CN113822496A - Multi-unit thermal power plant heat supply mode and parameter online optimization method - Google Patents

Abstract

The invention discloses a multi-unit thermal power plant heat supply mode and parameter online optimization method, which comprises the following steps: s1, setting a multi-heating mode combination scheme when the heating unit participates in deep peak shaving cooperative operation; s2, constructing a digital twin model of the unit in multi-heating mode cooperative operation by adopting a mechanism modeling and data identification method; s3, constructing a unit multi-mode collaborative operation evaluation model; step S4, processing historical operation data of the heat supply unit by adopting an intelligent algorithm to obtain a heat load demand and an electric load demand; step S5, calculating the economic index and peak regulation capacity under the combination of the power plant level multi-heating mode; and S6, carrying out optimization analysis and optimization calculation of multiple heating modes aiming at peak regulation capacity, economic indexes and evaluation indexes under different operation schemes of the multi-mode peak regulation of the heating unit, preferably optimizing a multi-mode cooperative operation mode and a multi-mode peak regulation cooperative operation optimal combination scheme, and guiding the unit to optimize power generation and heating operation on line.

Description

Multi-unit thermal power plant heat supply mode and parameter online optimization method

Technical Field

The invention belongs to the technical field of intelligent heat supply, and particularly relates to a multi-unit thermal power plant heat supply mode and parameter online optimization method.

Background

With the continuous promotion of the clean heating policy of northern regions of China, a large-scale cogeneration system represented by a coal-fired heat supply unit and a gas combined cycle heat supply unit becomes a main heat source of large and medium cities in northern China, so that heat supply to scattered regional boiler rooms is accelerated to replace the large and medium cities, and the heat supply unit accounts for about 1/4 of the total installed capacity of thermal power units in China. From the national clean heating policy, the ultra-low emission cogeneration is the first technology of 'clean heating', and from the energy structure, the coal-fired cogeneration is also a typical mode for clean and efficient utilization of coal. The combined heat and power generation realizes the cascade utilization of energy by adopting a mode of firstly generating high-grade heat energy and then supplying heat so as to improve the overall utilization efficiency of the energy and reduce the overall energy consumption, and is an energy utilization form with high comprehensive efficiency. The cogeneration can effectively reduce the power generation energy consumption, and is an important energy-saving and emission-reducing technology of the thermal power generating unit. Meanwhile, in order to reduce the environmental pollution of large cities, some cities adopt measures of replacing coal with electricity, replacing coal with gas and the like in heat supply in recent years, and heat is supplied by an electric boiler and a gas boiler.

At present, in order to match with the demands of urban heating and heat supply and adapt to flexible peak regulation, some power generation enterprises successively carry out technical transformation of steam extraction and heat supply of a steam turbine intermediate pressure cylinder, optical axis heat supply of a low pressure cylinder, high back pressure heat supply, cylinder switching heat supply of the low pressure cylinder, a heat storage water tank and electric boiler heat supply, and the situation of cooperative operation of multiple heat supply modes and deep peak regulation of a unit is formed, however, the existing technology faces the problems of insufficient peak regulation capacity, reasonable distribution of heat supply and power generation loads, economic combination of different modes and the like.

Based on the technical problems, a new method for optimizing the heat supply mode and parameters of the multi-unit thermal power plant on line needs to be designed.

Disclosure of Invention

The invention aims to provide an online optimization method for heat supply modes and parameters of a multi-unit thermal power plant.

In order to solve the technical problem, the invention provides an online optimization method for the heat supply mode and parameters of a multi-unit thermal power plant, which comprises the following steps:

s1, setting a multi-heating mode combination scheme when the heating unit participates in deep peak shaving cooperative operation;

s2, constructing a digital twin model of the unit in multi-heating mode cooperative operation by adopting a mechanism modeling and data identification method;

s3, constructing a unit multi-mode collaborative operation evaluation model;

step S4, predicting the heat supply load and the power generation load of the thermal power plant;

step S5, calculating the economic index and peak regulation capacity under the combination of the power plant level multi-heating mode;

and S6, carrying out optimization analysis and optimization calculation of multiple heating modes aiming at peak regulation capacity, economic indexes and evaluation indexes under different operation schemes of the multi-mode peak regulation of the heating unit, preferably optimizing a multi-mode cooperative operation mode and a multi-mode peak regulation cooperative operation optimal combination scheme, and guiding the unit to optimize power generation and heating operation on line.

Further, in step S1, a multi-heating-mode combination scheme in which the heating unit participates in deep peak shaving cooperative operation is set, which specifically includes:

based on unit transformation cost, complexity, heat economy, the demand and the coal type of different regions of power plant, select multi-mode heat supply combination scheme according to the technical adaptability of different heat supply modes, the heat supply mode includes high back pressure heat supply mode, steam extraction heat supply mode, cuts jar heat supply mode, high-low pressure bypass heat supply mode, heat accumulation water pitcher heat supply mode and electric boiler heat supply mode, multi-mode heat supply combination scheme includes that two liang of modes of above-mentioned each heat supply mode combine or more mode combine.

Further, in step S2, a mechanism modeling and data identification method is used to construct a digital twin model of the unit in the multi-heating mode cooperative operation, which specifically includes:

based on the basic principles of engineering thermodynamics, hydrodynamics and heat transfer, a mechanism simulation model consistent with the structure of a heat supply unit system is constructed by utilizing a modeling simulation technology, and theoretical calculation of the operation performance of the unit and a whole plant thermodynamic system under different load conditions is realized by inputting structural parameters and attribute information and setting boundary conditions; the mechanism simulation model at least comprises a steam turbine module, a boiler module, a feed water heat exchanger module, a condenser module, a steam-water flow module, a water pump module, a pipeline and a converging and crossing module, and each module needs to meet the mass conservation equation, the energy conservation equation and the constraint condition;

accessing multi-working-condition real-time operation data of the heat supply unit into the mechanism simulation model, and performing self-adaptive identification correction on a simulation result of the mechanism simulation model by adopting a reverse identification method;

the reverse identification method comprises the following steps: after missing value processing, abnormal value processing and data smoothing preprocessing operations are carried out on the operation data of the heat supply unit under multiple working conditions, the operation data containing measurement errors in the real-time operation data are primarily corrected into data meeting basic mechanism rules through historical operation data; inputting the input variables meeting the basic mechanism rule data into a mechanism simulation model to calculate the predicted values of the variables to be corrected in the variables; constructing an error membership function, and carrying out error detection and identification on data meeting basic mechanism rules of variables to be corrected to obtain data containing errors; and detecting and identifying errors through the predicted values, judging the reason containing the errors through an expert system, and correcting the operation data of the variable to be corrected with larger errors.

