Plant-level multi-unit load optimization distribution and control method based on unit characteristic differences

Abstract

The present invention discloses a plant-level multi-unit load optimization distribution method based on unit characteristic differences, including: establishing a plant-level digital twin model containing a gas generation system, a gas storage system, and a gas energy supply system; establishing a gas output prediction model for the gas generation system to obtain a gas output prediction value in each time period, and analyzing it with the total gas consumption of the gas energy system in each time period and the gas storage and discharge volume of the gas storage system to determine the total gas volume of the gas energy system in each time period; conducting simulation experimental analysis based on the plant-level digital twin model, establishing a load performance characteristic model of each boiler and steam turbine, and obtaining the performance index difference of each gas generator unit under each gas consumption volume; establishing an upper-layer gas generator unit gas volume optimization distribution model to optimize the distribution of the total gas volume to each gas generator unit; establishing a lower-layer gas production-storage-discharge optimization model to optimize the control of the gas generation system and the gas storage system.

Description

Technical Field

[0001] The present invention belongs to the technical field of intelligent scheduling of gas generator sets, and in particular relates to a plant-level multi-unit load optimization distribution and control method based on unit characteristic differences. Background Art

[0002] At present, in order to cope with possible emergencies and save electricity purchase costs, large-scale steel mills, chemical plants and other high-energy-consuming enterprises will generally add equipment such as generators, and use resources such as coal gas generated during the production process to generate electricity and heat to meet the electricity and heat needs within the factory. This can reduce waste while effectively alleviating the energy burden within the factory.

[0003] However, the gas supply in the plant is closely integrated with the production process, and the total gas demand of all units is related to the electricity and heat demand in the plant. This will lead to an imbalance between the supply and demand of gas. Sometimes it is necessary to purchase some electricity from the grid. In addition, the performance differences of each unit are also different, resulting in different power generation and heat production indicators of the units. How to use the gas supplied in the plant to meet the electricity and heat demand, consider the performance differences of each unit, optimize the gas allocation to each unit, optimize the supply and demand of gas, reduce the electricity purchase cost and improve the economic benefits of the entire plant are issues that need to be addressed urgently.

[0004] Based on the above technical problems, it is necessary to design a new plant-level multi-unit load optimization distribution and control method based on the differences in unit characteristics. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to overcome the shortcomings of the existing technology and provide a plant-level multi-unit load optimization distribution and control method based on the differences in unit characteristics, which can take into account the performance differences of each unit and the supply and demand of gas volume, establish an upper-level gas generator unit gas volume optimization distribution model and a lower-level gas production-storage and release optimization model, and can optimize the total gas volume distribution to each gas generator unit and obtain the gas volume adjustment strategy and gas storage and release strategy of the gas production equipment through interactive iterative solutions of the upper and lower models, effectively utilize the gas generated in the plant for power generation and heat supply, save plant-level energy costs, achieve supply and demand balance and maximize plant-level benefits.

[0006] In order to solve the above technical problems, the technical solution of the present invention is:

[0007] The present invention provides a plant-level multi-unit load optimization distribution and control method based on unit characteristic differences, which includes:

[0008] S1. Establish a plant-level digital twin model that includes a gas generation system, a gas storage system, and a gas energy supply system. The gas energy supply system includes multiple gas generator sets. Each gas generator set consists of a boiler and a steam turbine. The generator sets use gas as input, feed part of the steam produced by the boiler into the steam turbine to generate power, and extract part of the steam from the steam turbine to meet heat demand.

[0009] S2. Establish a plant-level electricity and heat load demand forecasting model to obtain the electricity and heat load demand combinations for each time period. Establish a relationship model between the total power generation steam flow, total extraction steam heat flow, and the electricity and heat load demand combinations for the gas energy supply system to obtain the total values ​​of the power generation steam flow and extraction steam heat flow required to be output by the gas energy supply system for each time period.

[0010] S3. Based on the total value of the required power generation steam flow rate and the extraction steam heating flow rate in each time period, combined with historical operating data, a total gas consumption prediction model is established to obtain the total gas consumption of the gas energy system in each time period; a gas output prediction model of the gas generation system is also established to obtain the predicted gas output value of the gas generation system in each time period. The predicted gas output value of the gas generation system in each time period is then comprehensively analyzed with the total gas consumption of the gas energy system in each time period and the gas storage and release capacity of the gas storage system to determine the total gas volume of the gas energy system in each time period;

[0011] S4. Conduct simulation experiments and analysis based on the plant-level digital twin model to establish load performance characteristic models for each boiler and steam turbine, and obtain performance indicator differences for each gas-fired power generation unit at various gas consumption rates.

[0012] S5. Optimizing the operating economy of all gas-fired power generation units, minimizing the gas consumption rate for steam production, and minimizing the gas consumption rate for power generation and heating, and based on the performance differences of each gas-fired power generation unit at various gas consumption rates, establish a gas volume optimization allocation model for the upper-layer gas-fired power generation units. This model optimally allocates the total gas volume of the gas energy system at each time period to each gas-fired power generation unit.

[0013] S6. With the goal of minimizing the gas production cost and storage and release cost, a lower-layer gas production-storage and release optimization model is established to optimize the control of the gas generation system and the gas storage system, and obtain the gas volume adjustment strategy and gas storage and release strategy of the gas production equipment.

