Generated power optimizing and improving method and equipment for gas turbine

Abstract

The invention relates to a method and equipment for optimizing and improving power generation power of a gas turbine, which are characterized in that a primary-effect bag filter, a medium-effect V filter and a high-efficiency refined filter three-stage air inlet filter system are connected to an air inlet pipeline of the gas turbine, and a cooling system and a dehumidification system are arranged between the medium-effect V filter and the high-efficiency refined filter; taking the pressure difference of each stage and the inlet air temperature of the gas turbine as input, taking the output power of the gas turbine as output training data to drive an algorithm, and obtaining a gas turbine output power prediction model; building a power generation power relation model according to the environment temperature and humidity, the temperature and humidity before and after entering and exiting a cooling and dehumidifying system, the water supply and return temperature and flow of a chilled water system, the pressure difference before and after primary-efficiency bag filtration, medium-efficiency V filtration and high-efficiency refined filtration and the power generation power; and constructing an energy consumption relation model according to the water supply and return temperature, flow and energy consumption of the chilled water system. And multi-target optimization is carried out according to the maximum generated power, the minimum difference value between the generated power and the predicted power and the minimum energy consumption, the optimal temperature point of the inlet of the gas turbine is determined, and the generated power of the gas turbine is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of gas turbine power generation, and more specifically, to a method and device for optimizing and improving the power generation capacity of a gas turbine. Background Art

[0002] Gas turbines play an important role in ensuring the supply of electricity and heat. With the national dual carbon goals, the power generation efficiency of gas turbines should be further improved to reduce carbon emissions. In the prior art, ZL202011458763.2 discloses a system and method for increasing the power of a gas turbine generator set. The system is equipped with a gas storage tank and an air compressor. The air compressor is used to provide compressed air to the gas storage tank in high-altitude areas, so that the oxygen content in the compressed air is greater than or equal to 21%. The pressure and temperature of the gas storage tank are monitored, and the ambient air pressure is calculated based on geographic information. Then, the speed range of the motor is set, and the speed of the motor is specifically adjusted according to the pressure and temperature of the gas storage tank. This method uses the gas storage tank to make the compressed air meet the standard atmospheric pressure and increase the output power of the generator set. It is mainly used in areas above 1500m above sea level. For example, ZL2021103013732 discloses a gas turbine intake air filtration system. In order to address the problem that the air filtration system is under heavy operating load due to the high salt fog and humidity in coastal areas, and liquid particles are easily frosted on the filter element, causing blockage and easily causing the filter element to fail, a droplet separation unit and a filtration unit are used to reduce the liquid particles in the gas before it enters the air filtration system, thereby ensuring the safe and stable operation of the gas turbine.

[0003] Since the population of my country is mainly located in the central and eastern regions, many gas turbine thermal power plants have been built in addition to high-altitude areas and coastal areas. There have long been problems such as large pressure difference in the air intake filtration system and high air intake temperature, which leads to a decrease in gas turbine power generation. The above methods have no substantial effect on the central and eastern regions. The first technology mainly sets up a gas storage tank, which can produce a standard atmospheric pressure, but the plains in the central and eastern regions are all standard atmospheric pressure, and this device is not needed. The second technology is mainly to reduce the entry of liquid particles into the filtration system, but first set up a droplet generation unit to first generate liquid particles of different particle sizes and then remove them. It has no practical effect on the central and eastern regions.

[0004] Therefore, this application proposes a new solution for increasing the power generation capacity of gas turbines in the central and eastern regions. Summary of the invention

[0005] In view of the above problems, the purpose of the present invention is to propose a method and device for optimizing and improving the power generation of a gas turbine. The method improves the power generation of a gas turbine by controlling the inlet temperature of the gas turbine. The device can not only reduce the particulate matter entering the air inlet of the gas turbine, but also reduce the air temperature and humidity at the air inlet in summer.

[0006] To achieve the above object, the present invention adopts the following technical solutions: In a first aspect, the present invention provides a method for optimizing and improving the power generation of a gas turbine, wherein a three-stage air intake filtration system of a primary bag filter, a medium-efficiency V filter, and a high-efficiency fine filter is connected to the air intake pipe of the gas turbine, and a cooling system and a dehumidification system are arranged between the medium-efficiency V filter and the high-efficiency fine filter, the air temperature is first cooled, and then the air is dehumidified, and energy is provided by a chilled water system; the improvement method comprises the following contents: Obtain real-time monitoring data of pressure difference at each level after primary, medium and high efficiency treatment, ambient temperature and humidity, temperature and humidity before and after entering and exiting the cooling and dehumidification system, supply and return water temperature and flow of the chilled water system, and gas turbine inlet temperature, and at the same time obtain real-time monitoring data of gas turbine output power; Construct a gas turbine output power prediction model, take the pressure difference at each level and the gas turbine inlet air temperature as input, and use the gas turbine output power as output training data to drive the algorithm, and obtain the gas turbine output power prediction model; The power generation relationship model was constructed with the ambient temperature and humidity, the temperature and humidity before and after entering and leaving the cooling and dehumidification system, the supply and return water temperature and flow rate of the chilled water system, and the pressure difference before and after the primary bag filter, the medium-efficiency V filter and the high-efficiency fine filter as independent variables and the power generation as the dependent variable. Taking the supply and return water temperature and flow rate of the chilled water system as input, the energy consumption under different power generation is calculated to form an energy consumption relationship model; Based on the power generation relationship model and the energy consumption relationship model, multi-objective optimization is performed with the goal of maximizing the power generation, minimizing the difference between the power generation and the predicted power, and minimizing the energy consumption. The optimal temperature point of the gas turbine inlet is determined by the Pareto frontier, and the temperature and flow of the chilled water system at this time are determined. The gas turbine power generation is controlled by this temperature and flow.