Further, in step S3, constructing a unit multi-mode collaborative operation evaluation model specifically includes:

step S31, setting an objective function: thermal economy and pollutant emission indices;

the thermal economy index is expressed by the total operating revenue of the unit as:

the total operation income of the unit is equal to the heat supply income, the power generation income, the peak regulation compensation income and the unit operation cost;

heat supply of the unit in the peak regulation cycle timeThe benefits are as follows: r_h＝∑D_h×T×P_h，R_hThe total heat supply income for the unit; d_hThe flow rate of the heating steam or hot water is adopted; t is a peak regulation period; p_hA unit price for supplying heat;

the power generation benefits are as follows: r_g＝∑W_p×T_p×P_gp+∑W×(T-T_p)×P_g，R_gThe total income of the unit power generation; w_pIs the generated power during peak shaving; t is_pIs the peak shaver duration; p_gpElectricity prices for peak shaving periods; w is the generated power in the non-peak regulation period; p_gElectricity prices for non-peak shaver periods;

the peak regulation compensation yield is as follows:

R_ccompensating the total gain for peak shaving in the maximum heating period; s is the unit capacity; a. the_iThe lower limit of the ith gear load factor is set; a is the load rate of the unit; c_iThe total gear of the electricity price is subsidized;

the pollutant emission index is characterized in that the load distribution of the unit is optimized by combining the pollutant emission characteristics of the unit in each load section, so that the optimal pollutant emission is realized, and the pollutant emission index is expressed as follows:

L(W_it) The pollutant discharge amount of the ith unit in the t period is shown;

step S32, setting constraint conditions: a safety index;

the safety index is defined by the total constraint conditions of the unit, and the total constraint conditions of the unit at least comprise unit capacity constraint, boiler capacity constraint, heat supply load upper and lower limit constraint, heat supply load equality constraint, electric energy balance constraint, heat energy balance constraint and deep peak regulation power constraint;

the unit capacity constraint is expressed as:

P_i ^min≤P_i≤P_i ^max；

in the formula (I), the compound is shown in the specification,

allowing the minimum steam inlet flow for the ith steam turbine;

allowing the maximum steam inlet flow for the ith steam turbine; p_i ^minThe minimum generating power of the ith turbine; p_i ^maxThe maximum generating power of the ith turbine;

the boiler capacity constraint is expressed as:

the minimum steam production flow of the ith boiler is obtained;

the maximum steam production flow of the ith boiler is obtained;

the upper and lower limits of the heating load are constrained as follows: h_imin＜H_i＜H_imax，H_iminThe minimum heat supply quantity of the ith unit; h_imaxThe maximum heat supply amount of the ith unit;

the heating load equality constraint is expressed as:

D_hthe total load for heat supply;

the electric energy balance constraint is as follows: p_load(t)＝P_CHP(t)-P_EB(t)-P_CY(t)，P_load(t) is the electrical load demand of the system during the time period t; p_CHP(t) is the electric power output value of the thermoelectric unit at the moment t; p_EB(t) is the electric power consumed by the electric boiler at time t; p_CY(t) is the service load at the time period t;

the heat energy balance constraint is H_load(t)＝H_CHP(t)+H_EB(t)+H_TS(t)-H_TS(t-Δt)，H_load(t) is the thermal load demand of the system over a period of t; h_CHP(t) heat generated by the thermoelectric generator set in a time period t; h_EB(t) the heat generated by the electric boiler at time t; h_TS(t) is the heat storage capacity of the heat storage device over time period t; Δ t is a unit time length;

and the depth peak regulation power constraint is as follows:

P_feasiblethe method is characterized in that the method provides the minimum power generation load for the thermal power plant on the basis of meeting the heat supply requirement, namely the deep peak shaving capacity of each unit operation feasible region;

a grid load instruction is given in a period t; p_abilityThe maximum load capacity of the thermal power plant, namely the top spike capacity.

Further, in step S4, predicting the heating load and the power generation load of the thermal power plant specifically includes:

building a BP artificial neural network model, wherein an input layer of the BP artificial neural network load prediction model at least comprises: DCS unit operation data, meteorological information, power generation and heat supply prices, coal prices, peak regulation bidding and optimizer operation configuration information; the output of the corresponding model is a load value corrected by combining weather data under the input condition, and a load prediction model is obtained based on the training of a BP neural network method; and importing input layer data based on the characteristics of a regional heating mode and environmental climate change factors, and predicting a heating load prediction value and a power generation load prediction value of the thermal power plant under the current working condition through the generated load prediction model.

Further, in step S5, calculating an economic indicator under the combination of the plant-level multiple heating modes specifically includes:

based on actual operation parameters or simulation parameters of the heat supply unit, economic indexes including steam consumption rate, heat consumption rate, power generation coal consumption rate, power supply coal consumption rate, plant power consumption rate, unit efficiency and unit heat supply amount are calculated in sequence;

calculating the steam consumption rate:

d is the steam consumption rate of the unit; d₀The steam inlet quantity of the steam turbine; p_eGenerating power for the unit;

calculating the heat rate:

q is heat rate; q is the heat consumption of the steam turbine; h is₀The enthalpy value of the main steam is; d_zrrFor the flow rate of hot reheat steam, h_zrrIs an enthalpy value; d_zrlFor the flow rate of cold reheat steam, h_zrlIs an enthalpy value; d_fwFor water supply flow rate, h_fwIs an enthalpy value; d_gFor superheating and reducing the temperature and water flow h_gIs an enthalpy value; d_zFor reheating and reducing the temperature water flow, h_zIs an enthalpy value;

calculating the power generation coal consumption rate:

B_bis the standard coal consumption rate; eta_gdFor pipeline efficiency; eta_gTo boiler efficiency;

calculating the power supply coal consumption rate:

η_ethe plant power rate;

calculating the plant power consumption rate:

P_efthe power consumption is the plant power consumption;

calculating the unit efficiency:

η_efthe mechanical efficiency of the unit; eta_mThe motor efficiency of the unit;

the heat supply of the computer set is as follows: q_gr＝D_gr×h_gr，D_grThe heat supply flow is adopted; h is_grThe enthalpy value of heat supply is obtained.

Further, the calculation of the economic indexes also comprises single working condition calculation and statistical value calculation, the power generation and heat supply efficiency of the unit under the current operating working condition is obtained through the economic index calculation of the single working condition, the operating working conditions with high efficiency and low energy consumption are obtained through the performance indexes of different working conditions, and an optimization direction is provided for the energy-saving and consumption-reducing operation of the unit; and calculating the economic index of the statistical value by adopting the statistical values of the generated energy, the heat supply load, the deep peak regulation subsidy and the coal consumption within a period of time, acquiring the overall economic benefit within the period of time and providing guidance for the scheduling of the thermoelectric load.

Further, in step S5, calculating the peak shaving capacity of the unit under the combination of the plant-level multiple heating modes specifically includes:

establishing a maximum power generation capacity, a maximum heat supply capacity and a minimum heat supply model, and optimizing load distribution of different heat supply units within a model boundary limiting condition;

the maximum generating capacity is obtained by setting thermoelectric load constraint according to an objective function of the maximum generating capacity of the whole plant and solving the thermoelectric load constraint by adopting an intelligent algorithm, and the maximum generating capacity model is expressed as follows:

an objective function:

constraint conditions are as follows:

MIN(P_i)≤P_i≤MAX(P_i)；

in the formula: p_iThe electric load of each unit; n is the number of units; h_totalSupplying heat to each unit to supply total load;

the maximum heating capacity model is expressed as:

maximum heating capacity ═ Σ Q_{Row board}+(∑G-∑Q₁)(H_{Master and slave}-H_{For supplying to})/(H_{For supplying to}-H_{To give})-Q_From+Q_{Store up}；

In the formula: q_{Row board}The maximum steam discharge or the maximum steam extraction of the steam turbine; g is the rated evaporation capacity of the boiler; q1 is the maximum steam inlet amount for the back pressure machine, and is the minimum steam inlet amount for the extraction condenser when the steam is extracted at the maximum; h is the enthalpy value of main steam, steam supply and water supply; q_FromThe total amount of the self-consumption steam; q_{Store up}The self-consumption steam can be replaced for the daytime peak of the heat storage equipment.