[0014] Furthermore, in S1, a plant-level digital twin model including the gas generation system, gas storage system, and gas energy supply system is established, including:

[0015] Identify the physical entities within the plant, including the gas generation system, gas storage system, and gas energy supply system;

[0016] Establish the geometric model, physical model, behavioral model and rule model of the physical entities in the factory, and after integrating the models, build a virtual entity mechanism model that is highly consistent with the actual physical entities in the factory;

[0017] Taking the virtual entity mechanism model as the main body, the residual of the virtual entity mechanism model is calculated using historical data. The input of the virtual entity mechanism model and the model residual results are preprocessed and used as the input and output of the machine learning network respectively. After training and learning, a digital twin data-driven model is obtained, and the residual of the virtual entity mechanism model is compensated and corrected;

[0018] The revised virtual entity mechanism model and the digital twin data-driven model are integrated to establish a factory-level digital twin model.

[0019] Furthermore, in S2, a relationship model is established between the total power generation steam flow, the total extraction steam heating flow, and the combination of the power load and the heat load demand of the gas energy supply system, including:

[0020] Obtain historical operating data under plant-level supply and demand balance operating conditions, including the historical total power generation steam flow, total extraction steam heating flow, historical electrical load, thermal load, and the power generation steam flow, power generation power, exhaust steam pressure, exhaust steam temperature, turbine thermal efficiency, thermal power, equivalent enthalpy drop, heating extraction steam flow, heating extraction steam pressure, and heating extraction steam temperature of the gas energy supply system;

[0021] A feature extraction algorithm is used to extract features from historical operating data, and key operating data that affects power generation steam flow and extraction steam heating flow are selected;

[0022] The historical operation data fitting method is used to establish the relationship model between the total power generation steam flow, total extraction steam heating flow, and the combination of electric load and heat load demand required by the gas energy supply system, which is expressed as follows:

[0023] (m g,t ,m h,t )=g(P e,t ,Q h,t ,E t );

[0024] m g,t is the total steam flow rate for power generation during period t; m h,t is the total extraction steam heating flow rate during period t; P e,t is the electric load demand during period t; Q h,t is the heat load demand during period t; E t is the key operating data that affects the steam flow rate for power generation and the steam extraction flow rate for heating; g( ) is the power generation and heating characteristic equation of the gas energy supply system.

[0025] Furthermore, the S3 includes:

[0026] Obtain historical operating data for each boiler and steam turbine, including the gas consumption, steam production, steam parameters, flue gas parameters, combustion efficiency of each boiler, and the steam inlet flow, pressure, temperature, output power generation steam flow, extraction steam heating flow of each steam turbine, as well as the total gas consumption of the gas energy supply system and the total output power generation steam flow and extraction steam heating flow of the system;

[0027] Based on the historical operating data of each boiler and steam turbine, a machine learning algorithm is used to train and learn the total gas consumption prediction model of the gas energy supply system;

[0028] The total value of the required output steam flow for power generation and steam extraction for heating in each time period is input into the established total gas consumption prediction model of the gas energy supply system to obtain the total gas consumption of the gas energy supply system in each time period;

[0029] Obtain historical operating data of the gas generation system, establish a gas volume prediction model for the gas generation system, describe the relationship between gas production and related equipment operating parameters, and then obtain the predicted gas volume output value of the gas generation system in each future period;

[0030] When the predicted gas output of the gas generation system in each future period is greater than the total gas consumption of the gas energy system, it indicates that the gas output exceeds the demand. The excess gas will be stored in the gas storage system to ensure that the total gas output of the gas energy system in each period is equal to the total gas consumption. Alternatively, the excess electricity produced will be sold online to ensure that the total gas output of the gas energy system in each period is equal to the predicted gas output.

[0031] When the predicted gas output of the gas generation system in each future period is less than the total gas consumption of the gas supply system, it indicates that the gas output is less than the demand. The gas stored in the gas storage system is released to ensure that the total gas volume of the gas supply system in each period is equal to the predicted gas output value plus the released gas volume, or the total gas consumption is reduced by purchasing electricity online to ensure that the total gas volume of the gas supply system in each period is equal to the predicted gas output value.

[0032] Further, the S4 includes:

[0033] Set boiler load performance indicators, including boiler efficiency, gas consumption rate, boiler steam parameters, boiler load adjustment range, boiler load adjustment speed, and boiler heat loss;

[0034] Set turbine load performance indicators, including steam consumption rate, power generation efficiency, heating efficiency, heating steam extraction capacity, turbine load adjustment range, turbine load adjustment flexibility, and overload capacity;

[0035] Calculate the weight of each load performance index of boiler and steam turbine that affects load optimization distribution;

[0036] A simulation experiment was conducted based on the plant-level digital twin model. The same gas consumption volume was set as the input condition of the experiment. At the same time, the consistency of gas quality, pressure, and temperature parameters was taken into consideration. The boilers and steam turbines were compared under the same external conditions. The operating data of each boiler and steam turbine were recorded, and the load performance indicators of each boiler and steam turbine were calculated. Combined with the calculated weights of each load performance indicator, the differences in the load performance indicators of each boiler and steam turbine under the same gas consumption volume were evaluated and analyzed.

[0037] Furthermore, the weight calculation method includes subjective weighting method, objective weighting method and combined weighting method.

