Control method and device of steam power system, storage medium and processor

Abstract

The invention provides a control method and device of a steam power system, a storage medium and a processor. The method comprises the steps that a plurality of boiler energy efficiency models corresponding to a plurality of boilers are established; establishing a plurality of steam turbine energy efficiency models corresponding to the plurality of steam turbines; at the initial moment of the multiple time periods, multiple steam demanded quantities of the steam power system in the multiple time periods are obtained, and multiple steam turbine target operation efficiencies and multiple boiler target operation efficiencies are determined according to the multiple steam demanded quantities, the multiple constraint conditions and the load dispatching optimization model; according to the multiple steam turbine target operation efficiencies, the multiple boiler target operation efficiencies, the multiple boiler energy efficiency models and the multiple steam turbine energy efficiency models, operation loads of the multiple boilers and operation loads of the multiple steam turbines are determined; and the multiple boilers and the multiple steam turbines are controlled to operate according to the operation loads of the multiple boilers and the operation loads of the multiple steam turbines, and then control over the steam power system is achieved.

Description

Technical Field

[0001] This application relates to the field of smart heating technology, and more specifically, to a control method for a steam power system, a control device for a steam power system, a computer-readable storage medium, a processor, and an electronic device. Background Technology

[0002] Steam power systems are widely used in power plants, petrochemical plants, metallurgical plants, paper mills, and combined heat and power (CHP) enterprises. To more flexibly meet production heat load demands, most enterprises adopt a multi-furnace, multi-unit busbar operation mode. Steam from multiple furnaces mixes in the busbar and becomes the unified heat load for subsequent production. Therefore, the stability of the busbar steam pressure is crucial for subsequent process production. Achieving stable control of the busbar steam pressure requires considering the balanced distribution of loads across the furnaces. Because the combustion states of multiple boilers are not uniform, parallel operation often leads to load competition, resulting in significant load deviations between boilers, delayed dynamic response time, difficulty in coordinating boiler and turbine control, inability to respond promptly to changes in production heat load demands, large fluctuations in busbar pressure, and poor stability. These problems significantly impact the stability of subsequent production operations and severely affect the overall economic efficiency of the unit. Summary of the Invention

[0003] The main objective of this application is to provide a control method for a steam power system, a control device for a steam power system, a computer-readable storage medium, a processor, and an electronic device, so as to at least solve the problem that the prior art cannot simultaneously optimize multiple devices in a steam power system.

[0004] To achieve the above objectives, according to one aspect of this application, a control method for a steam power system is provided, comprising: establishing multiple boiler energy efficiency models corresponding to the multiple boilers based on their historical operating efficiency and historical steam output over the same multiple time periods; establishing multiple turbine energy efficiency models corresponding to the multiple turbines based on first historical data of the multiple turbines in the same multiple time periods, wherein the first historical data includes: the turbine's steam inlet flow rate, operating load, extraction steam flow rate, exhaust steam flow rate, inlet steam pressure, exhaust steam pressure, extraction steam pressure, exhaust steam temperature, extraction steam temperature, and inlet steam temperature; and at the initial stage of the multiple time periods... The system acquires multiple steam demands of the steam power system within multiple time periods, and determines multiple target operating efficiencies of steam turbines and multiple target operating efficiencies of boilers based on the multiple steam demands, multiple constraints, and a load scheduling optimization model. Based on the multiple target operating efficiencies of steam turbines, multiple target operating efficiencies of boilers, multiple boiler energy efficiency models, and multiple steam turbine energy efficiency models, the system determines the operating loads of multiple boilers and multiple steam turbines. Based on the operating loads of the multiple boilers and multiple steam turbines, the system controls the operation of the multiple boilers and multiple steam turbines, thereby achieving control of the steam power system.

[0005] Optionally, obtaining multiple steam demands of the steam power system within multiple time periods includes: establishing a steam load prediction model based on second historical data and multiple algorithms, wherein the steam load prediction model is used to predict the steam demand within a future preset time period based on first real-time data, and the second historical data and the first real-time data include at least: steam flow rate, fuel type, and equipment parameters of the steam power system; obtaining the first real-time data at the start time of each time period, and determining the steam demand for each time period based on the first real-time data and the steam load prediction model.

[0006] Optionally, establishing multiple turbine energy efficiency models corresponding to multiple turbines includes: acquiring the first historical data of multiple turbines within the same multiple time periods; determining the inlet steam enthalpy, extraction steam enthalpy, and exhaust steam enthalpy of multiple turbines based on the thermodynamic property equation of steam, the inlet steam pressure, and the inlet steam temperature of multiple turbines; and establishing multiple turbine energy efficiency models based on the energy balance formula, the inlet steam flow rate, the extraction steam flow rate, the inlet steam enthalpy, the extraction steam enthalpy, and the exhaust steam enthalpy of multiple turbines.

[0007] Optionally, the control method further includes: obtaining the operating load curve of the steam turbine based on the steam turbine energy efficiency model and multiple second real-time data, wherein the operating load curve represents the steam intake of the steam turbine at different operating efficiencies, and the second real-time data and the first historical data have the same parameter types; dividing the operating load curve into multiple regions, and establishing multiple steam turbine energy efficiency sub-models with linear characteristics based on the relationship between the operating efficiency and the steam intake represented by the multiple regions.

[0008] Optionally, obtaining the operating load curve of the steam turbine based on the steam turbine energy efficiency model and the second real-time data includes: acquiring the second real-time data of multiple steam turbines at multiple identical time periods; determining the real-time inlet steam enthalpy, extraction steam enthalpy, and exhaust steam enthalpy of multiple steam turbines based on the thermodynamic property equation of steam, the real-time inlet steam pressure, and the inlet steam temperature of multiple steam turbines; determining the real-time target operating efficiency of multiple steam turbines based on the steam turbine energy efficiency model, the real-time inlet steam flow rate, the extraction steam flow rate, the inlet steam enthalpy, the extraction steam enthalpy, and the exhaust steam enthalpy of multiple steam turbines; determining the target inlet steam flow rate based on the real-time extraction steam flow rate, the inlet steam enthalpy, the extraction steam enthalpy, the exhaust steam enthalpy, the steam turbine mechanical efficiency, the steam turbine power generation efficiency, and the steam turbine output power; and obtaining the operating load curve based on the multiple target operating efficiencies and the multiple target inlet steam flows rate.

[0009] Optionally, the control method further includes: determining the turbine output power based on the steam inlet flow rate, the steam inlet enthalpy, the exhaust enthalpy, the turbine mechanical efficiency, and the turbine power generation efficiency when the turbine has not undergone steam extraction treatment; and determining the turbine output power based on the steam inlet flow rate, the steam extraction flow rate, the steam extraction enthalpy, the steam inlet enthalpy, the exhaust enthalpy, the turbine mechanical efficiency, and the turbine power generation efficiency when the turbine has undergone steam extraction treatment.

[0010] Optionally, the load dispatch optimization model is constructed based on the total operating cost of the steam power system, the start-up and shutdown status of the steam power system, the depreciation cost of the steam power system, the fuel price, the fuel consumption, the price of purchased steam, the steam demand, the price of purchased electricity, and the power supply of purchased electricity.

[0011] According to another aspect of this application, an optimized control device for a steam power system is provided, comprising: a first establishment module, configured to establish multiple boiler energy efficiency models corresponding to the multiple boilers based on the historical operating efficiency and historical steam output of multiple boilers of the steam power system in the same multiple time periods; a second establishment module, configured to establish multiple turbine energy efficiency models corresponding to the multiple turbines based on first historical data of multiple turbines of the steam power system in the same multiple time periods, wherein the first historical data includes: the steam inlet flow rate, operating load, extraction steam flow rate, exhaust steam flow rate, inlet steam pressure, and inlet steam temperature of the turbines; and a first determination module, configured to acquire multiple time periods at the initial moment of the multiple time periods. The system has several functions: a first, a steam power system; a second, a steam demand determination module; a third, a boiler control module; and a fourth, a control module. The first function determines the target operating efficiency of the steam power system based on the steam demand, constraints, and a load scheduling optimization model. The second function determines the operating load of the boilers and the turbines based on the target operating efficiencies of the steam turbines, the boilers, the boilers, and the turbines.

[0012] According to another aspect of this application, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device where the computer-readable storage medium is located to perform the control method of the steam power system.

[0013] According to another aspect of this application, a processor is provided for running a program, wherein the program executes the control method of the steam power system when it runs.

[0014] Applying the technical solution of this application, firstly, based on the historical operating efficiency and historical steam output of multiple boilers in the steam power system over the same multiple time periods, multiple boiler energy efficiency models are established corresponding to the multiple boilers; based on the first historical data of multiple steam turbines in the steam power system over the same multiple time periods, multiple steam turbine energy efficiency models are established corresponding to the multiple steam turbines; at the initial moment of multiple time periods, multiple steam demands of the steam power system within multiple time periods are obtained, and based on multiple steam demands, multiple constraints, and a load scheduling optimization model, the target operating efficiencies of multiple steam turbines and multiple boilers are determined; based on the target operating efficiencies of multiple steam turbines, multiple boilers, multiple boiler energy efficiency models, and multiple steam turbine energy efficiency models, the operating loads of multiple boilers and multiple steam turbines are determined; based on the operating loads of multiple boilers and multiple steam turbines respectively, the operation of multiple boilers and multiple steam turbines is controlled, thereby achieving control of the steam power system. Through the above method, the simultaneous control of multiple boilers and multiple steam turbines is achieved, and the load distribution of multiple boilers and multiple steam turbines is performed, solving the problem that the prior art cannot simultaneously optimize multiple devices in a steam power system. Attached Figure Description

[0015] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:

[0016] Figure 1 A hardware structure block diagram of a mobile terminal for executing a control method for a steam power system according to an embodiment of this application is shown.

