Optimization method for guiding economic operation of power plant, storage medium and equipment

Abstract

The invention discloses an optimization method for guiding economic operation of a power plant, a storage medium and equipment, and the method comprises the steps: obtaining a large amount of power plant operation historical data from an SIS database, carrying out the modeling analysis of a unit, and obtaining the net output power of the unit under various conditions; acquiring local climate conditions and the like, and performing corresponding prediction through an artificial intelligence algorithm based on big data analysis; and a staged economic operation analysis model is built by combining data such as a specific coal type heat value, a coal price, a steam supply amount, a heat price and an electricity price. Artificial intelligence, big data and other methods are used for predicting or analyzing the optimal net output power of the unit; and further integrating models containing various economic operation influence factors, and specifically analyzing the economic operation mode which is most consistent with the current situation and is related to the starting number of the auxiliary equipment. By adopting the optimization method for guiding the economic operation of the power plant to guide the operation of power plant personnel, the operation cost can be reduced, and the economic benefit can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of thermal power generation, and particularly relates to an optimization method, a storage medium and a device for guiding the economic operation of a power plant. Background Art

[0002] At present, large-scale thermal power generating units mainly adopt the wet condensing steam method with water as the cooling medium. The cold end system of the thermal power generating unit mainly consists of the last stage group of the low-pressure cylinder of the steam turbine, the circulating water supply system, the condenser, etc. Among them, the auxiliary equipment such as the circulating water pump and the fan in the circulating water supply system is one of the auxiliary equipment with relatively large power consumption. In order to reduce the power consumption rate of the thermal power plant and promote energy conservation and consumption reduction, it is necessary to timely adjust the number of operating units of the auxiliary equipment according to the change of the unit load to achieve optimal operation.

[0003] In the cold end system, increasing the circulating cooling water flow can improve the unit vacuum and increase the power generation of the steam turbine. However, at the same time, it will also lead to an increase in the power of the circulating water pump. Therefore, there is an optimal operation mode of the circulating water pump that makes the difference between the power increment of the steam turbine and the power consumption increment of the circulating water pump the largest, and the unit operation economy is the best. At this time, it is called the optimal vacuum, that is, the optimal operation mode of the circulating water pump.

[0004] At present, in addition to the power plant itself, the main factors affecting the economic benefits of the power plant include external factors such as electricity price and coal price. For heat supply units, there are also factors such as steam price. Due to the frequent fluctuation of coal price, poor homogeneity of coal types, and uncertain calorific value, the power plant urgently needs a carrier that can intuitively reflect its economy. Summary of the Invention

[0005] An optimization method, a system, a device and a storage medium for guiding the economic operation of a power plant proposed by the present invention can at least solve one of the technical problems in the background art.

[0006] To achieve the above object, the present invention adopts the following technical solutions:

[0007] An optimization method for guiding the economic operation of a power plant includes the following steps:

[0008] S1: Obtain the historical data of unit operation, and screen out the abnormal values in the historical data of unit operation;

[0009] For single and continuously occurring missing and incorrect data, use the interpolation method to average the nearest normal values before and after the abnormal value for repair and filling.

[0010] S2: According to whether there is medium-pressure steam supply, use a large amount of historical data of unit operation samples to perform multiple fittings on the unit load load and the condenser inlet steam volume D_c, and select a first-order fitting as the final fitting result;

[0011] S3: Calculate the total power and water flow of different numbers of circulating water pumps opened by using the historical data of the unit operation samples and the final fitting results, and determine the number of circulating water pumps to be opened according to the actual situation of the target power plant;

[0012] S4: Build a partial model of the condenser according to the historical data of the operating conditions of the opened circulating water pumps:

[0013] S5: Obtain the cooling ratio m, the latent heat of water phase change deita_h, the specific heat cp_w, and the cooling area A_c of the condenser according to the partial model of the condenser, and calculate the terminal difference of the condenser, the condenser pressure, the condenser vacuum, and the outlet water temperature of the cooling water;

[0014] S6: According to the technical specifications of the power plant, combine the condenser pressure with the condenser back pressure - power generation power correction coefficient diagram, fit the correction coefficient curve, and expand the correction coefficient range;

[0015] S7: Calculate the power generation power and the net output power according to the unit load, the consumption of auxiliary equipment, and the power generation power correction coefficient;

[0016] S8: Build a prediction model by using the artificial intelligence algorithm, collect relevant parameters for data training, use the local temperature, humidity, and sunshine duration as input parameters, predict the cooling water temperature through the algorithm model, and then import the cooling water temperature as an input parameter into the partial model of the condenser to obtain the corresponding results, thereby guiding the operation of the power plant.