[0007] Furthermore, a K-means clustering algorithm is used for the acquired real-time monitoring data to identify abnormal data including missing and mutations; and a machine learning algorithm is used to repair the abnormal data to obtain preprocessed data for subsequent model establishment; the machine learning algorithm is a BP neural network or a K nearest neighbor classification.

[0008] Furthermore, the data-driven algorithm includes artificial neural network (ANN), support vector regression (SVR), random forest or extreme gradient boosting algorithm, etc.

[0009] In a second aspect, the present invention provides a device for optimizing and improving power generation of a gas turbine, wherein the device executes the method described above.

[0010] In a third aspect, the present invention provides a device for optimizing and improving power generation of a gas turbine, the device comprising: The air intake filtration system is equipped with three levels of filtration: primary bag filter, medium-efficiency V filter, and high-efficiency fine filter; The cooling and dehumidification system has a cooling system and a dehumidification system, which are located between the medium-efficiency V filter and the high-efficiency fine filter. The air temperature is first cooled and then the air is dehumidified. The cooling system of the cooling and dehumidification system is supplied with energy by the chilled water system. Pressure sensor, used to collect the pressure difference before and after the primary bag filter, medium-efficiency V filter and high-efficiency fine filter; Temperature sensor, used to monitor the supply and return water temperature of the chilled water system; Flow sensor, monitoring the flow of chilled water system; Temperature and humidity sensors collect ambient temperature and humidity as well as temperature and humidity before and after entering and exiting the cooling and dehumidification system; The intelligent control system for intake air filtration obtains data from the above-mentioned pressure sensors, temperature sensors, flow sensors, and temperature and humidity sensors, respectively monitoring the pressure difference of the three-stage filtration, monitoring the temperature and flow of the chilled water supply and return water, monitoring the ambient temperature and humidity, and the temperature and humidity before and after entering the cooling and dehumidification system, and communicating with the gas turbine DCS system in real time; Finally, the clean, dry, low-temperature air treated by high-efficiency fine filtration passes through the gas turbine air inlet and enters the gas turbine combustion chamber under the action of the gas turbine air compressor.

[0011] Furthermore, the intake air filtration intelligent control system includes: Local storage units and cloud platforms are used to store normal data during device operation; The analysis unit obtains the total output power and total heat consumption of the gas turbine under factory conditions and records them as the standard reference value of output power. and heat consumption standard reference value , then the total output power of the gas turbine under actual operating conditions is According to the following formula:

[0012] Where: —Correction coefficient of ambient temperature to output power; —Correction factor of pressure difference to output power; —Correction factor of relative humidity to output power; —Correction factor of fuel lower calorific value to output power; —Correction coefficient of exhaust pressure to output power; The total heat consumption of the gas turbine under actual operating conditions is calculated as follows:

[0013] Where: —Correction coefficient of ambient temperature to heat consumption; —Correction factor of atmospheric pressure on heat consumption; —Correction factor of relative humidity to heat loss; —Correction factor of fuel lower calorific value to heat consumption; —Correction coefficient of exhaust pressure to heat consumption; According to the ambient temperature, high-efficiency fine filtration pressure difference, humidity before and after entering and leaving the cooling and dehumidification system, the relationship curves between the output power and the relationship curves between the output power and the heat consumption are established respectively, and the correction coefficients for the output power and the heat consumption under the respective conditions are obtained respectively; Optimize and adjust the gas turbine inlet temperature to maximize output power and minimize heat consumption; The display unit is used to display the relationship curves between various indicators and output power, the relationship curves between various indicators and heat consumption, and the optimization results.

[0014] Furthermore, the intake air filtration intelligent control system is loaded with a large-scale language model based on Transformers. The large-scale language model based on Transformers takes the pressure differences of each level after primary, medium and high efficiency processing, the ambient temperature and humidity, the temperature and humidity before and after entering and exiting the cooling and dehumidification system, the supply and return water temperature and flow of the chilled water system, and the gas turbine inlet temperature as input, and takes the output power and heat consumption as output. The output of the large-scale language model based on Transformers is compared with the set normal value range of the output power and heat consumption to determine whether the gas turbine has a fault, which is used for gas turbine intake system fault diagnosis.