The minimum heat supply model is expressed as: the lowest heat supply is ═ sigma G₂-∑Q_{Straight coagulation}-Q_From-Q_{Store up}；

In the formula: g2 is the lowest evaporation capacity allowed by the safe operation of the boiler; q straight condensing is the rated steam inlet quantity of the straight condensing working condition of the extraction condensing machine.

Further, in step S6, performing optimization analysis and optimization calculation of multiple heating modes according to peak regulation capability, economic indicators and evaluation indicators under different operation schemes of the multi-mode peak regulation of the heating unit, preferably selecting a multi-mode cooperative operation mode and a multi-mode peak regulation cooperative operation optimal combination scheme, and guiding the unit to optimize power generation and heating operation on line, specifically including:

step S61, calculating economic indexes and peak shaving capacities of the heat supply unit under different operation schemes of multi-mode peak shaving, and obtaining unit steam consumption rate, heat consumption rate, power generation coal consumption rate, power supply coal consumption rate, plant power consumption rate, unit efficiency, unit heat supply capacity, maximum power generation capacity, maximum heat supply capacity and minimum heat supply capacity parameter indexes under different modes;

s62, acquiring operation parameters and sold heat, sold electricity, coal price and water price data of the heat supply unit under different operation schemes of multi-mode peak regulation, establishing a multi-objective optimization function model for maximizing the total operation income and minimizing pollutant emission of the unit through the established unit multi-mode collaborative operation evaluation model, and determining corresponding constraint conditions according to different operation schemes;

s63, solving an optimal solution set by adopting a multi-objective optimization algorithm according to a target function and constraint conditions to obtain a multi-mode combined optimal scheme set for unit cooperative operation, and selecting a multi-mode peak shaving cooperative operation optimal combined scheme by combining the actual complexity and the technical adaptability of the power plant unit;

and S64, optimizing the heat supply parameters of the unit through the obtained optimal combination scheme of the multi-mode peak shaving cooperative operation, and guiding the unit to optimize power generation and heat supply operation on line.

Further, the multi-objective optimization algorithm in the step S63 adopts a multi-objective cuckoo search algorithm.

The invention has the beneficial effects that:

(1) according to the method, a technical method combining 'structural mechanism modeling and data identification and correction' is adopted, a structural mechanism model which is mapped with a practical structure of a thermodynamic system of a power plant unit is constructed by utilizing a digital twin modeling technology based on basic principles such as engineering thermodynamics, hydrodynamics and heat transfer, and meanwhile, a simulation result of the model is subjected to self-adaptive identification and correction by adopting a reverse identification method, so that the deviation between a theoretical value and a measured value is reduced to the greatest extent; by inputting structural parameters and attribute information and setting boundary conditions, theoretical calculation can be carried out on the operation performance of the unit and the whole plant thermodynamic system under different load conditions, high-precision simulation and emulation of the operation performance of the thermoelectric unit are realized, and core technical support is provided for further quantitative analysis of operation safety, energy consumption and environmental emission indexes, and research and establishment of a multi-mode collaborative operation scheme under different load requirements;

(2) according to the invention, the operation performance of the unit is obtained by calculating the unit economic index under the combination of multiple heat supply modes, and the energy efficiency and the operation economy of the unit in different thermoelectric load operation ranges are accurately evaluated on the basis for optimizing main operation parameters of the unit, so that on one hand, an operation parameter optimization scheme of different loads in the daily operation process of the unit is provided, the energy consumption and the environmental emission are reduced, on the other hand, energy consumption characteristic curves of the unit under different heat and electric loads in the full load range are obtained, and basic data are provided for thermoelectric load distribution and collaborative operation optimization under the source network collaboration;

(3) the peak load regulation capacity of the unit under the combination of multiple heat supply modes is calculated, the maximum power generation capacity, the maximum heat supply capacity and the minimum heat supply capacity model are established, and the load distribution of different heat supply units is optimized within the boundary limit condition of the models; and establishing a multi-mode collaborative operation evaluation model of the unit, which comprises a thermal economy index and a pollutant emission index, providing a multi-unit load optimization distribution scheme and a collaborative scheduling strategy which simultaneously meet a power grid load scheduling instruction, a total heat supply demand and a certain boundary condition for the thermal power plant, establishing an evaluation objective function and a constraint condition of the whole plant, combining peak regulation capability, economic index and evaluation index under different operation schemes, adopting an optimization algorithm and calling a verified simulation model, outputting an intelligent optimized mode combination scheme, guiding the unit to optimize power generation and heat supply operation on line, and guiding the coal distribution, heat supply and power generation modes of the unit in advance by establishing an accurate and reasonable collaborative operation evaluation model, practically realizing the safe, efficient and flexible operation of multiple furnaces of an enterprise, participating in deep peak regulation, and realizing comprehensive optimal profit of heat supply, heat supply and peak regulation, the economical efficiency of the source network load storage operation and the production management level are further improved, and the profitability of the thermal power plant is integrally improved.

Additional features and advantages will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.

In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.

FIG. 1 is a schematic flow chart of a multi-unit thermal power plant heat supply mode and parameter online optimization method of the present invention;

FIG. 2 is a schematic view of a combination of multiple heating modes according to the present invention;

FIG. 3 is a diagram of a single-unit simulation model according to the present invention.

Detailed Description

To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

Example 1

FIG. 1 is a schematic flow chart of a heat supply mode and parameter online optimization method for a multi-unit thermal power plant according to the present invention.

As shown in fig. 1, this embodiment 1 provides an online optimization method for heat supply modes and parameters of multiple thermal power plants, where the online optimization method includes:

s1, setting a multi-heating mode combination scheme when the heating unit participates in deep peak shaving cooperative operation;

s2, constructing a digital twin model of the unit in multi-heating mode cooperative operation by adopting a mechanism modeling and data identification method;

s3, constructing a unit multi-mode collaborative operation evaluation model;

step S4, processing historical operation data of the heat supply unit by adopting an intelligent algorithm to obtain a heat load demand and an electric load demand;

step S5, calculating the economic index and peak regulation capacity under the combination of the power plant level multi-heating mode;

and S6, carrying out optimization analysis and optimization calculation of multiple heating modes aiming at peak regulation capacity, economic indexes and evaluation indexes under different operation schemes of the multi-mode peak regulation of the heating unit, preferably optimizing a multi-mode cooperative operation mode and a multi-mode peak regulation cooperative operation optimal combination scheme, and guiding the unit to optimize power generation and heating operation on line.

Fig. 2 is a schematic view of a combination of multiple heating modes according to the present invention.

