Byproduct gas optimization scheduling method based on Pareto optimization

Abstract

The invention belongs to the technical field of by-product gas optimal scheduling, and provides a by-product gas optimal scheduling method based on Pareto optimization. Comprising the steps of target function determination, initialization penalty factor determination, operation data collection, adjustment on the initialization penalty factor based on the Pareto optimal principle, weight configuration, strategy updating, operation data real-time collection and strategy real-time optimization. According to the method, the Pareto optimal principle is introduced, so that the optimal balance of the complex relation among the stability of the gas holder, the stability of the boiler and the total cost is realized; through real-time operation data collection and real-time strategy optimization, the adaptive capacity and reliability of the system are improved; and the accuracy and the reliability of the optimization scheduling result are ensured by constructing the objective function and the penalty factor.

Description

Technical Field

[0001] The invention relates to the technical field of by-product coal gas optimization scheduling, and in particular to a by-product coal gas optimization scheduling method based on Pareto optimality. Background Art

[0002] Against the backdrop of the rapid development of the steel industry, energy management has become an important part of improving corporate competitiveness and achieving sustainable development. In the steel production process, coal is the main energy source. The energy generated by its combustion is not only directly used in the high-temperature smelting process, but also produced in large quantities in the form of by-product gas. According to statistics, about 33% of the energy value of coal used in steel production is converted into by-product gas, including blast furnace gas, coke oven gas and converter gas, which contain huge energy potential. However, the traditional by-product gas management methods of steel enterprises often have many problems, such as low resource utilization efficiency, inflexible scheduling, and high production costs. Specifically, the distribution of by-product gas among various production links is unbalanced, resulting in oversupply and waste of gas in some links, and insufficient gas supply in some links affecting production; second, the operating stability of key equipment such as gas cabinets and boilers is difficult to guarantee, and frequent fluctuations not only affect production efficiency, but also increase equipment maintenance costs; third, there is a lack of effective real-time monitoring means, making it difficult to respond and adjust parameter changes in the production process in a timely manner. In order to solve the above problems, the steel industry has been constantly exploring new technologies and methods for optimizing the scheduling of by-product gas in recent years. Among them, the introduction of industrial Internet technology provides a new idea for by-product gas management. By building a by-product gas management platform for steel enterprises, the centralized collection, storage, processing and analysis of production data can be realized, providing data support for optimized scheduling. In the prior art, there are some implementation schemes similar to the present invention. For example, some steel companies have adopted a by-product gas prediction method based on statistical models, and predicted the output and consumption of by-product gas in the future through historical data analysis, and made preliminary production scheduling arrangements based on this. However, this method can usually only provide relatively rough prediction results, and it is difficult to cope with the complex and changeable situations in actual production. Another more advanced solution is to use intelligent algorithms to optimize the scheduling of by-product gas. These schemes usually include building an optimization scheduling model and obtaining the optimal gas distribution plan by solving the model.

[0003] In summary, the main problems of the existing solutions include: First, the scheduling systems in the existing technology are mostly based on simple rules or empirical judgments, and lack scientific optimization algorithm support. This makes it difficult to fully consider the actual needs and constraints of each production link in the distribution and scheduling of by-product gas, such as the capacity limit of gas tanks and the combustion efficiency of boilers, so that the maximum utilization of resources cannot be achieved. Secondly, the real-time performance of the existing technology is poor, and it is difficult to adapt to the rapid changes in the steel production process. Steel production is a highly dynamic process, and the generation and consumption of by-product gas fluctuate with the changes in the production rhythm. However, the existing technology often cannot capture these changes in real time, resulting in the scheduling strategy lagging behind the actual production, affecting production efficiency and stability. Furthermore, the existing technology has limitations in data processing and analysis. With the continuous development of industrial Internet technology, steel companies have accumulated a large amount of production data. However, the existing technology often cannot make full use of these data resources, lacks efficient data processing and analysis methods, and is difficult to explore the value behind the data and provide strong support for optimized scheduling. Summary of the invention

[0004] In order to overcome the shortcomings of the prior art, the purpose of the present invention is to provide a by-product gas optimization scheduling method based on Pareto optimality, which achieves the optimal balance of the complex relationship between gas tank stability, boiler stability and total cost by introducing the Pareto optimal principle; improves the adaptability and reliability of the system by real-time collection of operation data and real-time strategy optimization; and ensures the accuracy and reliability of the optimization scheduling results by constructing objective functions and penalty factors.

