Mine integrated energy system operation optimization method and system considering equipment importance
By using a large-scale constrained multi-objective evolutionary algorithm and fuzzy decision-making method that takes into account the importance of equipment, the optimization problem of integrated energy systems in mines under large-scale decision space and complex constraints is solved, and efficient, economical and safe automated operation is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA UNIV OF MINING & TECH
- Filing Date
- 2026-04-10
- Publication Date
- 2026-07-10
AI Technical Summary
Under the conditions of large-scale decision space and complex constraints, traditional optimization methods are difficult to achieve efficient search in integrated energy systems for mines, resulting in slow convergence speed, poor solution quality, high computational cost, and intelligent optimization algorithms are prone to getting stuck in infeasible solution dilemmas, making it difficult to improve optimization results.
A large-scale constrained multi-objective evolutionary algorithm that considers the importance of equipment is adopted, combined with fuzzy decision-making methods. By establishing an operation optimization model for the integrated energy system of the mine, a competitive particle swarm optimization algorithm is used to generate a Pareto optimal solution set, and automated scheduling is achieved through multiple communication protocols.
With limited computing resources, a diverse set of Pareto optimal solutions is generated to optimize equipment operating costs and energy curtailment costs, improve scheduling efficiency and safety, and realize the automated operation of the mine's integrated energy system.
Smart Images
Figure CN122371329A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of mine energy system optimization technology, and in particular to a method and system for optimizing the operation of a comprehensive mine energy system that takes into account the importance of equipment. Background Technology
[0002] Integrated energy systems in mines represent a typical application of integrated energy systems in mining scenarios. They typically consist of multiple energy subsystems, including electricity, compressed air, ventilation, heating, energy storage, and renewable energy generation. Their operation is characterized by deep coupling of multiple energy sources, interweaving of multiple spatiotemporal scales, coexistence of multiple constraints, and significant uncertainties. With the continuous advancement of intelligent mine construction, integrated energy systems are playing an increasingly important role in ensuring safe production, reducing operational energy consumption, and improving energy utilization efficiency. However, due to the complex interactions between different energy devices and the diversity of their operating states, the optimization problem of this system is characterized by high-dimensional decision variables, nonlinear objective functions, and strong constraints. Traditional optimization methods often struggle to obtain high-quality solutions within acceptable computational costs.
[0003] Currently, intelligent optimization algorithms have become the mainstream method for solving the operational optimization problem of integrated energy systems. Although such methods have the ability to handle complex optimization problems to a certain extent, they still face the following challenges in the context of integrated energy systems in mines: On the one hand, integrated energy systems in mines typically contain multiple types of energy equipment, and each equipment needs to consider the operating status of multiple time periods, which causes the algorithm to face the problem of exponential expansion of the decision space during the search process. Existing methods are difficult to achieve efficient search, resulting in slow convergence speed. On the other hand, there are multiple types of constraints in the system, such as energy balance constraints, equipment safe operation constraints, conversion efficiency constraints, and output upper and lower bound constraints. Intelligent optimization algorithms are prone to getting stuck in the dilemma of difficulty in finding feasible solutions and an excessively high proportion of infeasible solutions during the solution process, which further restricts the improvement of optimization results. Summary of the Invention
[0004] The purpose of this invention is to provide a method and system for optimizing the operation of a mine integrated energy system that takes into account the importance of equipment, so as to overcome the problems of low search efficiency, poor solution quality and high computational cost in the existing technology when dealing with large-scale decision spaces and complex constraints, and to achieve efficient, economical and safe operation of the mine integrated energy system under limited computing resources.
[0005] To achieve the above objectives, the present invention provides a method for optimizing the operation of a mine integrated energy system that takes into account the importance of equipment, comprising the following steps: Step S1: Establish an operation optimization model for the integrated energy system of the mine, including determining the type of equipment to be optimized, collecting system operating parameters, and determining the optimization objectives and constraints. Step S2: Use a large-scale constrained multi-objective evolutionary algorithm that considers the importance of equipment to solve the operation optimization model of the integrated energy system in the mine, and obtain the Pareto optimal solution set; Step S3: Use fuzzy decision-making to select a compromise solution from the Pareto optimal solution set as the final scheduling scheme, and send the scheduling scheme to the corresponding equipment through multiple communication protocols to realize the automated operation of the mine's integrated energy system.
