Turbine cold end optimization method and system based on mechanism and data hybrid drive modeling

Abstract

The invention discloses a steam turbine cold end optimization method and system based on mechanism and data hybrid drive modeling, and the method comprises the steps: building a steam turbine cold end system mechanism model, and determining the to-be-identified characteristic parameters of each model; collecting steam turbine cold end system data; feature parameter historical data preprocessing and steady state judgment; steady-state data working condition division: performing working condition division on the steady-state data of the cold-end system to obtain a steady-state working condition cluster of the cold-end system; establishing a characteristic identification data model which takes the operation parameters of the cold-end system and the characteristic parameters of the mechanism model to be identified as input and the pressure of the condenser as output; performing mechanism model characteristic regression; on the basis of all steady-state working conditions of the cold-end system, a regression prediction model of steam turbine exhaust parameters is established; updating mechanism model characteristics; establishing a steam turbine cold end optimization model; and solving the cold end optimization model. According to the invention, by establishing the mechanism and data hybrid driving optimization model in the full working condition range of the cold end of the steam turbine, the optimization guidance of the operation adjustment of the cold end of the steam turbine is realized, so that the heat consumption of the steam turbine is reduced.

Description

Technical Field

[0001] The present invention relates to a steam turbine cold end optimization method and system, and in particular to a steam turbine cold end optimization method and system based on mechanism and data hybrid driven modeling. Background Art

[0002] As an important part of thermal power units, the cold end system of the steam turbine has the largest heat loss in the thermal system and is the part with the greatest energy saving potential. Through cold end optimization, the cost of power generation can be reduced, which is of great significance for improving the economy of unit operation and reducing energy consumption.

[0003] Traditional steam turbine cold end operation optimization methods are mainly based on thermal tests and condenser variable operating condition calculation models, but the optimization results of these methods may not be accurate. The main reason is that after the unit has been running for a period of time, due to the pollution of the condenser heat exchange surface and equipment aging, the actual operating performance of the unit will change, deviate from the test results and calculation models, and cannot reflect the actual operation of the unit in real time. At present, the operation of the steam turbine cold end system mainly relies on the experience of the operating personnel for adjustment, which lacks the real-time and economical adjustment. Summary of the invention

[0004] Purpose of the invention: The purpose of the present invention is to provide a steam turbine cold end optimization method and system based on mechanism and data hybrid driven modeling, to achieve optimized guidance of steam turbine cold end operation adjustment, so as to reduce steam turbine heat consumption and improve the overall economic benefits of steam turbine generator sets.

[0005] Technical solution: The present invention comprises the following steps:

[0006] Establish the mechanism model of the steam turbine cold end system and clarify the characteristic parameters to be identified in each model;

[0007] Data collection of the cold end system of the steam turbine: collect relevant process parameters. The collected data is used for historical data condition extraction and real-time optimization calculation;

[0008] Preprocessing of characteristic parameter historical data and steady-state judgment: extract the recent operation data of the cold end system from the historical data, make steady-state judgment on the preprocessed operating data, and retain the steady-state operating data as the data basis for the identification of the characteristics of the cold end system mechanism model;

[0009] Steady-state data working condition division: The working condition of the cold-end system steady-state data is divided, and after the working condition division is completed, the cold-end system steady-state working condition cluster is obtained;

[0010] Intelligent identification of characteristic parameters of mechanism model: On each operating condition cluster of the cold end system, a characteristic identification data model is established with the cold end system operating parameters and the characteristic parameters of the mechanism model to be identified as input and the condenser pressure as output;

[0011] Mechanism model characteristic regression: After completing the identification of the characteristics of each operating condition cluster, the C operating condition parameters at the center of each operating condition cluster are used as variables to perform regression fitting of the mechanism model characteristic parameters between different operating condition clusters;

[0012] Steam turbine exhaust parameter modeling: Based on all steady-state conditions of the cold end system, a regression prediction model for steam turbine exhaust parameters is established;