[0017] Figure 2 A schematic flowchart of a control method for a steam power system according to an embodiment of this application is shown.

[0018] Figure 3 A schematic diagram of a boiler energy efficiency model provided according to an embodiment of this application is shown;

[0019] Figure 4 A schematic diagram of a steam turbine energy efficiency model provided according to an embodiment of this application is shown;

[0020] Figure 5 A schematic flowchart illustrating the process of establishing a steam load prediction model according to an embodiment of this application is shown.

[0021] Figure 6 A flowchart illustrating the loss analysis model provided according to an embodiment of this application is shown;

[0022] Figure 7A structural block diagram of a control device for a steam power system according to an embodiment of this application is shown;

[0023] The above figures include the following reference numerals:

[0024] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0025] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate for the embodiments of this application described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] As described in the background section, steam power systems are widely used in power, petrochemical, metallurgical, papermaking, and combined heat and power (CHP) enterprises. To more flexibly meet production heat load demands, most enterprises adopt a multi-furnace, multi-machine busbar operation mode. Steam from multiple furnaces mixes in the busbar and becomes the unified heat load for subsequent production. Therefore, the stability of the busbar steam pressure is crucial for subsequent processes. Achieving stable control of the busbar steam pressure requires considering the balanced distribution of loads from each furnace. Due to the inconsistent combustion states of multiple boilers, parallel operation often leads to load competition, resulting in significant load deviations between boilers, delayed dynamic response time, difficulty in coordinating boiler and turbine control, inability to respond promptly to changes in production heat load demands, large fluctuations in busbar pressure, and poor stability. These problems significantly impact the stability of subsequent production operations and severely affect the overall economic efficiency of the unit. To address the problem of the inability to simultaneously optimize multiple devices in a steam power system in existing technologies, embodiments of this application provide a control method for a steam power system, a control device for a steam power system, a computer-readable storage medium, a processor, and electronic equipment.

[0029] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0030] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a control method of a steam power system according to an embodiment of the present invention. (See diagram below.) Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0031] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the control method of the steam power system in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0032] This embodiment provides a control method for a steam power system that runs on a mobile terminal, computer terminal, or similar computing device. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Also, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0033] Figure 2 This is a flowchart of a control method for a steam power system according to an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0034] Step S1: Based on the historical operating efficiency and historical steam output of multiple boilers in the steam power system over the same multiple time periods, establish multiple boiler energy efficiency models corresponding to the multiple boilers. Figure 3 As a representation of the boiler energy efficiency model, in Figure 3 The paper involves six boiler models (boiler energy efficiency models), and illustrates the relationship between the evaporation rate and steam output (the steam production rate) - efficiency (the operating efficiency) of the above six boiler models.

[0035] Specifically, the enthalpy change of the circulating air within the boiler is calculated by measuring the inlet and outlet temperatures, composition, and pressure of the circulating air. The enthalpy difference of heat absorption is calculated using the pressure and temperature of the boiler feedwater and steam. The boiler efficiency is calculated in real-time based on the heat absorbed by the steam-water system and the heat released by the circulating air within the furnace, using the system's performance calculation function. Regression analysis is performed using historical boiler efficiency and boiler evaporation data to establish a boiler energy efficiency curve model (the aforementioned boiler energy efficiency model). Optimizing fuel supply through big data analysis ensures maximum energy utilization efficiency. The establishment of the boiler energy efficiency model helps to accurately predict boiler efficiency under different loads, reduce energy waste, and improve operational economy.

[0036] Step S2: Based on the first historical data of multiple steam turbines in the steam power system at the same multiple time periods, establish multiple steam turbine energy efficiency models corresponding to multiple steam turbines. The first historical data includes: steam inlet flow rate, operating load, extraction steam flow rate, exhaust steam flow rate, inlet steam pressure, exhaust steam pressure, extraction steam pressure, exhaust steam temperature, extraction steam temperature and inlet steam temperature of the steam turbine.

[0037] Specifically, the operating performance (heat rate, steam rate) of a steam turbine is related to the inlet steam parameters (flow rate, temperature, pressure), cold-end parameters (exhaust steam pressure, ambient temperature), and heating extraction steam parameters (flow rate, temperature, pressure). Figure 4 The system provides a representation of the turbine energy efficiency model. Through the calculation function provided by the system, the turbine efficiency and steam intake under different loads (power generation) and extraction steam volume can be calculated in real time. The system establishes a linear regression calculation model based on historical operating big data of steam intake, load, and extraction steam volume, and establishes the turbine energy efficiency model. Based on the calculation model, the predicted future operating status of the turbine performance (such as turbine power generation and turbine efficiency) can be obtained.

[0038] Step S3: At the initial moment of multiple time periods, obtain multiple steam demands of the steam power system within multiple time periods, and determine multiple target operating efficiencies of steam turbines and multiple target operating efficiencies of boilers based on multiple steam demands, multiple constraints and load scheduling optimization models.

[0039] Specifically, the constraints mentioned above include conservation of mass, conservation of energy, limitations on equipment capacity, and energy and electricity demand. Among these:

[0040] The mass conservation constraint states that the mass of the medium, such as steam entering and leaving each steam turbine and water entering and leaving each boiler, is equal.

[0041]

[0042] Among them, F n,in F is the mass flow rate of the medium entering device n. n,out Let be the mass flow rate of the medium leaving device n.

[0043] The energy balance constraint is that the energy carried by the medium entering each steam turbine and boiler is equal to the sum of the output energy of each device, the energy carried by the output medium of each device, and the heat dissipation losses of the devices.

[0044]

[0045] Where n is the number of n devices, F n,in F is the mass flow rate of the medium entering device n. n,out H is the mass flow rate of the medium leaving device n. n,in The specific enthalpy of the medium entering device n; H n,out W is the specific enthalpy of the medium leaving device n. n Q is the power output of device n; n Let n be the heat loss of device n.

[0046] Equipment capacity constraints require that the operating load of each piece of equipment, such as boilers, steam turbines, and pipelines, must be controlled within the range that can be adjusted according to the design load.

[0047] F n,out,min ≤F n,out ≤F n,out,max ;

[0048] F n,in,min ≤F n,in ≤F n,out,max ;

[0049] Among them, F n,in F is the mass flow rate of the medium entering device n. n,out F is the mass flow rate of the medium leaving device n. n,out,min F is the minimum mass flow rate of the medium leaving device n. n,out,max F is the maximum mass flow rate of the medium leaving device n. n,in,min F represents the minimum mass flow rate of the medium entering device n. n,out,max The maximum mass flow rate of the medium entering device n.

[0050] The work capacity constraint is that the work capacity of each steam turbine must be maintained within a relatively reasonable range:

[0051] W n,min ≤W n ≤W n,max ;

[0052] Among them, W n,min W is the minimum power output of device n. n,max Let n be the maximum power output by device n.

[0053] Demand constraints mainly refer to the requirement that the energy medium and energy output from each boiler and steam turbine must meet the steam consumption and electricity demand of downstream equipment and devices.

[0054]

[0055] Where n is the number of the nth boiler / turbine; s is the steam type, such as s=1 for high-pressure steam, s=2 for medium-pressure steam; k is the statistical time period; F n,s,k F represents the type s steam produced by the nth device during time period k; s,k For period k, the amount of type S steam supplied / purchased externally; F s,dem,k W represents the total demand for type S steam during time period k; n Let P be the power generation capacity of the nth steam turbine. dem This represents the total power demand of the system.

[0056] Step S4: Based on the target operating efficiencies of multiple steam turbines, the target operating efficiencies of multiple boilers, the energy efficiency models of multiple boilers, and the energy efficiency models of multiple steam turbines, determine the operating loads of multiple boilers and multiple steam turbines.

[0057] Specifically, based on the target operating efficiency of the steam turbine and boiler, and combined with the predictions of their respective energy efficiency models, the theoretical steam intake or fuel consumption of each steam turbine and boiler is calculated and converted into actual operating load commands. This reduces manual intervention, automatically adjusts the operating load, achieves precise equipment control, improves the level of operational automation, and ensures that heat and power demands are met in a timely and economical manner.

[0058] Step S5: Based on the operating loads of multiple boilers and multiple steam turbines, control the operation of multiple boilers and multiple steam turbines respectively, thereby realizing the control of the steam power system.

[0059] Specifically, control commands are sent to each boiler and each turbine to adjust their combined operating state. Each boiler and turbine adjusts according to the real-time updated operating load commands, and closed-loop control ensures that load distribution matches the target efficiency. The closed-loop control mechanism dynamically adjusts equipment load, maintains stable system operation, improves flexibility and responsiveness, ensures a balance between heat and power supply and demand, reduces operating costs, and improves energy utilization efficiency.