[0017] Furthermore, the historical data of the unit operation samples in step S1 of the present invention includes: the circulating water flow of the unit, the inlet water temperature and outlet water temperature of the circulating water, the condenser vacuum, the pump motor current, the generator power, the medium and low pressure heating steam flow, the steam and water temperature of the condenser, and the inlet and outlet water pressures of the condenser.

[0018] Furthermore, the method for screening outliers in the historical data of the unit operation samples in step S1 of the present invention is as follows:

[0019] Screen for missing values;

[0020] Screen for error values: realized by using an intelligent algorithm, trained by taking the adjacent change rate of the same parameter of each historical data sample as the target, and automatically generating the normal range interval to identify error values and continuous error intervals;

[0021] Screen for single errors and missing values:

[0022] Data_1, Data_2 (error / None), Data_3

[0023] Data_2_new = (Data_1 + Data_3) / 2

[0024] Continuous errors and missing values:

[0025] Data_1, Data_2 (error / None), …, Data_(n - 1) (error / None), Data_n

[0026] Data_(error / None) = (Data_1 + Data_n) / 2.

[0027] Further, the fitting method for the unit load load and the condenser inlet steam flow D_c in step S2 of the present invention includes:

[0028] With medium - pressure steam supply D_c (t / h):

[0029] D_c = 5.8739 * load * 100 + 60.4245

[0030] Without medium - pressure steam supply D_c (t / h):

[0031] D_c = 5.1205 * load * 100 + 33.1475.

[0032] Further, the method for building the condenser part model in step S4 of the present invention includes:

[0033] Search for the corresponding density ρ and specific heat c according to the cooling water temperature,

[0034] Select different numbers of operating circulating water pumps n, and the corresponding pump circulating water flow D_pump(),

[0035] Calculate the cooling water flow D_w (t / h):

[0036] D_w = D_pump() * ρ / 1000 * n

[0037] Calculate the basic heat transfer coefficient K0_w according to the number of cooling water pipes num_tube, the inner diameter of the pipe d_in, and the cooling water density ρ;

[0038] Calculate the flow velocity v_w (m / s) of the fluid in the pipe:

[0039] v_w = D_w * 1000 / 3600 / num_tube / density_w / (3.14 * d_in * d_in / 4 / 1000000) * 2

[0040] Retrieve the corresponding K0_w from v_w to obtain K0_w,

[0041] According to the cleanliness rate beta_f, the cooling water temperature correction rate beta_t_w, the correction rate beta_m of the material and wall thickness of the condenser pipe, and the basic heat transfer coefficient K0_w;

[0042] Determine the average heat transfer coefficient K:

[0043] K = K0_w * beta_f * beta_t_w * beta_m.

[0044] Furthermore, the methods for calculating the condenser terminal temperature difference, condenser pressure, condenser vacuum, and cooling water outlet temperature in step S5 of the present invention include:

[0045] Cooling ratio m: m = D_w / D_c

[0046] Latent heat of water phase change deita_h (kJ / kg): deita_h = 2300

[0047] Cooling water temperature rise deita_t_w (°C): deita_t_w = deita_h / cp_w / m

[0048] Condenser terminal temperature difference deita_t (°C): B = K * A_c / (cp_w * 1000 / 3600) / D_w / 1000, deita_t = deita_h / cp_w / m / e^(B) - 1)

[0049] Condenser saturated steam temperature t_c (°C): t_c = t_w1 + deita_h / cp_w / m + deita_t

[0050] Condenser pressure p_c (kPa): p_c = 0.00981 * ((t_c + 100) / 57.66) ** 7.46

[0051] Condenser vacuum vacuum (kPa): vacuum = 100.1 - p_c

[0052] Cooling water outlet temperature t_w2 (°C): t_w2 = t_w1 + deita_t_w.

[0053] Furthermore, the methods for calculating the power generation power and net output power according to the unit load and the consumption of auxiliary equipment in step S7 of the present invention include: Power generation power P_t (Mw): P_t = 330 * load * (1 + deita_Pt(p_c) / 100)

[0054] Net output power P_net_con (kw): P_net_con = P_t * 1000 - P_pump - P_ex Power consumption of vacuum pump P_ex (kw): P_ex = 140.22

[0055] deita_Pt(p_c): Correction factor.

