Power generation scheduling method and device for metallurgical enterprise

Abstract

The invention discloses a power generation scheduling method and device for a metallurgical enterprise. The method comprises the following steps: acquiring power generation cost data and power purchase cost data of the metallurgical enterprise; obtaining energy management basic data of the metallurgical enterprise, and determining a dynamic balance constraint condition in the steel production process according to the energy management basic data; the generation amount of each type of coal gas, the consumption amount of the coal gas passing through different steel production processes and parameter data of the different steel production processes are obtained in real time, the production and consumption prediction model corresponding to the type of coal gas is input, and the generation amount of the type of coal gas within a preset duration and the consumption amount of the coal gas passing through each steel production process are output; according to the generation amount of each type of gas in the preset duration, the consumption amount of each steel production process, the dynamic balance constraint condition, the power generation cost data and the power purchase cost data, the power generation scheduling mode of the metallurgical enterprise is determined, peak shifting power generation optimal scheduling can be achieved under the condition that energy dynamic balance is guaranteed, and energy conservation and cost reduction are facilitated.

Description

Technical Field

[0001] The present invention relates to the field of metallurgical technology, and in particular to a power generation dispatching method and device for a metallurgical enterprise. Background Art

[0002] This section is intended to provide a background or context to the embodiments of the invention recited in the claims. No admission is made that the description herein is prior art by inclusion in this section.

[0003] In the current smelting production process of steel enterprises, high energy consumption is a major factor restricting the development of steel enterprises. In the current smelting production process, the consumption of gas and electricity accounts for a relatively high proportion of the total energy consumption of the enterprise. Combined with the changes in the company's own demand for gas and electricity in different production cycles, the selection of the process and timing of the mutual conversion of gas and electricity is crucial. At present, various metallurgical enterprises have set up professional gas and electricity dispatching commanders, formulated a number of dispatching plans, and standardized and guided the specific work of dispatching personnel on the premise of ensuring production needs to ensure the standardization and stability of smelting production.

[0004] However, in the existing power generation dispatching process, the dispatching process is easily affected by many factors such as data timeliness, the personal ability, experience, and equipment status of the dispatchers, which affects the rhythm control of energy balance and cannot accurately perform standardized power generation dispatching operations, resulting in energy waste and increased costs. Summary of the invention

[0005] The embodiment of the present invention provides a power generation scheduling method for a metallurgical enterprise, which is used to achieve peak-shifting power generation optimization scheduling under the condition of ensuring dynamic balance of energy, which is beneficial to energy saving and cost reduction. The method includes:

[0006] Obtain the power generation cost data and power purchase cost data of metallurgical enterprises, where the power purchase cost data includes the power purchase price data during peak hours, valley hours and normal hours;

[0007] Obtain the basic energy management data of the metallurgical enterprise, and determine the dynamic balance constraints in the steel production process based on the basic energy management data; the basic energy management data includes: steel production plan data, gas tank capacity limit data, and operating load data of generator equipment;

[0008] During the steel production process, the amount of each type of gas generated and the amount consumed in different steel production processes, as well as parameter data of different steel production processes, are obtained in real time;

[0009] Input the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as the parameter data of different steel production processes, into the production and consumption prediction model corresponding to the type of coal gas, and output the generation amount of the type of coal gas within a preset time period and the consumption amount through each steel production process;

[0010] The power generation dispatching method of the metallurgical enterprise is determined according to the generation amount of each type of coal gas within a preset time period and the consumption through each steel production process, the dynamic balance constraint conditions, the power generation cost data and the power purchase cost data.

[0011] The embodiment of the present invention further provides a power generation dispatching device for a metallurgical enterprise, which is used to achieve peak-shifting power generation optimization dispatching under the condition of ensuring dynamic balance of energy, which is beneficial to energy saving and cost reduction. The device includes:

[0012] The cost data acquisition module is used to obtain the power generation cost data and power purchase cost data of the metallurgical enterprise, wherein the power purchase cost data includes the power purchase price data during peak hours, valley hours and normal hours;

[0013] The dynamic balance constraint condition determination module is used to obtain the basic energy management data of the metallurgical enterprise and determine the dynamic balance constraint conditions in the steel production process based on the basic energy management data; the basic energy management data includes: steel production plan data, gas tank capacity limit data, and operating load data of generator set equipment;