[0005] To achieve the above object, the present invention provides the following solutions:

[0006] A method for optimizing the scheduling of by-product gas based on Pareto optimality, comprising:

[0007] Determine the objective function; the objective function includes: gas tank fluctuation penalty cost function, boiler fluctuation penalty cost function and energy and environmental cost function;

[0008] Determining an initialization penalty factor according to the objective function;

[0009] Collect gas recovery data and key production parameters to obtain operation data;

[0010] Based on the Pareto optimal principle, the initialization penalty factor is adjusted using the operation data to obtain an optimal penalty factor;

[0011] Based on the optimal penalty factor, weight configuration is performed on the objective function to obtain an optimal operation strategy;

[0012] Updating the optimal operation strategy into the target by-product gas scheduling model;

[0013] When the target by-product gas scheduling model is updated, the operation data is collected in real time;

[0014] The optimal operation strategy is optimized based on the Pareto optimal principle using the operating data collected in real time.

[0015] Preferably, the calculation formula of the objective function is:

[0016] Z = min{GPC+BPC+EEC};

[0017] Among them, Z is the objective function; GPC is the gas tank fluctuation penalty cost function; BPC is the boiler fluctuation penalty cost function; EEC is the energy and environmental cost function.

[0018] Preferably, the initialization penalty factor is inversely proportional to the volume of the gas tank during operation.

[0019] Preferably, the initialization penalty factor is adjusted using the operation data based on the Pareto optimality principle to obtain an optimal penalty factor, including:

[0020] The operation data is projected and displayed using the initialization penalty factor to obtain gas tank fluctuation data, boiler load change data, energy consumption data and environmental cost data;

[0021] The Pareto optimal principle is used to eliminate the gas tank fluctuation data, the boiler load change data, the energy consumption data and the environmental cost data to obtain Pareto frontier data;

[0022] The initialization penalty factors of different combinations are analyzed according to the Pareto front data to obtain the optimal penalty factor.

[0023] Preferably, the gas recovery data includes: blast furnace gas data, coke oven gas data and converter gas data.

[0024] Preferably, the calculation formula of the gas tank fluctuation penalty cost function is:

[0025]

[0026] Wherein, GPC is the gas tank fluctuation penalty cost function; GPC j GPF is the fluctuation penalty cost of the gas tank where the j-th by-product gas is located; j is the penalty factor of the j-th gas tank; ΔV j,t,dev 、V j,t 、V j,midThey are respectively the offset of the gas tank where the j-th by-product gas is located in the t-th period relative to the middle tank, the real-time tank of the j-th gas in the t-th period, and the middle tank of the gas tank where the j-th by-product gas is located; G is the total number of by-product gas types; P is the total number of scheduling cycles.

[0027] Preferably, the calculation formula of the boiler fluctuation penalty cost function is:

[0028]

[0029] Wherein, BPC is the boiler fluctuation penalty cost function; BPF 1s 、BPF 2s 、BPF 3s They are the first penalty factor, the second penalty factor and the third penalty factor respectively; It means that the ith boiler turns on the igniter of the gas tank where the jth byproduct gas is located in the tth cycle; It means that the i-th boiler shuts down the igniter of the gas tank where the j-th by-product gas is located in the t-th cycle; B is the total number of boilers.

[0030] Preferably, the calculation formula of the energy and environmental cost function is:

[0031]

[0032] Wherein, EEC is the energy and environmental cost function; C flar , C wat , C elec are the unit price of by-product gas release, water unit price and electricity unit price respectively; V j,t,flar The emission volume of the gas tank where the j-th by-product gas is located in the t-th period; The water consumption of the ith boiler in the tth period; E t,pur is the amount of electricity purchased in the tth period; E t,dem is the total power demand in the tth period; E t,gen is the total power generation of the captive power plant in the tth period.