As shown in fig. 2, in this embodiment, in step S1, the method for setting a multiple heating mode combination scheme when the heating unit participates in the deep peak shaving collaborative operation specifically includes:

based on unit transformation cost, complexity, heat economy, requirements of different regions of a power plant and coal types, a multi-mode heat supply combination scheme is selected according to technical adaptability of different heat supply modes of a high back pressure, steam extraction, cylinder cutting, a high-low pressure bypass, a heat storage water tank and an electric boiler, and the multi-mode heat supply combination scheme comprises two modes or more modes.

In practical application, the most mature technologies are heat storage and heat supply of a hot water tank and heat supply of an electric boiler, the 2 technologies have better heat economy, but relatively higher transformation cost and larger occupied area; secondly, the bypass technology of the steam turbine is adopted, so that the transformation cost is low, but the thermal economy is poor; the high-pressure bypass and the low-pressure bypass are combined for heat supply, more high-quality steam is extracted for heat supply by means of the high-pressure bypass valve and the low-pressure bypass valve, and the cylinder is cut, so that the heat supply capacity is improved by a back pressure heat supply mode that the steam discharged by the intermediate pressure cylinder is directly used for heat supply. Both heating modes have advantages and disadvantages. The high-low pressure bypass combined heat supply uses high-grade steam for low-grade heat supply, so that the overall heat economy is low; the cylinder cutting technology realizes the cascade utilization of heat, has higher energy efficiency, but has higher potential safety hazard.

Due to the cost and complexity of unit modification and the instability of unit operation caused by too many mode combinations, the combination commonly used at present is the combination of two heating modes. Typical combinations include: high back pressure + steam extraction, high back pressure + cylinder cutting, high-low side + steam extraction, high-low side + cylinder cutting, steam extraction + heat storage water tank, cylinder cutting + heat storage water tank, steam extraction + electric boiler, cylinder cutting + electric boiler, high back pressure + electric boiler, high-low side + electric boiler and the like. The situation of different mode combinations is more, and corresponding multi-mode combinations need to be selected according to the adaptability of specific technologies aiming at the requirements and coal types of different regions of a power plant. In the technical adaptability, different modes are selected according to different unit characteristics. The technical adaptability and the peak regulation capability of the heat storage electric boiler are stronger than those of other transformation technologies, but the static investment is high, and the thermal efficiency of the system is lower; backpressure heat supply (including optical axis and cylinder cutting technology), static investment is low, the total efficiency of the system is high, but certain improvement needs to be further made on the basis of backpressure heat supply improvement by considering the safety of a low-pressure cylinder; and the high-low pressure bypass heat supply mode also needs to meet the requirements of blade strength and unit transverse thrust on safe operation standards. The actual transformation technology selection needs comprehensive consideration of comprehensive economical efficiency and technological adaptability.

FIG. 3 is a schematic diagram of a single unit simulation model according to the present invention;

as shown in fig. 3, in this embodiment, in step S2, a mechanism modeling and data identification method is used to construct a digital twin model for the multiple heat supply modes of the unit to cooperatively operate, which specifically includes:

based on the basic principles of engineering thermodynamics, hydrodynamics and heat transfer, a mechanism simulation model consistent with the structure of a heat supply unit system is constructed by utilizing a modeling simulation technology, and theoretical calculation of the operation performance of the unit and a whole plant thermodynamic system under different load conditions is realized by inputting structural parameters and attribute information and setting boundary conditions; the mechanism simulation model at least comprises a steam turbine module, a boiler module, a feed water heat exchanger module, a condenser module, a steam-water flow module, a water pump module, a pipeline and a converging and crossing module, and each module needs to meet the mass conservation equation, the energy conservation equation and the constraint condition of the module;

accessing real-time operation data of the heat supply unit into a mechanism simulation model, and performing self-adaptive identification correction on a simulation result of the mechanism simulation model by adopting a reverse identification method;

the reverse identification method comprises the following steps: after missing value processing, abnormal value processing and data smoothing preprocessing operations are carried out on the operation data of the heat supply unit under multiple working conditions, the operation data containing measurement errors in the real-time operation data are primarily corrected into data meeting basic mechanism rules through historical operation data; inputting the input variables meeting the basic mechanism rule data into a mechanism simulation model to calculate the predicted values of the variables to be corrected in the variables; constructing an error membership function, and carrying out error detection and identification on data meeting basic mechanism rules of variables to be corrected to obtain data containing errors; and detecting and identifying errors through the predicted values, judging the reason containing the errors through an expert system, and correcting the operation data of the variable to be corrected with larger errors.

In practical application, the data twin model generation is to perform virtual-real fusion on the logic model, the simulation model and the data driving model, and finally establish a digital twin model of the physical entity of the thermal power plant in a virtual space. Wherein the profiles of the models are as follows: (1) the physical model reflects each physical entity in the physical system of the thermal power plant, and the geometric attributes and the functional attributes of the physical model are defined according to the geometric shapes and the mechanical mechanisms of the physical entities; the physical entities mainly comprise boilers, turbines, pumps/fans, valves, heat exchangers, condensers and cooling towers, the idea of building an integral-module-integral physical model is adopted according to different devices of the physical entities of the thermal power plant, an independent physical model is built for each device, and finally each module is connected into a whole. (2) The logic model establishes a controllable closed-loop logic model according to the supply-demand relationship, distribution and transportation among all physical entities of the thermal power plant, and maps the physical model to the logic model. (3) The simulation model can adjust and optimize parameters of the simulation model according to the error of the output predicted value and the actual value of the simulation model based on the acquired operation data, state data and physical attribute data of the thermal power plant. (4) The data-driven model is based on collected normal operation data of the thermal power plant, a data fusion and deep learning algorithm can be adopted, each physical entity of the thermal power plant performs feature extraction on each input data in normal operation according to a working principle, the input data is used as the input of the data-driven model, and a predicted value output by the model can be used for parameter optimization.

Selecting multiple groups of measured data of the power plant under various steady-state working conditions in the reverse identification process of the characteristic parameters of the digital twin model; calculating a characteristic coefficient theoretical value of each device; and then, identifying and calculating the characteristic coefficient correction quantity of each device by utilizing a particle swarm algorithm and combining a plurality of groups of measured data, and obtaining corrected parameters. And comparing different characteristic coefficient correction amounts in the simulation model with corresponding measured data under multiple working conditions to identify the optimal characteristic parameters. The corrected model can better describe an actual physical system, and the calculation precision of the power plant multi-working-condition calculation simulation is improved.