[0006] Preferably, step S1 specifically includes: Step S11: Determine the types and quantities of equipment participating in the scheduling of the integrated energy system of the mine, and set the scheduling cycle; Step S12: Collect and preprocess the data required to build the optimization model. The data includes equipment operating status, environmental information, load demand, energy price and historical performance parameters of the equipment, and unify all data to the time scale of the scheduling cycle. Step S13: Determine the optimization objectives, which include minimizing daily operating costs and minimizing system energy curtailment costs; Step S14: Determine the constraints that need to be satisfied; Step S15: Based on steps S11 to S14, construct an optimization model with equipment output as the decision variable, aiming to minimize daily operating costs and system energy curtailment costs, and satisfying the constraints.
[0007] Preferably, the daily operating costs are as follows: ; ; ; The system's energy curtailment costs are as follows: ; in, Indicates daily operating costs, Indicates the cost of energy purchase. Indicates operating and maintenance costs. express time, This indicates the total number of time periods divided within the scheduling cycle. express Electricity price at any time express The amount of electricity that the power grid needs to output at any given time. express Real-time natural gas prices express Real-time natural gas consumption. This indicates the total number of devices participating in the scheduling. Indicates the index of the device participating in the scheduling. Indicates the first The operation and maintenance costs of individual devices express Time of the first The output of each device Indicates the first Each device's energy curtailment penalty factor express Time of the first The maximum output of each device.
[0008] Preferably, the constraints include energy balance constraints, energy conversion constraints, equipment operation constraints, and cogeneration unit ramp-up constraints.
[0009] Preferably, step S2 specifically includes: Step S21: Sample each device variable uniformly within its value range, calculate the constraint violation degree of each sampled individual, and determine the importance of the device variable to the constraint based on the magnitude of the constraint violation degree of each device variable to different constraints. Step S22: Sort and group all equipment variables according to their importance to the constraints to obtain a group set; Step S23: Optimize using a competitive particle swarm optimization algorithm. During the optimization process, randomly select a subset of device variables from the group set according to probability for updating until the maximum number of evaluations is reached, and output the Pareto optimal solution set.
[0010] Preferably, in step S21, the importance index of the equipment variable to the constraint is determined as: the difference between the maximum and minimum values of the constraint violation caused by the equipment variable changing within its value range, while keeping other equipment variables unchanged.
[0011] Preferably, in step S22, all device variables are sorted non-dominated based on the cumulative importance value of each device variable to all constraints, and the device variables are divided into several groups according to the sorting results. The number of groups is preset according to the total dimension of the device variables.
[0012] Preferably, in step S23, the individual update strategy of the competitive particle swarm algorithm is as follows: individuals are selected from the winning population and the losing population respectively, the subset of device variables to be updated is determined according to the importance and random probability of the device variable subset, and an adaptive parameter is introduced to control the update probability of individuals in low-dimensional space and high-dimensional space. The adaptive parameter is dynamically adjusted according to the survival rate of individuals generated by low-dimensional update and high-dimensional update in the population.
[0013] Preferably, in step S3, a fuzzy decision-making method is used to select a compromise solution from the Pareto optimal solution set. Specifically, the membership function value of each solution is calculated, and the solution with the largest membership function value is taken as the final scheduling scheme. The final scheduling scheme is then distributed through multiple communication protocols. Specifically, the final scheduling scheme is distributed to the edge computing node through the MQTT protocol, and then distributed to the control systems of different devices through multiple industrial control protocols.
[0014] This invention also provides a mine integrated energy system operation optimization system that considers equipment importance, for executing the mine integrated energy system operation optimization method considering equipment importance as described above, including: The model building module is used to establish an operation optimization model for the integrated energy system of a mine, including determining the type of equipment to be optimized, collecting system operating parameters, and determining optimization objectives and constraints. The optimization solution module is used to solve the operation optimization model of the integrated energy system in the mine using a large-scale constrained multi-objective evolutionary algorithm that takes into account the importance of equipment, and obtain the Pareto optimal solution set; The decision execution module is used to select a compromise solution from the Pareto optimal solution set as the final scheduling scheme using fuzzy decision-making methods, and to send the scheduling scheme to the corresponding equipment through various communication protocols to realize the automated operation of the mine's integrated energy system.