[0060] This embodiment determines the target operating efficiencies of multiple steam turbines and boilers based on the obtained steam demand, constraints, and load scheduling optimization model of the steam power system over multiple time periods. Then, based on the boiler energy efficiency model and the multiple steam turbine energy efficiency models, it determines the corresponding operating loads for each of the target operating efficiencies. In a multi-boiler, multi-turbine scenario, the optimal load allocation scheme is determined. The system then controls multiple boilers and multiple steam turbines according to this optimal load allocation scheme. The constraints are set to control parameters that achieve optimal energy consumption while satisfying the load scheduling optimization model. Under the premise of ensuring the main steam pressure of the steam power system, the load allocation is optimized based on the boiler operating conditions, allowing for a fixed deviation in boiler load. This improves the economic operation level of the unit and solves the problem of the inability to simultaneously optimize multiple devices in a steam power system in existing technologies.

[0061] Step S2 of this application establishes multiple turbine energy efficiency models corresponding to multiple turbines, including:

[0062] Step S21: Obtain first historical data for multiple steam turbines within the same multiple time periods; the multiple time periods may include a first time period and a second time period. The first historical data includes the steam inlet flow rate Q of the multiple steam turbines within the first time period. in Operating load P, extraction steam volume Q ext Displacement Q exh Steam inlet pressure P in Exhaust pressure P exh extraction steam pressure P ext Exhaust temperature T exh extraction steam temperature T ext and inlet steam temperature T in During the second time period, the steam inflow Q of multiple steam turbines in Operating load P, extraction steam volume Q ext Displacement Q exh Steam inlet pressure P in Exhaust pressure P exh extraction steam pressure P ext Exhaust temperature T exh extraction steam temperature T ext and inlet steam temperature T in .

[0063] Step S22: Determine the inlet enthalpy h of the multiple steam turbines based on the thermodynamic property equation of steam and the inlet steam pressure and temperature of the multiple steam turbines. in =f(P in T in ), extraction enthalpy h ext =f(P exh Tiexh ) and exhaust enthalpy h exh =f(P ext T ext The enthalpy value can be output using Python software based on the data collected above.

[0064] Step S23: Based on the energy balance formula and the steam inlet flow rate, extraction flow rate, steam inlet enthalpy, extraction enthalpy, and exhaust enthalpy of multiple steam turbines, establish multiple steam turbine energy efficiency models. Collect operating data of the steam turbines at various load points, including parameters from the first historical data. Calculate the steam inlet enthalpy, extraction enthalpy, and exhaust enthalpy using the steam thermodynamic property equation, combined with steam inlet pressure and temperature. Based on these parameters, and using the energy balance formula and historical operating big data, establish an energy efficiency model for each steam turbine using a linear regression calculation model. This model is used to predict the steam turbine efficiency and power generation under different loads and extraction flows. By establishing energy efficiency models, the operating status of the steam turbines can be evaluated in real time, their future power generation capacity and efficiency can be predicted, load adjustments and operational optimizations can be guided, energy losses can be reduced, and energy utilization efficiency can be improved.

[0065] The formula for calculating the theoretical efficiency of a steam turbine is:

[0066]

[0067] Where, η theory h is the theoretical efficiency of the steam turbine. in,isentropic h is the enthalpy of isentropic expansion to the exhaust pressure. in h is the enthalpy of the steam. ext h is the enthalpy of extraction. exh Q is the enthalpy of exhaust. in For steam intake, Q ext This refers to the amount of steam extracted.

[0068] Calculate the theoretical steam inlet flow rate Q of the steam turbine. in,theory The formula is:

[0069]

[0070] Among them, Q in,theory h represents the theoretical steam inlet flow rate of the steam turbine. in h is the enthalpy of the steam. ext h is the enthalpy of extraction. exh Q is the enthalpy of exhaust. in For steam intake, Q ext For the extraction steam rate, h s This is the enthalpy value under saturated steam conditions.

[0071] Using historical data η theory Q in,throry P and Q extThe neural network model is trained, and the output bias ΔQ is obtained. in =Q in,actual -Q in,throry The parameters of the neural network model are corrected based on the deviation, the deviation between the learned value and the actual value is corrected, and the turbine energy efficiency model is established.

[0072] Because the power output process of a steam turbine exhibits significant nonlinear characteristics, regulation methods include throttling, nozzle regulation, and bypass regulation. Based on the turbine's power load curve, it can be rationally partitioned to establish a linear model. This not only makes the model closer to reality but also reduces the number of binary variables required, decreasing computation time and improving computational efficiency. In some optional implementations, the control method also includes:

[0073] Based on the turbine energy efficiency model and multiple second real-time data, the turbine's operating load curve is obtained. The operating load curve characterizes the steam inlet flow rate of the turbine at different operating efficiencies. The second real-time data has the same parameter types as the first historical data. The second real-time data includes the current load P. real Steam extraction volume Q ext,real Steam parameters (P) in T in P exh T exh P ext and T ext ).

[0074] The operating load curve is divided into multiple regions, and based on the relationship between operating efficiency and steam intake represented by these regions, multiple turbine energy efficiency sub-models with linear characteristics are established.

[0075] The operating load curve is divided into multiple regions and subjected to partitioned linearization, for example, multiple steam turbines are designated as T1 and T2:

[0076] For the T1 nozzle-regulated steam turbine, based on its load-efficiency curve, it is divided into three linear regions: low load region (10-20MW), medium load region, medium load region (20-28MW), and high load region (28-30MW). Within each region, the linear relationship between efficiency and load is fitted, such as η in the low load region. T1,1 =0.01·W T1 +0.75. For the T2 throttling turbine, it is divided into two linear regions: low load region (10-30MW) and high load region (30-50MW), and the fitted linear relationship ηT is calculated. 2,1 =0.005·W T2 +0.7 (low load zone), η T2，2 =0.003·W T2 +0.75 (high load area).

[0077] Based on the turbine energy efficiency model and second real-time data, the turbine's operating load curve is obtained, including:

[0078] Acquire second real-time data from multiple steam turbines at multiple simultaneous time periods; based on the International Assay Steam Theorem (IAPWS) and the real-time inlet steam pressure P of multiple steam turbines... in and steam inlet temperature T in Determine the real-time inlet steam enthalpy h of multiple steam turbines. in,real Enthalpy of extraction h ext,real and exhaust enthalpy h exh,real ;

[0079] Based on the turbine energy efficiency model and the real-time steam inlet Q of multiple turbines in Steam extraction volume Q ext Enthalpy of steam h in Enthalpy of extraction h ext Exhaust enthalpy h exh and saturated vapor enthalpy h s Determine the target operating efficiency of multiple steam turbines in real time; calculate the current operating condition based on the aforementioned second real-time data: real-time inlet steam enthalpy h. in,real Real-time exhaust enthalpy h exh,real and real-time enthalpy of extraction h ext,real The real-time target operating efficiency is the operating efficiency of the steam turbine, and the formula for calculating the operating efficiency of the steam turbine is:

[0080] The meanings of each parameter are as follows:

[0081] η ri The relative internal efficiency of a steam turbine;

[0082] h in : The enthalpy of the steam entering the turbine, in kJ / kg, is determined by the pressure and temperature of the steam entering the turbine. It can be obtained by referring to the table of thermodynamic properties of steam or the enthalpy = entropy (hs diagram).

[0083] n: Number of extraction stages in the steam turbine, indicating that the steam turbine has n extraction ports;

[0084] α i The proportion of the i-th stage steam extraction rate to the total steam intake rate, i.e. Q ext,i Q is the extraction steam rate of the i-th stage. in It is the total steam intake of the steam turbine. This indicates the total amount of extracted steam relative to the total amount of steam entering the steam tank;

[0085] h ext,i The enthalpy of the i-th stage extraction steam, in kJ / kg, can be obtained by consulting the thermodynamic properties of steam or the enthalpy-entropy (hs diagram) based on the pressure and temperature of the steam at the extraction port.

[0086] h exh Actual exhaust steam enthalpy, expressed in kJ / kg, is the enthalpy of steam after it has actually expanded and done work in the turbine before being expelled.

[0087] h s Ideal exhaust enthalpy, expressed in kJ / kg, is the enthalpy value when steam undergoes isentropic expansion (without any irreversible loss) within the turbine to the exhaust pressure. It can be obtained by referring to the steam thermodynamic property table or the enthalpy-entropy (hs diagram).

[0088] Based on the real-time extraction steam volume Q of multiple steam turbines ext Enthalpy of steam h in Enthalpy of extraction h ext Exhaust enthalpy h exh Steam turbine mechanical efficiency η mech Steam turbine power generation efficiency η gen and turbine output power P real Determine the target steam intake; the actual steam intake Q of the steam turbine. in,theory,real :

[0089]

[0090] Where, η mech For the mechanical efficiency of the steam turbine, η gen For the power generation efficiency of the steam turbine, P real Q represents the current load. ext,real For the extraction steam rate, h in,real For real-time steam enthalpy, h exh,real For real-time exhaust enthalpy, h ext,real This is the real-time enthalpy of the exhaust gas; 3600 is the number of seconds per hour. To retrieve the bias from the training model, input the theoretical value plus the real-time operating condition (P). real Q ext,real The predicted deviation of the actual efficiency of the steam turbine is: Δη real = Model prediction (η) theory,real ,P real Q ext,real The predicted deviation of the actual steam inlet flow rate of the steam turbine is: ΔQ in,real =Model prediction (Q) intheoryr,eal ,P real The actual efficiency, obtained after correction, is: η (Q, extreal). actu,arelal =η theo,ryeal +Δη rea The actual steam intake is: Q in,actual,real =Q in,theory,real +ΔQ in,real .