In this embodiment, in step S3, constructing a unit multi-mode collaborative operation evaluation model specifically includes:

step S31, setting an objective function: thermal economy and pollutant emission indices;

the thermal economy index is expressed by the total operating revenue of the unit as:

the total operation income of the unit is equal to the heat supply income, the power generation income, the peak regulation compensation income and the unit operation cost;

the heat supply benefit of the unit in the peak regulation period time is as follows: r_h＝∑D_h×T×P_h，R_hThe total heat supply income for the unit; d_hThe flow rate of the heating steam or hot water is adopted; t is a peak regulation period; p_hA unit price for supplying heat;

the power generation benefit is as follows: r_g＝∑W_p×T_p×P_gp+∑W×(T-T_p)×P_g，R_gThe total income of the unit power generation; w_pIs the generated power during peak shaving; t is_pIs the peak shaver duration; p_gpElectricity prices for peak shaving periods; w is the generated power in the non-peak regulation period; p_gElectricity prices for non-peak shaver periods;

the peak-shaving compensation yield is as follows:

R_ccompensating the total gain for peak shaving in the maximum heating period; s is the unit capacity; a. the_iThe lower limit of the ith gear load factor is set; a is the load rate of the unit; c_iThe total gear of the electricity price is subsidized;

the pollutant discharge index is characterized in that the load distribution of the unit is optimized by combining the pollutant discharge characteristics of the unit in each load section, so that the optimal pollutant discharge is realized, and the pollutant discharge index is expressed as follows:

L(W_it) The pollutant discharge amount of the ith unit in the t period is shown;

step S32, setting constraint conditions: a safety index;

the safety index is defined by the total constraint conditions of the unit, and the total constraint conditions of the unit at least comprise unit capacity constraint, boiler capacity constraint, heat supply load upper and lower limit constraint, heat supply load equality constraint, electric energy balance constraint, heat energy balance constraint and deep peak regulation power constraint;

the unit capacity constraint is expressed as:

P_i ^min≤P_i≤P_i ^max；

in the formula (I), the compound is shown in the specification,

allowing the minimum steam inlet flow for the ith steam turbine;

allowing the maximum steam inlet flow for the ith steam turbine; p_i ^minThe minimum generating power of the ith turbine; p_i ^maxThe maximum generating power of the ith turbine;

the boiler capacity constraint is expressed as:

the minimum steam production flow of the ith boiler is obtained;

the maximum steam production flow of the ith boiler is obtained;

upper and lower limits of heating loadThe bundle is represented as: h_imin＜H_i＜H_imax，H_iminThe minimum heat supply quantity of the ith unit; h_imaxThe maximum heat supply amount of the ith unit;

the heating load equality constraint is expressed as:

D_hthe total load for heat supply;

electric energy balance constraint: p_load(t)＝P_CHP(t)-P_EB(t)-P_CY(t)，P_load(t) is the electrical load demand of the system during the time period t; p_CHP(t) is the electric power output value of the thermoelectric unit at the moment t; p_EB(t) is the electric power consumed by the electric boiler at time t; p_CY(t) is the service load at the time period t;

heat energy balance constraint H_load(t)＝H_CHP(t)+H_EB(t)+H_TS(t)-H_TS(t-Δt)，H_load(t) is the thermal load demand of the system over a period of t; h_CHP(t) heat generated by the thermoelectric generator set in a time period t; h_EB(t) the heat generated by the electric boiler at time t; h_TS(t) is the heat storage capacity of the heat storage device over time period t; Δ t is a unit time length;

deep peak regulation power constraint:

P_feasiblethe method is characterized in that the method provides the minimum power generation load for the thermal power plant on the basis of meeting the heat supply requirement, namely the deep peak shaving capacity of each unit operation feasible region;

a grid load instruction is given in a period t; p_abilityThe maximum load capacity of the thermal power plant, namely the top spike capacity.

In this embodiment, in step S4, the predicting the heating load and the power generation load of the thermal power plant specifically includes:

building a BP artificial neural network model, wherein an input layer of the BP artificial neural network load prediction model at least comprises: DCS unit operation data, meteorological information, power generation and heat supply prices, coal prices, peak regulation bidding and optimizer operation configuration information; the output of the corresponding model is a load value corrected by combining weather data under the input condition, and a load prediction model is obtained based on the training of a BP neural network method; and importing input layer data based on the characteristics of a regional heating mode and environmental climate change factors, and predicting a heating load prediction value and a power generation load prediction value of the thermal power plant under the current working condition through the generated load prediction model.

In this embodiment, in step S5, calculating the unit economic indicator under the combination of multiple heating modes specifically includes:

based on actual operation parameters or simulation parameters of the heat supply unit, economic indexes including steam consumption rate, heat consumption rate, power generation coal consumption rate, power supply coal consumption rate, plant power consumption rate, unit efficiency and unit heat supply amount are calculated in sequence;

and (3) calculating the steam consumption rate:

d is the steam consumption rate of the unit; d₀The steam inlet quantity of the steam turbine; p_eGenerating power for the unit;

calculating the heat rate:

q is heat rate; q is the heat consumption of the steam turbine; h is₀The enthalpy value of the main steam is; d_zrr,h_zrrThe flow and enthalpy of the hot reheat steam are the same; d_zrl,h_zrlThe flow and enthalpy of the cold reheat steam are the same; d_fw,h_fwThe water supply flow and the enthalpy value are obtained; d_g,h_gThe water flow and enthalpy are the overheating temperature reduction; d_z,h_zThe water flow and enthalpy value are reheat temperature-reducing water flow and enthalpy value;

calculating the power generation coal consumption rate:

B_bis the standard coal consumption rate; eta_gdFor pipeline efficiency; eta_gTo boiler efficiency;

calculating the power supply coal consumption rate:

η_ethe plant power rate;

calculating the plant power consumption rate:

P_efthe power consumption is the plant power consumption;

calculating the unit efficiency:

η_efthe mechanical efficiency of the unit; eta_mThe motor efficiency of the unit;

the heat supply of the computer set is as follows: q_gr＝D_gr×h_gr，D_grThe heat supply flow is adopted; h is_grThe enthalpy value of heat supply is obtained.

In this embodiment, the calculation of the economic indicators further includes calculation of a single working condition and calculation of a statistical value, the power generation and heat supply efficiency of the unit under the current operating condition is obtained through calculation of the economic indicators of the single working condition, and the operating conditions with high efficiency and low energy consumption are obtained through comparison of performance indicators of different working conditions, so that an optimization direction is provided for energy-saving and consumption-reducing operation of the unit; and calculating the economic indexes of the statistical values by adopting the generated energy, the heat supply load, the deep peak regulation subsidy and the coal consumption statistical value in a period of time to obtain the overall economic benefit in the period of time and provide guidance for thermoelectric load scheduling.

In this embodiment, in step S5, calculating the peak shaving capacity of the unit under the combination of multiple heating modes specifically includes: establishing a maximum power generation capacity, a maximum heat supply capacity and a minimum heat supply model, and optimizing load distribution of different heat supply units within the limit conditions of model boundary conditions;

the maximum generating capacity is obtained by setting thermoelectric load constraint according to an objective function of the maximum generating capacity of the whole plant and solving by adopting an intelligent algorithm, and the maximum generating capacity model is expressed as follows:

an objective function:

constraint conditions are as follows:

MIN(P_i)≤P_i≤MAX(P_i)；

in the formula: p_iThe electric load of each unit; n is the number of units; h_totalSupplying heat to each unit to supply total load;

the maximum heating capacity model is expressed as:

maximum heating capacity ═ Σ Q_{Row board}+(∑G-∑Q₁)(H_{Master and slave}-H_{For supplying to})/(H_{For supplying to}-H_{To give})-Q_From+Q_{Store up}；

In the formula: q_{Row board}The maximum steam discharge or the maximum steam extraction of the steam turbine; g is the rated evaporation capacity of the boiler; q1 is the maximum steam inlet amount for the back pressure machine, and is the minimum steam inlet amount for the extraction condenser when the steam is extracted at the maximum; h is the enthalpy value of main steam, steam supply and water supply; q_FromThe total amount of the self-consumption steam; q_{Store up}The self-consumption steam can be replaced for the daytime peak of the heat storage equipment.

