Intelligent maintenance decision-making method for gas turbine based on reverse fitting of component characteristics

Abstract

The invention relates to a gas turbine intelligent maintenance decision-making method based on reverse fitting of component characteristics, and the method comprises the steps: obtaining the current operation data of a target gas turbine; inputting the current operation data into a pre-constructed gas turbine performance degradation simulation model to obtain flow degradation data and efficiency degradation data; based on the flow degradation data and the efficiency degradation data, whether the target gas turbine meets a preset early warning condition or not is judged; and if the preset early warning condition is not met, calculating a target washing period of the target gas turbine by utilizing a pre-constructed washing economy target function so as to execute a washing maintenance action of the target gas turbine. Therefore, the problems that the evaluation result of the performance of the gas compressor is greatly deviated from the actual condition, an accurate judgment basis cannot be provided for maintenance, a regular maintenance mode generates relatively high manpower and economic cost and the like due to the fact that the thermal performance model depends on a general component characteristic diagram and the individual performance difference of the gas turbine is not considered in the related technology are solved.

Description

Technical Field

[0001] This application relates to the field of condition-based maintenance technology for thermal equipment, and in particular to an intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics. Background Technology

[0002] Currently, gas turbines are the core equipment of modern energy and power systems, and their performance directly affects energy utilization efficiency, operating economy, and environmental emissions. The compressor, as the most important of the three core components of a gas turbine (compressor, combustion chamber, and turbine), plays a crucial role in providing high-pressure air for the combustion process. The compressor's energy efficiency, i.e., its efficiency in compressing air, is one of the decisive factors determining the overall gas turbine cycle efficiency, fuel consumption rate, and operating economy. In actual operation, compressor performance can degrade or deviate from design conditions due to various factors, such as blade fouling, wear, corrosion, changes in sealing clearances, fluctuations in intake conditions (temperature, humidity, pressure, pollution), and operation under non-design conditions. These factors can lead to a decrease in the compressor's isentropic efficiency, a reduction in pressure ratio, and a decrease in surge margin, which in turn causes a decrease in the overall gas turbine output power, an increase in heat rate, an increase in operating costs, and even threatens the safe and stable operation of the unit.

[0003] In related technologies, to ensure the performance of gas turbines, a thermodynamic performance model based on a general component characteristic diagram is constructed to calculate the key parameters of the compressor to assess its performance degradation and provide a reference for maintenance. At the maintenance execution level, a periodic maintenance mode is adopted, that is, maintenance operations are carried out on the compressor according to a fixed time cycle and in combination with the evaluation results of the above model.

[0004] However, in related technologies, the thermodynamic performance model relies on a general component characteristic diagram, which does not take into account the individual performance differences of the same model of gas turbine due to manufacturing tolerances, installation differences, and different actual operating conditions. This results in a large deviation between the compressor performance evaluation results and the actual situation, making it impossible to provide an accurate basis for maintenance. Furthermore, the periodic maintenance mode, which is based on a fixed cycle, has resulted in significant human and economic costs, which urgently need to be improved. Summary of the Invention

[0005] This application provides a gas turbine intelligent maintenance decision-making method based on inverse fitting of component characteristics. This method addresses the problems in related technologies, where the thermodynamic performance model relies on a general component characteristic diagram that does not consider the individual performance differences of the gas turbine. This results in a large deviation between the evaluation results of the compressor performance and the actual performance, making it impossible to provide accurate judgment for maintenance. Furthermore, the periodic maintenance mode, which is based on a fixed cycle, leads to significant manpower and economic costs.

[0006] The first aspect of this application provides a method for intelligent maintenance decision-making of gas turbines based on inverse fitting of component characteristics, comprising the following steps: acquiring current operating data of a target gas turbine; inputting the current operating data into a pre-constructed gas turbine performance degradation simulation model to obtain flow degradation data and efficiency degradation data; determining whether the target gas turbine meets preset early warning conditions based on the flow degradation data and the efficiency degradation data; if the preset early warning conditions are not met, calculating the target water washing cycle of the target gas turbine using a pre-constructed water washing economic objective function, and performing water washing maintenance actions on the target gas turbine based on the target water washing cycle.

[0007] Optionally, in one embodiment of this application, before inputting the current operating data into the pre-constructed gas turbine performance degradation simulation model, the method further includes: acquiring multi-condition operating data of the target gas turbine under a preset health state, and filtering out a steady-state operating condition dataset that satisfies preset thermodynamic equilibrium conditions from the multi-condition operating data; using the thermodynamic relationship between the components of the target gas turbine and the flow-power balance as constraints, calculating the component baseline health characteristic parameters of the target gas turbine using the steady-state operating condition dataset; determining the component characteristic diagram of the target gas turbine using the component baseline health characteristic parameters, and constructing a gas turbine performance simulation model using the component characteristic diagram, so as to obtain the gas turbine performance degradation simulation model using the gas turbine performance simulation model.

[0008] Through the above-mentioned technical means, the embodiments of this application can generate a unit-specific component characteristic diagram and construct a performance simulation model based on the actual operating data of the target gas turbine under its own health state, through thermodynamic balance constraints and the matching relationship between components. This effectively eliminates individual performance deviations caused by manufacturing tolerances, installation differences, etc., and lays a precise initial benchmark for the subsequent construction of the performance simulation model, providing reliable model support for intelligent maintenance decisions.

[0009] Optionally, in one embodiment of this application, obtaining the gas turbine performance degradation simulation model using the gas turbine performance simulation model includes: inputting historical input parameters from the steady-state operating condition dataset of the target gas turbine into the pre-constructed gas turbine performance simulation model to obtain theoretical output data; comparing the actual output data corresponding to the historical input parameters with the theoretical output data to determine whether the gas turbine performance simulation model meets preset accuracy conditions; if the preset accuracy conditions are met, then introducing a degradation factor in the component characteristic diagram to transform the gas turbine performance simulation model into the gas turbine performance degradation simulation model.

[0010] Through the above-mentioned technical means, the embodiments of this application can verify the model by comparing the theoretical output of the model with actual historical data, ensuring the reliability of the benchmark model in a healthy state. By introducing a degradation factor into the verified and accurate component characteristic diagram, the degradation assessment deviation caused by inaccurate basic simulation is avoided, thereby making the degradation model fit the individual characteristics of the unit, accurately reflecting the performance degradation law, and providing a more accurate status basis for maintenance decisions.

[0011] Optionally, in one embodiment of this application, before introducing the degradation factor, the method further includes: tracking the changing trends of the efficiency, power, and flow rate and efficiency of each component of the target gas turbine based on the operating data of the target gas turbine; determining whether the target gas turbine is under a preset performance degradation condition based on the changing trends; if it is under the preset performance degradation condition, calculating the degradation theoretical output data based on the degradation operating data of the target gas turbine and the gas turbine performance simulation model; and obtaining the degradation factor using the degradation theoretical output data and the degradation actual output data corresponding to the degradation operating data.

[0012] Through the above-mentioned technical means, the embodiments of this application can realize the dynamic tracking of the performance degradation process and the accurate calibration of the degradation factor. By dynamically tracking the performance change trend, the degradation initiation node can be captured in time. Then, based on the unit's own degradation data, the factor can be calculated so that the degradation factor can accurately quantify the actual degradation degree, further enhancing the adaptability of the performance degradation simulation model to the actual working conditions, and providing more realistic parameter support for subsequent maintenance timing judgment.

[0013] Optionally, in one embodiment of this application, before calculating the target washing cycle of the target gas turbine using a pre-constructed washing economic objective function, the method further includes: constructing a two-stage exponential function to characterize the performance degradation trend characteristics caused by compressor fouling of the target gas turbine; modifying the pre-constructed exponential function characterizing the heat consumption degradation rate of the target gas turbine based on the performance degradation trend characteristics caused by compressor fouling, to obtain a modified exponential function; calculating the combined cycle power generation revenue loss caused by the performance degradation of the target gas turbine based on the two-stage exponential function and the modified exponential function; and constructing the washing economic objective function by combining the combined cycle power generation revenue loss and the shutdown washing cost.