[0033] The present invention discloses the following technical effects:

[0034] The present invention provides a by-product gas optimization scheduling method based on Pareto optimality. By introducing the Pareto optimality principle, the defect of the existing scheme that a single target is considered is solved, and the optimal balance of the complex relationship between the stability of the gas holder, the stability of the boiler and the total cost is achieved; by real-time collection of operation data and real-time strategy optimization, the defect of the existing scheme that the real-time update capability is not available is solved, and the real-time update of the scheduling strategy according to the actual production process is achieved; by constructing the objective function and the penalty factor, the parameter selection problem is solved, and the optimal selection of the penalty factor using the Pareto optimality principle is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0036] Figure 1 A schematic diagram of a by-product gas optimization scheduling process based on Pareto optimality provided by an embodiment of the present invention;

[0037] Figure 2 A flowchart of by-product gas optimization scheduling based on Pareto optimality is provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0039] The purpose of the present invention is to provide a by-product gas optimization scheduling method based on Pareto optimality, which achieves the optimal balance of the complex relationship between gas tank stability, boiler stability and total cost by introducing the Pareto optimal principle; improves the adaptability and reliability of the system by real-time collection of operation data and real-time strategy optimization; and ensures the accuracy and reliability of the optimization scheduling results by constructing objective functions and penalty factors.

[0040] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0041] Figure 1 A schematic diagram of a by-product gas optimization scheduling process based on Pareto optimality provided by an embodiment of the present invention is shown in FIG. Figure 1 As shown, the present invention provides a method for optimizing the scheduling of by-product gas based on Pareto optimality, comprising:

[0042] Step 100: Determine the objective function; the objective function includes: gas tank fluctuation penalty cost function, boiler fluctuation penalty cost function and energy and environmental cost function;

[0043] Step 200: Determine an initialization penalty factor according to the objective function;

[0044] Step 300: Collect gas recovery data and key production parameters to obtain operation data;

[0045] Step 400: adjusting the initialization penalty factor using the operating data based on the Pareto optimal principle to obtain the optimal penalty factor;

[0046] Step 500: weight the objective function based on the optimal penalty factor to obtain the optimal operation strategy;

[0047] Step 600: updating the optimal operation strategy to the target by-product gas scheduling model;

[0048] Step 700: After the target by-product gas scheduling model is updated, the operation data is collected in real time;

[0049] Step 800: Optimize the optimal operation strategy using the real-time collected operation data based on the Pareto optimality principle.

[0050] Specifically, the calculation formula of the objective function is:

[0051] Z = min{GPC+BPC+EEC};

[0052] Among them, Z is the objective function; GPC is the gas tank fluctuation penalty cost function; BPC is the boiler fluctuation penalty cost function; EEC is the energy and environmental cost function.

[0053] Preferably, the initialization penalty factor is inversely proportional to the gas tank volume during operation.

[0054] Furthermore, based on the Pareto optimal principle, the initialization penalty factor is adjusted using the operating data to obtain the optimal penalty factor, including:

[0055] The operation data is projected and displayed using the initialization penalty factor to obtain the gas tank fluctuation data, boiler load change data, energy consumption data, and environmental cost data;

[0056] The Pareto optimal principle is used to eliminate the gas tank fluctuation data, boiler load change data, energy consumption data and environmental cost data to obtain the Pareto frontier data;

[0057] According to the Pareto frontier data, the initialization penalty factors of different combinations are analyzed to obtain the optimal penalty factor.

[0058] Preferably, the gas recovery data includes: blast furnace gas data, coke oven gas data and converter gas data.

[0059] Specifically, the calculation formula of the gas tank fluctuation penalty cost function is:

[0060]

[0061] Among them, GPC is the gas tank fluctuation penalty cost function; GPC j GPF is the fluctuation penalty cost of the gas tank where the j-th by-product gas is located; j is the penalty factor of the j-th gas tank; ΔV j,t,dev 、V j,t 、V j,mid They are respectively the offset of the gas tank where the j-th by-product gas is located relative to the middle tank in the t-th period, the real-time tank position of the gas tank where the j-th by-product gas is located in the t-th period, and the middle tank position of the gas tank where the j-th by-product gas is located; G is the total number of by-product gas types; P is the total number of scheduling cycles.