The lowest heat supply model is expressed as: the lowest heat supply is ═ sigma G₂-∑Q_{Straight coagulation}-Q_From-Q_{Store up}；

In the formula: g2 is the lowest evaporation capacity allowed by the safe operation of the boiler; q straight condensing is the rated steam inlet quantity of the straight condensing working condition of the extraction condensing machine.

In this embodiment, in step S6, for peak shaving capacity, economic indicators, and evaluation indicators under different operation schemes of the multi-mode peak shaving of the heat supply unit, optimization analysis and optimization calculation of multiple heat supply modes are performed, and a multi-mode cooperative operation mode and a multi-mode peak shaving cooperative operation optimal combination scheme are preferably selected to guide the unit to optimize power generation and heat supply operation on line, which specifically includes:

step S61, calculating economic indexes and peak shaving capacities of the heat supply unit under different operation schemes of multi-mode peak shaving, and obtaining unit steam consumption rate, heat consumption rate, power generation coal consumption rate, power supply coal consumption rate, plant power consumption rate, unit efficiency, unit heat supply capacity, maximum power generation capacity, maximum heat supply capacity and minimum heat supply capacity parameter indexes under different modes;

s62, acquiring operation parameters and sold heat, sold electricity, coal price and water price data of the heat supply unit under different operation schemes of multi-mode peak regulation, establishing a multi-objective optimization function model for maximizing the total operation income and minimizing pollutant emission of the unit through the established unit multi-mode collaborative operation evaluation model, and determining corresponding constraint conditions according to different operation schemes;

s63, solving an optimal solution set by adopting a multi-objective optimization algorithm according to a target function and constraint conditions to obtain a multi-mode combined optimal scheme set for unit cooperative operation, and selecting a multi-mode peak shaving cooperative operation optimal combined scheme by combining the actual complexity and the technical adaptability of the power plant unit;

and S64, optimizing the heat supply parameters of the unit through the obtained optimal combination scheme of the multi-mode peak shaving cooperative operation, and guiding the unit to optimize power generation and heat supply operation on line.

In the present embodiment, the multi-objective optimization algorithm in step S63 employs a multi-objective cuckoo search algorithm.

In practical application, the implementation process of the multi-target cuckoo search algorithm comprises the following steps:

(1) initializing, the number of the bird nests is n (namely the finally generated Pareto optimal solution set comprises n optimal solutions), and finding the probability P_a0.25, 100 is the maximum iteration number MaxIter, 0 is the initial iteration number k;

(2) randomly generating n cuckoo bird nests, wherein each bird nest corresponds to one solution, namely n non-inferior solutions meeting constraint conditions are initialized, and the corresponding fitness f is calculated₁(x)，f₂(x) A value of (d); setting a fitness function based on the total unit operation income C and the pollutant emission index W

(3) Updating the position, applying a Levy flight principle to update the solution to obtain a new solution X1,

wherein alpha is a dynamic self-adaptive step length coefficient, and a solution set is recorded as newest;

(4) sorting the solutions in the nownst by combining a non-dominated sorting algorithm of an NSGA algorithm, determining the advantages and disadvantages of the solutions in the nownst, and generating the same number of new solutions by adopting local random walk for the solutions with the non-dominated level as a first level, wherein a solution set of the new solutions is an elite solution set elitnest;

(5) merging the nest, the newest and the elitnest, and marking as allnest;

(6) combining an elite strategy of an NSGA-II algorithm, improving the convergence speed of the traditional MOCS, performing non-dominated ranking and crowding distance on all solutions in the allnest through fitness to complete non-dominated ranking, selecting the first n individuals, replacing the solutions in the nest, and recording the ranked solutions as n +1 to 2n to generate a solution set as badnest;

(7) randomly walking the individuals in badnest locally at random according to the probability Pa, replacing the solutions, and collecting the updated solution as a newest;

(8) merging the nest and the newest into an allnest, and calculating in an algorithm step five;

(9) dynamically updating the value of the step length coefficient alpha, and jumping to the algorithm step two to perform iterative operation, wherein an iterative algebra k is k + 1;

(10) and exiting iteration when the maximum iteration times are reached.

And outputting the finally generated nest, namely the finally generated Pareto optimal solution set, wherein the Pareto optimal solution set comprises n Pareto optimal solutions.

The invention adopts a technical method combining 'structural mechanism modeling and data identification and correction', and based on the basic principles of engineering thermodynamics, hydrodynamics, heat transfer and the like, constructs a mechanism simulation model which is mapped with the practical structure of the thermodynamic system of the demonstration power plant unit by using a digital twin modeling technology, and simultaneously adopts a reverse identification method to carry out self-adaptive identification and correction on the simulation result of the model, thereby reducing the deviation between a theoretical value and a measured value to the maximum extent; and by inputting structural parameters and attribute information and setting boundary conditions, theoretical calculation can be carried out on the operation performance of the unit and the whole plant thermodynamic system under different load conditions, high-precision simulation and emulation of the operation performance of the thermoelectric unit are realized, and core technical support is provided for further quantitative analysis of operation safety, energy consumption and environmental emission indexes, and research and establishment of a multi-mode collaborative operation scheme under different load requirements.

The method obtains the operation performance of the unit by calculating the economic indexes of the unit under the combination of multiple heat supply modes, accurately evaluates the energy efficiency and the operation economy of the unit in different thermoelectric load operation ranges on the basis, optimizes the main operation parameters of the unit, provides an operation parameter optimization scheme of different loads in the daily operation process of the unit on one hand, reduces energy consumption and environmental emission on the other hand, obtains energy consumption characteristic curves of the unit under different heat and electric loads in the full load range on the other hand, and provides basic data for thermoelectric load distribution and collaborative operation optimization under the source network collaboration.

The peak load regulation capacity of the unit under the combination of multiple heat supply modes is calculated, the maximum power generation capacity, the maximum heat supply capacity and the minimum heat supply capacity model are established, and the load distribution of different heat supply units is optimized within the boundary limit condition of the models; and establishing a multi-mode collaborative operation evaluation model of the unit, which comprises a thermal economy index and a pollutant emission index, providing a multi-unit load optimization distribution scheme and a collaborative scheduling strategy which simultaneously meet a power grid load scheduling instruction, a total heat supply demand and a certain boundary condition for the thermal power plant, establishing an evaluation objective function and a constraint condition of the whole plant, combining peak regulation capability, economic index and evaluation index under different operation schemes, adopting an optimization algorithm and calling a verified simulation model, outputting an intelligent optimized mode combination scheme, guiding the unit to optimize power generation and heat supply operation on line, and guiding the coal distribution, heat supply and power generation modes of the unit in advance by establishing an accurate and reasonable collaborative operation evaluation model, practically realizing the safe, efficient and flexible operation of multiple furnaces of an enterprise, participating in deep peak regulation, and realizing comprehensive optimal profit of heat supply, heat supply and peak regulation, the economical efficiency of the source network load storage operation and the production management level are further improved, and the profitability of the thermal power plant is integrally improved.