[0014] A real-time data acquisition module is used to acquire the amount of each type of gas generated and the amount consumed in different steel production processes, as well as parameter data of different steel production processes in real time during the steel production process;

[0015] The first production and consumption prediction module is used to input the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as parameter data of different steel production processes, into the production and consumption prediction model corresponding to the type of coal gas, and output the generation amount of the type of coal gas within a preset time period and the consumption amount through each steel production process;

[0016] The power generation scheduling mode determination module is used to determine the power generation scheduling mode of the metallurgical enterprise based on the generation amount of each type of coal gas within a preset time period and the consumption through each steel production process, the dynamic balance constraint conditions, the power generation cost data and the power purchase cost data.

[0017] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the power generation scheduling method for the metallurgical enterprise when executing the computer program.

[0018] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the power generation scheduling method for the metallurgical enterprise is implemented.

[0019] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the power generation scheduling method for the metallurgical enterprise is implemented.

[0020] In an embodiment of the present invention, the power generation cost data and power purchase cost data of the metallurgical enterprise are obtained; the energy management basic data of the metallurgical enterprise are obtained, and the dynamic balance constraint conditions in the steel production process are determined based on the energy management basic data; in the steel production process, the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as the parameter data of different steel production processes are obtained in real time; the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as the parameter data of different steel production processes, are input into a production and consumption prediction model corresponding to the type of coal gas, and the generation amount of the type of coal gas within a preset time period and the consumption amount through each steel production process are output; the power generation scheduling method of the metallurgical enterprise is determined based on the generation amount of each type of coal gas within a preset time period and the consumption through each steel production process, the dynamic balance constraint conditions, the power generation cost data and the power purchase cost data.

[0021] The present invention determines the dynamic balance constraints in the steel production process and constructs a production and consumption prediction model for different types of coal gas, thereby achieving the goal of optimizing the scheduling of peak-shifting power generation in existing steel enterprises, that is, rationally utilizing existing energy, reducing waste, coordinating energy distribution, and achieving peak-shifting power generation on the basis of achieving relative energy balance, thereby achieving the goal of saving energy and reducing production costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 creative work. In the drawings:

[0023] Figure 1 It is a processing flow chart of the power generation scheduling method of a metallurgical enterprise in an embodiment of the present invention;

[0024] Figure 2 A flow chart of a method for determining dynamic balance constraint conditions in an embodiment of the present invention;

[0025] Figure 3A flowchart of the training and testing process of each production and consumption prediction model in an embodiment of the present invention;

[0026] Figure 4 A flow chart of a specific example of predicting the production and consumption of various types of coal gas in an embodiment of the present invention;

[0027] Figure 5 It is a structural schematic diagram of a power generation dispatching device for a metallurgical enterprise in an embodiment of the present invention;

[0028] Figure 6 The figure is a schematic diagram of the structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0029] To make the purpose, technical solution and advantages of the embodiments of the present invention more clear, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings. Here, the exemplary embodiments of the present invention and their descriptions are used to explain the present invention, but are not intended to limit the present invention.

[0030] Figure 1 FIG. 1 is a processing flow chart of the power generation dispatching method for a metallurgical enterprise in an embodiment of the present invention. Figure 1 As shown, the power generation scheduling method for a metallurgical enterprise in an embodiment of the present invention may include:

[0031] Step 101, obtaining power generation cost data and power purchase cost data of the metallurgical enterprise, wherein the power purchase cost data includes power purchase price data during peak hours, valley hours, and normal hours;

[0032] Step 102: Obtain the basic energy management data of the metallurgical enterprise, and determine the dynamic balance constraint conditions in the steel production process according to the basic energy management data; wherein the basic energy management data includes: steel production plan data, gas tank capacity limit data, and operating load data of the generator set equipment;

[0033] Step 103: During the steel production process, the amount of each type of coal gas generated and the amount of gas consumed in different steel production processes, as well as parameter data of different steel production processes, are obtained in real time;

[0034] Step 104: input the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as parameter data of different steel production processes, into the production and consumption prediction model corresponding to the type of coal gas, and output the generation amount of the type of coal gas within a preset time period and the consumption amount through each steel production process;

[0035] Step 105: Determine the power generation dispatching method of the metallurgical enterprise according to the generation amount of each type of coal gas within the preset time period and the consumption amount through each steel production process, the dynamic balance constraint condition, the power generation cost data and the power purchase cost data.