[0013] Update of mechanism model characteristics: Based on the mechanism model of characteristic identification and the prediction model of steam turbine exhaust parameters, a hybrid model of the steam turbine cold end is constructed, and the prediction error of the hybrid model is used as the criterion to determine whether the characteristic parameters of the mechanism model should be updated;

[0014] Establishment of turbine cold end optimization model: Based on the mechanism model of characteristic identification and the prediction model of turbine exhaust parameters, the turbine cold end optimization model is established with the goal of maximizing the turbine net power after deducting the incremental power consumption of the circulating pump;

[0015] Solution of cold-end optimization model: The intelligent optimization algorithm is used to optimize and solve the cold-end optimization model under specific constraints to obtain the recommended operation mode of the circulating pump under the real-time working conditions of the steam turbine. The optimization result X is used as the recommended value of the operation mode or operation frequency of the circulating pump of the cold-end system of the steam turbine.

[0016] The steam turbine cold end system mechanism model includes a steam turbine slight power increase characteristic model, a condenser characteristic model, and a circulating water pump power consumption characteristic model.

[0017] The turbine power increase characteristic model is:

[0018] ΔP t =f(P t ,p k )

[0019] Where ΔP t is the turbine power increase, P t is the turbine active power, p k It is the exhaust back pressure of the steam turbine.

[0020] The condenser characteristic model includes:

[0021] Saturation temperature of turbine exhaust steam at condenser pressure t s for:

[0022] t s =t w1 +Δt+δt

[0023] Among them, t w1 is the condenser circulating water inlet temperature, ℃; Δt is the condenser circulating water temperature rise, ℃; δt is the condenser heat transfer end difference, ℃;

[0024] The circulating water temperature rise Δt is:

[0025]

[0026] Among them, D c , D w Respectively turbine exhaust flow and circulating water flow, t / h; h c ,h ′ c are the specific enthalpy of steam and condensed water in the condenser, kJ / kg;

[0027] The heat transfer end difference δt of the condenser is:

[0028]

[0029] Among them, A c is the condenser heat exchange area, m 2 ; K is the overall heat transfer coefficient of the condenser, kJ / (m 2 ·h·K).

[0030] The characteristic parameters to be identified include the condenser heat transfer coefficient, the turbine power increment characteristic parameters, and the circulating pump characteristic parameters, a total of P parameters to be identified.

[0031] The working condition cluster structure is as follows:

[0032]

[0033] The intelligent identification of the characteristic parameters of the mechanism model is specifically as follows: using an intelligent optimization algorithm to take the deviation between the output value of the condenser pressure data model and the actual value as the target, perform an inversion solution on the characteristic parameters of the mechanism model, and obtain the characteristic parameters of the cold end system mechanism model on M operating condition clusters:

[0034]

[0035] During the updating process of the mechanism model characteristics, if the model error is greater than the threshold, the process of intelligently identifying the mechanism model characteristic parameters from the data collected from the cold end system of the steam turbine is repeated to update and regress the mechanism model characteristic parameters.

[0036] The optimization model of the turbine cold end is: maxF = ∑P t -∑P pump .

[0037] A turbine cold end optimization system based on mechanism and data hybrid driven modeling, including:

[0038] Steam turbine cold end system mechanism model building module: Establish the steam turbine cold end system mechanism model and clarify the characteristic parameters to be identified of each model;

[0039] Steam turbine cold end system data acquisition module: collects relevant process parameters of the steam turbine cold end system;

[0040] Characteristic parameter historical data preprocessing and steady-state judgment module: extract historical data of the cold end system for a certain period of time, perform operating condition data preprocessing, and perform steady-state operating condition judgment on the preprocessed characteristic parameter operating condition data;

[0041] Steady-state data working condition division module: divides the working condition of the steady-state data of the cold-end system of the steam turbine to form a working condition cluster for the characteristic identification of the cold-end system mechanism model;

[0042] Intelligent identification module of characteristic parameters of mechanism model: for each operating condition cluster generated by operating condition division, a data model of operating parameters and characteristic parameters of cold end system is constructed;