[0038] Furthermore, in S5, a gas quantity optimization distribution model for the upper gas power generation unit is established, including:

[0039] Based on the performance index differences of each gas generating unit under different gas consumption, the total gas volume of the gas energy supply system in each period is defined as Z coalgas_all,t , assume that n gas generating units have a preliminary gas volume distribution result in each period, which is defined as (S coalgas_x1,t ,S coalgas_x2,t ,…,S coalgas_xn,t );

[0040] The goal is to optimize the operating economy of all gas-fired generator sets, minimize the gas consumption rate for steam production, and minimize the steam consumption rate for power generation and heating, which can be expressed as:

[0041]

[0042] P e,i,t is the power generation of the i-th gas generator set in period t, is the self-used power generation; e P is the price of electricity purchased; c,i,t is the on-grid power of the i-th gas generator set in period t; c Q is the electricity price during the grid connection phase; h,i,t is the heat production of the i-th gas generator set in period t, is the self-use heat production; h P is the price of heat purchased; f,buy,t is the amount of electricity purchased to meet the peak power load during period t; η f is the electricity purchase price; Z coalgas_all,t is the total gas consumption of the gas energy supply system; μ coalgas To absorb the gas price; S coalgas_xi,t D is the amount of gas consumed by the i-th gas generating unit during period t; i,t is the steam production of the i-th gas generator set during period t; Me,i,t is the steam inlet flow rate of the i-th gas generator set during period t; M h,i,t is the heating extraction steam flow of the i-th gas generator set during period t;

[0043] Set the operating constraints of the gas-fired power generation unit, including: turbine capacity constraints, extraction steam flow constraints, exhaust steam flow constraints, thermal load constraints, electrical load constraints, boiler capacity constraints, steam production constraints, and gas consumption constraints;

[0044] Based on the goals of optimal operating economy, minimum gas consumption rate for steam production, and minimum steam consumption rate for power generation and heating of all gas-fired power generation units, and combined with the operating constraints of the gas-fired power generation units, an optimal gas allocation model for the upper-level gas-fired power generation units is established.

[0045] Further, the S6 includes:

[0046] With the goal of minimizing the gas production cost and storage and discharge cost, a lower-layer gas production-storage-discharge optimization model is established, which can be expressed as:

[0047]

[0048] C s,t 、C x,t are the production and operation cost of the gas generation system and the gas storage and release cost of the gas storage system during period t respectively;

[0049] Solve the lower-layer gas production-storage-release optimization model to obtain the gas volume adjustment strategy and gas storage-release strategy of the gas production equipment.

[0050] Furthermore, the constraints of the lower-layer gas production-storage-release optimization model include: gas supply and demand balance constraints, gas generation system equipment production capacity constraints, and gas storage system equipment capacity constraints.

[0051] Furthermore, the upper-layer gas power generation unit gas quantity optimization distribution model and the lower-layer gas production-storage-release optimization model are solved by using an algorithm that combines a genetic algorithm and a simulated annealing algorithm.

[0052] The beneficial effects of the present invention are:

[0053] (1) By establishing a plant-level digital twin model containing a gas generation system, a gas storage system, and a gas energy supply system, the present invention can virtually map the gas generation, storage, and usage conditions in the actual plant through digital twin technology, allowing for intuitive visualization of the operating status of each plant-level device. Furthermore, simulation analysis can be used to preview various strategic plans, facilitating subsequent optimization and control of each device.

[0054] (2) The present invention can obtain the total value of the power generation steam flow and the extraction steam heat flow required by the gas energy supply system in each time period based on the power load and heat load requirements, and then the total gas consumption required at the input end of the gas energy supply system in each time period. The total gas consumption required at the input end of the gas energy supply system can be reversely calculated from the load demand within the plant, facilitating subsequent gas supply and demand balancing scheduling;

[0055] (3) The present invention can effectively analyze the predicted gas output value of the gas generation system and the total gas consumption of the gas energy supply system, and can achieve a balance between gas supply and demand by combining the gas storage and release of the gas storage system, and ultimately determine the total gas volume of the gas energy supply system at each time period;

[0056] (4) The present invention establishes a load performance characteristic model for each boiler and steam turbine to obtain the performance index differences of each gas-fired power generation unit under different gas consumption rates. This facilitates the subsequent allocation of gas to each unit, focusing on the gas volume for the generator set with good performance, thereby producing more electricity and heat, while the other units operate in auxiliary mode.

[0057] (5) The present invention establishes an upper-layer gas generation unit gas quantity optimization allocation model and a lower-layer gas production-storage-release optimization model. Through interactive iterative solutions of the upper and lower models, the total gas quantity can be optimally allocated to each gas generation unit and the gas quantity adjustment strategy and gas storage-release strategy of the gas production equipment can be obtained. The gas generated in the plant can be effectively utilized for power generation and heat supply, saving plant-level energy costs, achieving supply and demand balance and maximizing plant-level benefits.

[0058] Other features and advantages will be described in the following description, and in part will become apparent from the description, or understood by practicing the invention. The purpose and other advantages of the invention are realized and obtained by the structures particularly pointed out in the description and the drawings.

[0059] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0061] Figure 1 This is a flow chart of a plant-level multi-unit load optimization distribution and control method based on unit characteristic differences according to the present invention;

[0062] Figure 2 This is a schematic diagram of the plant-level multi-unit load optimization distribution and control structure of the present invention. DETAILED DESCRIPTION

[0063] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0064] Example 1

[0065] like Figure 1 、 Figure 2 As shown, this embodiment 1 provides a plant-level multi-unit load optimization distribution and control method based on unit characteristic differences, which includes:

[0066] S1. Establish a plant-level digital twin model that includes a gas generation system, a gas storage system, and a gas energy supply system. The gas energy supply system includes multiple gas generator sets. Each gas generator set consists of a boiler and a steam turbine. The generator sets use gas as input, feed part of the steam produced by the boiler into the steam turbine to generate power, and extract part of the steam from the steam turbine to meet heat demand.

