[0094] In the formula, This represents the total heat exchange capacity of exhaust air per day, expressed in kWh. Exhaust air density, unit: kg / m³ 3 ; For heat exchange efficiency; Enthalpy difference between inlet and outlet, in kJ / kg; 3600 is the time conversion factor;

[0095] S43-3, The total energy output of the energy system is:

[0096] ;

[0097] In the formula, This represents the total daily energy output, expressed in kWh.

[0098] This invention first establishes a coupled prediction model of coal mining energy consumption, gas emission, and mine water inflow using a physical information neural network, describing the nonlinear and time-delayed characteristics of material output under the influence of mining power. Then, it establishes an energy-material correlation model covering core aspects of mining, transportation, ventilation, and drainage. Finally, it sets a coal mine production plan and, based on the coupled prediction model and production constraints, uses a system model to predict the unified temporal energy demand and output of the coal mine energy system. The proposed physical information-driven coal mine energy prediction method, which coordinates energy and material output in core aspects, enables flexible load adjustments based on actual operating conditions, promotes the deep transformation of mines towards green, low-carbon, and intelligent development, and provides scientific model support for precise coal mine energy scheduling and improved production efficiency. Attached Figure Description

[0099] Figure 1 This is a flowchart of the present invention;

[0100] Figure 2 This is a diagram showing the PINN training and testing results in an embodiment of the present invention;

[0101] Figure 3 This is a schematic diagram illustrating the energy demand and output of a core coal mine process in an embodiment of the present invention. Detailed Implementation

[0102] The invention will now be further described with reference to the accompanying drawings.

[0103] like Figure 1 As shown, a method for predicting coal mine production energy using a physical-information fusion neural network includes the following steps:

[0104] S1. A coupled prediction model for coal mining energy consumption, gas emission, and mine water inflow is established using a Physics-Informed Neural Network (PINN).

[0105] S2. Establish an energy-material correlation model for the core links of coal mine production;

[0106] S3. Based on the coal mine production plan, predict the energy demand and output of the coal mine production energy system.

[0107] As a preferred embodiment, the specific process of S1 is as follows:

[0108] S1.1 Obtain historical coal mining energy consumption, gas emission, and mine water inflow data, as well as mine geological parameters and mining progress information;

[0109] S1.2. A simplified first-order differential equation model is established to determine the relationship between coal mining energy consumption, gas emission, and mine water inflow:

[0110] ;

[0111] ;

[0112] In the formula, , These represent gas emission rate and water inflow rate, respectively, in meters. 3 / min、m 3 / h; for Energy consumption during coal mining at any given time, in kW; , These represent the gas emission and water inflow per unit time under the influence of coal mining, both in cubic meters (m³). 3 ; , These are the influence coefficients of gas emission per unit time and water inflow under the influence of coal mining, respectively. , These represent the baseline gas emission and water inflow per unit time under non-mining conditions, both in cubic meters (m³). 3 ; , These are the time lag coefficients for baseline gas emission and water inflow under non-mining conditions per unit time, respectively.

[0113] in:

[0114] ;

[0115] ;

[0116] In the formula, , These represent the gas discharge rate from the goaf and the gas discharge rate from adjacent layers per unit time, respectively, in cubic meters per second (m³). 3 1.355 is the conversion factor; Permeability coefficient, in m / h; The water level of the aquifer is in meters (m). This refers to the drawdown of the water level, expressed in meters (m). , These are the radius of influence and the equivalent radius, respectively, in meters.

[0117] S1.3 To address the impact of nonlinear dynamic changes in data on prediction results, a time-sliding window for coal mining energy consumption is established as follows:

[0118] ;

[0119] In the formula, It is a sliding window matrix; The length of the window;

[0120] S1.4. The residual function equation of PI-TDNN is established as follows:

[0121] ;

[0122] In the formula, , , , These are the total residual, data residual, physical residual, and data smoothing residual, respectively. , , These are the weighting coefficients for data residuals, physical residuals, and data smoothing residuals, respectively.

[0123] Wherein: the equation for the data residual function is:

[0124] ;

[0125] In the formula, Time scale; It is a 2-norm; , These are the predicted value and the actual value, respectively.