[0036] In the specific implementation, we can first obtain the power generation cost data and power purchase cost data of the metallurgical enterprise, where the power purchase cost data includes the power purchase price data during peak hours, valley hours and normal hours.

[0037] It should be noted that the power generation cost of metallurgical enterprises refers to the cost of converting different types of coal gas generated in the steel production process into corresponding electric energy through generator sets; the electricity generated by the enterprise can be used for the enterprise itself, including electricity used in the production process, daily life, etc.; in the specific operation of the steel production process, the coal gas energy generated in the steel production process can also be fully utilized for intermediate operations such as heating to improve the utilization rate of coal gas energy. In addition, in addition to converting coal gas energy into electric energy, electricity can also be purchased from outside. Generally speaking, the purchase price of electricity during peak hours is the highest, and the purchase price of electricity during valley hours is the lowest.

[0038] Next, step 102 is executed to obtain the basic energy management data of the metallurgical enterprise, and determine the dynamic balance constraints in the steel production process based on the basic energy management data; the basic energy management data includes: steel production plan data, gas tank capacity limitation data, and operating load data of generator equipment.

[0039] Figure 2 FIG. 1 is a flow chart of a method for determining dynamic balance constraint conditions in an embodiment of the present invention. Figure 2 As shown, in one embodiment, the method for determining the dynamic balance constraint condition includes:

[0040] Step 201: according to the steel production plan data, estimate the total amount of coal gas generated and the total amount of coal gas consumed in the steel production process;

[0041] Step 202: Determine the dynamic balance constraint conditions in the steel production process according to the estimated total gas generation, the estimated total gas consumption, the gas tank capacity limit data, and the operating load data of the generator set equipment.

[0042] In specific implementation, the total amount of gas generated may refer to the total amount of gas generated during the steel smelting process, and the total amount of gas consumed may refer to the total amount of gas consumed by power generation of generator sets, heating operations in the steel production process, etc. The unconsumed gas can also be temporarily stored in the gas tank for future use.

[0043] The dynamic balance constraint reflects the objective restriction rules in the steel production process, which can realize the dynamic balance monitoring of energy and dynamically calculate the energy production and consumption. For example, the gas content stored in the gas tank cannot be less than 30% of the capacity and cannot exceed 80% of the capacity; when the generator set generates electricity based on gas, the generator set cannot exceed its operating load, etc. Based on this, the relative balance of energy can be achieved according to different objective restriction rules.

[0044] In order to further improve the dynamic balance constraints, it is also possible to realize the pressure attenuation changes of each user end (equipment end corresponding to each production process) under different energy supply pressures based on properties such as the network management structure, the length of the current pipeline network, and the different pressure requirements of different pipeline locations, thereby improving the dynamic modeling of the energy balance rules.

[0045] After determining the dynamic balance constraints, the energy production and consumption data and real-time production data can be combined to display the dynamic real-time balance results using trend charts, energy flow charts, power flow charts and other graphic tools, thereby achieving real-time detection and dynamic display of energy balance.

[0046] Next, step 103 and step 104 are executed. During the steel production process, the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as the parameter data of different steel production processes can be obtained in real time; and the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as the parameter data of different steel production processes are input into the production and consumption prediction model corresponding to the type of coal gas, and the generation amount of the type of coal gas within a preset time period and the consumption amount through each steel production process are output.

[0047] In one embodiment, the gas type includes at least one of the following types or any combination: blast furnace gas, converter gas and coke oven gas; the steel production process includes at least one of the following processes or any combination: sintering, blast furnace, converter, continuous casting, steel rolling, lime kiln, power plant.

[0048] In one embodiment, each of the production and consumption prediction models corresponds to a type of gas, and is obtained by training the machine learning model based on historical parameter data of different steel production processes, the historical generation of this type of gas and the historical consumption through different steel production processes, as well as the actual generation of this type of gas and the actual consumption through different steel production processes after a preset time interval.

[0049] Figure 3 FIG. 4 is a flow chart of the training and testing process of each production and consumption prediction model in an embodiment of the present invention. Figure 3 As shown, in one embodiment, the training and testing process of each production and consumption prediction model includes:

[0050] Step 301: Use historical parameter data of different steel production processes, historical generation of corresponding types of coal gas and historical consumption of corresponding types of coal gas through different steel production processes, and actual generation of the type of coal gas and actual consumption of corresponding types of coal gas through different steel production processes after a preset time interval as sample data to construct a training set and a test set;

[0051] Step 302: training the machine learning model using the training set to obtain the production and consumption prediction model;

[0052] Step 303: Use the test set to test the production and consumption prediction model.