[0091] Based on multiple target operating efficiencies and multiple target steam inflow rates, an operating load curve is obtained. The target operating efficiency is the actual efficiency mentioned above, and the target steam inflow rate is the actual steam inflow rate mentioned above. The results are displayed in real-time on a monitoring interface (such as a web visualization or DCS screen) and stored in a real-time database (for subsequent analysis). The construction of the operating load curve enables the system to dynamically adjust the steam inflow rate to the turbine to maintain its operation under high-efficiency conditions, reduce energy waste, and improve power generation efficiency.

[0092] The control methods for predicting turbine power generation under different loads (power generation) and extraction rates also include:

[0093] Without any extraction process, the steam turbine output power is determined based on the steam inlet flow rate, steam inlet enthalpy, exhaust enthalpy, steam turbine mechanical efficiency, and steam turbine power generation efficiency.

[0094] The formula for the output power of a steam turbine is: Among them, Q in For steam intake, h in For the enthalpy of the steam, h exh For exhaust enthalpy, η mech For the mechanical efficiency of the steam turbine, η gen For steam turbine power generation efficiency;

[0095] Steam extraction is performed on the steam turbine (such as steam extraction for heating Q). ext Corresponding to extraction enthalpy h ext Under the condition of steam inlet flow rate, steam extraction flow rate, extraction enthalpy, steam inlet enthalpy, exhaust enthalpy, turbine mechanical efficiency, and turbine power generation efficiency, the turbine output power is determined.

[0096] If steam is extracted, the effective enthalpy drop needs to be corrected. In this case, the formula for the turbine's output power generation is: Among them, Q in For steam intake, h in h is the enthalpy of the steam. exh η is the exhaust enthalpy. mech For the mechanical efficiency of the steam turbine, η gen For the power generation efficiency of steam turbine, h ext Q is the enthalpy of extraction. ext This represents the extraction volume. The formula for the relative internal efficiency of a steam turbine is: The meanings of the parameters have been explained above and will not be repeated here.

[0097] Steam load forecasting models are based on extensive historical system operation data, combined with production planning data. Data mining algorithms are used to achieve online forecasting of steam production and demand over multiple future cycles. Simultaneously, a dual correction technique—deviation correction and online rolling correction—is employed to ensure forecast errors remain within a reasonable range. Based on load forecasting, major problems in the steam system operation can be identified in advance, allowing for the development of production plans and production-consumption balance schemes, thereby improving the stability of the system's pipeline network operation.

[0098] In the specific implementation process, step S3 above obtains multiple steam demands of the steam power system within multiple time periods, including:

[0099] Based on second historical data and multiple algorithms, a steam load prediction model is established. This model is used to predict steam demand within a preset time period based on first real-time data. The second historical data and the first real-time data include at least: steam flow rate, fuel type, and equipment parameters of the steam power system; such as... Figure 5 As shown, data collection is performed, and the obtained second historical data undergoes data cleaning. Data cleaning includes handling missing values, removing outliers, and time alignment. While the model is offline, the impact of different production schemes on steam demand can be simulated manually using offline tools. Corresponding feature engineering is input: time-series features (lag terms, moving averages) and operating condition features (coal calorific value, load factor, etc.). Algorithm selection is then performed: multiple algorithms are considered, including LSTM (Long Short-Term Memory network, used for periodic forecasting), Prophet (time series forecasting algorithm, used for long-term trends), and XGBoost (eXtreme Gradient Boosting algorithm (machine learning algorithm, used for feature importance analysis). These three algorithms form a hybrid model architecture. Model training begins: parameters in the hybrid model architecture (such as the number of LSTM layers, Dropout rate) are adjusted based on the second historical data over a certain period. After training, model validation is performed. A MAPE ≤ 5% on the test set is considered acceptable; otherwise, the model is returned for further adjustment and training continues to establish the final steam load forecasting model.

[0100] The system acquires the first real-time data at the start of each time period (e.g., 15 minutes / cycle), establishes a real-time database, and performs load forecasting based on the first real-time data and the steam load forecasting model to determine the steam demand for each time period. The model outputs the steam demand (with confidence interval) for a certain period in the future (e.g., 24 hours), and performs online rolling correction with dual correction: sliding window error correction (average of the last 6 times) and Kalman filter fusion of measured values, controlling the above errors to <3%. Dispatchers use an online dashboard to display forecast curves, pipeline pressure warnings, and other information in real time.

[0101] The steam load forecasting model features both online load forecasting and offline analysis and calculation capabilities. The online load forecasting function predicts the steam demand of major steam units under different coal types and operating conditions (full load, 90% load, etc.), providing a reference for optimizing steam production strategies and balancing the steam pipeline network. The offline analysis and calculation function utilizes a steam production and consumption offline calculation tool. Users can input parameters such as unit load, fuel type (coal, natural gas), and product quality requirements to calculate steam demand and by-product output, providing support for developing operational adjustment plans. The steam load forecasting model considers key parameters affecting efficiency in actual operation, such as changes in the enthalpy of circulating air and the enthalpy difference between boiler feedwater and steam. Combined with historical data regression analysis, this ensures the accuracy of forecasts and the precision of control.

[0102] For steam-using equipment, the process parameters such as steam temperature and pressure are basically fixed. Therefore, the main objective of optimizing the operation and scheduling of steam power systems is to optimize the load of boilers and turbines. Using energy consumption model curves of different boilers and turbines, the goal is to minimize the overall operating cost through load allocation optimization. Considering various constraints (such as the aforementioned mass conservation, energy conservation, equipment capacity limitations, and energy and electricity demand constraints), mixed-integer linear programming algorithms are used to achieve optimal load allocation for each turbine and boiler. Since the construction years, equipment structures, and design parameters of multiple boilers and turbines vary, the main objective of scheduling optimization is to achieve steam-electricity balance while maximizing energy utilization efficiency by adjusting the load of boilers and turbines according to different steam and electricity demands.

[0103] A load dispatch optimization model is constructed based on the total operating cost of the steam power system, the start-up and shutdown status of the steam power system, the depreciation cost of the steam power system, the fuel price, the fuel consumption, the price of purchased steam, the steam demand, the price of purchased electricity, and the purchased power supply.

[0104] The load scheduling optimization model is a model for steam power system scheduling optimization with the objective of minimizing the total system operating cost.

[0105]

[0106] Among them, Y n Z indicates the device's start / stop status as 0 or 1. n For equipment depreciation costs, C fuel F represents the price of fuel. fuel C represents fuel consumption. s F represents the price of purchased steam. s C represents the amount of steam purchased. power P represents the price of purchased electricity, and P represents the amount of purchased electricity.

[0107] Optimizing the operation of a steam power system based on a load scheduling optimization model can effectively reduce boiler energy loss and improve fuel and steam utilization efficiency, thereby achieving energy conservation and consumption reduction while meeting electricity and heat demand. The load scheduling optimization model mainly constructs a superstructure model of the steam power system. Steam scheduling optimization involves boiler coal consumption, steam production, power generation from the supporting steam turbine, and downstream steam demand, which is a nonlinear and strongly coupled relationship. This application addresses this characteristic by proposing a loss analysis model for steam load scheduling optimization. This loss analysis model is used to further optimize the control method of the steam power system based on the load scheduling optimization model.

[0108] like Figure 6 As shown, detailed steps are given for the loss analysis model of the load scheduling optimization model:

[0109] Data Input and Preprocessing: Collect actual operating data of the steam power system, including: Equipment parameters: boiler / turbine design compliance, efficiency curve, depreciation costs; Real-time demand: steam type demand and total electricity demand for each time period; External conditions: fuel prices and purchased steam / electricity prices;

[0110] Performance calculation and consumption error analysis:

[0111] Performance calculation: Based on actual operating conditions, calculate performance indicators such as boiler fuel consumption and steam turbine power generation, and combine steam specific enthalpy data to quantify the energy conversion efficiency of the equipment;

[0112] Energy consumption difference analysis: Extract ideal operating parameters of equipment as state benchmark values ​​(such as minimum fuel consumption and optimal efficiency under design load) from the benchmark database (including boundary index, state benchmark value, and operation benchmark value); compare the actual performance with the state benchmark value, and decompose traditional energy consumption difference (deviation of inherent characteristics of equipment, such as efficiency decline due to aging) and operation energy consumption difference (deviation of operation strategy, such as unreasonable load distribution).

[0113] Before determining the operational waste, a controllable factor analysis is conducted: operational variables that can be adjusted through scheduling optimization (such as boiler combustion rate and turbine steam intake) are screened, and their weights on the waste are clarified. After determining the operational waste, closed-loop management is implemented, operations are adjusted, and operational evaluation is conducted: the operational waste is linked to the performance of the operating team, and evaluation indicators (such as the operational waste reduction rate) are set to drive optimized execution.

[0114] Load scheduling optimization model construction and solution: Based on the load scheduling optimization model, continuous variables are used to describe the equipment processing capacity (e.g., boiler evaporation rate, turbine steam inlet rate) and flow rate; binary variables are used to mark the equipment operating status (e.g., start-up / shutdown, zoning). Substituting the objective function and constraints, a mixed-integer linear programming (or nonlinear programming, adapted turbine zoning model) algorithm is used to solve the problem, obtaining the optimal boiler and turbine combination and load allocation scheme under different steam demand conditions;

[0115] Closed-loop management and adjustment operations: The optimized scheme is output as actual operation variables (such as boiler combustion commands and turbine valve openings), and adjustments are executed through the DCS system; real-time operation data is collected, and the "performance calculation → consumption difference analysis" process is repeated to verify the optimization effect and continuously iterate and correct the scheduling strategy.