[0043] Mechanism model characteristic regression module: After completing the identification of the characteristics of each operating condition cluster, the regression fitting of the mechanism model characteristic parameters is performed based on the central operating condition parameters of each operating condition cluster;

[0044] Steam turbine exhaust parameter modeling module: Based on all steady-state conditions of the cold end system, a regression prediction model for steam turbine exhaust parameters is established;

[0045] Mechanism model characteristic update module: Based on the mechanism model of characteristic identification and the turbine exhaust parameter prediction model, a turbine cold end hybrid model is constructed, and the hybrid model prediction error is used as the criterion to determine whether the mechanism model characteristics should be updated;

[0046] Steam turbine cold end optimization model establishment module: Based on the mechanism model of characteristic identification and the prediction model of steam turbine exhaust parameters, the steam turbine cold end optimization model is established with the goal of maximizing the net power of the steam turbine after deducting the incremental power consumption of the circulating pump;

[0047] Cold end optimization model solving module: Use intelligent optimization algorithm to optimize and solve the cold end optimization model under specific constraints to obtain the circulation pump operation mode under the real-time working conditions of the steam turbine.

[0048] Beneficial effect: The present invention realizes the optimization guidance of the operation adjustment of the cold end of the steam turbine by establishing the mechanism and data hybrid driven optimization model of the full operating range of the cold end of the steam turbine, so as to reduce the heat consumption of the steam turbine and improve the overall economic benefits of the steam turbine generator set. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 is a flow chart of the present invention;

[0050] Figure 2 This is the technical roadmap for optimizing the cold end of a steam turbine based on mechanism and data hybrid driven modeling. DETAILED DESCRIPTION

[0051] The present invention will be further described below in conjunction with the accompanying drawings.

[0052] Example 1

[0053] like Figure 1 and Figure 2 As shown, the steam turbine cold end optimization method based on mechanism and data hybrid driven modeling of this embodiment optimizes the operation mode of the steam turbine cold end according to the real-time operation condition of the steam turbine, guides the steam turbine operation personnel to optimize and adjust the cold end system, so as to achieve the purpose of improving the overall economic benefits of the steam turbine generator set, and specifically includes the following steps:

[0054] Step 1: Establish the mechanism model of the steam turbine cold end system, including models such as the steam turbine slight power increase characteristics, condenser characteristics, and circulating water pump power consumption characteristics, and clarify the characteristic parameters to be identified in each model.

[0055] Steam turbine slight power increase characteristics:

[0056] ΔP t =f(P t ,p k )

[0057] Where ΔP t is the turbine power increase, P t is the turbine active power, p k It is the exhaust back pressure of the steam turbine.

[0058] Condenser characteristics:

[0059] Saturation temperature of turbine exhaust steam at condenser pressure t s It can be expressed as:

[0060] t s =t w1 +Δt+δt

[0061] Among them, t w1 is the condenser circulating water inlet temperature, ℃; Δt is the condenser circulating water temperature rise, ℃; δt is the condenser heat transfer end difference, ℃.

[0062] The circulating water temperature rise Δt can be expressed as:

[0063]

[0064] Among them, D c , D w Respectively turbine exhaust flow and circulating water flow, t / h; h c ,h′ c They are the specific enthalpy of steam and specific enthalpy of condensed water in the condenser, kJ / kg respectively.

[0065] The heat transfer end difference of the condenser δt can be expressed as:

[0066]

[0067] Among them, A c is the condenser heat exchange area, m 2 ; K is the overall heat transfer coefficient of the condenser, kJ / (m 2 ·h·K).

[0068] The characteristic parameters to be identified in the cold end system mechanism model are the condenser heat transfer coefficient, the turbine power increment characteristic parameters, the circulating pump characteristic parameters, etc., a total of P parameters to be identified.