[0056] Further, in step S8 of the present invention, the local temperature, humidity, and sunshine duration are used as input parameters by an intelligent algorithm to predict the cooling water temperature, and the method for guiding the operation of the power plant for a period of time in the future includes:

[0057] A number of measuring points are provided on the river side for collecting the original river water temperature. After the river water is introduced into the power plant and before it enters the condenser, a number of measuring points are set for collecting the temperature data before entering the condenser.

[0058] The above two data are the original river water temperature and the cooling water temperature at the inlet of the condenser of the open cooling system.

[0059] Collect and export the local authoritative climate data published by the meteorological bureau. Use the local temperature, relative humidity, and sunshine duration conditions on the current day as input parameters, and combine the original river water temperature measured by the measuring points and the cooling water temperature at the inlet of the condenser of the open cooling system. Through an intelligent algorithm, a large amount of data is trained to achieve the purpose of prediction.

[0060] Automatically collect the weather forecasts published by relevant departments every day and import them into the database.

[0061] Based on the weather forecast, the prediction of the cooling water is completed, and the predicted data is imported into the unit model to present the operation situation of the power plant for a period of time in the future.

[0062] On the other hand, the present invention also discloses a computer-readable storage medium storing a computer program, which when executed by a processor causes the processor to execute the steps of the above method.

[0063] On yet another aspect, the present invention also discloses a computer device including a memory and a processor, where the memory stores a computer program, and when the computer program is executed by the processor, it causes the processor to execute the steps of the above method.

[0064] As can be seen from the above technical solutions, the present invention obtains a large amount of historical data of power plant operation from the SIS database, models and analyzes the unit to obtain the net output power of the unit under various conditions; and obtains local climate conditions, etc. Based on big data analysis, corresponding predictions are made through artificial intelligence algorithms; combined with specific coal calorific value, coal price, steam supply volume, heat price, and electricity price data, a phased economic operation analysis model is built. Artificial intelligence, big data and other methods are used to predict or analyze the optimal net output power of the unit; further integrate the model containing various economic operation influencing factors, and can specifically analyze the economic operation mode of the number of auxiliary equipment started that is most in line with the current situation. Using the above optimization method for guiding the economic operation of the power plant to guide the operation of power plant personnel can reduce the operation cost and improve the economic benefit. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1 Schematic diagram of the process of the present invention;

[0066] Figure 2 Fitting curve graph with or without medium-pressure steam supply;

[0067] Figure 3 Schematic diagram of the condenser part model;

[0068] Figure 4 Schematic diagram of the output result of the condenser part model;

[0069] Figure 5 Schematic diagram of the net output power with different numbers of water pumps. Specific implementation manners

[0070] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention.

[0071] As Figure 1 shown, the optimization method for guiding the economic operation of a power plant described in this embodiment performs the following steps through a computer device.

[0072] S1: Obtain the historical operation data of the unit, and screen out the abnormal values in the historical operation data of the unit;

[0073] For single and continuously occurring missing and incorrect data, the interpolation method is used to average the nearest normal values before and after the abnormal value for repair and filling.

[0074] S2: According to whether there is medium-pressure steam supply, use a large amount of historical operation sample data of the unit to perform multiple fittings on the unit load load and the steam inlet quantity D_c of the condenser, and select one fitting as the final fitting result;

[0075] S3: Use the historical operation sample data of the unit and the final fitting result to calculate the total power and water flow of different numbers of circulating water pumps being turned on, and determine the number of circulating water pumps to be turned on according to the actual situation of the target power plant;

[0076] S4: Build a condenser part model according to the historical data of the operating conditions of the circulating water pumps being turned on:

[0077] S5: Obtain the cooling ratio m, the latent heat of water phase change deita_h, the specific heat cp_w, and the cooling area A_c of the condenser according to the condenser part model, and calculate the terminal difference of the condenser, the condenser pressure, the condenser vacuum, and the outlet water temperature of the cooling water;

[0078] S6: According to the technical specifications of the power plant, combined with the condenser pressure and the condenser back pressure - power generation power correction coefficient graph, fit the correction coefficient curve to expand the correction coefficient range;