[0015] Furthermore, under the premise of ensuring the intake pressure difference, the air intake filtration system is equipped with three-stage filter elements by optimizing the filter element structure and effective filtration area of ​​each stage, which are primary bag filter, medium-efficiency V filter and high-efficiency fine filter in sequence; the primary bag filter adopts a bag structure of at least 10 bags, and the filter material is M6 grade high-efficiency glass fiber; the medium-efficiency V filter adopts a 5V structure, and the filter material is F8 grade high-efficiency glass fiber; the high-efficiency fine filter adopts a cylindrical structure, the diameter and length are adjusted according to the intake space, and the filter material is F9 grade fully synthetic composite fiber.

[0016] Furthermore, the cooling system is arranged in layers and groups, grouped according to top and bottom, and layered according to inside and outside. The cooling coils in the group are connected in series in sequence, and the cooling coils in different layers are independent of each other. The cooling coils include a heat dissipation channel, and two heat dissipation fins 2 are arranged in the heat dissipation channel. Both ends of the heat dissipation pipeline of each layer are connected to the chilled water system through a chilled water supply pipe 3 and a chilled water return pipe 4 respectively. At least four groups of separate cooling coils, each group is provided with at least three layers, the angle between two radiating fins is 60°~120°, the radiating fins are 30°~60° with the air flow direction, and the two radiating fins need to overlap 1-2cm in the horizontal direction; the thickness of each group of cooling coils is 10-30cm; the radiating pipes are made of copper tubes or stainless steel tubes, and the radiating fins are made of anti-corrosion aluminum foil or stainless steel sheets; The dehumidification system adopts a water mist filter or a solid adsorbent or a lithium chloride rotary dehumidification system, with a thickness of 5 to 10 cm and a cross-sectional area adjusted according to the air intake space.

[0017] Furthermore, in summer, outdoor high-temperature, high-humidity, dusty air enters the air intake filtration system, and passes through the primary filter bag, using 10 bags of M6 filter material, filtering out about 60% of the dust with a particle diameter ≥ 0.4μm; passing through the medium-efficiency V filter, using 5V structure F8 filter material, filtering out about 90% of the dust with a particle diameter ≥ 0.4μm, and turning it into cleaner air; When the outdoor temperature exceeds 22°C, the air passes through the medium-efficiency V filter and enters the cooling system connected to the chilled water system. The cooling system consists of at least four sets of cooling coils. The chilled water system is turned on, and the chilled water enters the cooling coils in the cooling system to cool the high-temperature air to 22°C. The low-temperature air treated by the cooling system enters the dehumidification system, which removes condensed water and excess moisture in the air, turning it into cleaner, low-temperature dry air, and then enters the high-efficiency fine filter; The high-efficiency fine filtration uses a cylindrical structure and 1m long F9 grade fully synthetic composite fiber to filter out about 95% of dust with a particle diameter ≥ 0.4μm, turning it into clean, low-temperature dry air, which passes through the gas turbine air inlet and enters the gas turbine combustion chamber under the action of the air compressor.

[0018] Compared with the prior art, the method and device for optimizing and improving the power generation of a gas turbine provided by the present invention have at least the following effects: 1. The system of the present invention is equipped with an intelligent control system for intake air filtration, which can perform intelligent regulation and control according to relevant parameters of the equipment before the gas turbine air inlet, such as the three-stage filtration pressure difference and the chilled water supply and return water temperature and flow rate, so as to improve the power generation capacity of the gas turbine.

[0019] 2. The improvement method of the present invention monitors the gas turbine power generation, inlet temperature, three-stage filter element pressure difference, chilled water system supply and return water temperature, temperature and humidity before and after entering and leaving the cooling and dehumidification system, and other parameters in real time. The multi-objective optimization is performed with the maximum power generation, the minimum difference between the power generation and the predicted power, and the minimum energy consumption. The optimal temperature point of the gas turbine inlet is determined by the Pareto frontier, and the temperature and flow of the chilled water system at this time are determined. The gas turbine power generation is controlled by this temperature and flow, so that the gas turbine power generation is maintained at a high level. At the same time, the intake air filtration effect and the cooling and dehumidification effect can be effectively guaranteed.

[0020] 3. The present invention regulates and controls the inlet air temperature of the gas turbine, thereby solving the problem that the high inlet temperature in summer causes the power generation of the gas turbine to decrease, and realizes intelligent control with high control accuracy and fast response speed.