[0014] Through the above-mentioned technical means, the embodiments of this application can accurately characterize the deterioration pattern of slow initial accumulation and accelerated later accumulation through a two-stage exponential function, linking the loss of benefits with maintenance costs, so that the objective function can quantify the economic cost-effectiveness of water washing operations, providing a solid theoretical basis and data support for calculating the economically optimal water washing cycle, and avoiding decision-making imbalances caused by simply pursuing performance optimization or cost control.

[0015] Optionally, in one embodiment of this application, constructing the water washing economic objective function based on the basic parameters, economic parameters, and performance degradation parameters of the target gas turbine includes: obtaining a time-load mapping relationship based on the historical load data of the target gas turbine; constructing a load curve based on the mapping relationship and calculating the cycle-average load rate using the load curve; obtaining the load rate of the target gas turbine at each time point based on the load curve and the cycle-average load rate to determine the load fluctuation of the target gas turbine; and constructing the water washing economic objective function based on the impact of the load fluctuation on the economic parameters.

[0016] Through the above-mentioned technical means, the embodiments of this application can incorporate load fluctuation factors into the water washing economic objective function, so that the function can adapt to the actual operating conditions of the unit under varying loads. The calculated water washing cycle takes into account both the characteristics of scale buildup and cost balance, and fits the operating requirements under different load conditions, further improving the practical applicability of maintenance decisions.

[0017] Optionally, in one embodiment of this application, after calculating the target water washing cycle of the target gas turbine using a pre-constructed water washing economic objective function, the method further includes: determining whether the power degradation rate of the target gas turbine reaches a preset degradation threshold based on the target water washing cycle; if the preset degradation threshold is reached, then correcting the target water washing cycle based on a preset weight.

[0018] Through the above-mentioned technical means, the embodiments of this application can use the power degradation rate as the basis for periodic correction, and can superimpose safety constraints on the basis of optimal economy, so that the final determined water washing cycle can not only avoid unnecessary cost waste, but also prevent the unit's safe operation from being threatened by excessive power degradation, thus achieving a balance between economy and safety in maintenance decisions.

[0019] Optionally, in one embodiment of this application, after determining whether the target gas turbine meets the preset warning conditions, the method further includes: if the preset warning conditions are met, then performing a water washing maintenance operation on the target gas turbine.

[0020] Through the above-mentioned technical means, the embodiments of this application can directly execute the water washing maintenance action of the target gas turbine after determining that the target gas turbine meets the preset early warning conditions, fill the gap in the lack of emergency response procedures for maintenance, quickly alleviate the trend of performance degradation, block the path of fault expansion, ensure the safe and stable operation of the unit under emergency conditions, and form a complete intelligent maintenance system that combines routine dynamic periodic maintenance with emergency early warning response, which is of key significance for ensuring the continuous, safe and efficient operation of the unit.

[0021] A second aspect of this application provides an intelligent maintenance decision-making device for gas turbines based on inverse fitting of component characteristics, comprising: an acquisition module for acquiring current operating data of a target gas turbine; an input module for inputting the current operating data into a pre-constructed gas turbine performance degradation simulation model to obtain flow degradation data and efficiency degradation data; a judgment module for judging whether the target gas turbine meets preset early warning conditions based on the flow degradation data and the efficiency degradation data; and a maintenance module for calculating the target water washing cycle of the target gas turbine using a pre-constructed water washing economic objective function if the preset early warning conditions are not met, and performing water washing maintenance actions on the target gas turbine based on the target water washing cycle.

[0022] Optionally, in one embodiment of this application, it further includes: a filtering module, configured to obtain multi-condition operating data of the target gas turbine under a preset health state before inputting the current operating data into the pre-built gas turbine performance degradation simulation model, and filter out a steady-state operating condition dataset that satisfies a preset thermodynamic equilibrium condition from the multi-condition operating data; a calculation module, configured to calculate the component baseline health characteristic parameters of the target gas turbine using the steady-state operating condition dataset, with the thermodynamic relationship between the components of the target gas turbine and the flow-power balance as constraints, before inputting the current operating data into the pre-built gas turbine performance degradation simulation model; and a construction module, configured to determine the component characteristic map of the target gas turbine using the component baseline health characteristic parameters, and construct a gas turbine performance simulation model using the component characteristic map, so as to obtain the gas turbine performance degradation simulation model using the gas turbine performance simulation model.

[0023] Optionally, in one embodiment of this application, the construction module includes: a historical input unit, used to input historical input parameters from the steady-state operating condition dataset of the target gas turbine into a pre-constructed gas turbine performance simulation model to obtain theoretical output data; a comparison unit, used to compare the actual output data corresponding to the historical input parameters with the theoretical output data to determine whether the gas turbine performance simulation model meets the preset accuracy conditions; and a conversion unit, used to, if the preset accuracy conditions are met, introduce a degradation factor in the component characteristic diagram to convert the gas turbine performance simulation model into a gas turbine performance degradation simulation model.

[0024] Optionally, in one embodiment of this application, the construction module further includes: a tracking unit, used to track the changing trends of the efficiency, power, and flow rate and efficiency of each component of the target gas turbine based on the operating data of the target gas turbine before introducing the degradation factor; an operating condition judgment unit, used to determine whether the target gas turbine is in a preset performance degradation condition based on the changing trends before introducing the degradation factor; an output calculation unit, used to calculate theoretical degradation output data based on the degradation operating data of the target gas turbine and the gas turbine performance simulation model if it is in the preset performance degradation condition before introducing the degradation factor; and a degradation quantification unit, used to obtain the degradation factor using the theoretical degradation output data and the actual degradation output data corresponding to the degradation operating data before introducing the degradation factor.

[0025] Optionally, in one embodiment of this application, it further includes: an exponential function construction module, used to construct a two-stage exponential function characterizing the performance degradation trend of the gas turbine caused by compressor fouling before calculating the target water washing cycle of the target gas turbine using a pre-constructed water washing economic objective function; a function correction module, used to correct the pre-constructed exponential function characterizing the heat consumption degradation rate of the target gas turbine based on the performance degradation trend of the gas turbine caused by compressor fouling before calculating the target water washing cycle of the target gas turbine using the pre-constructed water washing economic objective function, to obtain a corrected exponential function; a loss calculation module, used to calculate the combined cycle power generation revenue loss caused by the performance degradation of the target gas turbine based on the two-stage exponential function and the corrected exponential function before calculating the target water washing cycle of the target gas turbine using the pre-constructed water washing economic objective function; and an objective function construction module, used to construct the water washing economic objective function by combining the combined cycle power generation revenue loss and the shutdown water washing cost.

[0026] Optionally, in one embodiment of this application, the objective function construction module includes: a mapping unit, used to obtain a time-load mapping relationship based on the historical load data of the target gas turbine; a load calculation unit, used to construct a load curve based on the mapping relationship and calculate the periodic average load rate using the load curve; a load determination unit, used to obtain the load rate of the target gas turbine at each time point based on the load curve and the periodic average load rate, so as to determine the load fluctuation of the target gas turbine; and a function construction unit, used to construct the water washing economic objective function based on the impact of the load fluctuation on the economic parameters.

[0027] Optionally, in one embodiment of this application, it further includes: a degradation judgment module, used to determine whether the power degradation rate of the target gas turbine reaches a preset degradation threshold based on the target water washing cycle after calculating the target water washing cycle of the target gas turbine using a pre-built water washing economic objective function; and a cycle correction module, used to correct the target water washing cycle based on a preset weight after calculating the target water washing cycle of the target gas turbine using a pre-built water washing economic objective function, if the preset degradation threshold is reached.

[0028] Optionally, in one embodiment of this application, it further includes: an execution module, configured to, after determining whether the target gas turbine meets the preset warning conditions, perform a water washing maintenance action on the target gas turbine if the preset warning conditions are met.

[0029] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor. The processor executes the program to implement the intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics as described in the above embodiments.

[0030] A fourth aspect of this application provides a non-volatile computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics.

[0031] A fifth aspect of this application provides a computer program product that stores a computer program that, when executed by a processor, implements the above-described intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics.