[0079] S7: Calculate the power generation power and the net output power according to the unit load and the consumption of auxiliary equipment (only the circulating water pump in the open cooling system) combined with the power generation correction coefficient;

[0080] S8: Use the intelligent algorithm to take the local temperature, humidity, sunshine time, etc. as input parameters to predict the temperature of the cooling water (river water) and guide the operation of the power plant for a period of time in the future;

[0081] The following is a detailed description of each step:

[0082] S1: Obtain the historical data of the unit operation samples and screen the outliers in the historical data of the unit operation samples;

[0083] Each piece of historical data of the unit operation samples includes but is not limited to: the circulating water flow of each unit, the inlet temperature and outlet temperature of the circulating water on each side, the condenser vacuum, the pump motor current, the generator power, the medium and low pressure heating steam flow, the condenser steam and water temperature, the inlet and outlet water pressure of the condenser, etc.

[0084] Use the interpolation method to average the two nearest normal values before and after the outlier for repair and filling;

[0085] When exporting the historical data of the unit operation samples, there will be situations such as missing and errors. First, preliminarily screen out the outliers (including missing and errors). For single or continuous missing and error data, use the interpolation method to average the two nearest normal values before and after the outlier for repair and filling;

[0086] For screening:

[0087] Screen for missing values (null values);

[0088] Screen for error values (implemented by an intelligent algorithm, trained by taking the adjacent change rate of the same parameter of each historical data sample as the target, and automatically generating the normal range interval to identify error values and continuous error intervals);

[0089] Single error or missing:

[0090] Data_1, Data_2 (error / None), Data_3

[0091] Data_2_new = (Data_1 + Data_3) / 2

[0092] Continuous error or missing:

[0093] Data_1, Data_2 (error / None), …, Data_(n - 1) (error / None), Data_n

[0094] Data_(error / None) = (Data_1 + Data_n) / 2

[0095] S2: According to whether there is medium - pressure steam supply, using a large number of historical data of unit operation samples, perform multiple fittings on the unit load load and the inlet steam flow of the condenser D_c, and select a first - order fitting as the final fitting result;

[0096] As Figure 2 shown, it is the fitting result of the unit load load and the inlet steam flow of the condenser D_c, and the fitting method is as follows:

[0097] With medium - pressure steam supply D_c (t / h):

[0098] D_c = 5.8739 * load * 100 + 60.4245

[0099] Without medium - pressure steam supply D_c (t / h):

[0100] D_c = 5.1205 * load * 100 + 33.1475.

[0101] S3: Using the historical data of unit operation and the final fitting result, calculate the total power and water flow of different numbers of circulating water pumps turned on, and determine that the number of circulating water pumps turned on is at least 2 and at most 3;

[0102] Obtained from the exported historical data of pump operating conditions:

[0103] Turn on 2 pumps:

[0104] The circulating water flow is: D_pump_2,

[0105] The power is: P_pump_2;

[0106] Turn on 3 pumps:

[0107] The circulating water flow is: D_pump_3,

[0108] The power is: P_pump_3.

[0109] S4: According to the historical data of the operating conditions of the circulating water pumps turned on, build a partial model of the condenser:

[0110] As Figure 3 shown, it is the partial model of the condenser, and the building method steps are as follows:

[0111] Look up the corresponding density ρ and specific heat c according to the cooling water temperature,

[0112] Select different numbers n of the circulating water pumps to be started,

[0113] and the corresponding circulating water flow rate D_pump() of the pumps,

[0114] Calculate the cooling water flow rate D_w (t / h):

[0115] D_w = D_pump() * ρ / 1000 * n

[0116] Calculate the basic heat transfer coefficient K0_w according to the number of cooling water pipes num_tube, the inner diameter d_in of the pipes, and the density ρ of the cooling water;

[0117] First, calculate the flow velocity v_w (m / s) of the fluid in the pipes:

[0118] v_w = D_w * 1000 / 3600 / num_tube / density_w / (3.14 * d_in * d_in / 4 / 1000000) * 2

[0119] Retrieve the corresponding K0_w based on v_w to obtain K0_w,

[0120] According to the cleaning rate beta_f, the cooling water temperature correction rate beta_t_w, the correction rate beta_m of the material and wall thickness of the condenser pipes, and the basic heat transfer coefficient K0_w.