[0116] The above-described loss analysis model can achieve the following technical effects:

[0117] Cost optimization: Reduce fuel and purchased steam / electricity costs and minimize equipment depreciation losses through precise load allocation and external procurement strategies.

[0118] Energy efficiency improvement: While balancing the supply and demand of steam and electricity, optimize the energy conversion path, reduce boiler energy loss, and improve the fuel-steam-electricity conversion efficiency.

[0119] High computational efficiency: The turbine partitioning linearization process reduces the number of binary variables and nonlinearity in the model, improves the solution speed, and adapts to the real-time scheduling needs of industry.

[0120] Closed-loop management: Combining cost difference analysis and operational evaluation, a closed loop of "analysis-optimization-execution-feedback" is constructed to ensure the continuous implementation of optimization strategies.

[0121] The following detailed description, in conjunction with specific embodiments, provides further details.

[0122] (1) System Overview

[0123] The steam power system is used to meet the steam and electricity needs of the chemical plant and thermal power plant in the industrial park. The system includes the following core equipment:

[0124] ① Boiler

[0125]

[0126] ② Steam turbine

[0127]

[0128]

[0129] ③ Demand for steam and electricity

[0130] Steam demand: High-pressure steam (3.5MPa, 435℃) peaks at 200t / h during the day and troughs at 120t / h at night; medium-pressure steam (1.2MPa, 300℃) peaks at 150t / h during the day and troughs at 80t / h at night.

[0131] Electricity demand: 60MW peak during the day and 30MW off-peak at night.

[0132] (2) Implementation steps

[0133] 1) Data Acquisition and Preprocessing

[0134] ① Data collection

[0135] Real-time database data is transmitted to the data acquisition server via industrial Ethernet using the OPC UA protocol. The acquired data includes:

[0136] Boiler data: Fuel consumption of B1-B3 (e.g., natural gas flow rate F in B1) fuel,B1 (B2 / B3 pulverized coal feed rate), steam output (F) steam,B1-B3 Steam parameters (pressure P) steam,B1-B3 Temperature T steam,B1-B3 ).

[0137] Steam turbine data: Steam inlet flow rate (F) for T1-T2 steam,T1-T2 ), exhaust parameters (pressure P) exhuast,T1-T2 Temperature T exhaust,T1-T2 ), power generation (W) T1-T2 ).

[0138] Pipeline and Demand Data: High-Pressure / Medium-Pressure Steam Pipeline Flow Rate (F) steam,HP F steam,MP ), pressure (P) steam,HP P steam,MP ), temperature (T) steam,HP T steam,MP Real-time electricity consumption (P) of the park's electricity meters demand ).

[0139] ② Data preprocessing

[0140] Outlier handling: A threshold method based on the physical limits of the equipment is adopted. For example, if the boiler steam temperature exceeds 450±10℃ or the pressure exceeds 3.8±0.2MPa, it is judged as an outlier and replaced with the average value of adjacent time points.

[0141] Data normalization: Converting parameters in different units (such as flow rate in t / h, power in MW) into dimensionless quantities to facilitate model calculations and formulas. Where x max x min Run the extreme values ​​for the parameters.

[0142] 2) Performance calculation and consumption difference analysis

[0143] ①Performance Calculation

[0144] Boiler efficiency calculation: Taking a B1 natural gas boiler as an example, based on energy balance, the boiler efficiency is... Among them, h steam,B1 The specific enthalpy of steam B1 (calculated from steam parameters using the IAPWS-IF97 formula), h feedwater For the feedwater specific enthalpy (taken as 200 kJ / kg), LHV natural-gas The low calorific value of natural gas (35588 kJ / m³) 3 ), F fuel，B1 This represents the fuel consumption for B1. Similarly, calculate the efficiencies of pulverized coal boilers B2 and B3, taking the lower calorific value of pulverized coal as 20900 kJ / kg.

[0145] Steam turbine efficiency calculation: For a T1 nozzle-regulated steam turbine, the relative internal efficiency... Among them, h in,T1 For the specific enthalpy of the steam, h out,T1 For exhaust enthalpy, h in,T1,isentropic The specific enthalpy is the result of isentropic expansion of the inlet steam to the exhaust steam pressure (calculated using the IAPWS-IF97 isentropic process). The efficiency calculation method for the T2 throttling regulating steam turbine is similar.

[0146] System overall parameter calculation: Steam production F steam,total =∑F steam,B1-B3 Total power generation W total =∑W T1-T2 Total fuel consumption F fuel,total =∑F fuel,B1-B3 Calculate the energy utilization rate of the system Among them, h condensate The enthalpy of condensate is taken as 100 kJ / kg. LHV refers to the lower heating value of fuel, expressed in kJ / kg (solid / liquid fuel) or kJ / m³. 3 (Gas fuel)

[0147] ② Loss Analysis

[0148] Benchmark database construction:

[0149] A. State benchmark value

[0150] Based on the design data from the boiler and turbine manufacturers, the design efficiencies of boilers B1-B3 were determined (B1 design efficiency 92%, B2 design efficiency 88%, B3 design efficiency 88%), and the design relative internal efficiencies of turbines T1-T2 were determined (T1 design efficiency 85%, T2 design efficiency 80%). Through historical best operating data (30 consecutive days of no failures and stable demand), the matching relationship between the system's optimal steam output and power generation was statistically determined, such as the minimum fuel consumption per unit area (B1 natural gas consumption 30m³). 3 / t, B2 / B3 pulverized coal consumption is 180kg / t steam).

[0151] B. Operating Benchmark Value

[0152] Analyze historical operation records to determine the optimal combustion air-fuel ratio of the boiler (B1 excess air coefficient 1.1, B2 / B3 excess air coefficient 1.2) and the optimal steam inlet valve opening sequence of the turbine (T1 nozzle adjustment opening at each load section, T2 throttling adjustment opening), etc. Establish boundary indexes, such as steam pressure fluctuation range ±0.1MPa and temperature fluctuation range ±5℃ as normal operating boundaries.

[0153] Calculation of consumption difference

[0154] A. Traditional consumption difference

[0155] The deviation between the actual performance of the calculated equipment and the benchmark value is as follows: For example, if the actual efficiency of B1 is 90%, the deviation from the design efficiency of 92% is 2%, corresponding to a fuel waste of [amount missing]. Similarly, calculate the traditional consumption difference of other boiler equipment, and sum them up to obtain the total traditional consumption difference of the system, F. fuel，B1 Indicates fuel consumption for B1, F steam，B1 For B1 steam production, h steam,B1 For the specific enthalpy of steam in boiler B1, h feedwater Specific enthalpy of water (taken as 200 kJ / kg), LHV natural-gas The low calorific value of natural gas (35588 kJ / m³) 3 ).

[0156] B. Operational cost difference

[0157] Compare the actual operating parameters with the benchmark values. For example, the actual excess air coefficient for B2 is 1.3, which is higher than the benchmark value of 1.2, leading to increased exhaust heat loss. Calculate the operating loss difference Δη caused by improper air distribution. operation,B2 =f(1.3-1.2), which is converted into fuel loss or efficiency reduction value through boiler heat balance. The system operating loss is obtained by summing up the operating loss differences of each piece of equipment.

[0158] 3) Controllable factors and operational evaluation

[0159] ① Controllable factor analysis

[0160] A. Factor Screening

[0161] By analyzing the operational variables affecting system operating costs and efficiency, controllable factors were identified, including: boiler burner fuel quantity F. fuel,B1-B3 Combustion air-fuel ratio α B1-B3 Steam turbine inlet valve opening degree O T1-T2 Desuperheater and pressure reducer in operation status Y desuperheater The binary variable 0 represents shutdown and 1 represents commissioning.

[0162] B. Factor Influence Weights

[0163] Multiple linear regression analysis was used to establish a correlation model between controllable factors and system operating costs and energy efficiency, such as the regression equation Cost = a·F fuel,B1 +b·α B1 +c·O T1 +…, by fitting coefficients a, b, c using historical data, the weight of each factor's impact on cost is quantified. The results show that B2 fuel flow rate has a 35% weighting on cost, T1 inlet valve opening has a 28% weighting on energy efficiency, and F… fuel Indicates fuel consumption, α B1 Combustion air-fuel ratio, O T1 Steam turbine inlet valve opening.

[0164] ② Operational assessment

[0165] A. Setting evaluation indicators

[0166] Set the operation loss reduction rate Load deviation rate

[0167] B. Performance-related

[0168] The evaluation indicators are linked to the performance-based wages of the operating teams. For every 1% increase in the rate of reduction of operational waste, 5 points are added to the performance score; for every 1% decrease in the rate of deviation from the allocation standard, 3 points are added to the performance score. The evaluation results are compiled monthly, and rewards and penalties are implemented accordingly.

[0169] 4) Optimization Model Construction and Solution

[0170] ①Construction of load scheduling optimization model

[0171] A. Variable Definition

[0172] Continuous variable: Boiler steam output (F) steam,B1-B3 (unit: t / h) and steam turbine inlet steam volume (F) steam,T1-T2 (unit: t / h) and power generation (W) T1-T2 Units: MW, purchased steam volume (F) steam,buy (unit: t / h) and purchased electricity (P) buy (unit: MW);

[0173] Binary variables: Equipment start-up / shutdown status (YB1-B3, YT1-T2, 0 for shutdown, 1 for operation), turbine zone status (ZT1-T2, 1-n, marking the linear zone where the turbine is located, n is the number of zones, such as T1 nozzle adjustment being divided into 3 linear zones), and desuperheater / pressure reducer operation status Y. desuperheater .