[0032] This application's embodiments can acquire the current operating data of the target gas turbine, output flow and efficiency degradation data through a performance degradation simulation model, and thus accurately determine whether the unit has triggered the warning conditions. For units that have not reached the warning conditions, the target water washing cycle is calculated through a water washing economic objective function and maintenance is performed. By combining real-time operating data with the simulation model, dynamic perception of the compressor performance degradation state is achieved. The maintenance timing is determined based on the economic function, thereby improving the accuracy of water washing cycle prediction and reducing operation and maintenance costs. This can be applied to the intelligent maintenance of gas turbines in combined cycle power plants. This solves the problems in related technologies, where the thermodynamic performance model relies on a general component characteristic diagram, which does not consider the individual performance differences of the gas turbine, resulting in a large deviation between the compressor performance evaluation results and the actual situation, failing to provide accurate judgment for maintenance. Furthermore, the fixed-cycle-based periodic maintenance mode leads to significant manpower and economic costs.

[0033] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0034] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein: Figure 1 This is a schematic diagram of a single-shaft gas turbine according to an embodiment of this application; Figure 2 This is a schematic diagram of the three main components and cross-section of a gas turbine according to an embodiment of this application; Figure 3 This is a flowchart of a gas turbine intelligent maintenance decision-making method based on inverse fitting of component characteristics, according to an embodiment of this application. Figure 4 This is a flowchart of a gas turbine intelligent maintenance decision-making method based on inverse fitting of component characteristics, according to an embodiment of this application; Figure 5 This is a schematic diagram of compressor characteristic fitting according to an embodiment of this application; Figure 6 This is a schematic diagram of turbine characteristic fitting according to an embodiment of this application; Figure 7 This is a schematic diagram illustrating the verification of compressor outlet temperature data according to an embodiment of this application; Figure 8 This is a schematic diagram illustrating the verification of compressor outlet pressure data according to an embodiment of this application; Figure 9 This is a schematic diagram of a gas turbine intelligent maintenance decision-making device based on inverse fitting of component characteristics, according to an embodiment of this application. Figure 10 This is a schematic diagram of the structure of an electronic device provided according to an embodiment of this application.

[0035] Figure label: 10-Intelligent maintenance decision-making device for gas turbines based on inverse fitting of component characteristics; 100-Acquisition module, 200-Input module, 300-Judgment module, 400-Maintenance module; 1001-Memory, 1002-Processor, 1003-Communication interface. Detailed Implementation

[0036] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0037] The following describes, with reference to the accompanying drawings, an embodiment of the present application of an intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics. In the related technologies mentioned in the background section, the thermodynamic performance models rely on general component characteristic diagrams, which do not consider the individual performance differences of gas turbines. This leads to significant deviations between the compressor performance evaluation results and actual conditions, failing to provide accurate judgment for maintenance. Furthermore, the fixed-cycle-based periodic maintenance mode results in substantial human and economic costs. This application provides an intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics. In this method, the current operating data of the target gas turbine can be obtained, and flow and efficiency degradation data can be output through a performance degradation simulation model to accurately determine whether the unit has triggered warning conditions. For units that have not reached the warning conditions, the target water washing cycle is calculated using a water washing economic objective function, and maintenance is performed. By combining real-time operating data with the simulation model, dynamic perception of the compressor performance degradation state is achieved. The maintenance timing is determined based on the economic function, thereby improving the accuracy of water washing cycle prediction and reducing operation and maintenance costs. This method is applicable to the intelligent maintenance of gas turbines in combined cycle power plants. This solves the problems in related technologies, where the thermodynamic performance model relies on a general component characteristic diagram that does not take into account the individual performance differences of the gas turbine, resulting in a large deviation between the evaluation results of the compressor performance and the actual situation. This makes it impossible to provide an accurate basis for maintenance judgment, and the fixed cycle of the periodic maintenance mode leads to large manpower and economic costs.

[0038] Before proceeding with the intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics proposed in the embodiments of this application, the gas turbines involved in the embodiments of this application will be introduced first.

[0039] like Figure 1 As shown, a gas turbine consists of a compressor, a combustion chamber, and a turbine connected in series via a mechanical shaft. The turbine output is connected to a generator. Air enters the compressor from the left, is compressed, and then sent to the combustion chamber. Fuel is introduced into the combustion chamber from above and mixes with the compressed air for combustion. The high-temperature, high-pressure gas drives the turbine to rotate, and the turbine drives the compressor and generator via the mechanical shaft. Finally, the exhaust gas is discharged from the right side of the turbine.

[0040] like Figure 2As shown in the diagram, the gas turbine includes its three main components: the compressor, the combustion chamber, and the turbine, clearly defining their physical positions within the unit. Section 1 is the compressor inlet, section 2 is the compressor outlet or combustion chamber inlet, section 3 is the turbine inlet, and section 4 is the turbine outlet. These sections are crucial for measuring and calculating thermodynamic parameters, and are essential for evaluating the performance of components and the entire turbine.

[0041] Specifically, Figure 3 This is a flowchart illustrating a gas turbine intelligent maintenance decision-making method based on inverse fitting of component characteristics, provided in an embodiment of this application.

[0042] like Figure 3 As shown, the intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics includes the following steps: In step S301, the current operating data of the target gas turbine is obtained.

[0043] It is understood that the current operating data in the embodiments of this application may include, but is not limited to, compressor inlet temperature, pressure, humidity, fuel, IGV (Inlet Guide Vanes) opening, gas composition, content, density, and lower heating value.

[0044] In practical implementation, the embodiments of this application can continuously measure and acquire core parameters, including but not limited to compressor inlet temperature, pressure, humidity, fuel, IGV opening, gas composition, content, density, and lower heating value, through sensors deployed at key locations such as the gas turbine inlet section, compressor, combustion chamber, turbine, and exhaust section. The data acquisition frequency can be set according to the unit's operational stability. After acquisition, the data needs to be preprocessed, including outlier removal, smoothing filtering, and data format standardization, to form a structured current operating dataset for use by downstream models.

[0045] The embodiments of this application can provide reliable input for the gas turbine performance degradation simulation model through high-precision, real-time acquisition of current operating data, ensuring that the subsequent model can calculate degradation data based on the actual operating state of the unit, guaranteeing the accuracy of maintenance decisions from the data source, and laying a reliable foundation for subsequent performance analysis and cycle calculation.

[0046] In step S302, the current operating data is input into the pre-built gas turbine performance degradation simulation model to obtain flow degradation data and efficiency degradation data.

[0047] It is understood that the flow rate degradation data in this application embodiment can be the decrease in the actual flow rate of the compressor or turbine under the current operating condition relative to the healthy state; the efficiency degradation data can be the decrease in the actual efficiency of the core component under the current operating condition relative to the healthy state.

[0048] In actual implementation, the embodiments of this application can use the acquired current operating data as an input vector and input it into a pre-built performance degradation simulation model. Through thermodynamic calculations, based on the thermodynamic relationship between the compressor and turbine components and the system equilibrium equation, the theoretical healthy flow rate and efficiency under the current operating condition are calculated. By comparing the actual parameters under the current operating state with the predicted parameters of the model for the same input under the baseline healthy state, the flow rate degradation data and efficiency degradation data can be obtained. The equation can be a linear function model y=ax+b, and the constraint condition is the conservation of flow rate and power.

[0049] The embodiments of this application can calculate and compare the current operating data through a performance degradation simulation model, accurately quantify the degree of degradation of the unit's flow and efficiency, and intuitively reflect the severity of the degradation through quantitative data, avoiding the deviation caused by relying solely on experience, and providing a quantitative basis for subsequent early warning condition judgment.

[0050] Optionally, in one embodiment of this application, before inputting the current operating data into the pre-built gas turbine performance degradation simulation model, the method further includes: acquiring multi-condition operating data of the target gas turbine under a preset health state, and filtering out a steady-state operating condition dataset that satisfies the preset thermodynamic equilibrium conditions from the multi-condition operating data; using the thermodynamic relationship between the components of the target gas turbine and the flow-power balance as constraints, calculating the component baseline health characteristic parameters of the target gas turbine using the steady-state operating condition dataset; determining the component characteristic diagram of the target gas turbine using the component baseline health characteristic parameters, and constructing a gas turbine performance simulation model using the component characteristic diagram, so as to obtain a gas turbine performance degradation simulation model using the gas turbine performance simulation model.