[0015] Therefore, the present invention adopts the above-mentioned method and system for optimizing the operation of a comprehensive energy system in a mine, which takes into account the importance of equipment, and the beneficial technical effects are as follows: (1) The present invention simultaneously optimizes equipment operating costs and energy curtailment costs, generating a diverse set of Pareto optimal solutions, allowing users to flexibly choose the final scheduling scheme according to actual operating needs and preferences.
[0016] (2) The present invention uses a 24-hour scheduling cycle and takes into account multiple types of operating constraints. The generated scheduling scheme can determine the output plan of each equipment for the whole day at once, which significantly improves scheduling efficiency and ease of operation while ensuring the safe operation of the mine.
[0017] (3) The present invention introduces a fuzzy decision-making method to automatically select a compromise solution from the Pareto solution set and distribute the scheduling scheme to the corresponding equipment through multiple communication protocols, thereby realizing full-process automation of the operation optimization of the mine integrated energy system.
[0018] (4) The present invention can achieve efficient search in a large-scale decision space and quickly locate the feasible region under limited computing resources, effectively improving the solution feasibility and engineering applicability of the operation optimization problem of the integrated energy system in the mine. Attached Figure Description
[0019] Figure 1 Diagram of the operational architecture of a mine's integrated energy system; Figure 2 A schematic diagram of the operation optimization of a mine's integrated energy system, taking into account the importance of equipment; Figure 3 Flowchart of a large-scale constrained multi-objective algorithm that takes into account the importance of equipment; Figure 4 This is a schematic diagram of the final scheduling plan issuance process. Detailed Implementation
[0020] The technical solution of the present invention will be further described below with reference to the accompanying drawings and embodiments.
[0021] Unless otherwise defined, the technical or scientific terms used in this invention shall have the ordinary meaning as understood by one of ordinary skill in the art to which this invention pertains.
[0022] Example 1 This embodiment provides a method for optimizing the operation of a comprehensive energy system in a mine, taking into account the importance of equipment. The following is a combination of... Figures 1 to 4 The specific implementation process of this embodiment will be described in detail.
[0023] like Figure 1 The diagram shown is an operational architecture diagram of a mine's integrated energy system. The system mainly includes various energy production and conversion equipment such as fans, photovoltaic arrays, absorption chillers, electric chillers, waste air heat storage oxidation devices, heat pumps, batteries, and thermal storage devices.
[0024] like Figure 2 The diagram shows a flowchart of the mine integrated energy system operation optimization method that considers the importance of equipment according to the present invention. The specific steps are as follows: Step S1: Establish an optimization model for the operation of the integrated energy system in the mine.
[0025] Step S11: Determine the type and number of devices participating in the scheduling.
[0026] This embodiment first determines the types and quantities of energy equipment participating in the scheduling of the integrated energy system in the mine. For different types of equipment, a uniform hourly scheduling cycle is set, generating start / stop commands and continuous power adjustment schemes for each piece of equipment every hour. Specifically, wind turbines and photovoltaic equipment primarily adjust their output power; heat pump equipment determines its operating mode and output power based on heat / cold source conditions; and batteries and thermal storage equipment need to consider charge / discharge status, power, and capacity constraints. By uniformly modeling the operating status and controllable equipment variables of each piece of equipment, a complete decision variable space can be provided for subsequent optimized scheduling.
[0027] In this embodiment, eight device variables are considered at each time step, and their specific meanings are shown in Table 1: Table 1 The types of equipment to consider and their meanings
[0028] Step S12: Collect the data needed to build the model.
[0029] To construct an optimization model, this embodiment collects and preprocesses key data during the operation of the mine's integrated energy system. The required data includes the real-time operating status of each device (start / stop signals, power output), environmental information (wind speed, sunlight, temperature, humidity), load demand data (electricity load, cooling load, heating load), energy price information (electricity purchase price, gas price), and historical performance parameters of the equipment, as shown in Table 2. Table 2. Relevant parameters required for model construction
[0030] Because different devices have different sampling periods, the data needs to be standardized to the time step (1 hour) of the optimization model: for high-frequency data, such as photovoltaic and wind turbine data, which are usually sampled on a minute-by-minute basis, the average value is calculated and mapped to a 1-hour scale; for low-frequency data, such as load and meteorological data, linear interpolation is used to map them to a 1-hour scale. Simultaneously, missing data is imputed, and outlier data is identified and removed to effectively ensure the accuracy of the model and the reliability of the scheduling scheme.