[0069] Step 2: Data collection of the cold end system of the steam turbine. According to the area where the system is deployed, relevant process parameters are collected from the unit DCS or SIS system through the interface, including generator active power, main steam pressure, main steam temperature, high-control valve opening feedback, cold reheat steam pressure, reheat steam pressure, reheat steam temperature, medium-control valve opening feedback, steam extraction pressure and temperature of each section, condenser pressure, condenser water level, condenser hot well temperature, circulating pump current and frequency, circulating water pipe pressure, circulating water pipe flow, condenser inlet and outlet water pressure and temperature and other parameters. The collected data are used for historical data condition extraction and real-time optimization calculation.

[0070] Step 3: Preprocessing of historical data of characteristic parameters and steady-state judgment: extract the recent operation data of the cold-end system from the historical data, and perform data cleaning operations to deal with abnormal values ​​and missing values ​​of the operating data. For the preprocessed operating data, a steady-state operating condition judgment based on the R statistical test method is performed. If the threshold condition is met, it is the steady-state operating condition data of the cold-end system. The steady-state operating condition data is retained as the data basis for the identification of the characteristics of the cold-end system mechanism model.

[0071] Step 4: Steady-state data working condition division: Fuzzy C-means clustering is performed on the cold-end system steady-state data. After the working condition division is completed, M cold-end system steady-state working condition clusters are obtained. The working condition cluster structure is as follows:

[0072]

[0073] Step 5: Intelligent identification of the characteristic parameters of the mechanism model. On each operating condition cluster of the cold end system, a characteristic identification data model is established with the cold end system operating parameters and the characteristic parameters of the mechanism model to be identified as input and the condenser pressure as output, with a total of M characteristic identification data models. Then, the intelligent optimization algorithm is used to take the deviation between the output value and the actual value of the condenser pressure data model as the target to perform the inversion solution of the characteristic parameters of the mechanism model. The characteristic parameters of the cold end system mechanism model such as the condenser heat transfer characteristics, the turbine micro-increase power characteristics, and the circulating pump characteristics on M operating condition clusters can be obtained, with a total of M groups of characteristic parameters of the mechanism model, to realize the intelligent identification of multiple operating condition clusters of the characteristic parameters of the cold end system mechanism model.

[0074]

[0075] Step six, mechanism model characteristic regression. After completing the identification of the characteristics of each operating condition cluster, the C operating condition parameters at the center of each operating condition cluster, such as turbine active power and circulating water inlet temperature, are used as variables to perform regression fitting of the mechanism model characteristic parameters between different operating condition clusters. The characteristic parameter regression results are as follows, which can improve the operating condition applicability and model accuracy of the turbine cold end mechanism model.

[0076]

[0077] Step seven, steam turbine exhaust parameter modeling. For the calculation of steam turbine exhaust enthalpy and exhaust flow, all steady-state conditions of the cold end system are taken as the basis, with steam turbine main steam parameters, regulating valve opening, extraction parameters as input, and exhaust enthalpy and exhaust flow as output. A regression prediction model MODEL_TURBINE of steam turbine exhaust parameters is established, which can calculate the exhaust parameters under the real-time operating conditions of the steam turbine.

[0078] Step 8: Update the characteristics of the mechanism model. Based on the mechanism model of characteristic identification and the prediction model of steam turbine exhaust parameters, a hybrid model of the steam turbine cold end is constructed. The prediction error of the hybrid model (including mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE)) is used as the criterion to determine whether the characteristic parameters of the mechanism model are updated. If the model error is greater than the threshold, that is, |parameter predict -parameter real |>ε, repeat steps 2 to 5 to update and regress the characteristic parameters of the mechanism model such as the condenser heat transfer characteristics, the turbine power increase characteristics, and the circulating pump characteristics.

[0079] Step nine, the turbine cold end optimization model is established. Based on the characteristic identification mechanism model and the turbine exhaust parameter prediction model, the turbine cold end optimization model is established with the goal of maximizing the turbine net power after deducting the incremental power consumption of the circulating pump.