[0121] Determine the average heat transfer coefficient K:

[0122] K = K0_w * beta_f * beta_t_w * beta_m

[0123] S5: Obtain the cooling ratio m, the latent heat of water phase change deita_h, the specific heat cp_w, and the cooling area A_c of the condenser according to the partial model of the condenser, and calculate the terminal temperature difference of the condenser, the condenser pressure, the condenser vacuum, and the outlet temperature of the cooling water;

[0124] As Figure 4 shown, it is a schematic diagram of the output results of the partial model of the condenser, and the specific steps are as follows:

[0125] Cooling ratio m:

[0126] m = D_w / D_c

[0127] Latent heat of water phase change deita_h (kJ / kg):

[0128] deita_h = 2300

[0129] Cooling water temperature rise deita_t_w (°C):

[0130] delta_t_w = delta_h / cp_w / m

[0131] Condenser terminal temperature difference delta_t (°C):

[0132] B = K * A_c / (cp_w * 1000 / 3600) / D_w / 1000

[0133] delta_t = delta_h / cp_w / m / (e ^ (B) - 1)

[0134] Condenser saturated steam temperature t_c (°C):

[0135] t_c = t_w1 + delta_h / cp_w / m + delta_t

[0136] Condenser pressure p_c (kPa):

[0137] p_c = 0.00981 * ((t_c + 100) / 57.66) ** 7.46

[0138] Condenser vacuum (kPa):

[0139] vacuum = 100.1 - p_c

[0140] Cooling water outlet temperature t_w2 (°C):

[0141] t_w2 = t_w1 + delta_t_w

[0142] S6: According to the power plant technical specifications, combined with the condenser pressure and condenser back pressure - power generation capacity correction factor diagram, fit the correction factor curve to expand the correction factor range;

[0143] delta_Pt(p_c) = a * p_c ** 2 + b * p_c + c

[0144] a = -0.03326042031253084,

[0145] b = -0.14104948165717687,

[0146] c = 2.253859266286696,

[0147] Power generation capacity correction factor: delta_Pt(p_c) (%),

[0148] Condenser back pressure: p_c (kpa),

[0149] Then, based on the p_c calculated from the condenser model, obtain delta_Pt(p_c).

[0150] S7: Calculate the power generation power and the net output power according to the unit load and the consumption of auxiliary equipment (only the circulating water pump in the open cooling system) combined with the power generation work correction factor;

[0151] As Figure 5 shown, it is a schematic diagram of the net output power with different numbers of water pumps. The methods for calculating the power generation power and the net output power include:

[0152] Power generation power Pt (Mw): Pt = 330 * load * (1 + deita_Pt(p_c) / 100)

[0153] Net output power P_net_con (kw): P_net_con = P_t * 1000 - P_pump - P_ex Power consumption of the vacuum pump P_ex (kw): P_ex = 140.22

[0154] deita_Pt(p_c): Correction factor.

[0155] S8: Build a prediction model using an artificial intelligence algorithm, collect relevant parameters for data training, use the local temperature, humidity, and sunshine duration as input parameters, predict the cooling water temperature through the algorithm model, and then import the cooling water temperature as an input parameter into the condenser part model to obtain the corresponding results, thereby guiding the operation of the power plant.

[0156] Several measuring points are set in the river (the water is still in the river channel) to collect the original river water temperature. After the river water is introduced into the power plant and before it enters the condenser, several measuring points are set to collect the temperature data before entering the condenser. The above two data are the original river water temperature and the cooling water temperature at the inlet of the condenser of the open cooling system, and the two are different.

[0157] Collect and export the local authoritative climate data published by the meteorological bureau, use the local temperature, relative humidity, sunshine duration and other conditions on that day as input parameters, and combine the original river water temperature measured by the measuring points and the cooling water temperature at the inlet of the condenser of the open cooling system, and train a large amount of data through an intelligent algorithm to achieve the purpose of prediction.

[0158] Automatically collect the weather forecasts published by relevant departments every day and import them into the database. Complete the prediction of the cooling water based on the weather forecast, and import the predicted data into the unit model to present the operation situation of the power plant in the future for a period of time, which has a certain degree of foresight.

[0159] The main factors affecting the economic benefits of the power plant are coal price, coal consumption, calorific value, heat price, electricity price, net output power, etc. The above factors can simply present the economic benefits to a certain extent.