[0062] Furthermore, the calculation formula of the boiler fluctuation penalty cost function is:

[0063]

[0064] Among them, BPC is the boiler fluctuation penalty cost function; BPF is 1s 、BPF 2s 、BPF 3s They are the first penalty factor, the second penalty factor and the third penalty factor respectively; It means that the ith boiler turns on the igniter of the gas tank where the jth byproduct gas is located in the tth cycle; It means that the i-th boiler shuts down the igniter of the gas tank where the j-th by-product gas is located in the t-th cycle; B is the total number of boilers.

[0065] Specifically, the calculation formula of energy and environmental cost function is:

[0066]

[0067] Among them, EEC is the energy and environmental cost function; C flar , C wat , C elec are the unit price of by-product gas release, water unit price and electricity unit price respectively; V j,t,flar The emission volume of the gas tank where the j-th by-product gas is located in the t-th period; The water consumption of the ith boiler in the tth period; E t,pur is the amount of electricity purchased in the tth period; E t,dem is the total power demand in the tth period; E t,gen is the total power generation of the captive power plant in the tth period.

[0068] Preferably, the enterprise uses the produced by-product gas for production processes such as coking, sintering, ironmaking, steelmaking (including continuous casting) and steel rolling, and uploads the parameter data to the by-product gas management platform of the steel enterprise; the by-product gas management platform of the steel enterprise establishes a by-product gas optimization scheduling model based on the Pareto algorithm in the by-product gas prediction model; the by-product gas management platform of the steel enterprise inputs the data of the by-product gas production process into the by-product gas optimization scheduling model of the Pareto algorithm, reasonably selects the penalty factor parameters, and selects the penalty factor parameter values ​​with the lowest gas tank stability, boiler stability and total cost; the by-product gas parameter monitoring module monitors the production data and reports the predicted data to the enterprise in real time.

[0069] refer to Figure 2 The specific steps for building a Pareto optimal by-product gas model for steel enterprises are as follows:

[0070] S1: Generation of by-product gas and data upload:

[0071] Generation of by-product gas: By-product gas is a secondary energy source associated with the steel production process, mainly divided into blast furnace gas, coke oven gas and converter gas. According to different production processes, enterprises recover and utilize these by-product gases in various production links.

[0072] Blast furnace gas: During the ironmaking process, raw materials such as sintered ore and coke are added through the top of the blast furnace, and molten iron and slag are formed through blast combustion, while blast furnace gas containing CO, CO2 and other components is generated. Blast furnace gas recovery data includes gas flow, air volume, air temperature, furnace top pressure difference and hot blast furnace gas consumption. These data are uploaded to the by-product gas management platform of steel enterprises.

[0073] Coke oven gas: During the coke production process, the raw gas is condensed, cooled, absorbed and purified to obtain purified gas and other chemical products. The coke oven gas recovery data includes gas flow, coke pushing plan, carbonization chamber temperature and combustion chamber gas consumption flow, etc. The enterprise uploads these data to the by-product gas management platform.

[0074] Converter gas: During the converter smelting process, liquid steel, furnace gas and slag are generated through molten iron pretreatment, oxygen blowing, secondary metallurgy and other processes, and converter gas is recovered at the same time. The key data of converter gas recovery include gas flow, oxygen content, blowing start and end time, etc. The company uploads these data to the by-product gas management platform.

[0075] Data upload and processing: The steel enterprise by-product gas management platform receives and stores gas recovery data from each production link, performs protocol conversion, data compression and standardization. The platform also dynamically manages the recovered by-product gas, and some of the gas is stored in the gas tank to balance the pipe network pressure and ensure the stable operation of the gas system.

[0076] Application of by-product gas: Enterprises use the recovered by-product gas for energy supply in processes such as coking, sintering, ironmaking, steelmaking (including continuous casting) and steel rolling. The key production parameters of these processes, such as combustion air preheating, material temperature changes, process gas consumption, furnace entry temperature, etc., are also uploaded to the by-product gas management platform in real time to ensure full monitoring and optimization of energy utilization efficiency.