[0031] Step S13: Determine the optimization objective.
[0032] This embodiment defines two optimization objectives as follows: 1) Keep daily operating costs as low as possible, specifically: ; ; ; in, Indicates daily operating costs, Indicates the cost of energy purchase. Indicates operating and maintenance costs. This indicates the total number of time periods divided within the scheduling cycle. This indicates the total number of devices participating in the scheduling.
[0033] 2) The system's energy curtailment cost should be kept as low as possible, specifically expressed as: ; in, This represents the cost of energy curtailment.
[0034] Step S14: Determine the constraints that need to be satisfied.
[0035] Based on the specific scenario of the integrated energy system in the mine, the following constraints need to be met: Energy balance constraints refer to the requirement that the supply and demand of electrical energy, thermal energy, and cold energy in a comprehensive energy system for mining must be balanced, as specifically expressed below: ; ; ; in, This represents the constraints of the electrical balance equation. This indicates the constraint of the thermal balance equation. This represents the constraint of the cold balance equation. , and They represent The electrical load, thermal load, and cooling load at any given time; , and These respectively represent oxidation heat pumps, water source heat pumps, and electric chillers in... Power required at any given moment; and Indicates in The heat generated by the cogeneration and the heat required by the absorption chiller.
[0036] The energy conversion constraints are specifically: ; ; ; ; in, This indicates the energy conversion constraint of combined heat and power generation. This indicates the energy conversion constraint of the oxidation heat pump. This indicates the energy conversion constraint of the water source heat pump. This indicates the energy conversion constraint of the electric chiller. This indicates the energy conversion constraint of the absorption chiller. express The amount of electricity required by a constant absorption chiller.
[0037] Equipment operation constraints refer to the requirement that the energy output of each piece of equipment must meet certain limits to ensure the safety and reliability of the system. The specific details are as follows: ; ; in, This represents the inequality constraint on the energy output of the device. This represents the inequality constraint on the power grid's energy output. and They represent The minimum and maximum output of the power grid at any given time.
[0038] Ramp-up constraints refer to the requirement that combined heat and power (CHP) systems, which use natural gas to efficiently generate electricity and heat, must ensure that the energy output equipment variations between adjacent time periods do not become excessive to guarantee system reliability and safety. A detailed description follows: ; in, This indicates the energy output inequality constraint of combined heat and power (CHP). and They represent Time and The amount of electricity required by CHP at any given time; and These represent the minimum and maximum differences in CHP outputs at adjacent times, respectively.
[0039] Step S15: Construct the final optimized model.
[0040] Taking into account the equipment variables, objectives, and constraints involved, a final optimization model is constructed. During the solution process, each device is treated as a decision variable. We need to constantly optimize the output of 8 devices, which means we need to optimize 8 device variables: For the remaining device variables Then, through energy conversion constraints To obtain this, for each time step, three energy balance constraints need to be satisfied. and CHP slope constraint For equipment operating constraints and power grid operation constraints During the optimization process, samples are directly sampled within the upper and lower bounds to satisfy the energy conversion constraints. The conditions have already been met during the solution of the remaining equipment variables, and do not need to be considered separately. Based on the above description, the optimization problem of the mine's integrated energy system operation can be modeled as a large-scale constrained multi-objective optimization problem, as detailed below: ; in, There are 8 device variables to be optimized at any given time, which need to satisfy 3 equality constraints and 1 inequality constraint. The total number of device variables to be optimized is... The number of constraints that need to be satisfied is (The inequality constraint is a time-dependent ramp constraint.) (Climbing constraints need not be met at any time).
[0041] Step S2: Solve the optimization model using a large-scale constrained multi-objective evolutionary algorithm that considers the importance of equipment.