[0051] It is understood that the preset health state in the embodiments of this application can be the gas turbine in the optimal performance state, such as the stable operating state confirmed by commissioning after a new machine leaves the factory or after a major overhaul. The preset health state can be set by those skilled in the art according to the actual situation, and no specific restrictions are made here. The preset thermodynamic equilibrium condition steady-state operating condition dataset can be the operating condition that satisfies energy conservation and the balance equations of flow and power. The preset thermodynamic equilibrium condition can be set by those skilled in the art according to the actual situation, and no specific restrictions are made here.

[0052] In practical implementation, this application embodiment can collect multi-condition operating data of a gas turbine under healthy conditions after overhaul, and filter the steady-state operating condition dataset that satisfies thermodynamic equilibrium. For example, the stable operating condition data after overhaul is selected with IGV openings of 16%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100%, and 113%. Here, IGVs of 16% and 113% represent the minimum and maximum openings in the normal stable operating data, respectively. Simulation and diagnosis of the gas turbine during normal stable operation are also required; therefore, the selected operating conditions are chosen during stable operation, excluding start-up and shutdown states. 32 operating point points are selected under each IGV line. The selection principle is to first find the maximum and minimum loads during stable operation, then evenly generate 30 load values ​​between them, and select the point closest to the corresponding load from the original data. Gas turbine measurement point data under the same IGV include temperature, pressure, etc.

[0053] Furthermore, a steady-state operating condition dataset that meets the preset thermodynamic equilibrium conditions is selected from the multi-condition operating data. The reference health characteristic parameters of the target gas turbine components are calculated using the steady-state operating condition dataset, with the thermodynamic relationship between the components and the flow-power balance as constraints.

[0054] Specifically, the calculation of baseline health characteristics is based on a thermal balance calculation model where performance parameters are calculated directly from measurement data, without relying on component characteristic diagrams. Components are connected based on thermodynamic relationships, and the entire system is constrained by the balance equations of flow rate and power.

[0055] In the compressor module of the heat balance calculation model, the compressor flow rate (gc) is used as the iteration variable, and gc1 is the compressor flow rate after removing the bleed air. The performance parameters are calculated as follows: The pressure ratio is: , The ideal enthalpy at export is: , The actual enthalpy of exports is: , Efficiency is: , The power consumption is: , Power is: , In the combustion chamber module, the fuel temperature is 303.15 K. The formula for calculating the outlet temperature is: , .

[0056] Furthermore, the component characteristic diagram of the target gas turbine is determined by using the component baseline health characteristic parameters, and the gas turbine performance simulation model is constructed using the component characteristic diagram, so as to obtain the gas turbine performance degradation simulation model using the gas turbine performance simulation model.

[0057] Specifically, the natural gas used in the embodiments of this application may be composed of methane (CH4), ethane (C2H6), propane (C3H8), and butane (C4H4). 10 Nitrogen (N2) gas, the composition of substances before and after combustion is calculated based on mass and element conservation, mainly the consumption of oxygen and the generation of carbon dioxide in the combustion chamber. If the air flow rate entering the combustion chamber is g... c The natural gas flow rate is g f The changes in matter during combustion can be described by the following formula: , , , , .

[0058] To ensure that the sum of the percentages of all components is 1, subsequent calculations need to be based on the percentages of the substances. Therefore, a normalization operation is performed here, as shown in the following formula: , , , , , .

[0059] In the turbine module, the flow rate entering the turbine is the mixture of gas from the combustion chamber outlet and gas drawn from the compressor. The temperature and pressure of the gas at the turbine inlet are the temperature and pressure parameters of the mixed gas. The mixing principle of the two fluids is based on the conservation of mass and flow rate. Stream1 and Stream2 are two mixed fluids, with the following flow rate, pressure, temperature, and molar mass parameters of their components: , , According to the law of conservation of flow rate, the flow rate of the mixed gas is: , Since the flow rate at the combustion chamber outlet of the mixture is much larger than the bleed air flow rate, the pressure of the mixture is approximately equal to the pressure of the fluid at the combustion chamber outlet.

[0060] , .

[0061] The number of moles of the gas is calculated as follows: , , The temperature of the mixed gas is: , The number of moles of the same substance in the two fluids is: , In summary, the fluid parameters entering the turbine are: , The entrance enthalpy is: , The entry entropy is: , The expansion ratio is: , The actual enthalpy of exports is: , The ideal enthalpy at export is: , Efficiency is: , The function is: , Power is: , The turbine power calculation here follows the principle of power conservation, and it is also necessary to ensure the flow rate conservation of the gas turbine. The turbine outlet flow rate is: , .

[0062] Furthermore, the simulation model is implemented through modular modeling. When modeling the entire gas turbine, it is mainly divided into three key components: the compressor, the combustion chamber, and the turbine. This process is crucial for accurately simulating the operating state and performance of the gas turbine. The remaining units are simplified. A gas turbine performance simulation model is constructed using component characteristic diagrams, and then a gas turbine performance degradation simulation model is obtained from this model.

[0063] This application embodiment can generate a unit-specific component characteristic diagram and construct a performance simulation model based on the actual operating data of the target gas turbine under its own health state, through thermodynamic balance constraints and the matching relationship between components. This effectively eliminates individual performance deviations caused by manufacturing tolerances, installation differences, etc., and lays a precise initial benchmark for the subsequent construction of the performance simulation model, providing reliable model support for intelligent maintenance decisions.

[0064] Optionally, in one embodiment of this application, obtaining a gas turbine performance degradation simulation model using a gas turbine performance simulation model includes: inputting historical input parameters from the steady-state operating condition dataset of the target gas turbine into a pre-constructed gas turbine performance simulation model to obtain theoretical output data; comparing the actual output data corresponding to the historical input parameters with the theoretical output data to determine whether the gas turbine performance simulation model meets preset accuracy conditions; if the preset accuracy conditions are met, then introducing a degradation factor in the component characteristic diagram to transform the gas turbine performance simulation model into a gas turbine performance degradation simulation model.

[0065] It is understood that the historical entry parameters in this application embodiment can refer to the component entry operation parameters that have been included in the steady-state dataset under the target unit's healthy state; the preset accuracy condition can be that 95% of the data error is within ±2%, which is used to determine whether the model is reliable. The preset accuracy condition can be set by those skilled in the art according to the actual situation, and no specific restrictions are made here; the degradation factor can be understood as a coefficient that quantifies the degree of component performance degradation.

[0066] In practical implementation, this embodiment of the application can input historical input parameters from the steady-state operating condition dataset of the target gas turbine into a pre-constructed gas turbine performance simulation model, calculate component cross-sectional parameters, obtain theoretical output data, and compare it with actual output data to verify the accuracy of the simulation model. By comparing the actual output data corresponding to the historical input parameters with the theoretical output data, it is determined whether the gas turbine performance simulation model meets the preset accuracy conditions. If 95% of the data errors are within ±2%, it is determined that the preset accuracy conditions are met. A degradation factor is introduced into the component characteristic diagram, so that the model can output performance data under different degrees of degradation according to the factor size, transforming the gas turbine performance simulation model into a gas turbine performance degradation simulation model. The degradation factor is multiplied into the compressor characteristic array by a coefficient of (1 - degradation).

[0067] This application embodiment can verify the model by comparing the theoretical output of the model with actual historical data, ensuring the reliability of the benchmark model in a healthy state. A degradation factor is introduced into the verified and accurate component characteristic diagram to avoid degradation assessment deviations caused by inaccurate basic simulation. This allows the degradation model to fit the individual characteristics of the unit, accurately reflect the performance degradation law, and provide a more accurate status basis for maintenance decisions.

[0068] Optionally, in one embodiment of this application, before introducing the degradation factor, the method further includes: tracking the changing trends of the efficiency, power, and flow rate and efficiency of each component of the target gas turbine based on the operating data of the target gas turbine; determining whether the target gas turbine is under a preset performance degradation condition based on the changing trends; if it is under a preset performance degradation condition, calculating the degradation theoretical output data based on the degradation operating data of the target gas turbine and the gas turbine performance simulation model; and obtaining the degradation factor using the degradation theoretical output data and the degradation actual output data corresponding to the degradation operating data.