[0053] It should be noted that the types of gas generated or consumed in each steel production process are different. For example, the blast furnace process can only be used to generate blast furnace gas, while the steel rolling process can consume blast furnace gas, converter gas or coke oven gas. Therefore, in order to improve the prediction accuracy of gas generation and consumption, the corresponding production and consumption prediction model can be trained according to the actual characteristics of different types of gas, and then the generation and consumption of each type of gas can be predicted separately.

[0054] In specific implementation, the previous real-time calculation results of gas balance and the measurement and production data values ​​can be saved in the real-time and historical data tables respectively, and can be used to train the production and consumption prediction models corresponding to different types of gas. Taking the prediction of blast furnace gas generation and consumption as an example, blast furnace production is a continuous production. When the blast furnace air supply parameters and the air volume entering the furnace are stable, the generation of blast furnace gas is also uniform and continuous. The model can predict the generation of blast furnace gas based on the hourly air volume of the blast furnace, the oxygen enrichment, the current gas utilization rate of the furnace top and other data; the consumption of blast furnace gas can be predicted based on the differences in steel grades and specifications of the products produced in different processes such as steel rolling, and the unit consumption data of similar products in historical data can be extracted, and energy consumption can be predicted in combination with the actual situation of current production (such as the heating furnace entry temperature, the number of billets in the furnace, the time in the furnace, the distribution of billets in each section of the current furnace, the actual data of the required temperature for rolling, etc.).

[0055] In order to further improve the accuracy of the prediction of the production and consumption of various types of gas, the maintenance plan data of the production equipment can also be taken into account. In the actual steel production process, various production equipment needs to be regularly maintained, and the timing and duration of maintenance of different production equipment are also different. During the maintenance period, the corresponding equipment stops running, and the production and consumption of various types of gas will also change accordingly. Therefore, when predicting the production and consumption of various types of gas, it is also necessary to take into account the actual situation of the maintenance plan of the production equipment.

[0056] Figure 4 FIG. 1 is a flow chart of a specific example of predicting the production and consumption of various types of coal gas in an embodiment of the present invention. Figure 4 As shown, in one embodiment, it may also include:

[0057] Step 401, obtaining production equipment maintenance plan data; and estimating the downtime of different steel production processes in the steel production process according to the production equipment maintenance plan data;

[0058] Step 402: During the steel production process, the amount of each type of coal gas generated and the amount of gas consumed in different steel production processes, as well as parameter data of different steel production processes, are obtained in real time;

[0059] Step 403: Input the generation amount of each type of coal gas and the consumption amount through different steel production processes, parameter data of different steel production processes, and downtime of different steel production processes into a production and consumption prediction model corresponding to the type of coal gas, and output the generation amount of the type of coal gas within a preset time period and the consumption amount through each steel production process; each of the production and consumption prediction models is obtained by training a machine learning model based on historical parameter data of different steel production processes, historical downtime of different steel production processes, historical generation amount of the type of coal gas and historical consumption through different steel production processes, as well as actual generation amount of the type of coal gas after a preset time interval and actual consumption through different steel production processes.

[0060] In specific implementation, in order to further improve the flexibility and applicability of the production and consumption prediction model, the priorities of different steel production processes can be pre-set according to the actual production situation. For example, if the priority of the steel rolling process is higher than that of the continuous casting process, when the amount of gas available for the steel production process is limited, the available gas will be consumed in the steel rolling process first, which is more conducive to the smooth progress of steel production. After determining the priorities of different steel production processes, the historical data involving the execution priorities of different steel production processes can also be used as training data to train the machine learning model.

[0061] Finally, step 105 is executed to determine the power generation dispatching mode of the metallurgical enterprise according to the generation amount of each type of coal gas within the preset time period and the consumption through each steel production process, the dynamic balance constraint condition, the power generation cost data and the power purchase cost data.

[0062] In one embodiment, the power generation scheduling method of the metallurgical enterprise may include: increasing the gas consumption for power generation or reducing the gas consumption for power generation.