[0160] The coal price data is obtained when the power plant purchases coal;

[0161] The coal consumption is exported from the power plant SIS system;

[0162] Combined with artificial intelligence algorithms, historical data can be labeled with coal consumption, and relevant operating parameters can be screened. Training can be carried out using a large amount of data to achieve the prediction of coal consumption;

[0163] The calorific value is obtained from the coal quality inspection of the coal entering the furnace;

[0164] The heat price (unit: yuan / GJ). For a cogeneration power plant that transports steam outwards, the heat price is provided by the power plant;

[0165] The electricity price (unit: yuan / 1000 kWh). The electricity generated by the power plant will be purchased, and the specific price is provided by the power plant;

[0166] Calculated in combination with the net output power:

[0167] Total revenue = net output power × electricity price + heat quantity × heat price

[0168] Total coal consumption price = coal price × coal consumption.

[0169] In summary, in the present invention, variables related to economic analysis are input into the model, the influence of limited factors on the operating economy of the power plant is considered, and the economic benefits of the power plant under the influence of limited factors are visually presented. By comparing and analyzing the economic benefits in different situations and combining with the intelligent prediction module, the economic benefit situation of the power plant operation can be grasped in advance.

[0170] On the other hand, the present invention also discloses a computer device, including a memory and a processor. The memory stores a computer program. When the computer program is executed by the processor, the processor executes the steps of the above method.

[0171] In another embodiment provided by the present application, there is also provided a computer program product containing instructions. When it runs on a computer, it enables the computer to execute any one of the optimization methods and systems for guiding the economic operation of the power plant in the above embodiments.

[0172] It can be understood that the system, device, and storage medium provided in the embodiments of the present invention correspond to the method provided in the embodiments of the present invention. The explanations, examples, and beneficial effects of the relevant content can refer to the corresponding parts in the above method.

[0173] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, hard disk, magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)).

[0174] It should be noted that in this document, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including", or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article, or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, article, or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article, or device including the said element.

[0175] Each embodiment in this specification is described in a related manner. The same or similar parts between the embodiments can be referred to each other, and the differences between each embodiment and other embodiments are emphasized. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiment.

[0176] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An optimization method for guiding the economic operation of a power plant, characterized in that: The following steps are involved: S1: Obtain historical operation data of the unit and filter out abnormal values ​​in the historical operation data of the unit; For single or continuous missing or erroneous data, interpolation method is used to average the normal values ​​closest to the abnormal value before and after the abnormal value for filling. S2: According to the presence or absence of medium-pressure steam supply, a large number of historical data of unit operation samples are used to perform multiple fittings on the unit load and the condenser steam inlet volume D_c, and one fitting is selected as the final fitting result; S3: Using the historical data of the unit operation samples and the final fitting results, calculate the total power and water flow of different numbers of circulating water pumps, and determine the number of circulating water pumps to be started according to the actual situation of the target power plant; S4: Based on the historical data of the operating conditions of the circulating water pump, build a condenser model: S5: According to the condenser partial model, the cooling rate m, the water phase change latent heat deita_h, the specific heat cp_w, the condenser cooling area A_c, and the condenser end difference, the condenser pressure, the condenser vacuum, and the cooling water outlet temperature are obtained; S6: According to the technical specifications of the power plant, combined with the condenser pressure and condenser back pressure-power generation correction factor diagram, fit the correction factor curve and expand the correction factor range; S7: Calculate the power generation power and net output power according to the unit load and auxiliary machine consumption combined with the power generation correction factor; S8: Use artificial intelligence algorithms to build a prediction model, collect relevant parameters for data training, use local temperature, humidity, and sunshine time as input parameters, predict the cooling water temperature through the algorithm model, and then import the cooling water temperature as an input parameter into the condenser part model to obtain the corresponding results, thereby providing guidance for power plant operation.

2. The optimization method for guiding the economic operation of a power plant according to claim 1, characterized in that: The historical data of the unit operation samples in step S1 include: unit circulating water flow, circulating water inlet temperature, outlet temperature, condenser vacuum, water pump motor current, generator power, medium and low pressure heating steam flow, condenser steam-water temperature, and condenser inlet and outlet water pressures.

3. The optimization method for guiding the economic operation of a power plant according to claim 1, characterized in that: The method for screening outliers in the historical data of the unit operation samples in step S1 is: Screening for missing values; Screening for error values: This is achieved using an intelligent algorithm. By taking the adjacent change rate of the same parameter of each historical data sample as the target, training is performed and the normal range interval is automatically generated to identify error values ​​and continuous error intervals. Filter single errors and omissions: Data_1,Data_2(error / None),Data_3 Data_2_new=(Data_1+Data_3) / 2 Continuous errors and omissions: Data_1,Data_2(error / None),…,Data_(n-1)(error / None),Data_n Data_(error / None)=(Data_1+Data_n) / 2.