[0174] B. Objective Function (The above load scheduling optimization model is adjusted according to this embodiment)

[0175] With the goal of minimizing the total system operating cost, the formula is:

[0176]

[0177] Among them, Y n Z indicates the device's start / stop status as 0 or 1. n Let C be the depreciation cost of boiler n (B1 depreciation cost 1000 yuan / h, B2 depreciation cost 2000 yuan / h, B3 depreciation cost 3000 yuan / h), and C be the depreciation cost of boiler n. fuel,n Fuel price (natural gas price 2 yuan / m³) 3 Coal powder price 0.8 yuan / kg, F fuel C represents fuel consumption. s The price of purchased steam (200 yuan / ton), F s C represents the amount of steam purchased. power The price of purchased electricity is 0.8 yuan / kWh, where P represents the amount of purchased electricity.

[0178] C. Substituting constraints

[0179] Mass conservation constraint:

[0180] For high-pressure steam pipeline networks, ∑F steam,B1-B3,HP +F steam,buy,HP =F steam,demand,HP +F steam,MP,HP Considering that the desuperheater and pressure reducer converts some of the high-pressure steam into medium-pressure steam, F steam,MP,HP F converts traffic for them steam,B1-B3,HP For the boiler's high-pressure steam output, F steam,buy,HP To purchase high-pressure steam, F steam,demand,HP The specific formula for the flow rate of the high-pressure steam pipeline network in the park is as follows:

[0181] Among them, F desuperheater For the desuperheater and pressure reducer to handle flow, Y desuperheate For the desuperheater and pressure reducer to be in operation, F steam,demand,HP F represents the flow rate of the high-pressure steam pipeline network in the industrial park. steam,buy,HP To purchase high-pressure steam, Fsteam,n,HP Y represents the flow rate of the high-pressure steam pipeline network for this equipment. n This indicates that the device's start / stop status is 0 or 1, and n is B1.

[0182] Energy balance constraints:

[0183] Taking the T1 steam turbine as an example, F steam,T1,in ·h steam,T1,in =W T1 +F steam,T1,out ·h steam,T1,out +Q T1 QT1 represents the heat loss (design value 500 kJ / h), calculated using IAPWS-IF97. steam,T1,in h steam,T1,out .

[0184] Equipment capacity constraints:

[0185] F steam,B1,min ·Y B1 ≤F steam,B1 ≤F steam,B1,max ·Y B1 B1 minimum steam production F steam,B1,min With a capacity of 10 t / h and a maximum steam output F steam,B1,max For a capacity of 50 t / h, similarly set constraints for other equipment, Y B1 This indicates the start / stop status of device B1.

[0186] Apply work capacity constraints:

[0187] W T1,min ·Y T1 ≤W T1 ≤W T1,max ·Y T1 T1 minimum power W T1,min It is 5MW, with a maximum power of W. T1,max For 30MW, Y T1 This indicates the start / stop status of device T1; W T2,min ·Y T2 ≤W T2 ≤W T2,max ·Y T2 T2 minimum power W T2,min 10MW, maximum power W T2,max For 50MW, Y T2 This indicates the start / stop status of device T2.

[0188] Demand constraints:

[0189]

[0190] Among them, P demand W is the real-time electricity consumption of the park's electricity meters.n P is the power output of device n. buy For purchased electricity, Y n For the start / stop status of device T1, F steam,buy,HP For the purchase of high-pressure steam for equipment T1, F steam,n,HP For the high-pressure steam demand of equipment T1, Y desuperheater For the desuperheater and pressure reducer to be in operation, F desuperheater For the desuperheater and pressure reducer to handle flow rate, F steam,demand,HP F represents the flow rate of the high-pressure steam pipeline network in the industrial park. steam,n,MP For the medium-pressure steam demand of equipment T1, F steam,buy,MP For the purchase of medium-pressure steam for equipment T1, F steam,demand,MP Let n be the flow rate of the medium-pressure steam pipeline network in the park, and n be B1.

[0191] ② Nonlinear processing and model solution of steam turbine

[0192] A. Linearization

[0193] For the T1 nozzle-regulated steam turbine, based on its load-efficiency curve, it is divided into three linear regions: low load region (10-20MW), medium load region, medium load region (20-28MW), and high load region (28-30MW). Within each region, the linear relationship between efficiency and load is fitted, such as the efficiency in the low load region: η T1,1 =0.01·W T1 +0.75, W T1 Let T1 be the power generation. For the T2 throttling turbine, it is divided into two linear regions: a low-load region (10-30MW) and a high-load region (30-50MW), and the fitted linear relationship η is... T2,1 =0.005·W T2 +0.7 (efficiency in low load area), η T2，2 =0.003·W T2 +0.75 ( High load area efficiency), W T2 This refers to the amount of electricity generated by T2.

[0194] B. Model Solving

[0195] The Gurobi solver was used, with a solution time limit of 10 minutes and an error tolerance of 0.01%. The objective function, constraints, and turbine partitioning linearization model were input, and the optimized solution was obtained, as follows:

[0196] During peak daytime demand:

[0197] Operating systems are as follows: B1 (50t / h steam production), B2 (100t / h steam production), and B3 (50t / h steam production); T1 (30MW power generation) and T2 (30MW power generation); 0t / h of externally purchased steam and 0MW of externally purchased electricity. All equipment loads are within their design adjustment ranges, meeting steam and electricity demands. The system operating cost is 15,000 yuan / h.

[0198] During periods of low demand at night:

[0199] System B1 is shut down; B2 is in operation (producing 80 t / h of steam); B3 is shut down; T1 is in operation (generating 15 MW of electricity); T2 is in operation (generating 15 MW of electricity); 20 t / h of steam and 0 MW of electricity are purchased externally. The system operating cost is 8000 yuan / h.

[0200] 5) Closed-loop management and optimization

[0201] ① Issuance and execution of operation instructions

[0202] A. Boiler Instructions

[0203] B1 fuel flow rate adjusted to 40m 3 / h (corresponding to 50t / h steam production), air distribution ratio 1:1; B2 coal feed rate is adjusted to 18t / h (corresponding to 100t / h steam production), air distribution ratio 1:2.

[0204] B. Steam Turbine Command

[0205] The opening of the T1 inlet valve is adjusted to 80% (corresponding to 30MW of power generation); the opening of the T2 inlet valve is adjusted to 60% (corresponding to 30MW of power generation).

[0206] C. Temperature and pressure reduction command

[0207] It is put into operation with a processing capacity of 30t / h (converting high-pressure steam into medium-pressure steam).

[0208] ②Effect verification and iteration

[0209] Real-time collection of optimized equipment operation data, re-performance calculation and consumption difference analysis. For example, after daytime peak optimization, B1 efficiency increased to 91%, and operation consumption difference decreased by 1.5%; system energy utilization rate increased to 82%, an improvement of 3% compared to before optimization.

[0210] A benchmark database was established through energy consumption difference analysis of the unit. This database analyzed stable operating conditions under different historical evaporation rates and heat / electricity loads, aiming to maximize boiler and turbine efficiency. Optimal control indicators under different operating conditions were selected, and this database was used as a benchmark. The operating conditions of evaporation rates and heat / electricity loads obtained from the load scheduling optimization model were compared with the benchmark database in real time for optimization. The energy consumption difference analysis model displayed benchmark guidance values ​​for the best controllable indicators affecting energy consumption, guiding operators to make targeted adjustments to achieve optimal unit operation.

[0211] This application also provides a control device for a steam power system. It should be noted that the control device for the steam power system in this application can be used to execute the control method for a steam power system provided in this application. This device is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0212] The control device for the steam power system provided in the embodiments of this application will be described below.

[0213] Figure 7 This is a schematic diagram of the control device for a steam power system according to an embodiment of this application. Figure 7 As shown, the device includes: a first establishment module 10, used to establish multiple boiler energy efficiency models corresponding to multiple boilers based on the historical operating efficiency and historical steam output of multiple boilers in the steam power system over the same multiple time periods; a second establishment module 20, used to establish multiple turbine energy efficiency models corresponding to multiple turbines based on first historical data of multiple turbines in the steam power system over the same multiple time periods, the first historical data including: turbine steam inlet flow rate, operating load, extraction steam flow rate, exhaust steam flow rate, steam inlet pressure, and steam inlet temperature; and a first determination module 30, used to acquire multiple time periods at the initial moment of the multiple time periods. The system has multiple steam demands, and based on these demands, constraints, and a load scheduling optimization model, it determines the target operating efficiencies of multiple steam turbines and boilers. A second determining module 40 determines the operating loads of multiple boilers and steam turbines based on these target operating efficiencies, boiler energy efficiency models, and turbine energy efficiency models. A regulating module 50 controls the operation of multiple boilers and steam turbines based on their respective operating loads, thereby achieving control of the steam power system.