[0080] maxF=∑P t -∑P pump

[0081] Step 10, solving the cold-end optimization model: Use the intelligent optimization algorithm to optimize and solve the cold-end optimization model under specific constraints, and obtain the recommended operation mode of the circulating pump under the real-time working conditions of the steam turbine. The optimization result X can be used as the recommended value of the operation mode or operation frequency of the circulating pump of the cold-end system of the steam turbine to reduce the heat consumption of the steam turbine and improve the overall economic benefits of the steam turbine generator set.

[0082] X=[run_flag1,…,run_flag num ,n1,…,n num ]

[0083] Intelligent optimization algorithms include constrained particle swarm optimization, grey wolf algorithm and other optimization algorithms, among which constraint processing methods include penalty function method, C-constraint processing method and hybrid method.

[0084] Example 2

[0085] The steam turbine cold end optimization system based on mechanism and data hybrid driven modeling in this embodiment includes:

[0086] Steam turbine cold end system mechanism model building module: Establish the steam turbine cold end system mechanism model, including steam turbine slight increase power characteristics, condenser characteristics, circulating water pump power consumption characteristics and other models, and clarify the characteristic parameters to be identified in each model;

[0087] Steam turbine cold end system data acquisition module: collects relevant process parameters of the steam turbine cold end system from the unit DCS or SIS system through the interface, including generator active power, main steam pressure, main steam temperature, high-pressure valve opening feedback, cold reheat steam pressure, reheat steam pressure, reheat steam temperature, medium-pressure valve opening feedback, steam extraction pressure and temperature of each section, condenser pressure, condenser water level, condenser hot well temperature, circulating pump current and frequency, circulating water pipe pressure, circulating water pipe flow, condenser inlet and outlet water pressure and temperature and other parameters. The collected data is saved as historical data for historical data processing and working condition identification;

[0088] Characteristic parameter historical data preprocessing and steady-state judgment module: extract historical data of the cold-end system for a certain period of time, perform operating condition data preprocessing, perform steady-state operating condition judgment based on certain algorithm rules for the preprocessed characteristic parameter operating condition data, and extract steady-state operating condition data of the steam turbine cold-end system;

[0089] Steady-state data working condition division module: For the steady-state data of the steam turbine cold end system, the working condition division of the steam turbine cold end data is realized based on the classification algorithm to form a working condition cluster for the cold end system mechanism model characteristic identification;

[0090] Intelligent identification module of characteristic parameters of mechanism model: for each operating condition cluster generated by operating condition division, a data model of operating parameters and characteristic parameters of the cold end system is constructed, and the parameters to be identified are inverted using intelligent optimization algorithms to realize intelligent identification of characteristic parameters of the mechanism model of the cold end system in a single operating condition cluster;

[0091] Mechanism model characteristic regression module: After completing the identification of the characteristics of each operating condition cluster, the characteristic parameters of the mechanism model are regressed and fitted based on the central operating condition parameters of each operating condition cluster, so as to achieve the applicability of the mechanism model parameters in a wider load range, thereby improving the model accuracy and operating condition applicability of the steam turbine cold end mechanism model;

[0092] Steam turbine exhaust parameter modeling module: For the calculation of steam turbine exhaust enthalpy and exhaust flow, based on all steady-state conditions of the cold end system, with steam turbine main steam parameters, valve opening, extraction parameters as input, and exhaust enthalpy and exhaust flow as output, a regression prediction model of steam turbine exhaust parameters is established, which can calculate exhaust parameters under steam turbine operating conditions;

[0093] Mechanism model characteristic update module: Based on the mechanism model of characteristic identification and the turbine exhaust parameter prediction model, a turbine cold end hybrid model is constructed. The hybrid model prediction error is used as the criterion to determine whether the mechanism model characteristics are updated. If the model error is greater than the threshold, the process of intelligent identification of the mechanism model characteristic parameters from the turbine cold end system data collection is repeated to update and regress the mechanism model characteristic parameters such as the condenser heat transfer coefficient, turbine slight power increase characteristics, and circulating pump characteristics.