[0042] This step uses a large-scale constrained multi-objective evolutionary algorithm that considers equipment importance to solve the established optimization model and obtain the Pareto optimal solution set. The algorithm optimization process is as follows: Figure 3 As shown. The specific process is as follows: Step S21: First, within the range of the device's maximum and minimum output, evenly divide each device variable to form... The variable pool, the th The variable pool corresponding to each device variable is: ,in Indicates the first Each device variable This indicates the total number of device variables (equal to the total number of variables in the variable pool). and Indicates the first The upper bound (maximum output of the device) and the lower bound (minimum output of the device) of each device variable. Indicates the first The device variable is evenly divided within its value range. One sampling point, The number of divisions (arbitrarily set) is indicated in this embodiment. =50. Next, determine the importance of each device variable to each constraint in turn. For the first... Each constraint is first determined from the variable pool of each device variable. A value is randomly selected from the data to form the initial individual. (Line 3). Specifically, it is expressed as follows: Where rand represents a number from 1 to 1. A random integer.
[0043] Then, use replace ,and Other device variables remain unchanged, forming a set containing The intermediate population of individuals Calculate using constraint functions The constraint violation degree of each individual, using The difference between the maximum and minimum constraint violation of an individual is used to represent the first constraint violation. The device variable for the first The importance of each constraint .
[0044] Step S22: Obtain the device importance of each device variable. Afterwards, based on Perform non-dominated sorting on equipment variables (by accumulation within the same Pareto front). (To rank), obtain the importance ranking of each device variable. Finally, the device variables were categorized based on their ranking. Group, among which This indicates the rounding up operation. Indicates the number of groups. In this embodiment... =192, =4. The specific grouping process is as follows: ,in Indicates the first The group corresponding to each device variable. After obtaining the group for each device variable, we can obtain the group for the first device variable. The set of device variables contained in the group: The final grouping results are expressed as follows: .
[0045] Step S23: First, divide the population into a winning population (WP) and a losing population (LP) based on their fitness values. Then, let the losing population learn from the winning population. The specific process is as follows: Select a winning individual from WP. Select a failure from the LP. Generate a random number between 0 and 1. ,if ( (representing the probability of an individual searching in a low-dimensional space), then from... Two elements are randomly selected from the data. and ( and All are 0- (random integers between), let the set of device variables to be searched be... (in (This represents a function that takes the minimum value). New individuals are generated using the following formula and added to the lower-dimensional child set. .
[0046] ; in Indicates the first Failed particles in the next iteration The corresponding number One velocity component ( It itself indicates the first Each device variable corresponds to a specific velocity component, so they need to be represented using the same letter. Indicates the first Failed particles in the next iteration The Each location component (same as above); Indicates the first Winning particle in the next iteration The One location component; and Represents a random number between 0 and 1; if Then let Similarly, new individuals are generated using the above formula and added to the high-dimensional child set. .
[0047] In the above process, This parameter needs to be adaptively adjusted based on the current population state. The specific process is as follows: First, merge the current population. Low-dimensional space offspring and higher-dimensional offspring The next generation of population is selected from the merged population based on fitness values. .calculate exist Survival rate and exist Survival rate Finally, based on the ratio of the two survival rates, the updated search probability is obtained: Iterate step S2 until the maximum number of evaluations is reached. Table 3 shows the final performance metrics of the proposed algorithm and four comparative algorithms. The last row represents the method proposed in this invention. Table 3. HV Indices for Different Algorithms
[0048] HV stands for Hypervolume Index, a performance metric that comprehensively evaluates the convergence and diversity of multi-objective algorithms. An algorithm with better convergence and diversity will have a larger HV index. In Table 3, since the POCEA algorithm could not find a feasible solution, the corresponding HV values are represented by NaN. Furthermore, the proposed method has the largest HV index (shown in bold in the last row), indicating that the proposed algorithm has the best overall performance.
[0049] Step S3: Use the fuzzy decision method to select a compromise solution from the solution set as the final scheduling scheme. The fuzzy decision method evaluates the satisfaction of the solution by calculating the membership function value of each solution. To select a satisfactory solution from the Pareto solution set, the satisfaction of each solution is first calculated, as follows: ; ; in, Indicates the current population individual in the [number]th [year]. The maximum value on each target; Indicates the current population individual in the [number]th [year]. Minimum value on each objective; Indicates the current population number The individual in the first Values on each target; Indicates the first The individual for the first Membership degree of each objective; Indicates the first Individual satisfaction; Indicates the number of objectives in the problem to be solved; Indicates the number of individuals in a population.