[0067] S2. Establish a plant-level electricity and heat load demand forecasting model to obtain the electricity and heat load demand combinations for each time period. Establish a relationship model between the total power generation steam flow, total extraction steam heat flow, and the electricity and heat load demand combinations for the gas energy supply system to obtain the total values ​​of the power generation steam flow and extraction steam heat flow required to be output by the gas energy supply system for each time period.

[0068] S3. Based on the total value of the required power generation steam flow rate and the extraction steam heating flow rate in each time period, combined with historical operating data, a total gas consumption prediction model is established to obtain the total gas consumption of the gas energy system in each time period; a gas output prediction model of the gas generation system is also established to obtain the predicted gas output value of the gas generation system in each time period. The predicted gas output value of the gas generation system in each time period is then comprehensively analyzed with the total gas consumption of the gas energy system in each time period and the gas storage and release capacity of the gas storage system to determine the total gas volume of the gas energy system in each time period;

[0069] S4. Conduct simulation experiments and analysis based on the plant-level digital twin model to establish load performance characteristic models for each boiler and steam turbine, and obtain performance indicator differences for each gas-fired power generation unit at various gas consumption rates.

[0070] S5. Optimizing the operating economy of all gas-fired power generation units, minimizing the gas consumption rate for steam production, and minimizing the gas consumption rate for power generation and heating, and based on the performance differences of each gas-fired power generation unit at various gas consumption rates, establish a gas volume optimization allocation model for the upper-layer gas-fired power generation units. This model optimally allocates the total gas volume of the gas energy system at each time period to each gas-fired power generation unit.

[0071] S6. With the goal of minimizing the gas production cost and storage and release cost, a lower-layer gas production-storage and release optimization model is established to optimize the control of the gas generation system and the gas storage system, and obtain the gas volume adjustment strategy and gas storage and release strategy of the gas production equipment.

[0072] In this embodiment, in S1, a plant-level digital twin model including a gas generation system, a gas storage system, and a gas energy supply system is established, including:

[0073] Identify the physical entities within the plant, including the gas generation system, gas storage system, and gas energy supply system;

[0074] Establish the geometric model, physical model, behavioral model and rule model of the physical entities in the factory, and after integrating the models, build a virtual entity mechanism model that is highly consistent with the actual physical entities in the factory;

[0075] Taking the virtual entity mechanism model as the main body, the residual of the virtual entity mechanism model is calculated using historical data. The input of the virtual entity mechanism model and the model residual results are preprocessed and used as the input and output of the machine learning network respectively. After training and learning, a digital twin data-driven model is obtained, and the residual of the virtual entity mechanism model is compensated and corrected;

[0076] The revised virtual entity mechanism model and the digital twin data-driven model are integrated to establish a factory-level digital twin model.

[0077] In practical applications, taking a steel plant as an example, depending on the production process, the gas generation system includes at least blast furnace gas equipment, coke oven gas equipment, and converter gas equipment. The gas storage system includes at least blast furnace gas storage cabinets, coke oven gas storage cabinets, and converter gas storage cabinets, respectively, used to store excess gas produced by the corresponding gas equipment and release it during peak load periods. Utilizing the gas energy supply system not only maximizes gas resource recovery and reduces environmental pollution from exhaust gas, but also improves power generation and heating efficiency.

[0078] Steel mills generally utilize the production process of "coking, sintering, ironmaking, steelmaking, and steel rolling." The coking process produces over 20% coke oven gas, the blast furnace ironmaking process produces nearly 30% blast furnace gas, and the converter steelmaking process produces 5% converter gas. Therefore, the entire production process generates over 50% of gas. Only a small portion of this gas is used for the process itself, leaving a significant surplus. This surplus gas is used to generate electricity and heat through gas-fired generators, including boilers and steam turbines, to meet the steel mill's electrical and thermal loads. Any excess electricity can be sold online, generating a portion of the revenue. Furthermore, gas-fired power generation reduces the steel mill's own electricity purchases, saving costs. Furthermore, depending on peak and valley periods in electrical and thermal demand, excess gas can be stored in gas storage tanks by adjusting gas valves during these periods. The gas is burned in the boiler, and the chemical energy released during the combustion process is utilized. In the process of heating the boiler, the chemical energy is converted into thermal energy. The water in the boiler is converted into steam after heating, and then the generator is operated through the steam turbine to achieve the purpose of power generation, and some steam is extracted from the steam turbine for heating.