[0077] S2: Construction of the objective function of the by-product gas optimization scheduling model:

[0078] Based on the uploaded real-time production data, the by-product gas management platform of the steel enterprise has established a by-product gas optimization scheduling model based on the Pareto algorithm. The goal of the model is to minimize the operating cost of the entire by-product gas system, taking into account the stability of the gas holder and boiler as well as the energy and environmental costs. The objective function can be divided into the following parts: gas holder penalty cost (Gasholder penalty cost, GPC), boiler penalty cost (Boiler penalty cost, BPC) and energy and environmental cost (Energy and environmental cost, EEC). The specific objective function is implemented by the following formula:

[0079] Z=min{GPC+BPC+EEC}

[0080] Gas tank fluctuation penalty cost: Gas tanks are important devices for storing byproduct gas, and their cabinet fluctuations have a significant impact on system stability. Gas tanks need to be kept near the middle cabinet to maintain the best anti-fluctuation capability. Therefore, a simplified method for calculating the gas tank fluctuation penalty cost is proposed. The specific formula is as follows:

[0081]

[0082] Boiler fluctuation penalty cost: The boiler fluctuation penalty cost consists of three parts, namely, the penalty cost of turning on or off one boiler igniter, the penalty cost of turning on or off two igniters at the same time, and the penalty cost of turning on or off three igniters at the same time. The penalty cost calculation model is based on Kim's model, and its calculation formula is as follows:

[0083]

[0084] Energy and environmental costs: Energy and environmental costs include by-product gas release costs, boiler water costs and electricity purchase costs:

[0085]

[0086] S3: Selection and analysis of penalty factors:

[0087] In the by-product gas optimization scheduling model, the selection and analysis of penalty factors are key steps. In order to ensure the stable operation of the three gas tanks of blast furnace gas, coke oven gas and converter gas in the middle tank, the selection of penalty factors is optimized and determined according to the volume of each gas tank. The platform determines a reasonable penalty factor by analyzing the historical operation data of the gas tank and boiler and combining it with the current real-time operation status. Specifically, the selection of penalty factors follows the following principles:

[0088] The penalty factor is inversely proportional to the gas tank volume:

[0089] The size of each gas tank directly affects the size of the penalty factor. Due to the different sizes of gas tanks, the amount of gas that can be held during operation is different, so the tolerance for fluctuations is also different. Smaller gas tanks have limited capacity and are prone to overfilling or underfilling, so their penalty factors are larger. Larger gas tanks have stronger regulation capabilities and relatively smaller penalty factors. Specifically, the penalty factor is inversely proportional to the size of the gas tank, that is, the smaller the gas tank, the larger the penalty factor, and vice versa.

[0090] Collaborative optimization to avoid gas tank lockout:

[0091] By analyzing the volumes of three gas tanks for blast furnace gas, coke oven gas, and converter gas, the penalty factors of each gas tank are determined, so that each gas tank can work together during operation to prevent any of the gas tanks from being "locked" (i.e., a gas tank cannot be dispatched or stored due to excessive penalty factors). This collaborative optimization process ensures the reasonable distribution of loads between different gas tanks and maximizes the overall stability and operating efficiency of the gas system.

[0092] Dynamic adjustment of penalty factor:

[0093] Since the operating status of the gas tank during the production process will change according to real-time demand and external factors, the selection of the penalty factor is not static. In the process of by-product gas scheduling, the penalty factor needs to be dynamically adjusted according to the actual situation to ensure the stability of the gas supply of blast furnace gas, coke oven gas and converter gas and reduce the system operation cost.

[0094] S4: Determination of the optimal solution:

[0095] Penalty factor debugging:

[0096] The penalty factors selected in the previous part are introduced into the optimization scheduling model and debugged based on the gasholder data during actual operation. The penalty factors of each gasholder where the by-product gas is located are gradually adjusted to observe its impact on the stability of the gas system, operating costs, and gasholder load balance. Through this debugging, the specific role of each penalty factor on system performance can be identified.