[0126] The process of establishing the physical residual function equation is as follows:

[0127] The physical residual operator for gas emission is:

[0128] ;

[0129] In the formula, For residual operators; This is the predicted amount of gas emission, in cubic meters (m³). 3 / min;

[0130] The physical residual operator for water inflow is:

[0131] ;

[0132] In the formula, Forecast water inflow, unit: m 3 / h;

[0133] The physical residual function equation is:

[0134] ;

[0135] The equation for the predictive smoothing loss function is:

[0136] ;

[0137] In the formula, Let be the expectation of the function.

[0138] As a preferred implementation, the core coal mine production processes in S2 include coal mining, transportation, ventilation, drainage, and underground coal and water storage. The specific energy-matter correlation model is established as follows:

[0139] S2.1 Energy consumption model for coal mining:

[0140] ;

[0141] In the formula, Energy consumption per unit of coal cutting, expressed in kWh / t; for Coal volume mined at any given time, in m³ 3 / min; This is the coal volume-to-mass conversion factor, in t / m³. 3 ;60 is the time conversion factor; For the efficiency of the coal mining machine;

[0142]

[0143] In the formula, The extraction height is expressed in meters (m). For thickness measurements, the unit is meters (m). The velocity is measured at all times, in m / min.

[0144] S2.2 Energy consumption model in the transportation process:

[0145] ;

[0146] In the formula, unit of time The operating power of the belt conveyor, measured in kW; for Time-of-use capacity, in meters 3 / s; This is the overall drag coefficient, expressed in units of 1 / s; unit of time The conveyor speed is measured in m / s. This refers to the total length of the belt, in meters (m).

[0147] S2.3, Energy consumption model for ventilation:

[0148] ;

[0149] In the formula, In order to be in The operating power of the ventilation fan at all times, in kW; In order to be in The air intake volume of the ventilation fan at all times, in m³. 3 / h; The total air pressure of the fan is expressed in Pa. To improve the operating efficiency of the ventilation fan;

[0150] S2.4 Energy consumption model for drainage process:

[0151] ;

[0152] In the formula, for The operating power of the drainage pump at any given time, in kW; Specific gravity of the medium, in kg / m³ 3 ; This is the acceleration due to gravity, expressed in N / kg. for The flow rate of the drainage pump at any time is expressed in m³ / s. 3 / h; The pump head is measured in meters (m). To improve the operating efficiency of the drainage pump;

[0153] S2.5, Coal Storage Bunker Model:

[0154] ;

[0155] In the formula, for Coal storage capacity in the coal bunker at any given time, in cubic meters (m³). 3 ;

[0156] S2.6, Water Storage Tank Model:

[0157] ;

[0158] In the formula, for The water storage capacity of the water tank at any given time is expressed in cubic meters (m³). 3 ; for Inflow rate at any given time, in meters (m³) 3 / h.

[0159] As a preferred embodiment, the prediction process in S3 is as follows:

[0160] S3.1, Set the coal mine production plan as follows: the planned daily coal mining volume is... The planned transport volume is Ventilation requirements are that the underground gas concentration is below the safe upper limit, and planned drainage is... ;

[0161] S3.2 The energy demand forecast for the coal mine energy system is as follows:

[0162] S3.2-1, Energy requirements for coal mining are:

[0163] ;

[0164] In the formula, This represents the total daily energy consumption for coal mining, expressed in kWh.

[0165] S3.2-2, Energy requirements for the transportation process are:

[0166] ;

[0167] In the formula, This represents the total daily energy consumption for transportation, expressed in kWh; it must meet the following requirements:

[0168]

[0169] In the formula, This represents the daily coal storage capacity in the coal bunker, in meters (m³). 3 ; This represents the maximum coal storage capacity of the coal bunker, expressed in cubic meters (m³). 3 ;

[0170] S3.2-3, Energy requirements for ventilation:

[0171] ;

[0172] In the formula, This represents the total daily ventilation energy consumption, expressed in kWh; it must meet the following requirements:

[0173] ;

[0174] ;

[0175] In the formula, Air volume required, unit is m³ 3 / h; 1.1 is the air leakage coefficient; 60 is the unit conversion coefficient; 0.909 is the ventilation safety redundancy conversion coefficient; for The methane concentration in the mine at any given time; for Predicted gas emission at any given time, in cubic meters (m³). 3 / min; The upper limit of safe gas concentration;