[0063] In the specific implementation, based on the comprehensive conditions of the difference in peak and valley electricity prices, the limited total amount of gas, the capacity of the gas storage device and the adjustable generator set, more gas is stored during peak electricity price periods, and more pre-stored gas is consumed during valley electricity price periods to generate electricity for self-use, thereby reducing the amount of electricity purchased during peak periods, reducing the total price of purchased electricity, and improving the utilization efficiency of self-generated electricity.

[0064] When the electricity price stage is in the peak period, if the blast furnace gas tank position is >50%, combined with the current predicted production and consumption difference results, such as total output > production user consumption + power generation consumption, the gas consumption can be increased according to the adjustment of the generator set that is not yet fully loaded, until the gas tank position can be stabilized within the 50% range. When the time period enters the end of the peak electricity price stage within half an hour, if the current load of the generator set is <rated load, and the predicted tank position is >30%, the gas consumption of power generation can continue to be increased until the predicted result is in the off-peak period, and the tank position drops to less than 30%. When used, the decision tree algorithm is used to make decisions and optimize different scheduling schemes and prediction results.

[0065] In addition, to ensure that power generation and dispatching are carried out under safe production conditions, an online early warning mechanism can also be added. When the production and consumption difference gradually increases, the production and consumption prediction model can be used to predict the future changes in gas tank positions, the time when the upper and lower limits are reached, and the necessary release time, so as to remind gas dispatchers to make dispatching preparations in advance; if the overall gas pipeline network still has loads that can be adjusted (such as generator sets), then consider increasing / reducing the load of downstream users at the same time to reduce or slow down the increase and decrease rate of the production and consumption difference.

[0066] The power generation scheduling method for a metallurgical enterprise in the embodiment of the present invention includes the following beneficial effects:

[0067] (1) The present invention can establish dynamic balance monitoring of enterprise energy, dynamically calculate energy production and consumption, and achieve relative balance of energy. Combined with production performance and process information, establish energy consumption analysis and prediction of key production capacity and energy-consuming equipment, and use the results of energy production and consumption prediction to warn of abnormal energy production and consumption indicators that may occur in the future, and combine energy scheduling plans to achieve energy scheduling in advance. And use the historical data regression of the energy scheduling plan to improve the post-optimization of the energy scheduling plan.

[0068] (2) The present invention can realize the autonomous optimization of energy scheduling schemes and dynamically realize energy balance prediction and scheduling. While reducing the labor intensity of energy scheduling and management personnel, it also reduces the dependence on the knowledge of the above personnel. Take a steel enterprise with an annual production capacity of 3 million tons as an example. Reduce the emission of energy media; the efficiency of gas power generation is increased by 5%, generating an economic benefit of about 2 million.

[0069] (2) The present invention can establish a mathematical model based on the cost of purchasing electricity during peak, valley and normal periods and the cost of self-generated electricity (fuel cost, electricity cost), fully considering the active power demand, reactive power demand and steam demand of each user, and at the same time combining factors such as unit equipment capacity limitation, maintenance plan, fuel supply situation, load change curve, and gas tank position change to formulate a cost-optimal peak-shifting power generation proposal plan, guide each generator set to generate more electricity during peak hours and store more gas during valley hours, and fully utilize the buffering capacity of each gas tank and the regulating capacity of the generator set under the premise of ensuring production, so as to achieve the optimal utilization of secondary energy.

[0070] The present invention also provides a power generation dispatching device for a metallurgical enterprise, as described in the following embodiments. Since the principle of solving the problem by the device is similar to the power generation dispatching method of the metallurgical enterprise, the implementation of the device can refer to the implementation of the power generation dispatching method of the metallurgical enterprise, and the repeated parts will not be repeated.