[0021] 4. The equipment of the present invention is provided with a three-stage filter element structure, and the filtering level of each stage of the filter element is strengthened. The medium filter adopts a special structure such as a 5V structure, which increases the circulation filtering area and reduces the pressure drop; while ensuring the quality of the intake air filtration, the service life of the filter element is extended, and the cost of frequent replacement of the filter element is reduced; the service life of the primary bag filter and the medium efficiency V filter exceeds 4000h or 1 year, and the service life of the high-efficiency fine filter is not less than 8000h. The problem of low service life and easy clogging of the filter element in the existing intake filtration system using single-stage or two-stage filtration is solved. Under the condition that the intake space of the gas turbine is limited and the intake volume reaches a large flow of 108.5 m³ / s, the present invention adds high-efficiency fine filtration to achieve the purpose of increasing the filtration efficiency in a limited space and under the condition of large flow, and it can reduce the frequency of filter element replacement (such as the existing technology requires at least 3-5 times a year to replace the filter element, while the present application is basically once a year). After setting up a three-stage filtration system, the pressure difference can be reduced from 60mmH2O to 40-42mmH2O, and the reduction ratio is 33%.

[0022] 5. The present invention can effectively control the inlet temperature of the gas turbine in summer and winter through the intelligent control system, accurately control the inlet air temperature of the gas turbine in winter and summer, and ensure the efficient power generation of the gas turbine. At the same time, the dehumidification system can effectively reduce the humidity of the intake air, avoid wet air from entering the high-efficiency fine filtration system, and cause the risk of fine filtration failure. It can increase the maximum power generation of the gas turbine by 2WM / h, and the increase ratio is 5.3%. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 An overall structural schematic diagram of an embodiment of a device for optimizing and improving power generation of a gas turbine according to the present invention; Figure 2 A schematic top view of the structure of a cooling system of an embodiment of a device for optimizing and improving power generation of a gas turbine according to the present invention; Figure 3A schematic cross-sectional view of the cooling system of an embodiment of a device for optimizing and improving power generation of a gas turbine according to the present invention. DETAILED DESCRIPTION

[0024] To more clearly describe the technical solution and advantages of the present invention, the working principle of the technical solution of the present invention in summer will be fully described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them.

[0025] Example 1 Figure 1 A schematic diagram of a method and device for optimizing and improving the power generation of a gas turbine provided in an embodiment of the present application, and a device for optimizing and improving the power generation of a gas turbine, comprising: The air intake filtration system is equipped with a three-stage system of primary bag filter, medium-efficiency V filter and high-efficiency fine filter; Cooling and dehumidification system: set up cooling system and dehumidification system, located between medium-efficiency V filter and high-efficiency fine filter, first cool the air temperature, and then dehumidify the air; The intelligent control system for intake air filtration can monitor the pressure difference of the three-stage filtration system separately, monitor the ambient temperature and humidity, and the temperature and humidity before and after entering the cooling and dehumidification system, monitor the supply and return temperature and flow of chilled water, and communicate with the gas turbine DCS system in real time; Finally, the clean, dry, low-temperature air treated by high-efficiency fine filtration passes through the gas turbine air inlet and enters the gas turbine combustion chamber under the action of the gas turbine air compressor.

[0026] Preferably, the air intake filtration system includes: the more filter levels there are, the greater the pressure difference is. Under the premise of ensuring the air intake pressure difference, by optimizing the filter structure and effective filtration area of ​​each level, a three-level filter element is set, which is primary bag filter, medium-efficiency V filter and high-efficiency fine filter. The primary bag filter adopts a bag structure of at least 10 bags, and the filter material is M6 grade high-efficiency glass fiber; the medium-efficiency V filter adopts a 5V structure, and the filter material is F8 grade high-efficiency glass fiber; the high-efficiency fine filter adopts a cylindrical structure, and the diameter and length are appropriately adjusted according to the air intake space, and the filter material is F9 grade fully synthetic composite fiber.

[0027] Preferably, the cooling and dehumidification system includes a cooling system and a dehumidification system. The cooling system is connected to a chilled water system. The chilled water system includes a chilled water supply pipe 3 and a chilled water return pipe 4. Figure 2 As shown. The cooling system is arranged in layers and groups, grouped according to top and bottom, and layered according to inside and outside. The cooling coils in the group are connected in series in sequence, and the cooling coils in different layers are independent of each other. The cooling coils include a heat dissipation channel, and two heat dissipation fins 2 are arranged in the heat dissipation channel. Both ends of the heat dissipation pipeline of each layer are connected to the chilled water system through a chilled water supply pipe 3 and a chilled water return pipe 4; At least four groups of separate cooling coils, each group is provided with at least three layers, the angle between two radiating fins is 60°~120°, the radiating fins are 30°~60° with the air flow direction, and the two radiating fins need to overlap 1-2cm in the horizontal direction; the thickness of each group of cooling coils (i.e. the width in the top view) is 10-30cm; the radiating pipes are made of copper tubes or stainless steel tubes, and the radiating fins are made of anti-corrosion aluminum foil or stainless steel sheets; The existing cooling system is an integrated system with one inlet and one outlet, which results in a long cooling coil and a maximum circulation loop of more than 20m, resulting in high energy consumption of the circulation pump. This embodiment adopts a grouped and layered structure, dividing the existing system into four groups of separate cooling coils, each group of coils has at least three layers of copper tubes, which increases the heat exchange effect and reduces the maximum circulation loop by more than 50%.