[0097] Determine the Pareto front:

[0098] During the debugging process, the actual operating data of each gas tank is projected and displayed, including indicators such as gas tank fluctuations, boiler load changes, energy consumption and environmental costs. By visually displaying these data, the trend of each parameter changing with the penalty factor can be clearly seen. Based on the Pareto optimal principle, the data that is not on the Pareto frontier is eliminated, and those data sets on the Pareto frontier are retained to ensure that the selected data set reflects the best equilibrium state.

[0099] Select the optimal solution based on the Pareto optimality principle:

[0100] Different penalty factor combinations are analyzed and the optimal solution is determined by applying the Pareto optimal principle. By gradually adjusting the penalty factor values, the parameter combination that optimizes the overall performance of the system is found. This step ensures the optimal balance between various indicators (such as gasholder stability, boiler load balance, and operating costs), and finally configures the weights to achieve the best by-product gas scheduling in steel enterprises.

[0101] Furthermore, the optimal scheduling of coal gas is realized based on the optimal solution. After determining the optimal solution, the final step of the by-product coal gas optimization scheduling model is to apply the optimal solution to the actual scheduling to complete the optimization scheduling process of the entire system. The specific process is as follows:

[0102] S1: Configuration of objective function weights:

[0103] Based on the optimal solution results in the previous part, the various costs (gas tank fluctuation penalty cost, boiler fluctuation penalty cost, energy and environmental cost) are reasonably weighted. By adjusting the weights of different objective functions, the performance of a certain aspect can be optimized according to the actual needs of the steel enterprise.

[0104] S2: Scheduling model execution:

[0105] After determining the weight of the objective function, it is introduced into the by-product gas optimization scheduling model. The model will automatically adjust the operation strategy of the gas system according to these weights to ensure that the scheduling of by-product gas of steel enterprises is completed with the lowest operating cost and the best energy efficiency under the premise of meeting various constraints.

[0106] S3: Dynamic monitoring and adjustment:

[0107] In the actual dispatching process, the byproduct gas management platform will monitor the operating status of the gas tank, boiler load, and the overall energy consumption and environmental emissions of the gas system in real time. If certain indicators are found to fluctuate, the system can dynamically adjust the weights to further optimize the dispatching strategy and ensure that the gas system is always in the best operating state.

[0108] S4: Final optimization effect:

[0109] Through scheduling execution based on the optimal solution, the by-product gas management platform of steel enterprises can effectively realize the reasonable scheduling of gas resources, minimize operating costs, improve energy efficiency, and ensure system stability and environmental compliance. Ultimately, the entire by-product gas system will achieve coordination and balance of various goals under the guidance of the optimal solution and achieve the best scheduling effect.

[0110] Furthermore, the penalty factor can be trained and optimized using historical data from ten consecutive days or one month. By analyzing and learning long-term data, the scheduling model can be adjusted more accurately to adapt to changes in different time periods and working conditions, thereby improving the accuracy and efficiency of scheduling.

[0111] Preferably, the multi-objective optimization problem in by-product gas scheduling is effectively solved by the Pareto algorithm. The method comprehensively considers factors such as gas tank stability, operating costs, and energy consumption, and can achieve optimal allocation of resources, improve energy utilization efficiency and production stability. At the same time, the dynamic adjustment mechanism of the penalty factor ensures the flexibility and adaptability of the scheduling process, avoiding the system instability caused by single optimization. This method not only reduces energy waste and production costs, but also promotes the green development and intelligent upgrading of steel enterprises, with significant economic and environmental benefits.