[0050] Will have the highest satisfaction Individual values are used as compromise solutions and applied to the scheduling scheme. The final scheduling scheme selected according to this method is shown in Table 4.
[0051] Table 4. Output of different equipment at 24 hours
[0052] As can be seen from Table 4, photovoltaic power generation... The output was 0, but from 7 to 18 o'clock, photovoltaic power generation increased, which is consistent with the pattern of photovoltaic power generation; from 8 to 18 o'clock, the output of the electric chiller... The output of the absorption chiller is close to 0. The increase is due to higher electricity prices during the corresponding period, leading to a reduction in the output of electric chillers to decrease overall energy purchase costs. In summary, through the complementarity of multiple energy sources, the input and output of multiple devices can jointly meet the constraints of electricity, cooling, and heat balance, minimizing operating costs and energy curtailment costs. Finally, the scheduling plan is distributed to specific devices to guide their operation according to different communication protocols. For example... Figure 4 The specific process is as follows: First, the scheduling plan is distributed to the edge computing nodes via the MQTT protocol. Then, the plan is distributed to the wind turbine control system using the OPC UA protocol; to the gas turbine control system using the CAN2.0B protocol; to the energy storage management control system using DNP3.0; and to the heat pump cluster control system using Modbus TCP. Each sub-control system adjusts its equipment output in a timely manner according to the specific scheduling plan received, achieving automatic and efficient operation of the mine's integrated energy system.
[0053] Example 2 A mine integrated energy system operation optimization system that considers the importance of equipment includes: The model building module is used to establish an operation optimization model for the integrated energy system of a mine, including determining the type of equipment to be optimized, collecting system operating parameters, and determining optimization objectives and constraints. The optimization solution module is used to solve the operation optimization model of the integrated energy system in the mine using a large-scale constrained multi-objective evolutionary algorithm that takes into account the importance of equipment, and obtain the Pareto optimal solution set; The decision execution module is used to select a compromise solution from the Pareto optimal solution set as the final scheduling scheme using fuzzy decision-making methods, and to send the scheduling scheme to the corresponding equipment through various communication protocols to realize the automated operation of the mine's integrated energy system.
[0054] It is worth noting that all contents not described in detail in this invention are existing technologies and are well known to those skilled in the art.
[0055] Therefore, the present invention adopts the above-mentioned mine integrated energy system operation optimization method and system that takes into account the importance of equipment, which can quickly obtain high-quality scheduling schemes under limited computing resources, effectively reduce system operating costs and energy waste costs, and improve the automation level and safety assurance capability of the mine integrated energy system.
[0056] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the technical solutions of the present invention, and these modifications or equivalent substitutions cannot cause the modified technical solutions to deviate from the spirit and scope of the technical solutions of the present invention.
Claims
1. A method for optimizing the operation of a mine's integrated energy system, considering the importance of equipment, characterized in that: Includes the following steps: Step S1: Establish an operation optimization model for the integrated energy system of the mine, including determining the type of equipment to be optimized, collecting system operating parameters, and determining the optimization objectives and constraints. Step S2: Use a large-scale constrained multi-objective evolutionary algorithm that considers the importance of equipment to solve the operation optimization model of the integrated energy system in the mine, and obtain the Pareto optimal solution set; Step S3: Use fuzzy decision-making to select a compromise solution from the Pareto optimal solution set as the final scheduling scheme, and send the scheduling scheme to the corresponding equipment through multiple communication protocols to realize the automated operation of the mine's integrated energy system.
2. The method for optimizing the operation of a mine integrated energy system considering equipment importance according to claim 1, characterized in that, Step S1 specifically includes: Step S11: Determine the types and quantities of equipment participating in the scheduling of the integrated energy system of the mine, and set the scheduling cycle; Step S12: Collect and preprocess the data required to build the optimization model. The data includes equipment operating status, environmental information, load demand, energy price and historical performance parameters of the equipment, and unify all data to the time scale of the scheduling cycle. Step S13: Determine the optimization objectives, which include minimizing daily operating costs and minimizing system energy curtailment costs; Step S14: Determine the constraints that need to be satisfied; Step S15: Based on steps S11 to S14, construct an optimization model with equipment output as the decision variable, aiming to minimize daily operating costs and system energy curtailment costs, and satisfying the constraints.