[0028] The dehumidification system can use a water mist filter or solid adsorbent such as silica gel or a lithium chloride rotary dehumidification system with a thickness of 5~10cm and the cross-sectional area adjusted according to the air intake space.

[0029] Example 2 In this embodiment, the intake air filtration intelligent control system includes: Local storage units and cloud platforms are used to store normal data during device operation; The analysis unit obtains the total output power and total heat consumption of the gas turbine under factory conditions and records them as the standard reference value of output power. and heat consumption standard reference value (unit [kJ / kWh]), then the total output power of the gas turbine under actual operating conditions According to the following formula:

[0030] Where: —Correction coefficient of ambient temperature to output power; —Correction factor of pressure difference to output power; —Correction factor of relative humidity to output power; —Correction factor of fuel lower calorific value to output power; —Correction coefficient of exhaust pressure to output power; The total heat consumption of the gas turbine under actual operating conditions is calculated as follows:

[0031] Where: —Correction coefficient of ambient temperature to heat consumption; —Correction factor of atmospheric pressure on heat consumption; —Correction factor of relative humidity to heat loss; —Correction factor of fuel lower calorific value to heat consumption; —Correction coefficient of exhaust pressure to heat consumption; According to the ambient temperature, high-efficiency fine filtration pressure difference, humidity before and after entering and leaving the cooling and dehumidification system, the relationship curves between the output power and the relationship curves between the output power and the heat consumption are established respectively, and the correction coefficients for the output power and the heat consumption under the respective conditions are obtained respectively; Optimize and adjust the gas turbine inlet temperature to maximize output power and minimize heat consumption; The display unit is used to display the relationship curves between various indicators and output power, the relationship curves between various indicators and heat consumption, and the optimization results.

[0032] The correction coefficients related to the lower calorific value of the fuel, atmospheric pressure and exhaust pressure mentioned above can be set as constants based on experience.

[0033] Monitor the pressure difference before and after the primary bag filter, medium-efficiency V filter and high-efficiency fine filter. When the pressure difference exceeds the limit, timely warn and replace it; monitor the ambient temperature and humidity and the temperature and humidity before and after the cooling and dehumidification system, and provide the control system with the cooling system temperature and humidity monitoring data; monitor the supply and return water temperature and flow of the chilled water system, and provide the control system with the chilled water system temperature and flow monitoring data.

[0034] The K-means clustering algorithm is used for the acquired real-time monitoring data to identify abnormal data including missing and mutations; and the machine learning algorithm is used to repair the abnormal data to obtain pre-processed data for the establishment of subsequent models; the machine learning algorithm is BP neural network or K nearest neighbor classification. The pre-processed data is stored in the local system and cloud platform.

[0035] Output power and heat consumption are important indicators of gas turbine power generation. Through the intelligent control system of the air intake system, the gas turbine inlet temperature is optimized and adjusted to maximize output power and minimize heat consumption, keeping these two indicators at the optimal operating level.

[0036] The display unit obtains data from the analysis unit and displays parameters such as ambient temperature and humidity, stage-by-stage pressure difference of the three-stage filtration system, supply and return water temperature and flow of the chilled water system, inlet and outlet temperature and humidity of the cooling and dehumidification system, gas turbine output power and heat consumption, and displays related relationship curves.

[0037] The control system is connected to the gas turbine DCS system. The intake air filtration intelligent control system is loaded with a large language model based on Transformers. The large language model based on Transformers takes the pressure difference at each level after primary, medium and high efficiency processing, the ambient temperature and humidity, the temperature and humidity before and after entering and exiting the cooling and dehumidification system, the supply and return water temperature and flow of the chilled water system, and the gas turbine inlet temperature as input, and outputs the output power and heat consumption. The output of the large language model based on Transformers is compared with the set normal value range of output power and heat consumption to determine whether the gas turbine has a fault, which is used for gas turbine intake system fault diagnosis. The DCS system for real-time closed-loop control of the intake temperature of the gas turbine intake cooling system is realized in the DCS system. The large language model based on Transformers is a generative pre-trained model that shows strong capabilities in interacting with humans, code generation, and reasoning using common sense and domain knowledge.