In the several embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other ways. The system embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.

Claims (10)

1. A multi-unit thermal power plant heat supply mode and parameter online optimization method is characterized by comprising the following steps:

s1, setting a multi-heating mode combination scheme when the heating unit participates in deep peak shaving cooperative operation;

s2, constructing a digital twin model of the unit in multi-heating mode cooperative operation by adopting a mechanism modeling and data identification method;

s3, constructing a unit multi-mode collaborative operation evaluation model;

step S4, predicting the heat supply load and the power generation load of the thermal power plant;

step S5, calculating the economic index and peak regulation capacity under the combination of the power plant level multi-heating mode;

and S6, carrying out optimization analysis and optimization calculation of multiple heating modes aiming at peak regulation capacity, economic indexes and evaluation indexes under different operation schemes of the multi-mode peak regulation of the heating unit, preferably optimizing a multi-mode cooperative operation mode and a multi-mode peak regulation cooperative operation optimal combination scheme, and guiding the unit to optimize power generation and heating operation on line.

2. The on-line optimization method according to claim 1, wherein in step S1, the setting of the multiple heating mode combination scheme when the heating unit participates in the deep peak shaving cooperative operation specifically includes:

based on unit transformation cost, complexity, heat economy, the demand and the coal type of different regions of power plant, select multi-mode heat supply combination scheme according to the technical adaptability of different heat supply modes, the heat supply mode includes high back pressure heat supply mode, steam extraction heat supply mode, cuts jar heat supply mode, high-low pressure bypass heat supply mode, heat accumulation water pitcher heat supply mode and electric boiler heat supply mode, multi-mode heat supply combination scheme includes that two liang of modes of above-mentioned each heat supply mode combine or more mode combine.

3. The on-line optimization method according to claim 1, wherein in step S2, a mechanism modeling and data identification method is used to construct a digital twin model for the unit to cooperatively operate in multiple heating modes, specifically including:

based on the basic principles of engineering thermodynamics, hydrodynamics and heat transfer, a mechanism simulation model consistent with the structure of a heat supply unit system is constructed by utilizing a modeling simulation technology, and theoretical calculation of the operation performance of the unit and a whole plant thermodynamic system under different load conditions is realized by inputting structural parameters and attribute information and setting boundary conditions; the mechanism simulation model at least comprises a steam turbine module, a boiler module, a feed water heat exchanger module, a condenser module, a steam-water flow module, a water pump module, a pipeline and a converging and crossing module, and each module needs to meet the mass conservation equation, the energy conservation equation and the constraint condition;

accessing multi-working-condition real-time operation data of the heat supply unit into the mechanism simulation model, and performing self-adaptive identification correction on a simulation result of the mechanism simulation model by adopting a reverse identification method;

the reverse identification method comprises the following steps: after missing value processing, abnormal value processing and data smoothing preprocessing operations are carried out on the operation data of the heat supply unit under multiple working conditions, the operation data containing measurement errors in the real-time operation data are primarily corrected into data meeting basic mechanism rules through historical operation data; inputting the input variables meeting the basic mechanism rule data into a mechanism simulation model to calculate the predicted values of the variables to be corrected in the variables; constructing an error membership function, and carrying out error detection and identification on data meeting basic mechanism rules of variables to be corrected to obtain data containing errors; and detecting and identifying errors through the predicted values, judging the reason containing the errors through an expert system, and correcting the operation data of the variable to be corrected with larger errors.

4. The on-line optimization method according to claim 1, wherein in the step S3, constructing a unit multi-mode collaborative operation evaluation model specifically includes:

step S31, setting an objective function: thermal economy and pollutant emission indices;

the thermal economy index is expressed by the total operating revenue of the unit as:

the total operation income of the unit is equal to the heat supply income, the power generation income, the peak regulation compensation income and the unit operation cost;

the heat supply benefit of the unit in the peak regulation period time is as follows: r_h＝∑D_h×T×P_h，R_hThe total heat supply income for the unit; d_hThe flow rate of the heating steam or hot water is adopted; t is a peak regulation period; p_hA unit price for supplying heat;

the power generation benefits are as follows: r_g＝∑W_p×T_p×P_gp+∑W×(T-T_p)×P_g，R_gThe total income of the unit power generation; w_pIs the generated power during peak shaving; t is_pIs the peak shaver duration; p_gpElectricity prices for peak shaving periods; w is the generated power in the non-peak regulation period; p_gElectricity prices for non-peak shaver periods;

the peak regulation compensation yield is as follows:

R_ccompensating the total gain for peak shaving in the maximum heating period; s is the unit capacity; a. the_iThe lower limit of the ith gear load factor is set; a is the load rate of the unit; c_iThe total gear of the electricity price is subsidized;

the pollutant discharge index is combined with pollutant discharge of the unit at each load sectionThe characteristic is put, optimize unit load distribution, realize pollutant discharge is optimal, show as:

L(W_it) The pollutant discharge amount of the ith unit in the t period is shown;

step S32, setting constraint conditions: a safety index;

the safety index is defined by the total constraint conditions of the unit, and the total constraint conditions of the unit at least comprise unit capacity constraint, boiler capacity constraint, heat supply load upper and lower limit constraint, heat supply load equality constraint, electric energy balance constraint, heat energy balance constraint and deep peak regulation power constraint;

the unit capacity constraint is expressed as:

P_i ^min≤P_i≤P_i ^max；

in the formula (I), the compound is shown in the specification,

allowing the minimum steam inlet flow for the ith steam turbine;

allowing the maximum steam inlet flow for the ith steam turbine; p_i ^minThe minimum generating power of the ith turbine; p_i ^maxThe maximum generating power of the ith turbine;

the boiler capacity constraint is expressed as:

the minimum steam production flow of the ith boiler is obtained;

the maximum steam production flow of the ith boiler is obtained;

the upper and lower limits of the heating load are constrained as follows: h_imin＜H_i＜H_imax，H_iminThe minimum heat supply quantity of the ith unit; h_imaxThe maximum heat supply amount of the ith unit;

the heating load equality constraint is expressed as:

D_hthe total load for heat supply;

the electric energy balance constraint is as follows: p_load(t)＝P_CHP(t)-P_EB(t)-P_CY(t)，P_load(t) is the electrical load demand of the system during the time period t; p_CHP(t) is the electric power output value of the thermoelectric unit at the moment t; p_EB(t) is the electric power consumed by the electric boiler at time t; p_CY(t) is the service load at the time period t;

the heat energy balance constraint is H_load(t)＝H_CHP(t)+H_EB(t)+H_TS(t)-H_TS(t-Δt)，H_load(t) is the thermal load demand of the system over a period of t; h_CHP(t) heat generated by the thermoelectric generator set in a time period t; h_EB(t) the heat generated by the electric boiler at time t; h_TS(t) is the heat storage capacity of the heat storage device over time period t; Δ t is a unit time length;

and the depth peak regulation power constraint is as follows:

P_feasiblethe method is characterized in that the method provides the minimum power generation load for the thermal power plant on the basis of meeting the heat supply requirement, namely the deep peak shaving capacity of each unit operation feasible region;

a grid load instruction is given in a period t; p_abilityFor maximum load energy of thermal power plantForce, i.e. top spike capability.