[0079] In this embodiment, in S2, a relationship model is established between the total power generation steam flow, the total extraction steam heat flow, and the combination of the power load and heat load demand of the gas energy supply system, including:

[0080] Obtain historical operating data under plant-level supply and demand balance operating conditions, including the historical total power generation steam flow, total extraction steam heating flow, historical electrical load, thermal load, and the power generation steam flow, power generation power, exhaust steam pressure, exhaust steam temperature, turbine thermal efficiency, thermal power, equivalent enthalpy drop, heating extraction steam flow, heating extraction steam pressure, and heating extraction steam temperature of the gas energy supply system;

[0081] A feature extraction algorithm is used to extract features from historical operating data, and key operating data that affects power generation steam flow and extraction steam heating flow are selected;

[0082] The historical operation data fitting method is used to establish the relationship model between the total power generation steam flow, total extraction steam heating flow, and the combination of electric load and heat load demand required by the gas energy supply system, which is expressed as follows:

[0083] (m g,t ,m h,t )=g(P e,t ,Q h,t ,E t );

[0084] m g,t is the total steam flow rate for power generation during period t; m h,t is the total extraction steam heating flow rate during period t; P e,tis the electric load demand during period t; Q h,t is the heat load demand during period t; E t is the key operating data that affects the steam flow rate for power generation and the steam extraction flow rate for heating; g( ) is the power generation and heating characteristic equation of the gas energy supply system.

[0085] In this embodiment, S3 includes:

[0086] Obtain historical operating data for each boiler and steam turbine, including the gas consumption, steam production, steam parameters, flue gas parameters, combustion efficiency of each boiler, and the steam inlet flow, pressure, temperature, output power generation steam flow, extraction steam heating flow of each steam turbine, as well as the total gas consumption of the gas energy supply system and the total output power generation steam flow and extraction steam heating flow of the system;

[0087] Based on the historical operating data of each boiler and steam turbine, a machine learning algorithm is used to train and learn the total gas consumption prediction model of the gas energy supply system;

[0088] The total value of the required output steam flow for power generation and steam extraction for heating in each time period is input into the established total gas consumption prediction model of the gas energy supply system to obtain the total gas consumption of the gas energy supply system in each time period;

[0089] Obtain historical operating data of the gas generation system, establish a gas volume prediction model for the gas generation system, describe the relationship between gas production and related equipment operating parameters, and then obtain the predicted gas volume output value of the gas generation system in each future period;

[0090] When the predicted gas output of the gas generation system in each future period is greater than the total gas consumption of the gas energy system, it indicates that the gas output exceeds the demand. The excess gas will be stored in the gas storage system to ensure that the total gas output of the gas energy system in each period is equal to the total gas consumption. Alternatively, the excess electricity produced will be sold online to ensure that the total gas output of the gas energy system in each period is equal to the predicted gas output.

[0091] When the predicted gas output of the gas generation system in each future period is less than the total gas consumption of the gas supply system, it indicates that the gas output is less than the demand. The gas stored in the gas storage system is released to ensure that the total gas volume of the gas supply system in each period is equal to the predicted gas output value plus the released gas volume, or the total gas consumption is reduced by purchasing electricity online to ensure that the total gas volume of the gas supply system in each period is equal to the predicted gas output value.

[0092] It should be noted that the predicted gas output value V of the gas generation system in each period in the future t As the supply value of gas volume, the total gas consumption of the gas energy supply system Lt As the gas demand value, when the supply value is greater than the demand value: V t >L t , you can choose to use the excess gas volume V t -L t Stored in the gas storage system, the total gas volume Z of the gas energy system at each time period coalgas_all,t =L t You can also choose to use the excess gas V t -L t The gas generator sets can generate more electricity and sell it to the grid to obtain some income. At this time, the total gas volume of the gas energy system in each period is Z. coalgas_all,t =V t ;

[0093] When the supply value is less than the demand value: V t <L t , you can choose to release the gas stored in the gas storage system. At this time, the total gas volume of the gas energy system in each period is Z coalgas_all,t =V t +B t You can also choose to purchase part of the electricity online to reduce the power load demand at the plant level, thereby reducing the demand for gas. At this time, the total gas volume of the gas energy supply system at each time period is Z coalgas_all,t =V t .

[0094] In this embodiment, the S4 includes:

[0095] Set boiler load performance indicators, including boiler efficiency, gas consumption rate, boiler steam parameters, boiler load adjustment range, boiler load adjustment speed, and boiler heat loss;

[0096] Set turbine load performance indicators, including steam consumption rate, power generation efficiency, heating efficiency, heating steam extraction capacity, turbine load adjustment range, turbine load adjustment flexibility, and overload capacity;

[0097] Calculate the weight of each load performance index of boiler and steam turbine that affects load optimization distribution;

[0098] A simulation experiment was conducted based on the plant-level digital twin model. The same gas consumption volume was set as the input condition of the experiment. At the same time, the consistency of gas quality, pressure, and temperature parameters was taken into consideration. The boilers and steam turbines were compared under the same external conditions. The operating data of each boiler and steam turbine were recorded, and the load performance indicators of each boiler and steam turbine were calculated. Combined with the calculated weights of each load performance indicator, the differences in the load performance indicators of each boiler and steam turbine under the same gas consumption volume were evaluated and analyzed.

[0099] It should be noted that in addition to setting the same gas consumption volume as the input condition of the experiment, it is also possible to set the gas consumption volume from one to another, such as reducing or increasing the gas consumption volume, monitor the changes in the operating parameters of each boiler and turbine, evaluate the relevant load performance indicators, and identify equipment or indicators with poor performance.

[0100] In this embodiment, the weight calculation method includes a subjective weighting method, an objective weighting method, and a combined weighting method.

[0101] It should be noted that the subjective weighting method includes AHP hierarchical analysis method and FAHP fuzzy hierarchical analysis method; the objective weighting method includes entropy method, principal component analysis method and CRITIC weight method; the combined weighting method is a combination of subjective weighting method and objective weighting method.