[0038] Example 3 This embodiment is used for the method for optimizing and improving the power generation of a gas turbine. A three-stage air intake filtration system of a primary bag filter, a medium-efficiency V filter, and a high-efficiency fine filter is connected to the air intake pipe of the gas turbine, and a cooling system and a dehumidification system are arranged between the medium-efficiency V filter and the high-efficiency fine filter. The air temperature is first cooled, and then the air is dehumidified, and energy is provided by the chilled water system. The improvement method includes the following contents: Obtain real-time monitoring data of pressure difference at each level after primary, medium and high efficiency treatment, ambient temperature and humidity, temperature and humidity before and after entering and exiting the cooling and dehumidification system, supply and return water temperature and flow of the chilled water system, and gas turbine inlet temperature, and at the same time obtain real-time monitoring data of gas turbine output power; Construct a gas turbine output power prediction model, take the pressure difference at each level and the gas turbine inlet air temperature as input, and use the gas turbine output power as output training data to drive the algorithm, and obtain the gas turbine output power prediction model; The power generation relationship model was constructed with the ambient temperature and humidity, the temperature and humidity before and after entering and leaving the cooling and dehumidification system, the supply and return water temperature and flow rate of the chilled water system, and the pressure difference before and after the primary bag filter, the medium-efficiency V filter and the high-efficiency fine filter as independent variables and the power generation as the dependent variable. Taking the supply and return water temperature and flow rate of the chilled water system as input, the energy consumption under different power generation is calculated to form an energy consumption relationship model; Based on the power generation relationship model and the energy consumption relationship model, multi-objective optimization is performed with the goal of maximizing the power generation, minimizing the difference between the power generation and the predicted power, and minimizing the energy consumption. The optimal temperature point of the gas turbine inlet is determined by the Pareto frontier, and the temperature and flow of the chilled water system at this time are determined. The gas turbine power generation is controlled by this temperature and flow.

[0039] The monitoring data collection time of this example is 10 minutes. Each collection obtains the corresponding pressure difference at each level after primary, medium and high efficiency processing, the ambient temperature and humidity, the temperature and humidity before and after entering and leaving the cooling and dehumidification system, the supply and return water temperature and flow of the chilled water system, and the real-time monitoring data of the gas turbine inlet temperature. At the same time, the real-time monitoring data of the gas turbine output power is obtained. Based on historical monitoring data, a data-driven algorithm is used for training to obtain a gas turbine output power prediction model. In this embodiment, support vector regression is used for training, so that a group of sample data is composed of pressure differences at various levels, gas turbine inlet air temperature, and gas turbine output power. Sample data of a large amount of historical monitoring data constitutes a data set. 80% of the data in the data set is used for training, and 20% of the data is used for verification. The output power prediction value in the future or a period of time in the future can be predicted.

[0040] The construction process of the gas turbine output power prediction model includes data preprocessing, feature engineering, model training, model evaluation, and result visualization. Feature engineering uses correlation analysis, recursive feature elimination, dimensionality reduction and other methods to select appropriate features as model inputs, select appropriate data-driven algorithms and hyperparameters for model training, and use artificial neural networks (ANN), support vector regression (SVR), random forests, and extreme gradient boosting algorithms for model evaluation.

[0041] Example 4 In this embodiment, in summer, high-temperature, high-humidity, and dusty outdoor air enters the air intake filtration system, passes through the primary bag filter in turn, using 10 bags of M6 grade filter materials to filter out about 60% of the dust with a particle diameter ≥ 0.4 μm; passes through the medium-efficiency V filter, using 5V structure F8 filter materials, and filters out about 90% of the dust with a particle diameter ≥ 0.4 μm, turning it into cleaner air.

[0042] When the outdoor temperature exceeds 22℃, the relatively clean high-temperature air passes through the medium-efficiency V filter and enters the cooling system connected to the chilled water system. The cooling system consists of at least 4 sets of cooling coils, each of which uses three rows of copper tubes and anti-corrosion aluminum foil structure with a thickness of 10-30cm. The intelligent control system turns on the chilled water system, and the chilled water enters the cooling coils in the cooling system to cool the high-temperature air to 22℃.

[0043] After passing through the cooling system, the relatively clean and low-temperature air enters the dehumidification system, which uses solid adsorbents such as silica gel or lithium chloride rotary dehumidification system with a thickness of 5~10cm. The dehumidification system can remove condensed water and excess moisture in the air, turning it into relatively clean and low-temperature dry air, and preventing humid air from entering the high-efficiency fine filtration system and affecting the filtration efficiency.

[0044] After passing through the dehumidification system, the relatively clean, low-temperature and dry air enters the high-efficiency fine filter, which uses a cylindrical structure and 1m long F9-grade fully synthetic composite fiber to filter out about 95% of dust with a particle diameter of ≥0.4μm, turning it into clean, low-temperature and dry air. It passes through the gas turbine air inlet and enters the gas turbine combustion chamber under the action of the air compressor.

[0045] According to the output power calculation formula in Example 2, the output power of the gas turbine decreases by 62KW / H, or about 1.3%, for every 100Pa increase in the intake pressure difference of the gas turbine. The three-stage intake filtration system proposed by the present invention can effectively reduce the annual average pressure difference by more than 200Pa, that is, it can increase the annual average output power of the gas turbine by about 2.6%.