[0176] S3.2-4, Energy requirements for drainage:

[0177] ;

[0178] In the formula, The total daily energy consumption for wastewater drainage is expressed in kWh; among which, the following conditions must be met:

[0179] ;

[0180] In the formula, for Predicted inflow volume in real time, in meters. 3 / h;

[0181] ;

[0182] In the formula, The remaining water volume in the reservoir the previous day, in cubic meters (m³). 3 ; This represents the maximum water storage capacity of the reservoir, expressed in cubic meters (m³). 3 ;

[0183] S3.2-5, The total energy demand of the energy system is:

[0184] ;

[0185] In the formula, This represents the total daily system energy consumption, expressed in kWh.

[0186] S3.3 The energy output forecast of the coal mine energy system is as follows:

[0187] S3.3-1, Direct heat exchange output of inrush water is:

[0188] ;

[0189] In the formula, This represents the total heat exchange capacity of the daily inflow, expressed in kWh. The density of the inflow water is expressed in kg / m³. 3 ; This refers to the specific heat capacity of the gushing water, in units of... ; The heat exchange temperature difference is expressed in °C; 3600 is the time conversion factor.

[0190] S3.3-2, the product of exhaust air passing through ethylene glycol heat exchange is:

[0191] ;

[0192] In the formula, This represents the total heat exchange capacity of exhaust air per day, expressed in kWh. Exhaust air density, unit: kg / m³ 3 ; For heat exchange efficiency; Enthalpy difference between inlet and outlet, in kJ / kg; 3600 is the time conversion factor;

[0193] S43-3, The total energy output of the energy system is:

[0194] ;

[0195] In the formula, This represents the total daily energy output, expressed in kWh.

[0196] Example: Using actual data from a coal mine in central and western China, after 2000 training iterations, the residual was less than 0.1, which yielded the following results: Figure 2 The PINN training test results are shown below. Assuming a daily production plan of 12,000 tons of coal, all of which is transported, an underground methane concentration below 0.7%, and all water inrushes are discharged on that day, the results are as follows: Figure 3 The data in (a) and (b) show the energy demand and output of the core processes in coal mines.

Claims

1. A method for predicting coal mine production energy using a physical-information fusion neural network, characterized in that, Includes the following steps: S1. A coupled prediction model of coal mining energy consumption power, gas emission, and mine water inflow is established by applying physical information neural networks. S2. Establish an energy-material correlation model for the core links of coal mine production; S3. Based on the coal mine production plan, predict the energy demand and output of the coal mine production energy system.

2. The coal mine production energy prediction method using a physical-information fusion neural network according to claim 1, characterized in that, The specific process of S1 is as follows: S1.1 Obtain historical coal mining energy consumption, gas emission, and mine water inflow data, as well as mine geological parameters and mining progress information; S1.

2. A simplified first-order differential equation model is established to determine the relationship between coal mining energy consumption, gas emission, and mine water inflow: ； ； In the formula, , These are the gas emission rate and the water inflow rate, respectively. for Energy consumption during coal mining at all times; , These represent the amount of gas emitted and the amount of water inflow per unit time under the influence of coal mining. , These are the influence coefficients of gas emission per unit time and water inflow under the influence of coal mining, respectively. , These are the baseline gas emission and water inflow per unit time under non-mining conditions, respectively. , These are the time lag coefficients for baseline gas emission and water inflow under non-mining conditions per unit time, respectively. in: ； ； In the formula, , These represent the gas discharge rate from the goaf and the gas discharge rate from adjacent layers per unit time, respectively; 1.355 is the conversion factor. Permeability coefficient; This refers to the water level height of the aquifer. To lower the water level; , These are the radius of influence and the equivalent radius, respectively. S1.3 To address the impact of nonlinear dynamic changes in data on prediction results, a time-sliding window for coal mining energy consumption is established as follows: ； In the formula, It is a sliding window matrix; The length of the window; S1.