3. The method for optimizing the operation of a mine integrated energy system considering equipment importance according to claim 2, characterized in that, The daily operating costs are as follows: ； ； ； The system's energy curtailment costs are as follows: ； in, Indicates daily operating costs, Indicates the cost of energy purchase. Indicates operating and maintenance costs. express time, This indicates the total number of time periods divided within the scheduling cycle. express Electricity price at any time express The amount of electricity that the power grid needs to output at any given time. express Real-time natural gas prices express Real-time natural gas consumption. This indicates the total number of devices participating in the scheduling. Indicates the index of the device participating in the scheduling. Indicates the first The operation and maintenance costs of individual devices express Time of the first The output of each device Indicates the first Each device's energy curtailment penalty factor express Time of the first The maximum output of each device.
4. The method for optimizing the operation of a mine integrated energy system considering equipment importance according to claim 2, characterized in that, The constraints include energy balance constraints, energy conversion constraints, equipment operation constraints, and cogeneration unit ramp-up constraints.
5. The method for optimizing the operation of a mine integrated energy system considering equipment importance according to claim 2, characterized in that, Step S2 specifically includes: Step S21: Sample each device variable uniformly within its value range, calculate the constraint violation degree of each sampled individual, and determine the importance of the device variable to the constraint based on the magnitude of the constraint violation degree of each device variable to different constraints. Step S22: Sort and group all equipment variables according to their importance to the constraints to obtain a group set; Step S23: Optimize using a competitive particle swarm optimization algorithm. During the optimization process, randomly select a subset of device variables from the group set according to probability for updating until the maximum number of evaluations is reached, and output the Pareto optimal solution set.
6. The method for optimizing the operation of a mine integrated energy system considering equipment importance according to claim 3, characterized in that, In step S21, the importance index of the equipment variable to the constraint is determined as: the difference between the maximum and minimum values of the constraint violation caused by the equipment variable changing within its value range, while keeping other equipment variables unchanged.
7. The method for optimizing the operation of a mine integrated energy system considering equipment importance according to claim 3, characterized in that, In step S22, all device variables are sorted in a non-dominated manner based on the cumulative importance value of each device variable to all constraints. The device variables are then divided into several groups according to the sorting results, with the number of groups preset according to the total dimension of the device variables.
8. The method for optimizing the operation of a mine integrated energy system considering equipment importance according to claim 3, characterized in that, In step S23, the individual update strategy of the competitive particle swarm algorithm is as follows: individuals are selected from the winning population and the losing population respectively, the subset of device variables to be updated is determined according to the importance of the device variable subset and the random probability, and an adaptive parameter is introduced to control the update probability of individuals in low-dimensional space and high-dimensional space. The adaptive parameter is dynamically adjusted according to the survival rate of individuals generated by low-dimensional update and high-dimensional update in the population.
9. The method for optimizing the operation of a mine integrated energy system considering equipment importance according to claim 1, characterized in that, In step S3, a compromise solution is selected from the Pareto optimal solution set using a fuzzy decision-making method. Specifically, the membership function value of each solution is calculated, and the solution with the largest membership function value is taken as the final scheduling scheme. The final scheduling scheme is distributed through multiple communication protocols. Specifically, the final scheduling scheme is distributed to the edge computing node through the MQTT protocol, and then distributed to the control systems of different devices through multiple industrial control protocols.
10. A mine integrated energy system operation optimization system considering the importance of equipment, characterized in that: The method for optimizing the operation of a mine integrated energy system considering equipment importance as described in any one of claims 1-9 includes: The model building module is used to establish an operation optimization model for the integrated energy system of a mine, including determining the type of equipment to be optimized, collecting system operating parameters, and determining optimization objectives and constraints. The optimization solution module is used to solve the operation optimization model of the integrated energy system in the mine using a large-scale constrained multi-objective evolutionary algorithm that takes into account the importance of equipment, and obtain the Pareto optimal solution set; The decision execution module is used to select a compromise solution from the Pareto optimal solution set as the final scheduling scheme using fuzzy decision-making methods, and to send the scheduling scheme to the corresponding equipment through various communication protocols to realize the automated operation of the mine's integrated energy system.