[0071] Figure 5 Schematic diagram of the structure of the power generation dispatching device of a metallurgical enterprise in an embodiment of the present invention. Figure 5 As shown, the power generation dispatching device of a metallurgical enterprise in the embodiment of the present invention may specifically include:

[0072] The cost data acquisition module 501 is used to acquire the power generation cost data and power purchase cost data of the metallurgical enterprise, wherein the power purchase cost data includes the power purchase price data during the peak period, the valley period and the normal period;

[0073] The dynamic balance constraint condition determination module 502 is used to obtain the basic energy management data of the metallurgical enterprise and determine the dynamic balance constraint conditions in the steel production process according to the basic energy management data; wherein the basic energy management data includes: steel production plan data, gas tank capacity limit data, and operating load data of the generator set equipment;

[0074] The real-time data acquisition module 503 is used to acquire the amount of each type of coal gas generated and the amount of gas consumed in different steel production processes, as well as parameter data of different steel production processes in real time during the steel production process;

[0075] The first production and consumption prediction module 504 is used to input the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as parameter data of different steel production processes, into the production and consumption prediction model corresponding to the type of coal gas, and output the generation amount of the type of coal gas within a preset time period and the consumption amount through each steel production process;

[0076] The power generation scheduling mode determination module 505 is used to determine the power generation scheduling mode of the metallurgical enterprise according to the generation amount of each type of coal gas within a preset time period and the consumption through each steel production process, the dynamic balance constraint conditions, the power generation cost data and the power purchase cost data.

[0077] In one embodiment, the dynamic balance constraint condition determination module 502 is specifically used to:

[0078] Based on the steel production plan data, the total amount of gas generated and consumed in the steel production process is estimated;

[0079] The dynamic balance constraints in the steel production process are determined based on the estimated total gas generation, the estimated total gas consumption, the gas tank capacity limitation data, and the operating load data of the generator set equipment.

[0080] In one embodiment, the gas type includes at least one or any combination of the following types:

[0081] Blast furnace gas, converter gas and coke oven gas;

[0082] The steel production process includes at least one or any combination of the following processes:

[0083] Sintering, blast furnace, converter, continuous casting, steel rolling, lime kiln, power plant.

[0084] In one embodiment, each of the production and consumption prediction models corresponds to a type of gas, and is obtained by training the machine learning model based on historical parameter data of different steel production processes, the historical generation of this type of gas and the historical consumption through different steel production processes, as well as the actual generation of this type of gas and the actual consumption through different steel production processes after a preset time interval.

[0085] In one embodiment, the training and testing process of each production and consumption prediction model includes:

[0086] The historical parameter data of different steel production processes, the historical generation amount of the corresponding type of gas and the historical consumption of the corresponding type of gas through different steel production processes, as well as the actual generation amount of the type of gas and the actual consumption of the corresponding type of gas through different steel production processes after a preset time interval are used as sample data to construct training sets and test sets;

[0087] Using the training set to train the machine learning model to obtain the production and consumption prediction model;

[0088] The production and consumption prediction model is tested using the test set.

[0089] In one embodiment, a second production and consumption prediction module is further included, which is specifically used to:

[0090] Obtaining production equipment maintenance plan data; based on the production equipment maintenance plan data, estimating the downtime of different steel production processes in the steel production process;

[0091] During the steel production process, the amount of each type of gas generated and the amount consumed in different steel production processes, as well as parameter data of different steel production processes, are obtained in real time;

[0092] The generation amount of each type of coal gas and the consumption amount through different steel production processes, the parameter data of different steel production processes, and the downtime of different steel production processes are input into the production and consumption prediction model corresponding to the type of coal gas, and the generation amount of this type of coal gas within a preset time period and the consumption amount through each steel production process are output; each of the production and consumption prediction models is obtained by training a machine learning model based on the historical parameter data of different steel production processes, the historical downtime of different steel production processes, the historical generation amount of this type of coal gas and the historical consumption through different steel production processes, as well as the actual generation amount of this type of coal gas after a preset time interval and the actual consumption through different steel production processes.

[0093] In one embodiment, the power generation scheduling method of the metallurgical enterprise includes:

[0094] Increase gas consumption for power generation or reduce gas consumption for power generation.

[0095] Based on the above invention concept, Figure 6 As shown, the present invention also proposes a computer device 600, including a memory 610, a processor 620, and a computer program 630 stored in the memory 610 and executable on the processor 620, wherein the processor 620 implements the aforementioned power generation scheduling method for the metallurgical enterprise when executing the computer program 630.

[0096] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the power generation scheduling method for the metallurgical enterprise is implemented.

[0097] An embodiment of the present invention further provides a computer program product, which includes a computer program. When the computer program is executed by a processor, the power generation scheduling method for the metallurgical enterprise is implemented.