5. The on-line optimization method according to claim 1, wherein the step S4 of predicting the heating load and the power generation load of the thermal power plant specifically comprises:

building a BP artificial neural network model, wherein an input layer of the BP artificial neural network load prediction model at least comprises: DCS unit operation data, meteorological information, power generation and heat supply prices, coal prices, peak regulation bidding and optimizer operation configuration information; the output of the corresponding model is a load value corrected by combining weather data under the input condition, and a load prediction model is obtained based on the training of a BP neural network method; and importing input layer data based on the characteristics of a regional heating mode and environmental climate change factors, and predicting a heating load prediction value and a power generation load prediction value of the thermal power plant under the current working condition through the generated load prediction model.

6. The on-line optimization method according to claim 1, wherein in step S5, the calculating the economic indicator under the combination of the plant-level multiple heating modes specifically includes:

based on actual operation parameters or simulation parameters of the heat supply unit, economic indexes including steam consumption rate, heat consumption rate, power generation coal consumption rate, power supply coal consumption rate, plant power consumption rate, unit efficiency and unit heat supply amount are calculated in sequence;

calculating the steam consumption rate:

d is the steam consumption rate of the unit; d₀The steam inlet quantity of the steam turbine; p_eGenerating power for the unit;

calculating the heat rate:

q is heat rate; q is the heat consumption of the steam turbine; h is₀The enthalpy value of the main steam is; d_zrrFor the flow rate of hot reheat steam, h_zrrIs an enthalpy value; d_zrlFor the flow rate of cold reheat steam, h_zrlIs an enthalpy value; d_fwFor water supply flow rate, h_fwIs an enthalpy value; d_gFor superheating and reducing the temperature and water flow h_gIs an enthalpy value; d_zFor reheating and reducing the temperature water flow, h_zIs an enthalpy value;

calculating the power generation coal consumption rate:

B_bis the standard coal consumption rate; eta_gdFor pipeline efficiency; eta_gTo boiler efficiency;

calculating the power supply coal consumption rate:

η_ethe plant power rate;

calculating the plant power consumption rate:

P_efthe power consumption is the plant power consumption;

calculating the unit efficiency:

η_efthe mechanical efficiency of the unit; eta_mThe motor efficiency of the unit;

the heat supply of the computer set is as follows: q_gr＝D_gr×h_gr，D_grThe heat supply flow is adopted; h is_grThe enthalpy value of heat supply is obtained.

7. The on-line optimization method according to claim 6, wherein the calculation of the economic indicators further comprises single working condition calculation and statistical value calculation, the power generation and heat supply efficiency of the unit under the current operating condition is obtained through the economic indicator calculation of the single working condition, and the operating conditions with high efficiency and low energy consumption are obtained through the performance indicators of different working conditions, so that an optimization direction is provided for the energy-saving and consumption-reducing operation of the unit; and calculating the economic index of the statistical value by adopting the statistical values of the generated energy, the heat supply load, the deep peak regulation subsidy and the coal consumption within a period of time, acquiring the overall economic benefit within the period of time and providing guidance for the scheduling of the thermoelectric load.

8. The on-line optimization method according to claim 1, wherein in step S5, the calculating the peak shaving capacity of the unit under the combination of the plant-level multiple heating modes specifically includes:

establishing a maximum power generation capacity, a maximum heat supply capacity and a minimum heat supply model, and optimizing load distribution of different heat supply units within a model boundary limiting condition;

the maximum generating capacity is obtained by setting thermoelectric load constraint according to an objective function of the maximum generating capacity of the whole plant and solving the thermoelectric load constraint by adopting an intelligent algorithm, and the maximum generating capacity model is expressed as follows:

an objective function:

constraint conditions are as follows:

MIN(P_i)≤P_i≤MAX(P_i)；

in the formula: p_iThe electric load of each unit; n is the number of units; h_totalSupplying heat to each unit to supply total load;

the maximum heating capacity model is expressed as:

maximum heating capacity ═ Σ Q_{Row board}+(∑G-∑Q₁)(H_{Master and slave}-H_{For supplying to})/(H_{For supplying to}-H_{To give})-Q_From+Q_{Store up}；

In the formula: q_{Row board}The maximum steam discharge or the maximum steam extraction of the steam turbine; g is the rated evaporation capacity of the boiler; q1 is the maximum steam inlet amount for the back pressure machine, and is the minimum steam inlet amount for the extraction condenser when the steam is extracted at the maximum; h is the enthalpy value of main steam, steam supply and water supply; q_FromThe total amount of the self-consumption steam; q_{Store up}Can be replaced by heat storage equipment during daytime peakThe amount of steam used.

The minimum heat supply model is expressed as: the lowest heat supply is ═ sigma G₂-∑Q_{Straight coagulation}-Q_From-Q_{Store up}；

In the formula: g2 is the lowest evaporation capacity allowed by the safe operation of the boiler; q straight condensing is the rated steam inlet quantity of the straight condensing working condition of the extraction condensing machine.

9. The on-line optimization method according to claim 1, wherein in step S6, for peak shaving capability, economic indicator and evaluation indicator under different operation schemes of multi-mode peak shaving of the heat supply unit, performing optimization analysis and optimization calculation of multiple heat supply modes, preferably optimizing a best combination scheme of a multi-mode cooperative operation mode and a multi-mode peak shaving cooperative operation, and guiding the unit to optimize power generation and heat supply operation on line, specifically comprising:

step S61, calculating economic indexes and peak shaving capacities of the heat supply unit under different operation schemes of multi-mode peak shaving, and obtaining unit steam consumption rate, heat consumption rate, power generation coal consumption rate, power supply coal consumption rate, plant power consumption rate, unit efficiency, unit heat supply capacity, maximum power generation capacity, maximum heat supply capacity and minimum heat supply capacity parameter indexes under different modes;

s62, acquiring operation parameters and sold heat, sold electricity, coal price and water price data of the heat supply unit under different operation schemes of multi-mode peak regulation, establishing a multi-objective optimization function model for maximizing the total operation income and minimizing pollutant emission of the unit through the established unit multi-mode collaborative operation evaluation model, and determining corresponding constraint conditions according to different operation schemes;

s63, solving an optimal solution set by adopting a multi-objective optimization algorithm according to a target function and constraint conditions to obtain a multi-mode combined optimal scheme set for unit cooperative operation, and selecting a multi-mode peak shaving cooperative operation optimal combined scheme by combining the actual complexity and the technical adaptability of the power plant unit;

and S64, optimizing the heat supply parameters of the unit through the obtained optimal combination scheme of the multi-mode peak shaving cooperative operation, and guiding the unit to optimize power generation and heat supply operation on line.

10. The on-line optimization method according to claim 9, wherein: the multi-target optimization algorithm in the step S63 adopts a multi-target cuckoo search algorithm.

Images