[0046] When the gas turbine inlet temperature exceeds 22°C in summer, the chilled water system is turned on by the control system, and the solenoid valve opening or the supply and return water temperature of the chilled water system is adjusted to reduce the gas turbine inlet temperature to 22°C; when the gas turbine inlet temperature is lower than 10°C in winter, the chilled water system is turned on by the control system, and the chilled water system is switched to the heating mode, and the solenoid valve opening or the supply and return water temperature of the chilled water system is adjusted to increase the gas turbine inlet temperature to 10°C.

[0047] The DCS system implements real-time closed-loop control of the intake air temperature of the gas turbine intake air cooling system, with a deviation of no more than 1.5%, and high-speed information interaction with the DCS, with an interaction time of no more than 2s.

[0048] In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0049] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0050] Any matters not described in the present invention are applicable to the prior art.

Claims

1. A method for optimizing and improving the power generation of a gas turbine, characterized in that: A three-stage air intake filtration system of primary bag filter, medium-efficiency V filter and high-efficiency fine filter is connected to the air intake pipe of the gas turbine, and a cooling system and a dehumidification system are arranged between the medium-efficiency V filter and the high-efficiency fine filter to first cool the air temperature and then dehumidify the air, and the chilled water system provides energy; the improvement method includes the following contents: Obtain real-time monitoring data of pressure difference at each level after primary, medium and high efficiency treatment, ambient temperature and humidity, temperature and humidity before and after entering and exiting the cooling and dehumidification system, supply and return water temperature and flow of the chilled water system, and gas turbine inlet temperature, and at the same time obtain real-time monitoring data of gas turbine output power; Construct a gas turbine output power prediction model, take the pressure difference at each level and the gas turbine inlet air temperature as input, and use the gas turbine output power as output training data to drive the algorithm, and obtain the gas turbine output power prediction model; The power generation relationship model was constructed with the ambient temperature and humidity, the temperature and humidity before and after entering and leaving the cooling and dehumidification system, the supply and return water temperature and flow rate of the chilled water system, and the pressure difference before and after the primary bag filter, the medium-efficiency V filter and the high-efficiency fine filter as independent variables and the power generation as the dependent variable. Taking the supply and return water temperature and flow rate of the chilled water system as input, the energy consumption under different power generation is calculated to form an energy consumption relationship model; Based on the power generation relationship model and the energy consumption relationship model, multi-objective optimization is performed with the goal of maximizing the power generation, minimizing the difference between the power generation and the predicted power, and minimizing the energy consumption. The optimal temperature point of the gas turbine inlet is determined by the Pareto frontier, and the temperature and flow of the chilled water system at this time are determined. The gas turbine power generation is controlled by this temperature and flow.

2. The method according to claim 1, characterized in that The K-means clustering algorithm is used for the acquired real-time monitoring data to identify abnormal data including missing and mutation; and a machine learning algorithm is used to repair the abnormal data to obtain preprocessed data for subsequent model establishment; the machine learning algorithm is BP neural network or K nearest neighbor classification.

3. The method according to claim 1, characterized in that The data-driven algorithms include artificial neural networks, support vector regression, random forests, or extreme gradient boosting algorithms.

4. A device for optimizing and improving power generation of a gas turbine, characterized in that: The device executes the method according to any one of claims 1 to 3.

5. A device for optimizing and improving power generation of a gas turbine, characterized in that: The device comprises: The air intake filtration system is equipped with three levels of filtration: primary bag filter, medium-efficiency V filter, and high-efficiency fine filter; The cooling and dehumidification system has a cooling system and a dehumidification system, which are located between the medium-efficiency V filter and the high-efficiency fine filter. The air temperature is first cooled and then the air is dehumidified. The cooling system of the cooling and dehumidification system is supplied with energy by the chilled water system. Pressure sensor, used to collect the pressure difference before and after the primary bag filter, medium-efficiency V filter and high-efficiency fine filter; Temperature sensor, used to monitor the supply and return water temperature of the chilled water system; Flow sensor, monitoring the flow of chilled water system; Temperature and humidity sensors collect ambient temperature and humidity as well as temperature and humidity before and after entering and exiting the cooling and dehumidification system; The intelligent control system for intake air filtration obtains data from the above-mentioned pressure sensors, temperature sensors, flow sensors, and temperature and humidity sensors, respectively monitoring the pressure difference of the three-stage filtration, monitoring the temperature and flow of the chilled water supply and return water, monitoring the ambient temperature and humidity, and the temperature and humidity before and after entering the cooling and dehumidification system, and communicating with the gas turbine DCS system in real time; Finally, the clean, dry, low-temperature air treated by high-efficiency fine filtration passes through the gas turbine air inlet and enters the gas turbine combustion chamber under the action of the gas turbine air compressor.