[0069] It is understood that in the embodiments of this application, the preset performance degradation condition can be the decrease in gas turbine efficiency and output power; the degradation operation data can be the actual operation data collected when the unit is in the degradation condition; the degradation theoretical output data can be the theoretical output data of the health state calculated by the performance simulation model under the same operating conditions; and the degradation factor can be the specific value of the degradation factor determined by calculation that best matches the model output with the actual data.

[0070] In actual implementation, the embodiments of this application can track the changing trends of the efficiency, power, and flow and efficiency of the target gas turbine and its components based on the operating data of the target gas turbine. When a continuous downward trend is observed, it can be determined that the preset performance degradation condition has been entered. If the preset performance degradation condition is in effect, the degradation operating data of the target gas turbine is input into the gas turbine performance simulation model to calculate the degradation theoretical output data. The degradation factor is obtained by using the degradation theoretical output data and the degradation actual output data corresponding to the degradation operating data.

[0071] Specifically, when a gas turbine experiences performance degradation, it is mainly manifested in a decrease in gas turbine efficiency and output power, as well as changes in the flow rate and efficiency of various components. Since the efficiency and flow rate of gas turbine components cannot be measured in real time, fault diagnosis requires analyzing the health status of each component using measurable gas turbine operating parameters. By analyzing the deviation between measured data and expected values, the correlation between various physical parameters can be determined, allowing for the deterioration trend of component performance and guiding gas turbine operation and maintenance. In simulation calculations, component efficiency and flow rate are obtained by interpolating the reduced rotational speed using the entropy of the corrected characteristic diagram, and the component's thermodynamic parameters are also calculated using these interpolated values. When component performance degrades, degradation factors for flow rate and efficiency can be defined, and these degradation factors are added to the characteristic diagram of the healthy state to obtain the characteristic diagram of the degraded system. The solution principle for the degraded system is the same as that for the healthy system. By continuously iterating the degradation factors, if the calculated parameters deviate very little from the actual parameters and also satisfy the internal equilibrium equations of the model, it indicates that the iterated degradation factors can describe the performance degradation of components in reality. This degradation factor can then serve as a standard for diagnosing gas path performance faults.

[0072] The embodiments of this application can realize dynamic tracking of the performance degradation process and accurate calibration of degradation factors. By dynamically tracking the performance change trend, the degradation initiation node can be captured in time. Then, based on the unit's own degradation data, the factors can be calculated, so that the degradation factors can accurately quantify the actual degradation degree, further enhancing the adaptability of the performance degradation simulation model to actual working conditions, and providing more realistic parameter support for subsequent maintenance timing judgment.

[0073] In step S303, based on the flow degradation data and efficiency degradation data, it is determined whether the target gas turbine meets the preset early warning conditions.

[0074] It is understood that the preset warning conditions in this application embodiment can be that when the traffic degradation data and efficiency degradation data exceed the threshold of 10%, a warning will be triggered. The preset warning conditions can be set by those skilled in the art according to the actual situation, and no specific restrictions are made here.

[0075] For example, in this application embodiment, a preset warning condition can be set as flow degradation data and efficiency degradation data exceeding a threshold. For example, the threshold can be set as flow degradation rate greater than 10% or efficiency degradation rate greater than 10%. The current flow degradation data and efficiency degradation data are compared with the threshold to determine whether the target gas turbine meets the preset warning condition.

[0076] The embodiments of this application can automatically determine from performance diagnosis to maintenance triggering, combining quantified performance degradation data with clear engineering guidelines to establish a clear and rapid decision-making mechanism, avoiding the expansion of economic losses caused by excessive performance degradation, and significantly improving the reliability and safety of unit operation.

[0077] In step S304, if the preset warning conditions are not met, the target water washing cycle of the target gas turbine is calculated using the pre-constructed water washing economic objective function, and the water washing maintenance action of the target gas turbine is performed based on the target water washing cycle.

[0078] It is understood that the objective function for water washing economy in the embodiments of this application can be a function used to solve for the optimal water washing cycle with the goal of minimizing the average cost per cycle.

[0079] In practical implementation, this embodiment can invoke a pre-built water washing economic objective function without immediate warning. This function comprehensively considers the power generation revenue loss due to performance degradation and the cost of shutdown water washing. Using currently assessed performance degradation data, unit operation plans, electricity prices, and water washing costs as input parameters, the function is iteratively calculated to determine the water washing interval that optimizes overall economics within a given plan—the target water washing cycle. Maintenance personnel then schedule water washing maintenance actions based on this calculation result. The water washing maintenance decision is made by combining the water washing time required to reach the degradation threshold with the minimum cost to determine the optimal water washing cycle.

[0080] The embodiments of this application can calculate the optimal water washing cycle that balances cost and performance through the water washing economic objective function, thereby achieving refined maintenance cycle and maximizing economic benefits. By balancing performance loss costs and maintenance action costs, maintenance costs are reduced to the minimum while ensuring unit performance, significantly improving the economic efficiency of gas turbine maintenance.

[0081] Optionally, in one embodiment of this application, before calculating the target water washing cycle of the target gas turbine using a pre-constructed water washing economic objective function, the method further includes: constructing a two-stage exponential function to characterize the performance degradation trend of the gas turbine caused by compressor fouling; modifying the pre-constructed exponential function characterizing the heat consumption degradation rate of the target gas turbine based on the performance degradation trend of the gas turbine fouling to obtain a modified exponential function; calculating the combined cycle power generation revenue loss caused by the performance degradation of the target gas turbine based on the two-stage exponential function and the modified exponential function; and constructing the water washing economic objective function by combining the combined cycle power generation revenue loss and the shutdown water washing cost.

[0082] It is understood that in the embodiments of this application, the two-stage exponential function can be a mathematical function that simulates the performance degradation law of compressor fouling; the heat consumption degradation rate exponential function can be a function that describes the increase of unit heat consumption rate with operating time; and the combined cycle power generation revenue loss can be the economic loss caused by the reduction in power generation and the increase in fuel consumption due to performance degradation.

[0083] In practical implementation, the embodiments of this application can construct a two-stage exponential function to characterize the performance degradation trend caused by compressor fouling in the target gas turbine. The performance degradation caused by compressor fouling is characterized by a dual model, and the power degradation rate is represented by a two-stage exponential function. This two-stage exponential function model accurately reflects the physical characteristics of rapid degradation in the early stage and slow degradation in the later stage of fouling.

[0084] , In this model, The item describes the initial rapid degradation phase, with parameter a controlling the degradation magnitude and parameter b controlling the degradation rate. The term describes the later, slow degradation stage, with parameter c controlling the amplitude and d controlling the rate. The maximum degradation rate is limited to 20% (0.2) to ensure that the model prediction does not exceed the compressor's safe operating range. This two-stage model accurately reflects the actual fouling process: rapid initial deposits of contaminants lead to a sharp decline in performance, while the later deposition rate slows down, resulting in stable degradation.

[0085] Furthermore, based on the performance degradation trend characteristics caused by compressor fouling, the pre-constructed exponential function characterizing the heat degradation rate of the target gas turbine is modified, resulting in a modified exponential function. The heat degradation rate is expressed using the modified exponential function: , Molecular part This is a standard exponential degradation model, where k is the maximum heat depletion degradation rate and τ is the time constant. A saturation effect term is introduced into the denominator. This model simulates the physical phenomenon of the degradation rate slowing down after scale buildup reaches a certain thickness. It overcomes the problem of traditional exponential models over-predicting degradation at high operating times and better reflects actual scale buildup kinetics.

[0086] Specifically, the combined cycle power generation revenue loss caused by the performance degradation of the target gas turbine is calculated based on a two-stage exponential function and a modified exponential function. The power generation loss C2 is the loss of reduced electricity sales profit due to the decrease in the combined cycle's maximum output capacity, and its calculation formula is as follows: , In the formula, C1 represents the power generation loss, Me represents the electricity price in yuan / (kW·h), and Mg represents the natural gas price (both calculated by volume under standard conditions) in yuan / m³. 3 η0 is the thermal efficiency of the unit under clean-state combined cycle operation at full load, expressed as %, Q is the lower heating value of natural gas, expressed as kJ / kg, and ρ is the density of natural gas, expressed as kg / m³. 3 P0 represents the unit's full-load combined cycle output (power) in clean state, in MW.