[0102] In this embodiment, in S5, establishing a gas quantity optimization distribution model for the upper gas power generation unit includes:

[0103] Based on the performance index differences of each gas generating unit under different gas consumption, the total gas volume of the gas energy supply system in each period is defined as Z coalgas_all,t , assume that n gas generating units have a preliminary gas volume distribution result in each period, which is defined as (S coalgas_x1,t ,S coalgas_x2,t ,…,S coalgas_xn,t );

[0104] The goal is to optimize the operating economy of all gas-fired generator sets, minimize the gas consumption rate for steam production, and minimize the steam consumption rate for power generation and heating, which can be expressed as:

[0105]

[0106] P e,i,t is the power generation of the i-th gas generator set in period t, is the self-used power generation; e P is the price of electricity purchased; c,i,t is the on-grid power of the i-th gas generator set in period t; c Q is the electricity price during the grid connection phase; h,i,t is the heat production of the i-th gas generator set in period t, is the self-use heat production; h P is the price of heat purchased; f,buy,t is the amount of electricity purchased to meet the peak power load during period t; η f is the electricity purchase price; Z coalgas_all,t is the total gas consumption of the gas energy supply system; μ coalgas To absorb the gas price; S coalgas_xi,t D is the amount of gas consumed by the i-th gas generating unit during period t; i,t is the steam production of the i-th gas generator set during period t; Me,i,t is the steam inlet flow rate of the i-th gas generator set during period t; M h,i,t is the heating extraction steam flow of the i-th gas generator set during period t;

[0107] Set the operating constraints of the gas-fired power generation unit, including: turbine capacity constraints, extraction steam flow constraints, exhaust steam flow constraints, thermal load constraints, electrical load constraints, boiler capacity constraints, steam production constraints, and gas consumption constraints;

[0108] Based on the goals of optimal operating economy, minimum gas consumption rate for steam production, and minimum steam consumption rate for power generation and heating of all gas-fired power generation units, and combined with the operating constraints of the gas-fired power generation units, an optimal gas allocation model for the upper-level gas-fired power generation units is established.

[0109] In this embodiment, S6 includes:

[0110] With the goal of minimizing the gas production cost and storage and discharge cost, a lower-layer gas production-storage-discharge optimization model is established, which can be expressed as:

[0111]

[0112] C s,t 、C x,t are the production and operation cost of the gas generation system and the gas storage and release cost of the gas storage system during period t respectively;

[0113] Solve the lower-layer gas production-storage-release optimization model to obtain the gas volume adjustment strategy and gas storage-release strategy of the gas production equipment.

[0114] In this embodiment, the constraints of the lower-layer gas production-storage-release optimization model include: gas supply and demand balance constraint, gas generation system equipment production capacity constraint, and gas storage system equipment capacity constraint.

[0115] In this embodiment, the upper-layer gas power generation unit gas quantity optimization distribution model and the lower-layer gas production-storage-release optimization model are solved by using an algorithm that combines a genetic algorithm and a simulated annealing algorithm.

[0116] In practical applications, the algorithm solution steps using a combination of genetic algorithm and simulated annealing algorithm include:

[0117] 1) Initialize the parameters and set the genetic algorithm parameters, including the population size, the maximum number of genetic iterations, the crossover probability and the mutation probability, as well as the simulated annealing algorithm parameters, including the initial temperature, the termination temperature and the annealing coefficient;

[0118] 2) Select the initial population code, construct the initial population, and calculate the fitness value of each individual in the population;

[0119] 3) Perform genetic operations on the initial population at the initial temperature to obtain subpopulations and calculate the fitness value;

[0120] 4) Using the Metropolis mechanism of the simulated annealing algorithm to perform chromosome selection operations, the appropriate chromosome is obtained to enter the next genetic iteration;

[0121] 5) Determine whether the genetic iterations have reached the maximum number of genetic iterations. If so, proceed to the next step; otherwise, go to step 3);

[0122] 6) Determine whether the termination temperature has been reached. If not, perform a cooling operation and go to step 3). Otherwise, the algorithm iteration ends and the optimal solution is output.

[0123] The Metropolis mechanism of the simulated annealing algorithm can escape local optimal solutions and incorporate them into the genetic selection strategy of the genetic algorithm to select the next generation of populations. The core of the simulated annealing algorithm lies in the Metropolis mechanism and the annealing process, which correspond to the inner and outer loops of the algorithm, respectively.

[0124] It should be noted that the solution of the upper-level gas-fired power generation unit gas quantity optimization allocation model and the lower-level gas production-storage-release optimization model is carried out interactively and iteratively. The gas quantity adjustment strategy and gas storage-release strategy of the gas production equipment output by the lower-level model affect the total gas quantity of the gas energy supply system, and thus affect the gas quantity allocation results of each gas-fired power generation unit; conversely, the gas quantity allocation results of each gas-fired power generation unit output by the upper-level model affect the total gas quantity of the gas energy supply system, and thus affect the gas quantity adjustment strategy and gas storage-release strategy of the gas production equipment.

[0125] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can also be implemented in other ways. The system embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architectures, functions, and operations of the systems, methods, and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment, or a portion of code, and the module, program segment, or a portion of code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the boxes can also occur in an order different from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart, can be implemented using a dedicated hardware-based system that performs the specified functions or actions, or can be implemented using a combination of dedicated hardware and computer instructions.