6. The device according to claim 5, characterized in that The intake air filtration intelligent control system includes: Local storage units and cloud platforms are used to store normal data during device operation; The analysis unit obtains the total output power and total heat consumption of the gas turbine under factory conditions and records them as the standard reference value of output power. and heat consumption standard reference value , then the total output power of the gas turbine under actual operating conditions is According to the following formula: ， Where: —Correction coefficient of ambient temperature to output power; —Correction coefficient of pressure difference to output power; —Correction factor of relative humidity to output power; —Correction factor of fuel lower calorific value on output power; —Correction coefficient of exhaust pressure to output power; The total heat consumption of the gas turbine under actual operating conditions is calculated as follows: ， Where: —Correction coefficient of ambient temperature to heat consumption; —Correction factor of atmospheric pressure on heat consumption; —Correction factor of relative humidity to heat loss; —Correction factor of fuel lower calorific value to heat consumption; —Correction coefficient of exhaust pressure to heat consumption; According to the ambient temperature, high-efficiency fine filtration pressure difference, humidity before and after entering and leaving the cooling and dehumidification system, the relationship curves between the output power and the relationship curves between the output power and the heat consumption are established respectively, and the correction coefficients for the output power and the heat consumption under the respective conditions are obtained respectively; Optimize and adjust the gas turbine inlet temperature to maximize output power and minimize heat consumption; The display unit is used to display the relationship curves between various indicators and output power, the relationship curves between various indicators and heat consumption, and the optimization results.

7. The device according to claim 5, characterized in that The intake air filtration intelligent control system is loaded with a large language model based on Transformers. The large language model based on Transformers takes the pressure differences of each level after primary, medium and high efficiency processing, the ambient temperature and humidity, the temperature and humidity before and after entering and exiting the cooling and dehumidification system, the supply and return water temperature and flow of the chilled water system, and the gas turbine inlet temperature as inputs, and takes the output power and heat consumption as outputs. The output of the large language model based on Transformers is compared with the set normal value range of the output power and heat consumption to determine whether the gas turbine has a fault.

8. The device according to claim 5, characterized in that The air intake filtration system, under the premise of ensuring the air intake pressure difference, optimizes the filter element structure and effective filtration area of ​​each stage, and sets three-stage filter elements, which are primary bag filter, medium-efficiency V filter and high-efficiency fine filter in sequence; the primary bag filter adopts a bag structure of at least 10 bags, and the filter material is M6 grade high-efficiency glass fiber; the medium-efficiency V filter adopts a 5V structure, and the filter material is F8 grade high-efficiency glass fiber; the high-efficiency fine filter adopts a cylindrical structure, the diameter and length of which are adjusted according to the air intake space, and the filter material is F9 grade fully synthetic composite fiber.

9. The device according to claim 5, characterized in that The cooling system is arranged in layers and groups, grouped according to top and bottom, and layered according to inside and outside. The cooling coils in the group are connected in series in sequence, and the cooling coils in different layers are independent of each other. The cooling coils include a heat dissipation channel, and two heat dissipation fins are arranged in the heat dissipation channel. Both ends of the heat dissipation pipeline of each layer are connected to the chilled water system through a chilled water supply pipe and a chilled water return pipe respectively. At least four groups of separate cooling coils, each group is provided with at least three layers, the angle between two radiating fins is 60°~120°, the radiating fins are 30°~60° with the air flow direction, and the two radiating fins need to overlap 1-2cm in the horizontal direction; the thickness of each group of cooling coils is 10-30cm; the radiating pipes are made of copper tubes or stainless steel tubes, and the radiating fins are made of anti-corrosion aluminum foil or stainless steel sheets; The dehumidification system adopts a water mist filter or a solid adsorbent or a lithium chloride rotary dehumidification system, with a thickness of 5 to 10 cm and a cross-sectional area adjusted according to the air intake space.

10. The device according to claim 5, characterized in that In summer, outdoor high-temperature, high-humidity, dusty air enters the air intake filtration system, passes through the primary filter bag, uses 10 bags of M6 filter material, and filters out about 60% of the dust with a particle diameter ≥ 0.4μm; passes through the medium-efficiency V filter, uses 5V structure F8 filter material, and filters out about 90% of the dust with a particle diameter ≥ 0.4μm, turning it into cleaner air; When the outdoor temperature exceeds 22°C, the air passes through the medium-efficiency V filter and enters the cooling system connected to the chilled water system. The cooling system consists of at least four sets of cooling coils. The chilled water system is turned on, and the chilled water enters the cooling coils in the cooling system to cool the high-temperature air to 22°C. The low-temperature air treated by the cooling system enters the dehumidification system, which removes condensed water and excess moisture in the air, turning it into cleaner, low-temperature dry air, and then enters the high-efficiency fine filter; The high-efficiency fine filtration uses a cylindrical structure and 1m long F9 grade fully synthetic composite fiber to filter out 95% of dust with a particle diameter ≥ 0.4μm, turning it into clean, low-temperature dry air, which passes through the gas turbine air inlet and enters the gas turbine combustion chamber under the action of the air compressor.

Images