4. The optimization method for guiding the economic operation of a power plant according to claim 1, characterized in that: The method for fitting the unit load and the condenser steam inlet volume D_c in step S2 includes: Medium pressure steam supply D_c(t / h): D_c=5.8739*load*100+60.4245 No medium pressure steam supply D_c(t / h): D_c=5.1205*load*100+33.1475.

5. The optimization method for guiding the economic operation of a power plant according to claim 1, characterized in that: The method for building the condenser partial model in step S4 includes: Find the corresponding density ρ and specific heat c according to the cooling water temperature. Select different circulating water pumps n and the corresponding circulating water flow rate D_pump(). Calculate cooling water flow D_w (t / h): D_w=D_pump()*ρ / 1000*n Calculate the basic heat transfer coefficient K0_w according to the number of cooling water tubes num_tube, the inner diameter of the pipe d_in, and the cooling water density ρ; Calculate the flow velocity v_w (m / s) of the fluid in the pipe: v_w=D_w*1000 / 3600 / num_tube / density_w / (3.14*d_in*d_in / 4 / 1000000)*2 Search for K0_w corresponding to v_w and get K0_w. According to the cleaning rate beta_f, the cooling water temperature correction rate beta_t_w, the correction rate beta_m of the material and wall thickness of the condenser pipe and the basic heat transfer coefficient K0_w; Determine the average heat transfer coefficient K: K=K0_w*beta_f*beta_t_w*beta_m.

6. The optimization method for guiding the economic operation of a power plant according to claim 1, characterized in that: The method for calculating the condenser end difference, condenser pressure, condenser vacuum, and cooling water outlet temperature in step S5 includes: Cooling ratio m: m = D_w / D_c Water phase heat deita_h (kJ / kg): deita_h = 2300 Cooling water temperature rise deita_t_w (℃): deita_t_w=deita_h / cp_w / m Condenser end difference deita_t (℃): B = K*A_c / (cp_w*1000 / 3600) / D_w / 1000, deita_t=deita_h / cp_w / m / e^(B)-1) Condenser saturated steam temperature t_c (℃): t_c=t_w1+deita_h / cp_w / m+deita_t Condenser pressure p_c (kPa): p_c = 0.00981*((t_c+100) / 57.66)**7.46 Condenser vacuum (kPa): vacuum = 100.1-p_c Cooling water outlet temperature t_w2 (℃): t_w2=t_w1+deita_t_w.

7. The optimization method for guiding the economic operation of a power plant according to claim 1, characterized in that: The method of calculating the power generation and net output power according to the load of the unit and the consumption of the auxiliary machine in step S7 includes: Power generation P_t (Mw): P_t = 330*load*(1+deita_Pt(p_c) / 100) Net output power P_net_con (kw): P_net_con = P_t*1000-P_pump-P_ex Vacuum pump power consumption P_ex (kw): P_ex = 140.22 deita_Pt(p_c): correction coefficient.

8. The optimization method for guiding the economic operation of a power plant according to claim 1, characterized in that: In step S8, the intelligent algorithm is used to take the local temperature, humidity and sunshine time as input parameters to predict the cooling water temperature, and the method for guiding the operation of the power plant in the future includes: Several measuring points are set on the river water side to collect the original river water temperature. After the river water is introduced into the power plant and before it enters the condenser, several measuring points are set to collect the temperature data before it enters the condenser; The above two data are the original river water temperature and the cooling water temperature at the condenser inlet of the open cooling system; Collect and export local authoritative climate data published by the Meteorological Bureau, use the local temperature, relative humidity and sunshine duration conditions as input parameters, combine the original river water temperature measured at the measuring point, and the cooling water temperature at the condenser inlet of the open cooling system, and train a large amount of data through intelligent algorithms to achieve the purpose of prediction; Automatically collect weather forecasts published by relevant departments every day and import them into the database; The cooling water forecast is completed based on the weather forecast, and the predicted data is imported into the unit model to present the operation status of the power plant in the future.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 8.

10. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor executes the method according to any one of claims 1 to 8.

Images