[0087] That is, it is necessary to judge the unit price of electricity per kWh and the fuel cost required to consume 1 kWh of electricity. If it is greater than 0, it means that the decrease in unit power of the unit will cause a loss of profit from selling less electricity. The total profit is the profit loss per unit kWh multiplied by the amount of electricity less generated due to the decrease in unit power during the water washing cycle T. If it is greater than 0, it means that the revenue from selling electricity cannot cover the fuel cost, that is, there will be no profit loss caused by less electricity generated due to the decrease in unit performance.

[0088] The calculation basis of the power generation efficiency loss C2 is the additional combined cycle gas consumption cost caused by the reduction of thermal efficiency under the maximum output capacity of the current unit. Its calculation formula is: , The loss item C3 of not generating electricity during water washing shutdown includes the loss of selling electricity during shutdown and the simultaneous gas consumption savings. Its calculation formula is: , In the formula, is the time for the unit to complete the turning gear water washing and drying steps during shutdown, with the unit of h. If water washing is not carried out a certain amount of electricity can be generated within the time, but generating this part of electricity also requires fuel cost. If the difference between the two is greater than 0, there will be a revenue loss caused by shutdown. If it is less than 0, there will be no loss.

[0089] The fixed cost C4 of water washing includes the detergent, electricity cost, etc. required for water washing. This part does not need to be expressed by a mathematical model and is directly recorded as a constant value. However, considering that the performance recovery after water washing is not complete, the fixed cost is equivalently amplified by a recovery efficiency factor of 95%: , The inputs of the model are the rated power (MW) of the gas turbine, the design thermal efficiency, the on-grid electricity price (yuan / kWh), the fuel price (yuan / m 3 ), the lower calorific value of the fuel (kJ / kg), the fuel density (kg / m 3 ), the water washing shutdown time (h), the fixed cost of water washing (yuan), the power degradation parameter and the heat consumption rate degradation parameter, the annual operating hours (h), and the actual operating hours (h). In the above water washing cost model, the optimization goal is to minimize the water washing cost (C) per unit time. By comparing the costs and benefits of water washing at the current operating hours (T current ) and the optimal water washing cycle (T opt ), it is judged whether it is suitable to carry out water washing currently. The specific decision logic is through the cost ratio rule: , where, when r < 1.05, water wash immediately; when 1.05 < r < 1.2, it is recommended to prepare for water washing; when r > 1.2, there is no need for water washing.

[0090] The objective function for the economic viability of water washing is constructed by combining the combined cycle power generation revenue loss and the downtime water washing cost. The formula is as follows: , Where C1 is the power generation loss, C2 is the power generation efficiency loss, C3 is the loss due to water washing shutdown and no power generation, and C4 is the fixed cost of water washing.

[0091] Specifically, the revenue loss from combined cycle power generation caused by gas turbine performance degradation can be divided into two parts: First, the reduced compressor flow area (lower flow rate) decreases the maximum output capacity of the combined cycle, resulting in a loss of profit from less electricity sales. Second, changes in blade profile and increased blade surface roughness lead to a decrease in the combined cycle's thermal efficiency, resulting in additional gas consumption costs. The cost of shutdown water washing consists of three parts: first, the cost of materials such as deionized water and detergents required for water washing maintenance; second, the loss of electricity sales due to the lack of power generation during the water washing shutdown period; and finally, the cost after deducting the gas consumption cost savings during the period of no power generation.

[0092] The embodiments of this application can accurately characterize the deterioration pattern of slow initial fouling and accelerated deterioration in the later stage through a two-stage exponential function, linking the loss of benefits with maintenance costs, so that the objective function can quantify the economic cost-effectiveness of water washing operations, providing solid theoretical and data support for calculating the economically optimal water washing cycle, and avoiding decision-making imbalances caused by simply pursuing performance optimization or cost control.

[0093] Optionally, in one embodiment of this application, a water washing economic objective function is constructed based on the basic parameters, economic parameters, and performance degradation parameters of the target gas turbine, including: obtaining the time-load mapping relationship based on the historical load data of the target gas turbine; constructing a load curve based on the mapping relationship and calculating the periodic average load rate using the load curve; obtaining the load rate of the target gas turbine at each time point based on the load curve and the periodic average load rate to determine the load fluctuation of the target gas turbine; and constructing the water washing economic objective function based on the impact of load fluctuation on the economic parameters.

[0094] It is understood that the time-load mapping relationship in the embodiments of this application can reflect the corresponding relationship of the rated load rate of the target unit in different time periods; the load curve is a curve drawn based on the mapping relationship.

[0095] In actual implementation, the embodiments of this application can construct a water washing economic objective function, the formula of which is: , Where C1 is the power generation loss, C2 is the power generation efficiency loss, C3 is the loss due to water washing shutdown and no power generation, and C4 is the fixed cost of water washing.

[0096] Specifically, the model constructs a complete economic parameter system for gas turbine water washing, including three core parameters: basic unit parameters, economic parameters, and performance degradation parameters. Basic unit parameters cover key performance indicators such as rated power and design thermal efficiency; economic parameters include cost factors such as grid-connected electricity price, fuel price, lower heating value of fuel, and fuel density; performance degradation parameters adopt a dual-parameter system, where power degradation parameters and heat consumption degradation parameters describe the characteristics of different degradation stages. In particular, since gas turbines cannot operate at rated power indefinitely, the load curve is defined as a time-load rate mapping relationship, accurately reflecting the changing characteristics of actual operating conditions. The load rate rises from 0.7 to 0.85 in the first 200 hours, to 0.92 in 400 hours, reaches 0.95 in 600 hours, peaks at 0.96 in 800 hours, and then stabilizes at 0.95. This parameter can be adjusted according to the actual operating conditions of the unit. To accurately assess the economy under actual operating conditions, the model introduces the load curve and calculates the periodic average load rate L. avg N equally spaced time points are generated in the interval [0,T]. The load factor L(t) at each time point is obtained by linear interpolation. i This design fully considers the impact of load fluctuations on performance degradation and economic efficiency, avoiding the deviation problem of using rated load in traditional models. The formula is as follows: , .

[0097] The embodiments of this application can incorporate load fluctuation factors into the water washing economic objective function, so that the function can adapt to the actual operating conditions of the unit under varying loads. The calculated water washing cycle takes into account both the characteristics of scale buildup and cost balance, and fits the operating requirements under different load conditions, further improving the practical applicability of maintenance decisions.

[0098] Optionally, in one embodiment of this application, after calculating the target water washing cycle of the target gas turbine using a pre-constructed water washing economic objective function, the method further includes: determining whether the power degradation rate of the target gas turbine reaches a preset degradation threshold based on the target water washing cycle; if the preset degradation threshold is reached, then correcting the target water washing cycle based on a preset weight.

[0099] It is understood that the preset degradation threshold in this application embodiment can be 15%, and the preset degradation threshold can be set by those skilled in the art according to the actual situation, without any specific restrictions.

[0100] For example, in this application embodiment, a dual safety mechanism is established in the model to prevent compressor surge risk caused by excessive degradation. The maximum allowable degradation rate of the gas turbine is set to 15%. After optimizing the optimal water washing cycle, the corresponding power degradation rate is checked. If it reaches 15%, the cycle needs to be readjusted. .

[0101] The embodiments of this application can use the power degradation rate as the basis for periodic correction. On the basis of optimal economy, safety constraints can be superimposed, so that the final determined water washing cycle can not only avoid unnecessary cost waste, but also prevent the unit's safe operation from being threatened by excessive power degradation, thus achieving a balance between economy and safety in maintenance decisions.

[0102] Optionally, in one embodiment of this application, after determining whether the target gas turbine meets the preset warning conditions, the method further includes: if the preset warning conditions are met, then performing a water washing maintenance operation on the target gas turbine.

[0103] In actual implementation, this embodiment can automatically generate a high-priority maintenance work order and trigger an alarm to notify the maintenance team after the preset early warning conditions are met. Simultaneously, the system can be integrated into the power plant maintenance management system to directly schedule resources and arrange for the water-washing maintenance action to be performed as quickly as possible, thus eliminating the need to enter the economic cycle calculation process and achieving a rapid response to severe performance degradation.