[0098] To summarize, in an embodiment of the present invention, the power generation cost data and power purchase cost data of a metallurgical enterprise are obtained; the energy management basic data of the metallurgical enterprise are obtained, and the dynamic balance constraints in the steel production process are determined based on the energy management basic data; in the steel production process, the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as the parameter data of different steel production processes are obtained in real time; the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as the parameter data of different steel production processes, are input into a production and consumption prediction model corresponding to the type of coal gas, and the generation amount of the type of coal gas within a preset time period and the consumption amount through each steel production process are output; the power generation scheduling method of the metallurgical enterprise is determined based on the generation amount of each type of coal gas within a preset time period and the consumption through each steel production process, the dynamic balance constraints, the power generation cost data and the power purchase cost data.

[0099] The present invention determines the dynamic balance constraints in the steel production process and constructs a production and consumption prediction model for different types of coal gas, thereby achieving the goal of optimizing the scheduling of peak-shifting power generation in existing steel enterprises, that is, rationally utilizing existing energy, reducing waste, coordinating energy distribution, and achieving peak-shifting power generation on the basis of achieving relative energy balance, thereby achieving the goal of saving energy and reducing production costs.

[0100] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0101] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0102] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0103] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0104] The specific embodiments described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A power generation dispatching method for a metallurgical enterprise, characterized in that: include: Obtain the power generation cost data and power purchase cost data of metallurgical enterprises, where the power purchase cost data includes the power purchase price data during peak hours, valley hours and normal hours; Obtain the basic energy management data of metallurgical enterprises and determine the dynamic balance constraints in the steel production process based on the basic energy management data; The basic data for energy management include: steel production plan data, gas tank capacity limit data, and operating load data of generator equipment; During the steel production process, the amount of each type of gas generated and the amount consumed in different steel production processes, as well as parameter data of different steel production processes, are obtained in real time; Input the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as the parameter data of different steel production processes, into the production and consumption prediction model corresponding to the type of coal gas, and output the generation amount of the type of coal gas within a preset time period and the consumption amount through each steel production process; The power generation dispatching method of the metallurgical enterprise is determined according to the generation amount of each type of coal gas within a preset time period and the consumption through each steel production process, the dynamic balance constraint conditions, the power generation cost data and the power purchase cost data.

2. The method according to claim 1, characterized in that Based on the basic data of energy management, the dynamic balance constraints in the steel production process are determined, including: Based on the steel production plan data, the total amount of gas generated and consumed in the steel production process is estimated; The dynamic balance constraints in the steel production process are determined based on the estimated total gas generation, the estimated total gas consumption, the gas tank capacity limitation data, and the operating load data of the generator set equipment.

3. The method according to claim 1, characterized in that The gas type includes at least one of the following types or any combination thereof: Blast furnace gas, converter gas and coke oven gas; The steel production process includes at least one or any combination of the following processes: Sintering, blast furnace, converter, continuous casting, steel rolling, lime kiln, power plant.

4. The method according to claim 1, characterized in that Each of the production and consumption prediction models corresponds to a type of gas, and is obtained by training the machine learning model based on the historical parameter data of different steel production processes, the historical generation of this type of gas and the historical consumption through different steel production processes, as well as the actual generation of this type of gas and the actual consumption through different steel production processes after a preset time interval.

5. The method according to claim 4, wherein the training and testing process of each production and consumption prediction model comprises: The historical parameter data of different steel production processes, the historical generation amount of the corresponding type of gas and the historical consumption of the corresponding type of gas through different steel production processes, as well as the actual generation amount of the type of gas and the actual consumption of the corresponding type of gas through different steel production processes after a preset time interval are used as sample data to construct training sets and test sets; Using the training set to train the machine learning model to obtain the production and consumption prediction model; The production and consumption prediction model is tested using the test set.

6. The method according to claim 1, characterized in that Also includes: Obtaining production equipment maintenance plan data; based on the production equipment maintenance plan data, estimating the downtime of different steel production processes in the steel production process; During the steel production process, the amount of each type of gas generated and the amount consumed in different steel production processes, as well as parameter data of different steel production processes, are obtained in real time; The generation amount of each type of coal gas and the consumption amount through different steel production processes, the parameter data of different steel production processes, and the downtime of different steel production processes are input into the production and consumption prediction model corresponding to the type of coal gas, and the generation amount of this type of coal gas within a preset time period and the consumption amount through each steel production process are output; each of the production and consumption prediction models is obtained by training a machine learning model based on the historical parameter data of different steel production processes, the historical downtime of different steel production processes, the historical generation amount of this type of coal gas and the historical consumption through different steel production processes, as well as the actual generation amount of this type of coal gas after a preset time interval and the actual consumption through different steel production processes.