[0214] The first module establishes multiple boiler energy efficiency models corresponding to multiple boilers based on their historical operating efficiency and historical steam output over the same multiple time periods. The second module establishes multiple turbine energy efficiency models corresponding to multiple turbines based on their first historical data over the same multiple time periods. The first determination module obtains multiple steam demands of the steam power system at the initial moment of multiple time periods, and determines the target operating efficiencies of multiple turbines and multiple boilers based on the multiple steam demands, multiple constraints, and load scheduling optimization models. The second determination module determines the operating loads of multiple boilers and multiple turbines based on the target operating efficiencies of multiple turbines, multiple boilers, multiple boiler energy efficiency models, and multiple turbine energy efficiency models. The regulation module controls the operation of multiple boilers and multiple turbines based on their respective operating loads, thereby achieving control of the steam power system. The above method enables the simultaneous control of multiple boilers and multiple steam turbines, and the load distribution of multiple boilers and multiple steam turbines, solving the problem that existing technologies cannot simultaneously optimize multiple devices in a steam power system.

[0215] As an optional approach, the first determining module includes a first sub-establishment module and a first determining module. The first sub-establishment module is used to establish a steam load prediction model based on second historical data and multiple algorithms. The steam load prediction model is used to predict the steam demand within a preset time period based on first real-time data. The second historical data and the first real-time data include at least: steam flow rate, fuel type, and equipment parameters of the steam power system. The first determining module is used to acquire the first real-time data at the start of each time period and determine the steam demand for each time period based on the first real-time data and the steam load prediction model.

[0216] In one optional scheme, the second establishment module includes a first sub-acquisition module, a second sub-determination module, and a second sub-establishment module. The first sub-acquisition module acquires first historical data from multiple steam turbines over the same multiple time periods. The second sub-determination module determines the inlet enthalpy, extraction enthalpy, and exhaust enthalpy of multiple steam turbines based on the thermodynamic property equation of steam and the inlet pressure and temperature of the multiple steam turbines. The second sub-establishment module establishes energy efficiency models for multiple steam turbines based on the energy balance formula and the inlet steam flow rate, extraction steam flow rate, inlet steam enthalpy, extraction steam enthalpy, and exhaust enthalpy of the multiple steam turbines.

[0217] In one optional scheme, the optimized control device for the steam power system further includes a third sub-confirmation module and a third sub-establishment module. The third sub-confirmation module obtains the operating load curve of the steam turbine based on the turbine energy efficiency model and multiple second real-time data. The operating load curve represents the steam intake of the steam turbine at different operating efficiencies. The second real-time data and the first historical data have the same parameter types. The third sub-establishment module divides the operating load curve into multiple regions and establishes multiple steam turbine energy efficiency sub-models with linear characteristics based on the relationship between operating efficiency and steam intake represented by the multiple regions.

[0218] In one optional scheme, the third sub-confirmation module includes a first acquisition unit, a first determination unit, a second determination unit, a third determination unit, and a fourth determination unit. The first acquisition unit acquires second real-time data from multiple steam turbines over multiple simultaneous time periods. The first determination unit determines the real-time inlet enthalpy, extraction enthalpy, and exhaust enthalpy of multiple steam turbines based on the thermodynamic property equation of steam and the real-time inlet pressure and temperature of the multiple steam turbines. The second determination unit determines the real-time target operating efficiency of multiple steam turbines based on the turbine energy efficiency model and the real-time inlet flow rate, extraction flow rate, inlet enthalpy, extraction enthalpy, and exhaust enthalpy of the multiple steam turbines. The third determination unit determines the target inlet flow rate based on the real-time extraction flow rate, inlet enthalpy, extraction enthalpy, exhaust enthalpy, turbine mechanical efficiency, turbine power generation efficiency, and turbine output power of the multiple steam turbines. The fourth determination unit obtains the operating load curve based on the multiple target operating efficiencies and multiple target inlet flow rates.

[0219] In one optional scheme, the optimized control device for the steam power system further includes a third sub-determination module and a fourth sub-determination module. The third sub-determination module is used to determine the steam turbine output power based on the steam inlet flow rate, steam inlet enthalpy, exhaust enthalpy, steam turbine mechanical efficiency, and steam turbine power generation efficiency when the steam turbine has not undergone steam extraction treatment. The fourth sub-determination module is used to determine the steam turbine output power based on the steam inlet flow rate, steam extraction flow rate, steam extraction enthalpy, steam inlet enthalpy, exhaust enthalpy, steam turbine mechanical efficiency, and steam turbine power generation efficiency when the steam turbine has undergone steam extraction treatment.

[0220] An alternative approach is to construct a load dispatch optimization model based on the total operating cost of the steam power system, the start-up and shutdown status of the steam power system, the depreciation cost of the steam power system, the fuel price, the fuel consumption, the price of purchased steam, the steam demand, the price of purchased electricity, and the power supply of purchased electricity.

[0221] The optimized control device for the steam power system includes a processor and a memory. The first establishment module, the second establishment module, the first determination module, the second determination module, and the adjustment module are all stored as program units in the memory. The processor executes the program units stored in the memory to achieve the corresponding functions. All of the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0222] The processor contains a kernel, which retrieves the corresponding program units from memory. One or more kernels can be configured, and by adjusting kernel parameters, multiple devices in the steam power system can be optimized simultaneously.

[0223] The memory may include non-permanent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0224] This invention provides a computer-readable storage medium including a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform a control method for a steam power system.

[0225] Specifically, the control methods for steam power systems include:

[0226] Step S1: Based on the historical operating efficiency and historical steam output of multiple boilers in the steam power system during the same multiple time periods, establish multiple boiler energy efficiency models corresponding to multiple boilers.

[0227] Step S2: Based on the first historical data of multiple steam turbines in the steam power system at the same multiple time periods, establish multiple steam turbine energy efficiency models corresponding to multiple steam turbines. The first historical data includes: steam inlet flow rate, operating load, extraction steam flow rate, exhaust steam flow rate, inlet steam pressure, exhaust steam pressure, extraction steam pressure, exhaust steam temperature, extraction steam temperature and inlet steam temperature of the steam turbine.

[0228] Step S3: At the initial moment of multiple time periods, obtain multiple steam demands of the steam power system within multiple time periods, and determine multiple target operating efficiencies of steam turbines and multiple target operating efficiencies of boilers based on multiple steam demands, multiple constraints and load scheduling optimization models.

[0229] Step S4: Based on multiple target operating efficiencies of steam turbines, multiple target operating efficiencies of boilers, multiple boiler energy efficiency models, and multiple steam turbine energy efficiency models, determine the operating load of multiple boilers and the operating load of multiple steam turbines.

[0230] Step S5: Based on the operating loads of multiple boilers and multiple steam turbines, control the operation of multiple boilers and multiple steam turbines respectively, thereby realizing the control of the steam power system.

[0231] This invention provides a processor for running a program, wherein the program executes a control method for a steam power system during runtime.

[0232] Specifically, the control methods for steam power systems include:

[0233] Step S1: Based on the historical operating efficiency and historical steam output of multiple boilers in the steam power system during the same multiple time periods, establish multiple boiler energy efficiency models corresponding to multiple boilers.

[0234] Step S2: Based on the first historical data of multiple steam turbines in the steam power system at the same multiple time periods, establish multiple steam turbine energy efficiency models corresponding to multiple steam turbines. The first historical data includes: steam inlet flow rate, operating load, extraction steam flow rate, exhaust steam flow rate, inlet steam pressure, exhaust steam pressure, extraction steam pressure, exhaust steam temperature, extraction steam temperature and inlet steam temperature of the steam turbine.

[0235] Step S3: At the initial moment of multiple time periods, obtain multiple steam demands of the steam power system within multiple time periods, and determine multiple target operating efficiencies of steam turbines and multiple target operating efficiencies of boilers based on multiple steam demands, multiple constraints and load scheduling optimization models.

[0236] Step S4: Based on multiple target operating efficiencies of steam turbines, multiple target operating efficiencies of boilers, multiple boiler energy efficiency models, and multiple steam turbine energy efficiency models, determine the operating load of multiple boilers and the operating load of multiple steam turbines.

[0237] Step S5: Based on the operating loads of multiple boilers and multiple steam turbines, control the operation of multiple boilers and multiple steam turbines respectively, thereby realizing the control of the steam power system.

[0238] This invention provides a device including a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, it performs at least the following steps: Step S1, establishing multiple boiler energy efficiency models corresponding to the multiple boilers based on their historical operating efficiency and historical steam output over the same multiple time periods; Step S2, establishing multiple turbine energy efficiency models corresponding to the multiple turbines based on first historical data of the multiple turbines in the same multiple time periods. The first historical data includes: turbine steam inlet flow rate, operating load, extraction steam flow rate, exhaust steam flow rate, inlet steam pressure, exhaust steam pressure, extraction steam pressure, exhaust steam temperature, and extraction steam temperature. Step S3: At the initial moment of multiple time periods, obtain multiple steam demands of the steam power system within multiple time periods, and determine the target operating efficiency of multiple steam turbines and multiple boilers based on multiple steam demands, multiple constraints, and load scheduling optimization models; Step S4: Based on the target operating efficiency of multiple steam turbines, multiple boilers, multiple boiler energy efficiency models, and multiple steam turbine energy efficiency models, determine the operating load of multiple boilers and multiple steam turbines; Step S5: Control the operation of multiple boilers and multiple steam turbines based on the operating load of multiple boilers and the operating load of multiple steam turbines respectively, thereby realizing the control of the steam power system.

[0239] The devices mentioned in this article can be servers, PCs, tablets, mobile phones, etc.