[0126] In addition, the functional modules in each embodiment of the present invention can be integrated together to form an independent part, or each module can exist separately, or two or more modules can be integrated to form an independent part. If the function is implemented in the form of a software functional module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0127] With the above-described preferred embodiments of the present invention as a guide, and with reference to the above description, relevant personnel are fully capable of making various changes and modifications without departing from the technical scope of this invention. The technical scope of this invention is not limited to the contents of the specification and must be determined according to the scope of the claims.

Claims

1. A plant-level multi-unit load optimization distribution and control method based on unit characteristic differences, characterized in that: It includes: S1. Establish a plant-level digital twin model that includes a gas generation system, a gas storage system, and a gas energy supply system. The gas energy supply system includes multiple gas generator sets. Each gas generator set consists of a boiler and a steam turbine. The generator sets use gas as input, feed part of the steam produced by the boiler into the steam turbine to generate power, and extract part of the steam from the steam turbine to meet heat demand. S2. Establish a plant-level electricity and heat load demand forecasting model to obtain the electricity and heat load demand combinations for each time period. Establish a relationship model between the total power generation steam flow, total extraction steam heat flow, and the electricity and heat load demand combinations for the gas energy supply system to obtain the total values ​​of the power generation steam flow and extraction steam heat flow required to be output by the gas energy supply system for each time period. S3. Based on the total value of the power generation steam flow and the extraction steam heating flow required in each time period, combined with historical operation data, a total gas consumption prediction model is established to obtain the total gas consumption of the gas energy supply system in each time period; A gas output prediction model for the gas generation system is established to obtain the predicted gas output value of the gas generation system at each time period, and a comprehensive analysis is conducted with the total gas consumption of the gas energy system at each time period and the gas storage and release capacity of the gas storage system to determine the total gas output value of the gas energy system at each time period; When the predicted gas output of the gas generation system in each future time period is greater than the total gas consumption of the gas energy system, it indicates that the gas output exceeds the demand. The excess gas will be stored in the gas storage system to ensure that the total gas output of the gas energy system in each time period is equal to the total gas consumption. Alternatively, the excess electricity produced will be sold online to ensure that the total gas output of the gas energy system in each time period is equal to the predicted gas output. When the predicted gas output of the gas generation system in each future period is less than the total gas consumption of the gas energy system, it indicates that the gas output is less than the demand. The gas stored in the gas storage system is released to ensure that the total gas volume of the gas energy system in each period is equal to the predicted gas output value plus the released gas volume. Alternatively, electricity is purchased online to reduce the total gas consumption, to ensure that the total gas volume of the gas energy system in each period is equal to the predicted gas output value. S4. Conduct simulation experiments and analysis based on the plant-level digital twin model to establish load performance characteristic models for each boiler and steam turbine, and obtain performance indicator differences for each gas-fired power generation unit at various gas consumption rates. S5. Optimizing the operating economy of all gas-fired power generation units, minimizing the gas consumption rate for steam production, and minimizing the gas consumption rate for power generation and heating, and based on the performance differences of each gas-fired power generation unit at various gas consumption rates, establish a gas volume optimization allocation model for the upper-layer gas-fired power generation units. This model optimally allocates the total gas volume of the gas energy system at each time period to each gas-fired power generation unit. The establishment of the upper gas generator set gas quantity optimization distribution model includes: Based on the performance index differences of each gas-fired power generation unit under different gas consumption volumes, the total gas volume of the gas energy supply system in each period is defined as , assume that n gas generating units have preliminary gas distribution results in each period, which is defined as ; The goal is to optimize the operating economy of all gas-fired generator sets, minimize the gas consumption rate for steam production, and minimize the steam consumption rate for power generation and heating, which can be expressed as: ； ； ； is the power generation of the i-th gas generator set in period t, and is the power generation for self-use; The price of electricity purchased; is the on-grid power of the i-th gas generator set in period t; The electricity price during the grid-connected phase; is the heat production of the i-th gas generator set in period t, and is the heat production for self-use; The price of heat purchased; is the amount of electricity purchased to meet the peak electricity load during period t; The price of electricity purchased; The total gas consumption of the gas energy supply system; To absorb the gas price; The amount of gas consumed by the i-th gas generating unit in period t; is the steam production of the i-th gas generator set during period t; is the steam inlet flow rate of the i-th gas generator set during period t; is the heating extraction steam flow of the i-th gas generator set during period t; Set the operating constraints of the gas-fired power generation unit, including: turbine capacity constraints, extraction steam flow constraints, exhaust steam flow constraints, thermal load constraints, electrical load constraints, boiler capacity constraints, steam production constraints, and gas consumption constraints; Based on the goals of optimizing the operating economy of all gas-fired power generation units, minimizing the gas consumption rate for steam production, and minimizing the steam consumption rate for power generation and heating, and in combination with the operating constraints of the gas-fired power generation units, a gas allocation optimization model for the upper-layer gas-fired power generation units was established. S6. With the goal of minimizing the gas production cost and storage and release cost, a lower-layer gas production-storage and release optimization model is established to optimize the control of the gas generation system and the gas storage system, and obtain the gas volume adjustment strategy and gas storage and release strategy of the gas production equipment.