7. The method according to claim 1, characterized in that The power generation dispatching methods of the metallurgical enterprise include: Increase gas consumption for power generation or reduce gas consumption for power generation.

8. A power generation dispatching device for a metallurgical enterprise, characterized in that: include: The cost data acquisition module is used to obtain the power generation cost data and power purchase cost data of the metallurgical enterprise, wherein the power purchase cost data includes the power purchase price data during peak hours, valley hours and normal hours; The dynamic balance constraint condition determination module is used to obtain the basic energy management data of the metallurgical enterprise and determine the dynamic balance constraint conditions in the steel production process based on the basic energy management data; The basic data for energy management include: steel production plan data, gas tank capacity limit data, and operating load data of generator equipment; A real-time data acquisition module is used to acquire the amount of each type of gas generated and the amount consumed in different steel production processes, as well as parameter data of different steel production processes in real time during the steel production process; The first production and consumption prediction module is used to input the generation amount of each type of coal gas and the consumption amount through different steel production processes, as well as parameter data of different steel production processes, into the production and consumption prediction model corresponding to the type of coal gas, and output the generation amount of the type of coal gas within a preset time period and the consumption amount through each steel production process; The power generation scheduling mode determination module is used to determine the power generation scheduling mode of the metallurgical enterprise based on the generation amount of each type of coal gas within a preset time period and the consumption through each steel production process, the dynamic balance constraint conditions, the power generation cost data and the power purchase cost data.

9. The device according to claim 8, characterized in that The dynamic balance constraint condition determination module is specifically used for: Based on the steel production plan data, the total amount of gas generated and consumed in the steel production process is estimated; The dynamic balance constraints in the steel production process are determined based on the estimated total gas generation, the estimated total gas consumption, the gas tank capacity limitation data, and the operating load data of the generator set equipment.

10. The device according to claim 8, characterized in that The gas type includes at least one of the following types or any combination thereof: Blast furnace gas, converter gas and coke oven gas; The steel production process includes at least one or any combination of the following processes: Sintering, blast furnace, converter, continuous casting, steel rolling, lime kiln, power plant.

11. The device according to claim 8, characterized in that Each of the production and consumption prediction models corresponds to a type of gas, and is obtained by training the machine learning model based on the historical parameter data of different steel production processes, the historical generation of this type of gas and the historical consumption through different steel production processes, as well as the actual generation of this type of gas and the actual consumption through different steel production processes after a preset time interval.

12. The device according to claim 11, characterized in that The training and testing process of each production and consumption prediction model includes: The historical parameter data of different steel production processes, the historical generation amount of the corresponding type of gas and the historical consumption of the corresponding type of gas through different steel production processes, as well as the actual generation amount of the type of gas and the actual consumption of the corresponding type of gas through different steel production processes after a preset time interval are used as sample data to construct training sets and test sets; Using the training set to train the machine learning model to obtain the production and consumption prediction model; The production and consumption prediction model is tested using the test set.

13. The device according to claim 8, characterized in that It also includes a second production and consumption prediction module, which is specifically used for: Obtaining production equipment maintenance plan data; based on the production equipment maintenance plan data, estimating the downtime of different steel production processes in the steel production process; During the steel production process, the amount of each type of gas generated and the amount consumed in different steel production processes, as well as parameter data of different steel production processes, are obtained in real time; The generation amount of each type of coal gas and the consumption amount through different steel production processes, the parameter data of different steel production processes, and the downtime of different steel production processes are input into the production and consumption prediction model corresponding to the type of coal gas, and the generation amount of this type of coal gas within a preset time period and the consumption amount through each steel production process are output; each of the production and consumption prediction models is obtained by training a machine learning model based on the historical parameter data of different steel production processes, the historical downtime of different steel production processes, the historical generation amount of this type of coal gas and the historical consumption through different steel production processes, as well as the actual generation amount of this type of coal gas after a preset time interval and the actual consumption through different steel production processes.

14. The device according to claim 8, characterized in that The power generation dispatching methods of the metallurgical enterprise include: Increase gas consumption for power generation or reduce gas consumption for power generation.

15. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

16. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

17. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images