[0240] This application also provides a computer program product, which, when executed on a data processing device, is suitable for executing an initialization program having at least the following method steps: establishing multiple boiler energy efficiency models corresponding to the multiple boilers based on the historical operating efficiency and historical steam output of multiple boilers in a steam power system over the same multiple time periods; establishing multiple turbine energy efficiency models corresponding to the multiple turbines based on first historical data of multiple steam turbines in a steam power system over the same multiple time periods, wherein the first historical data includes: steam inlet flow rate, operating load, extraction steam flow rate, exhaust steam flow rate, inlet steam pressure, exhaust steam pressure, extraction steam pressure, exhaust steam temperature, extraction steam temperature, and inlet steam flow rate. Temperature; at the initial moment of multiple time periods, obtain multiple steam demands of the steam power system within multiple time periods, and determine the target operating efficiencies of multiple steam turbines and multiple boilers based on multiple steam demands, multiple constraints, and load scheduling optimization models; determine the operating loads of multiple boilers and multiple steam turbines based on the target operating efficiencies of multiple steam turbines, multiple boilers, multiple boiler energy efficiency models, and multiple steam turbine energy efficiency models; control the operation of multiple boilers and multiple steam turbines based on the operating loads of multiple boilers and multiple steam turbines respectively, thereby achieving control of the steam power system.

[0241] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0242] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied 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.

[0243] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0244] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0245] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0246] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0247] Memory may include non-persistent memory in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, like read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0248] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0249] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0250] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0251] As can be seen from the above description, the embodiments of this application achieve the following technical effects:

[0252] 1) The control method for the steam power system of this application first establishes multiple boiler energy efficiency models corresponding to multiple boilers based on the historical operating efficiency and historical steam output of multiple boilers in the same multiple time periods; secondly, it establishes multiple turbine energy efficiency models corresponding to multiple turbines based on the first historical data of multiple steam turbines in the same multiple time periods; thirdly, it obtains multiple steam demands of the steam power system at the initial moment of multiple time periods, and determines the target operating efficiency of multiple turbines and multiple boilers based on multiple steam demands, multiple constraints, and a load scheduling optimization model; fourthly, it determines the operating load of multiple boilers and multiple turbines based on the target operating efficiency of multiple turbines, the target operating efficiency of multiple boilers, the multiple boiler energy efficiency models, and the multiple turbine energy efficiency models; and fifthly, it controls the operation of multiple boilers and multiple turbines based on the operating loads of multiple boilers and multiple turbines respectively, thereby achieving control of the steam power system. This method achieves simultaneous control of multiple boilers and multiple turbines, and load distribution among multiple boilers and multiple turbines, solving the problem that existing technologies cannot simultaneously optimize multiple devices in a steam power system.

[0253] 2) The load scheduling optimization model and the consumption difference analysis model of this application can achieve cost optimization by combining them: through precise load allocation and external procurement strategies, the costs of fuel and purchased steam / electricity are reduced, and ineffective equipment depreciation and losses are decreased. Energy efficiency is improved: while balancing the supply and demand of steam and electricity, the energy conversion path is optimized, boiler energy loss is reduced, and the fuel-steam-electricity conversion efficiency is improved. Computational efficiency is high: the turbine is processed by partitioned linearization, reducing the binary variables and nonlinearity of the model, improving the solution speed, and adapting to the real-time scheduling needs of industry.

[0254] The above are merely preferred embodiments of this application and are not intended to limit this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A control method for a steam power system, characterized in that, include: Based on the historical operating efficiency and historical steam output of multiple boilers in the steam power system during the same multiple time periods, establish multiple boiler energy efficiency models corresponding to the multiple boilers. Based on the first historical data of multiple steam turbines in the steam power system during the same multiple time periods, multiple steam turbine energy efficiency models are established for multiple steam turbines. The first historical data includes: steam inlet flow rate, operating load, steam extraction flow rate, steam exhaust flow rate, steam inlet pressure, steam exhaust pressure, steam extraction pressure, steam exhaust temperature, steam extraction temperature and steam inlet temperature of the steam turbine. At the initial moment of multiple time periods, multiple steam demands of the steam power system within the multiple time periods are obtained, and multiple target operating efficiencies of steam turbines and multiple target operating efficiencies of boilers are determined based on the multiple steam demands, multiple constraints and load scheduling optimization models. Based on the target operating efficiencies of multiple steam turbines, the target operating efficiencies of multiple boilers, the energy efficiency models of multiple boilers, and the energy efficiency models of multiple steam turbines, the operating loads of multiple boilers and the operating loads of multiple steam turbines are determined. The operation of the multiple boilers and the multiple steam turbines is controlled according to their respective operating loads, thereby achieving control of the steam power system.

2. The control method according to claim 1, characterized in that, The acquisition of multiple steam demands of the steam power system within multiple time periods includes: Based on second historical data and multiple algorithms, a steam load prediction model is established. The steam load prediction model is used to predict the steam demand in a future preset time period based on first real-time data. The second historical data and the first real-time data include at least: steam flow rate, fuel type and equipment parameters of the steam power system. The first real-time data at the start of each time period is acquired, and the steam demand for each time period is determined based on the first real-time data and the steam load prediction model.

3. The control method according to claim 1, characterized in that, The establishment of multiple turbine energy efficiency models corresponding to the multiple turbines includes: Acquire the first historical data of multiple steam turbines within the same multiple time periods; Based on the thermodynamic property equation of steam, the inlet steam pressure and the inlet steam temperature of the multiple steam turbines, the inlet steam enthalpy, extraction steam enthalpy and exhaust steam enthalpy of the multiple steam turbines are determined; Based on the energy balance formula, the steam inlet flow rate, steam extraction flow rate, steam inlet enthalpy, steam extraction enthalpy, and exhaust enthalpy of the various steam turbines, multiple steam turbine energy efficiency models are established.

4. The control method according to claim 3, characterized in that, The control method further includes: Based on the turbine energy efficiency model and multiple second real-time data, the operating load curve of the turbine is obtained. The operating load curve represents the steam intake of the turbine under different operating efficiencies. The second real-time data has the same parameter types as the first historical data. The operating load curve is divided into multiple regions, and multiple turbine energy efficiency sub-models with linear characteristics are established based on the relationship between the operating efficiency and the steam intake volume represented by the multiple regions.

5. The control method according to claim 4, characterized in that, The step of obtaining the operating load curve of the steam turbine based on the steam turbine energy efficiency model and second real-time data includes: Acquire the second real-time data of multiple steam turbines in multiple identical time periods; Based on the thermodynamic property equation of steam, the real-time inlet steam pressure and inlet steam temperature of the multiple steam turbines, the real-time inlet steam enthalpy, extraction steam enthalpy and exhaust steam enthalpy of the multiple steam turbines are determined; Based on the turbine energy efficiency model and the real-time steam inlet flow rate, steam extraction flow rate, steam inlet enthalpy, steam extraction enthalpy, and exhaust enthalpy of the multiple turbines, the real-time target operating efficiency of the multiple turbines is determined. The target steam intake is determined based on the real-time extraction steam volume, steam inlet enthalpy, extraction steam enthalpy, exhaust steam enthalpy, turbine mechanical efficiency, turbine power generation efficiency, and turbine output power of the multiple turbines. The operating load curve is obtained based on the multiple target operating efficiencies and the multiple target steam intake volumes.

6. The control method according to claim 5, characterized in that, The control method further includes: Without any extraction process performed on the steam turbine, the output power of the steam turbine is determined based on the steam inlet volume, the steam inlet enthalpy, the exhaust enthalpy, the steam turbine mechanical efficiency, and the steam turbine power generation efficiency. When the steam turbine has undergone extraction treatment, the output power of the steam turbine is determined based on the steam inlet flow rate, the steam extraction flow rate, the extraction enthalpy, the steam inlet enthalpy, the exhaust enthalpy, the steam turbine mechanical efficiency, and the steam turbine power generation efficiency.

7. The control method according to claim 1, characterized in that, The load dispatch optimization model is constructed based on the total operating cost of the steam power system, the start-up and shutdown status of the steam power system, the depreciation cost of the steam power system, the fuel price, the fuel consumption, the price of purchased steam, the steam demand, the price of purchased electricity, and the purchased power supply.

8. An optimized control device for a steam power system, characterized in that, include: The first module is used to establish multiple boiler energy efficiency models corresponding to the multiple boilers based on the historical operating efficiency and historical steam output of multiple boilers in the steam power system during the same multiple time periods. The second module is used to establish multiple turbine energy efficiency models corresponding to multiple turbines based on first historical data of multiple turbines of the steam power system in the same multiple time periods. The first historical data includes: the steam inlet flow rate, operating load, extraction flow rate, exhaust flow rate, steam inlet pressure and steam inlet temperature of the turbine. The first determining module is used to obtain multiple steam demands of the steam power system within multiple time periods at the initial moment of multiple time periods, and determine multiple target operating efficiencies of steam turbines and multiple target operating efficiencies of boilers based on the multiple steam demands, multiple constraints and load scheduling optimization models. The second determining module is used to determine the operating load of the multiple boilers and the operating load of the multiple steam turbines based on the multiple target operating efficiencies of the steam turbines, the multiple target operating efficiencies of the boilers, the multiple boiler energy efficiency models and the multiple steam turbine energy efficiency models. The regulating module is used to control the operation of the multiple boilers and the multiple steam turbines according to their respective operating loads, thereby realizing the control of the steam power system.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the computer-readable storage medium to perform the control method of the steam power system according to any one of claims 1 to 7.

10. A processor, characterized in that, The processor is used to run a program, wherein the program executes the control method of the steam power system according to any one of claims 1 to 7.

Images