[0094] Steam turbine cold end optimization model establishment module: Based on the mechanism model of characteristic identification and the prediction model of steam turbine exhaust parameters, the steam turbine cold end optimization model is established with the goal of maximizing the net power of the steam turbine after deducting the incremental power consumption of the circulating pump;

[0095] Cold-end optimization model solving module: The intelligent optimization algorithm is used to optimize and solve the cold-end optimization model under specific constraints to obtain the operation mode of the circulating pump under the real-time working conditions of the steam turbine. The optimization result can be used as the recommended value of the operation mode or operation frequency of the circulating pump of the cold-end system of the steam turbine to reduce the heat consumption of the steam turbine and improve the overall economic benefits of the steam turbine generator set.

[0096] The present invention optimizes the operation mode of the cold end of the steam turbine according to the real-time operation condition of the steam turbine, guides the operation personnel of the steam turbine to optimize and adjust the cold end system, and achieves the purpose of improving the overall economic benefits of the steam turbine generator set.

Claims

1. A steam turbine cold end optimization method based on mechanism and data hybrid driven modeling, characterized in that: The following steps are involved: Establish the mechanism model of the steam turbine cold end system and clarify the characteristic parameters to be identified in each model; Data collection of the cold end system of the steam turbine: collect relevant process parameters. The collected data is used for historical data condition extraction and real-time optimization calculation; Preprocessing of characteristic parameter historical data and steady-state judgment: extract the recent operation data of the cold end system from the historical data, make steady-state judgment on the preprocessed operating data, and retain the steady-state operating data as the data basis for the identification of the characteristics of the cold end system mechanism model; Steady-state data working condition division: The working condition of the cold-end system steady-state data is divided, and after the working condition division is completed, the cold-end system steady-state working condition cluster is obtained; Intelligent identification of characteristic parameters of mechanism model: On each operating condition cluster of the cold end system, a characteristic identification data model is established with the cold end system operating parameters and the characteristic parameters of the mechanism model to be identified as input and the condenser pressure as output; Mechanism model characteristic regression: After completing the identification of the characteristics of each operating condition cluster, the C operating condition parameters at the center of each operating condition cluster are used as variables to perform regression fitting of the mechanism model characteristic parameters between different operating condition clusters; Steam turbine exhaust parameter modeling: Based on all steady-state conditions of the cold end system, a regression prediction model for steam turbine exhaust parameters is established; Update of mechanism model characteristics: Based on the mechanism model of characteristic identification and the prediction model of steam turbine exhaust parameters, a hybrid model of the steam turbine cold end is constructed, and the prediction error of the hybrid model is used as the criterion to determine whether the characteristic parameters of the mechanism model should be updated; Establishment of turbine cold end optimization model: Based on the mechanism model of characteristic identification and the prediction model of turbine exhaust parameters, the turbine cold end optimization model is established with the goal of maximizing the turbine net power after deducting the incremental power consumption of the circulating pump; Solution of cold-end optimization model: Intelligent optimization algorithm is used to optimize and solve the cold-end optimization model under specific constraints, and the recommended operation mode of the circulating pump under the real-time working conditions of the steam turbine is obtained.

2. According to claim 1, a steam turbine cold end optimization method based on mechanism and data hybrid driven modeling is characterized in that: The steam turbine cold end system mechanism model includes a steam turbine slight power increase characteristic model, a condenser characteristic model, and a circulating water pump power consumption characteristic model.

3. The method for optimizing the cold end of a steam turbine based on mechanism and data hybrid driven modeling according to claim 2 is characterized in that: The turbine power increase characteristic model is: ΔP t =f(P t ,p k ) Among them, ΔP t is the turbine power increase, P t is the turbine active power, p k It is the exhaust back pressure of the steam turbine.