[0112] The beneficial effects of the present invention are as follows:

[0113] The present invention achieves the optimal balance of the complex relationship between gas tank stability, boiler stability and total cost by introducing the Pareto optimal principle; improves the adaptability and reliability of the system by real-time collection of operation data and real-time strategy optimization; ensures the accuracy and reliability of the optimization scheduling results by constructing the objective function and penalty factor

[0114] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0115] The principles and implementation methods of the present invention are described in this article using specific examples. The description of the above embodiments is only used to help understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for optimizing the scheduling of by-product gas based on Pareto optimality, characterized in that: include: Determine the objective function; The objective function includes: a gas tank fluctuation penalty cost function, a boiler fluctuation penalty cost function, and an energy and environmental cost function; Determining an initialization penalty factor according to the objective function; Collect gas recovery data and key production parameters to obtain operation data; Based on the Pareto optimal principle, the initialization penalty factor is adjusted using the operation data to obtain an optimal penalty factor; Based on the optimal penalty factor, weight configuration is performed on the objective function to obtain an optimal operation strategy; Updating the optimal operation strategy into the target by-product gas scheduling model; When the target by-product gas scheduling model is updated, the operation data is collected in real time; The optimal operation strategy is optimized based on the Pareto optimal principle using the operating data collected in real time.

2. The method for optimizing the scheduling of by-product gas based on Pareto optimality according to claim 1, characterized in that: The calculation formula of the objective function is: Z = min{GPC+BPC+EEC}; Among them, Z is the objective function; GPC is the gas tank fluctuation penalty cost function; BPC is the boiler fluctuation penalty cost function; EEC is the energy and environmental cost function.

3. The method for optimizing the scheduling of by-product gas based on Pareto optimality according to claim 1, characterized in that: The initialization penalty factor is inversely proportional to the volume of the gas tank during operation.

4. The method for optimizing the scheduling of by-product gas based on Pareto optimality according to claim 1, characterized in that: The initialization penalty factor is adjusted using the operation data based on the Pareto optimal principle to obtain an optimal penalty factor, including: The operation data is projected and displayed using the initialization penalty factor to obtain gas tank fluctuation data, boiler load change data, energy consumption data and environmental cost data; The Pareto optimal principle is used to eliminate the gas tank fluctuation data, the boiler load change data, the energy consumption data and the environmental cost data to obtain Pareto frontier data; The initialization penalty factors of different combinations are analyzed according to the Pareto front data to obtain the optimal penalty factor.

5. The method for optimizing the scheduling of by-product gas based on Pareto optimality according to claim 1, characterized in that: The gas recovery data includes: blast furnace gas data, coke oven gas data and converter gas data.

6. The method for optimizing the scheduling of by-product gas based on Pareto optimality according to claim 2, characterized in that: The calculation formula of the gas tank fluctuation penalty cost function is: Wherein, GPC is the gas tank fluctuation penalty cost function; GPC j GPF is the fluctuation penalty cost of the gas tank where the j-th by-product gas is located; j is the penalty factor of the gas tank where the j-th byproduct gas is located; ΔV j,t,dev 、V j,t 、V j,mid They are respectively the offset of the gas tank where the j-th by-product gas is located relative to the middle tank in the t-th period, the real-time tank position of the gas tank where the j-th by-product gas is located in the t-th period, and the middle tank position of the gas tank where the j-th by-product gas is located; G is the total number of by-product gas types; P is the total number of scheduling cycles.

7. The method for optimizing the scheduling of by-product gas based on Pareto optimality according to claim 6, characterized in that: The calculation formula of the boiler fluctuation penalty cost function is: Wherein, BPC is the boiler fluctuation penalty cost function; BPF 1s 、BPF 2s 、BPF 3s They are the first penalty factor, the second penalty factor and the third penalty factor respectively; It means that the ith boiler turns on the igniter of the gas tank where the jth byproduct gas is located in the tth cycle; It means that the i-th boiler shuts down the igniter of the gas tank where the j-th by-product gas is located in the t-th cycle; B is the total number of boilers.

8. The method for optimizing the scheduling of by-product gas based on Pareto optimality according to claim 7, characterized in that: The calculation formula of the energy and environmental cost function is: Wherein, EEC is the energy and environmental cost function; C flar , C wat , C elec are the unit price of by-product gas release, water unit price and electricity unit price respectively; V j,t,flar The emission volume of the gas tank where the j-th by-product gas is located in the t-th period; The water consumption of the ith boiler in the tth period; E t,pur is the amount of electricity purchased in the tth period; E t,dem is the total power demand in the tth period; E t,gen is the total power generation of the captive power plant in the tth period.

Images