[0104] The embodiments of this application can directly perform water washing maintenance on the target gas turbine after determining that the target gas turbine meets the preset early warning conditions, filling the gap in the lack of emergency response procedures for maintenance, quickly alleviating the trend of performance degradation, blocking the path of fault expansion, ensuring the safe and stable operation of the unit under emergency conditions, and forming a complete intelligent maintenance system that combines routine dynamic periodic maintenance with emergency early warning response, which is of key significance for ensuring the continuous, safe and efficient operation of the unit.

[0105] Specifically, it can be combined with Figures 4 to 8 As shown, a specific embodiment is used to elaborate in detail on the working principle of the intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics in this application.

[0106] like Figure 4 As shown, the embodiments of this application include model gas path diagnosis, model characteristic fitting, and model self-solving. Model gas path diagnosis, based on input data and processed by a deteriorating gas turbine, achieves gas path diagnosis by minimizing deviation calculations, identifying gas turbine performance degradation. Model characteristic fitting represents the baseline model of the unit under healthy conditions. It performs model self-solving through characteristic coupling and thermal balance calculations, outputting theoretical prediction values. Model self-solving, with the simulation model as its core, incorporates a degradation factor and a degradation system with iterative functionality, achieving autonomous solution of performance simulations, outputting realistic performance data, and supporting quantitative analysis for subsequent maintenance decisions.

[0107] Specifically, embodiments of this application can collect multi-condition operating data of a gas turbine under healthy conditions after overhaul, and filter the steady-state operating condition dataset that satisfies thermodynamic equilibrium. Based on a thermal equilibrium calculation model, baseline health characteristics are calculated, and a linear function is used to fit the data. The characteristic diagrams of the compressor and turbine are shown below. Figure 5 and Figure 6 As shown.

[0108] Furthermore, a gas turbine performance simulation model was constructed. Operating data of the gas turbine was input, and cross-sectional parameters were calculated. Compressor outlet temperature and pressure were used as verification parameters. The percentage error between the simulation results and the actual results was calculated as follows: Figure 7 and Figure 8 As shown, 95% of the data errors are within ±2%. Based on the performance simulation model, a degradation factor is introduced into the component characteristic diagram. Real-time operating data is input to calculate compressor flow degradation and efficiency degradation. When the degradation exceeds a threshold, a maintenance warning is triggered. Here, a 10% threshold is set.

[0109] Furthermore, the input parameters for the water washing economics model are as follows: The relevant parameters for a gas turbine are: rated power of 460MW, design thermal efficiency of 58.19%, grid-connected electricity price of 0.707 yuan / kWh, fuel price of 3 yuan / m³, lower heating value of fuel of 38945.7kJ / kg, fuel density of 0.75kg / m³, water washing downtime of 6 hours, water washing fixed cost of 30,000 yuan, power degradation parameters (0.05, 0.001, 0.08, 0.0001), heat rate degradation parameters (0.12, 500), and load curve stabilizing after the first 200 hours of load increase. The annual operating hours are 8000 hours, and the actual operating hours are 1200 hours. The model calculates the current optimal water washing cycle to be 3246 hours, with a minimum cycle average cost of 18.5 yuan / hour and a 1200-hour cycle cost of 28.4 yuan / hour. Compared to the 1200-hour cycle, the annual revenue increases by 79,000 yuan when the optimal cycle is 3246 hours. Therefore, water washing is unnecessary under the current 1200-hour operation period. This application embodiment can execute gas turbine compressor water washing maintenance decisions based on a gas turbine performance simulation model.

[0110] The intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics proposed in this application can acquire the current operating data of the target gas turbine, output flow and efficiency degradation data through a performance degradation simulation model, and thus accurately determine whether the unit has triggered the warning condition. For units that have not reached the warning condition, the target water washing cycle is calculated through the water washing economic objective function and maintenance is performed. By combining real-time operating data with the simulation model, dynamic perception of the compressor performance degradation state is achieved, and the maintenance timing is determined based on the economic function, thereby improving the accuracy of water washing cycle prediction and reducing operation and maintenance costs. This method can be applied to the intelligent maintenance of gas turbines in combined cycle power plants. This solves the problems in related technologies, where the thermodynamic performance model relies on a general component characteristic diagram, which does not consider the individual performance differences of the gas turbine, resulting in a large deviation between the compressor performance evaluation results and the actual situation, failing to provide accurate judgment basis for maintenance. Furthermore, the fixed-cycle-based periodic maintenance mode leads to significant manpower and economic costs.

[0111] Next, referring to the accompanying drawings, we describe the intelligent maintenance decision-making device for gas turbines based on inverse fitting of component characteristics, according to an embodiment of this application.

[0112] Figure 9 This is a schematic diagram of the structure of the intelligent maintenance decision-making device for gas turbines based on inverse fitting of component characteristics, according to an embodiment of this application.

[0113] like Figure 9 As shown, the intelligent maintenance decision-making device 10 for gas turbines based on inverse fitting of component characteristics includes: an acquisition module 100, an input module 200, a judgment module 300, and a maintenance module 400.

[0114] The acquisition module 100 is used to acquire the current operating data of the target gas turbine.

[0115] The input module 200 is used to input the current operating data into the pre-built gas turbine performance degradation simulation model to obtain flow degradation data and efficiency degradation data.

[0116] The judgment module 300 is used to determine whether the target gas turbine meets the preset early warning conditions based on the flow degradation data and efficiency degradation data.

[0117] The maintenance module 400 is used to calculate the target water washing cycle of the target gas turbine using a pre-built water washing economic objective function if the preset early warning conditions are not met, so as to perform water washing maintenance actions on the target gas turbine based on the target water washing cycle.

[0118] Optionally, in one embodiment of this application, the intelligent maintenance decision-making device 10 for gas turbines based on inverse fitting of component characteristics further includes: a screening module, a calculation module, and a construction module.

[0119] The filtering module is used to obtain multi-condition operating data of the target gas turbine under a preset healthy state before inputting the current operating data into the pre-built gas turbine performance degradation simulation model, and to filter out the steady-state operating condition dataset that meets the preset thermodynamic equilibrium conditions from the multi-condition operating data.

[0120] The calculation module is used to calculate the baseline health characteristic parameters of the target gas turbine components using a steady-state operating condition dataset, before inputting the current operating data into the pre-built gas turbine performance degradation simulation model, with the thermodynamic relationship between the components of the target gas turbine and the flow-power balance as constraints.

[0121] The module is used to determine the component characteristic diagram of the target gas turbine using the component baseline health characteristic parameters before inputting the current operating data into the pre-built gas turbine performance degradation simulation model, and to build the gas turbine performance simulation model using the component characteristic diagram, so as to obtain the gas turbine performance degradation simulation model using the gas turbine performance simulation model.

[0122] Optionally, in one embodiment of this application, the construction module includes: a historical input unit, a comparison unit, and a conversion unit.

[0123] Among them, the historical input unit is used to input the historical input parameters in the steady-state operating condition dataset of the target gas turbine into the pre-built gas turbine performance simulation model to obtain theoretical output data; The comparison unit is used to compare the actual output data and theoretical output data corresponding to the historical input parameters to determine whether the gas turbine performance simulation model meets the preset accuracy conditions.

[0124] The conversion unit is used to introduce a degradation factor into the component characteristic diagram if preset accuracy conditions are met, thereby converting the gas turbine performance simulation model into a gas turbine performance degradation simulation model.

[0125] Optionally, in one embodiment of this application, the construction module further includes: a tracking unit, a working condition judgment unit, an output calculation unit, and a decay quantification unit.

[0126] The tracking unit is used to track the changing trends of the efficiency, power, and flow and efficiency of each component of the target gas turbine based on the operating data of the target gas turbine before the degradation factor is introduced.

[0127] The operating condition judgment unit is used to determine whether the target gas turbine is in a preset performance degradation condition based on the trend of change before introducing the degradation factor.

[0128] The output calculation unit is used to calculate the theoretical output data of the degradation based on the degradation operation data of the target gas turbine and the gas turbine performance simulation model before introducing the degradation factor, if the gas turbine is under the preset performance degradation condition.