4. The method for optimizing the cold end of a steam turbine based on mechanism and data hybrid driven modeling according to claim 2 is characterized in that: The condenser characteristic model includes: Saturation temperature of turbine exhaust steam at condenser pressure t s for: t s =t w1 +Δt+δt Among them, t w1 is the condenser circulating water inlet temperature, ℃; Δt is the condenser circulating water temperature rise, ℃; δt is the condenser heat transfer end difference, ℃; The circulating water temperature rise Δt is: Among them, D c , D w Respectively turbine exhaust flow and circulating water flow, t / h; h c , h′ c are the specific enthalpy of steam and condensed water in the condenser, kJ / kg; The heat transfer end difference δt of the condenser is: Among them, A c is the condenser heat exchange area, m 2 ; K is the overall heat transfer coefficient of the condenser, kJ / (m 2 ·h·K).

5. The method for optimizing the cold end of a steam turbine based on mechanism and data hybrid driven modeling according to claim 1 is characterized in that: The characteristic parameters to be identified include the condenser heat transfer coefficient, the turbine power increment characteristic parameters, and the circulating pump characteristic parameters, a total of P parameters to be identified.

6. The method for optimizing the cold end of a steam turbine based on mechanism and data hybrid driven modeling according to claim 1 is characterized in that: The working condition cluster structure is as follows:

7. The method for optimizing the cold end of a steam turbine based on mechanism and data hybrid driven modeling according to claim 6 is characterized in that: The intelligent identification of the characteristic parameters of the mechanism model is specifically as follows: using an intelligent optimization algorithm to take the deviation between the output value of the condenser pressure data model and the actual value as the target, perform an inversion solution on the characteristic parameters of the mechanism model, and obtain the characteristic parameters of the cold end system mechanism model on M operating condition clusters:

8. The method for optimizing the cold end of a steam turbine based on mechanism- and data-driven hybrid modeling according to claim 1 is characterized in that: During the updating process of the mechanism model characteristics, if the model error is greater than the threshold, the process of intelligently identifying the mechanism model characteristic parameters from the data collected from the cold end system of the steam turbine is repeated to update and regress the mechanism model characteristic parameters.

9. The method for optimizing the cold end of a steam turbine based on mechanism and data hybrid driven modeling according to claim 3 is characterized in that: The optimization model of the turbine cold end is: maxF = ∑P t -∑P pump .

10. A steam turbine cold end optimization system based on mechanism and data hybrid driven modeling, characterized in that: include: Steam turbine cold end system mechanism model building module: Establish the steam turbine cold end system mechanism model and clarify the characteristic parameters to be identified of each model; Steam turbine cold end system data acquisition module: collects relevant process parameters of the steam turbine cold end system; Characteristic parameter historical data preprocessing and steady-state judgment module: extract historical data of the cold end system for a certain period of time, perform operating condition data preprocessing, and perform steady-state operating condition judgment on the preprocessed characteristic parameter operating condition data; Steady-state data working condition division module: divides the working condition of the steady-state data of the cold-end system of the steam turbine to form a working condition cluster for the characteristic identification of the cold-end system mechanism model; Intelligent identification module of characteristic parameters of mechanism model: for each operating condition cluster generated by operating condition division, a data model of operating parameters and characteristic parameters of cold end system is constructed; Mechanism model characteristic regression module: After completing the identification of the characteristics of each operating condition cluster, the regression fitting of the mechanism model characteristic parameters is performed based on the central operating condition parameters of each operating condition cluster; Steam turbine exhaust parameter modeling module: Based on all steady-state conditions of the cold end system, a regression prediction model for steam turbine exhaust parameters is established; Mechanism model characteristic update module: Based on the mechanism model of characteristic identification and the turbine exhaust parameter prediction model, a turbine cold end hybrid model is constructed, and the hybrid model prediction error is used as the criterion to determine whether the mechanism model characteristics should be updated; Steam turbine cold end optimization model establishment module: Based on the mechanism model of characteristic identification and the prediction model of steam turbine exhaust parameters, the steam turbine cold end optimization model is established with the goal of maximizing the net power of the steam turbine after deducting the incremental power consumption of the circulating pump; Cold end optimization model solving module: Use intelligent optimization algorithm to optimize and solve the cold end optimization model under specific constraints to obtain the circulation pump operation mode under the real-time working conditions of the steam turbine.

Images