4. The residual function equation of PI-TDNN is established as follows: ； In the formula, , , , These are the total residual, data residual, physical residual, and data smoothing residual, respectively. , , These are the weighting coefficients for data residuals, physical residuals, and data smoothing residuals, respectively. Wherein: the equation for the data residual function is: ； In the formula, Time scale; It is a norm 2; , These are the predicted value and the actual value, respectively. The process of establishing the physical residual function equation is as follows: The physical residual operator for gas emission is: ； In the formula, For residual operators; For the predicted amount of gas escape; The physical residual operator for water inflow is: ； In the formula, Forecast water inflow; The physical residual function equation is: ； The equation for the predictive smoothing loss function is: ； In the formula, Let be the expectation of the function.

3. The coal mine production energy prediction method using a physical-information fusion neural network according to claim 2, characterized in that, The core coal mine production processes in S2 include coal mining, transportation, ventilation, drainage, and underground coal and water storage. The specific energy-matter correlation model is established as follows: S2.1 Energy consumption model for coal mining: ； In the formula, Energy consumption per unit of coal cutting; for Coal volume at any given time; 60 is the coal volume-mass conversion factor; 60 is the time conversion factor. For the efficiency of the coal mining machine; In the formula, To raise the level; To obtain thicker materials; Real-time speed measurement; S2.2 Energy consumption model in the transportation process: ； In the formula, unit of time Belt conveyor operating power; for Time-of-use capacity; This is the overall drag coefficient; unit of time Belt conveyor speed; This is the total length of the belt; S2.3, Energy consumption model for ventilation: ； In the formula, In order to be in The operating power of the ventilation fan at all times; In order to be in The air intake volume of the ventilation fan at all times; The total air pressure of the fan; To improve the operating efficiency of the ventilation fan; S2.4 Energy consumption model for drainage process: ； In the formula, for Constant operating power of the drainage pump; Specific gravity of the medium; It is the acceleration due to gravity; for Constant flow rate of the drainage pump; For the head of the drainage pump; To improve the operating efficiency of the drainage pump; S2.5, Coal Storage Bunker Model: ； In the formula, for Coal storage capacity in the coal bunker at any given time; S2.6, Water Storage Tank Model: ； In the formula, for The water level in the reservoir at any given time; for Constant water flow rate.

4. The coal mine production energy prediction method using a physical-information fusion neural network according to claim 3, characterized in that, The prediction process in S3 is as follows: S3.1, Set the coal mine production plan as follows: the planned daily coal mining volume is... The planned transport volume is Ventilation requirements are that the underground gas concentration is below the safe upper limit, and planned drainage is... ; S3.2 The energy demand forecast for the coal mine energy system is as follows: S3.2-1, Energy requirements for coal mining: ； In the formula, This represents the total energy consumption for daily coal mining. S3.2-2, Energy requirements for the transportation process are: ； In the formula, The total daily energy consumption for transportation; among which, the following conditions must be met: In the formula, This represents the amount of coal stored in the coal storage bunker on that day. This represents the maximum coal storage capacity of the coal storage bunker. S3.2-3, Energy requirements for ventilation: ； In the formula, This represents the total daily energy consumption for ventilation; among which, the following conditions must be met: ； ； In the formula, 1.1 is the required air volume; 60 is the leakage coefficient; 0.909 is the ventilation safety redundancy conversion coefficient. for The methane concentration in the mine at any given time; for Predicted amount of gas escape at any given time; The upper limit of safe gas concentration; S3.2-4, Energy requirements for drainage: ； In the formula, The total daily energy consumption for drainage; where the following condition must be met: ； In the formula, for Real-time water inflow prediction; ； In the formula, This represents the remaining water level in the reservoir from the previous day. This represents the maximum water storage capacity of the reservoir. S3.2-5, The total energy demand of the energy system is: ； In the formula, This represents the total daily energy consumption of the system. S3.3 The energy output forecast of the coal mine energy system is as follows: S3.3-1, Direct heat exchange output of inrush water is: ； In the formula, This represents the total heat exchange capacity of the daily inflow. The density of the gushing water; The specific heat capacity of the gushing water; 3600 represents the heat exchange temperature difference; 3600 represents the time conversion factor. S3.3-2, the product of exhaust air passing through ethylene glycol heat exchange is: ； In the formula, This represents the total heat exchange capacity of the exhaust air per day. The density of the wind is low; For heat exchange efficiency; 3600 represents the enthalpy difference between import and export; 3600 is the time conversion factor. S43-3, The total energy output of the energy system is: ； In the formula, This represents the total daily energy output.

Images