2. The plant-level multi-unit load optimization distribution and control method according to claim 1 is characterized in that: In S1, a plant-level digital twin model including the gas generation system, gas storage system, and gas energy supply system is established, including: Identify the physical entities within the plant, including the gas generation system, gas storage system, and gas energy supply system; Establish the geometric model, physical model, behavioral model and rule model of the physical entities in the factory, and after integrating the models, build a virtual entity mechanism model that is highly consistent with the actual physical entities in the factory; Taking the virtual entity mechanism model as the main body, the residual of the virtual entity mechanism model is calculated using historical data. The input of the virtual entity mechanism model and the model residual results are preprocessed and used as the input and output of the machine learning network respectively. After training and learning, a digital twin data-driven model is obtained, and the residual of the virtual entity mechanism model is compensated and corrected; The revised virtual entity mechanism model and the digital twin data-driven model are integrated to establish a factory-level digital twin model.

3. The plant-level multi-unit load optimization distribution and control method according to claim 1 is characterized in that: In S2, a relationship model is established between the total power generation steam flow, the total extraction steam heating flow, and the combination of power load and heat load demand of the gas energy supply system, including: Obtain historical operating data under plant-level supply and demand balance operating conditions, including the historical total power generation steam flow, total extraction steam heating flow, historical electrical load, thermal load, and the power generation steam flow, power generation power, exhaust steam pressure, exhaust steam temperature, turbine thermal efficiency, thermal power, equivalent enthalpy drop, heating extraction steam flow, heating extraction steam pressure, and heating extraction steam temperature of the gas energy supply system; A feature extraction algorithm is used to extract features from historical operating data, and key operating data that affects power generation steam flow and extraction steam heating flow are selected; The historical operation data fitting method is used to establish the relationship model between the total power generation steam flow, total extraction steam heating flow, and the combination of electric load and heat load demand required by the gas energy supply system, which is expressed as follows: ； is the total power generation steam flow in period t; is the total extraction steam heating flow rate during period t; is the electric load demand during period t; is the heat load demand during period t; Key operating data that affects steam flow for power generation and steam extraction for heating; The power generation and heating characteristic equations of the gas energy supply system.

4. The plant-level multi-unit load optimization distribution and control method according to claim 1 is characterized in that: In S3, the total gas consumption of the gas energy supply system in each time period is obtained, including: Obtain historical operating data for each boiler and steam turbine, including the gas consumption, steam production, steam parameters, flue gas parameters, combustion efficiency of each boiler, and the steam inlet flow, pressure, temperature, output power generation steam flow, extraction steam heating flow of each steam turbine, as well as the total gas consumption of the gas energy supply system and the total output power generation steam flow and extraction steam heating flow of the system; Based on the historical operating data of each boiler and steam turbine, a machine learning algorithm is used to train and learn the total gas consumption prediction model of the gas energy supply system; The total value of the required output steam flow for power generation and steam extraction for heating in each time period is input into the established total gas consumption prediction model of the gas energy supply system to obtain the total gas consumption of the gas energy supply system in each time period; Furthermore, obtaining the predicted gas output value of the gas generation system in each time period includes: obtaining the historical operating data of the gas generation system, establishing a gas output prediction model for the gas generation system, describing the relationship between gas production and operating parameters of related equipment, and then obtaining the predicted gas output value of the gas generation system in each future time period.

5. The plant-level multi-unit load optimization distribution and control method according to claim 1 is characterized in that: The S4 includes: Set boiler load performance indicators, including boiler efficiency, gas consumption rate, boiler steam parameters, boiler load adjustment range, boiler load adjustment speed, and boiler heat loss; Set turbine load performance indicators, including steam consumption rate, power generation efficiency, heating efficiency, heating steam extraction capacity, turbine load adjustment range, turbine load adjustment flexibility, and overload capacity; Calculate the weight of each load performance index of boiler and steam turbine that affects load optimization distribution; A simulation experiment was conducted based on the plant-level digital twin model. The same gas consumption volume was set as the input condition of the experiment. At the same time, the consistency of gas quality, pressure, and temperature parameters was taken into consideration. The boilers and steam turbines were compared under the same external conditions. The operating data of each boiler and steam turbine were recorded, and the load performance indicators of each boiler and steam turbine were calculated. Combined with the calculated weights of each load performance indicator, the differences in the load performance indicators of each boiler and steam turbine under the same gas consumption volume were evaluated and analyzed.

6. The plant-level multi-unit load optimization distribution and control method according to claim 5 is characterized in that: The weight calculation method includes subjective weighting method, objective weighting method and combined weighting method.

7. The plant-level multi-unit load optimization distribution and control method according to claim 1 is characterized in that: The S6 includes: With the goal of minimizing the gas production cost and storage and discharge cost, a lower-layer gas production-storage-discharge optimization model is established, which can be expressed as: ； 、 are the production and operation cost of the gas generation system and the gas storage and release cost of the gas storage system during period t respectively; Solve the lower-layer gas production-storage-release optimization model to obtain the gas volume adjustment strategy and gas storage-release strategy of the gas production equipment.

8. The plant-level multi-unit load optimization distribution and control method according to claim 7 is characterized in that: The constraints of the lower-layer gas production-storage-release optimization model include: gas supply and demand balance constraints, gas generation system equipment production capacity constraints, and gas storage system equipment capacity constraints.

9. The plant-level multi-unit load optimization distribution and control method according to claim 1, characterized in that: The upper layer gas generator set gas quantity optimization distribution model and the lower layer gas production-storage-release optimization model are solved by using an algorithm combining a genetic algorithm and a simulated annealing algorithm.

Images