[0129] The recession quantification unit is used to obtain the recession factor by using the recession theory output data and the actual recession output data corresponding to the recession operation data before introducing the recession factor.

[0130] Optionally, in one embodiment of this application, the intelligent maintenance decision-making device 10 for gas turbines based on inverse fitting of component characteristics further includes: an exponential function construction module, a function correction module, a loss calculation module, and an objective function construction module.

[0131] The exponential function construction module is used to construct a two-stage exponential function to characterize the performance degradation trend of the gas turbine caused by compressor fouling before calculating the target water washing cycle of the target gas turbine using a pre-constructed water washing economic objective function.

[0132] The function correction module is used to correct the pre-built exponential function characterizing the heat consumption degradation rate of the target gas turbine based on the performance degradation trend characteristics caused by the fouling of the gas compressor before calculating the target water washing cycle of the target gas turbine using the pre-built water washing economic objective function, thus obtaining the corrected exponential function.

[0133] The loss calculation module is used to calculate the combined cycle power generation revenue loss caused by the performance degradation of the target gas turbine based on a two-stage exponential function and a modified exponential function before calculating the target washing cycle of the target gas turbine using a pre-built water washing economic objective function.

[0134] The objective function construction module is used to construct an economic objective function for water washing by combining the combined cycle power generation revenue loss and the downtime water washing cost.

[0135] Optionally, in one embodiment of this application, the objective function construction module includes: a mapping unit, a load calculation unit, a load determination unit, and a function construction unit.

[0136] The mapping unit is used to obtain the time-load mapping relationship based on the historical load data of the target gas turbine.

[0137] The load calculation unit is used to construct load curves based on mapping relationships and to calculate the periodic average load rate using the load curves.

[0138] The load determination unit is used to obtain the load rate of the target gas turbine at each time point based on the load curve and the periodic average load rate, so as to determine the load fluctuation of the target gas turbine.

[0139] The function construction unit is used to construct the economic objective function for water washing based on the impact of load fluctuations on economic parameters.

[0140] Optionally, in one embodiment of this application, the intelligent maintenance decision-making device 10 for gas turbines based on inverse fitting of component characteristics further includes: a deterioration judgment module and a periodic correction module.

[0141] The degradation judgment module is used to determine whether the power degradation rate of the target gas turbine has reached the preset degradation threshold after calculating the target water washing cycle of the target gas turbine using the pre-built water washing economic objective function.

[0142] The cycle correction module is used to correct the target water washing cycle based on a preset weight after calculating the target water washing cycle of the target gas turbine using a pre-built water washing economic objective function. If the target deterioration threshold is reached, the target water washing cycle is corrected.

[0143] Optionally, in one embodiment of this application, the gas turbine intelligent maintenance decision-making device 10 based on component characteristic inverse fitting further includes an execution module.

[0144] The execution module is used to determine whether the target gas turbine meets the preset warning conditions. If the preset warning conditions are met, the execution module will perform a water washing maintenance action on the target gas turbine.

[0145] It should be noted that the foregoing explanation of the embodiment of the intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics also applies to the intelligent maintenance decision-making device for gas turbines based on inverse fitting of component characteristics in this embodiment, and will not be repeated here.

[0146] The intelligent maintenance decision-making device for gas turbines based on inverse fitting of component characteristics proposed in this application can acquire the current operating data of the target gas turbine, output flow and efficiency degradation data through a performance degradation simulation model, and thus accurately determine whether the unit has triggered the warning condition. For units that have not reached the warning condition, the target water washing cycle is calculated through the water washing economic objective function and maintenance is performed. By combining real-time operating data with the simulation model, dynamic perception of the compressor performance degradation state is achieved, and the maintenance timing is determined based on the economic function, thereby improving the accuracy of water washing cycle prediction and reducing operation and maintenance costs. It can be applied to the intelligent maintenance of gas turbines in combined cycle power plants. This solves the problems in related technologies, where the thermodynamic performance model relies on a general component characteristic diagram, which does not consider the individual performance differences of the gas turbine, resulting in a large deviation between the compressor performance evaluation results and the actual situation, failing to provide accurate judgment basis for maintenance. Furthermore, the fixed-cycle-based periodic maintenance mode leads to significant manpower and economic costs.

[0147] Figure 10A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include: The memory 1001, the processor 1002, and the computer program stored on the memory 1001 and capable of running on the processor 1002.

[0148] When the processor 1002 executes the program, it implements the intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics provided in the above embodiments.

[0149] Furthermore, electronic devices also include: Communication interface 1003 is used for communication between memory 1001 and processor 1002.

[0150] The memory 1001 is used to store computer programs that can run on the processor 1002.

[0151] The memory 1001 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.

[0152] If the memory 1001, processor 1002, and communication interface 1003 are implemented independently, then the communication interface 1003, memory 1001, and processor 1002 can be interconnected via a bus to complete communication between them. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. Buses can be categorized into address buses, data buses, control buses, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0153] Optionally, in a specific implementation, if the memory 1001, processor 1002, and communication interface 1003 are integrated on a single chip, then the memory 1001, processor 1002, and communication interface 1003 can communicate with each other through an internal interface.

[0154] The processor 1002 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.

[0155] This application also provides a non-volatile computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics.

[0156] This application also provides a computer program product storing a computer program that, when executed by a processor, implements the above-described intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics.

[0157] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0158] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0159] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0160] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0161] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, it can be implemented using any one or more of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0162] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.

[0163] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0164] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.

Claims

1. A gas turbine intelligent maintenance decision-making method based on inverse fitting of component characteristics, characterized in that, Includes the following steps: Obtain the current operating data of the target gas turbine; The current operating data is input into a pre-built gas turbine performance degradation simulation model to obtain flow degradation data and efficiency degradation data; Based on the flow rate degradation data and the efficiency degradation data, determine whether the target gas turbine meets the preset early warning conditions; If the preset warning conditions are not met, the target water washing cycle of the target gas turbine is calculated using a pre-constructed water washing economic objective function, and the water washing maintenance action of the target gas turbine is performed based on the target water washing cycle.

2. The method according to claim 1, characterized in that, Before inputting the current operating data into the pre-built gas turbine performance degradation simulation model, the following steps are also included: Acquire multi-condition operating data of the target gas turbine under a preset health state, and filter out the steady-state operating condition dataset that satisfies the preset thermodynamic equilibrium condition from the multi-condition operating data; Using the thermodynamic relationships and flow-power balance between the components of the target gas turbine as constraints, the reference health characteristic parameters of the components of the target gas turbine are calculated using the steady-state operating condition dataset; The component characteristic diagram of the target gas turbine is determined using the component baseline health characteristic parameters, and a gas turbine performance simulation model is constructed using the component characteristic diagram, so as to obtain the gas turbine performance degradation simulation model using the gas turbine performance simulation model.

3. The method according to claim 2, characterized in that, The process of obtaining the gas turbine performance degradation simulation model using the gas turbine performance simulation model includes: The historical input parameters from the steady-state operating condition dataset of the target gas turbine are input into the pre-built gas turbine performance simulation model to obtain theoretical output data; By comparing the actual output data corresponding to the historical input parameters with the theoretical output data, it is determined whether the gas turbine performance simulation model meets the preset accuracy conditions. If the preset accuracy conditions are met, a degradation factor is introduced into the component characteristic diagram to transform the gas turbine performance simulation model into a gas turbine performance degradation simulation model.

4. The method according to claim 3, characterized in that, Before the introduction of the degradation factor, it also included: Based on the operating data of the target gas turbine, track the changing trends of the target gas turbine's efficiency, power, and the flow and efficiency of each component; Based on the aforementioned trend, determine whether the target gas turbine is under a preset performance degradation condition; If the target gas turbine is in the preset performance degradation condition, then the degradation theoretical output data is calculated based on the degradation operation data of the target gas turbine and the gas turbine performance simulation model. The recession factor is obtained by using the recession theory output data and the actual recession output data corresponding to the recession operation data.

5. The method according to claim 1, characterized in that, Before calculating the target water washing cycle of the target gas turbine using a pre-built water washing economic objective function, the following steps are also included: A two-stage exponential function is constructed to characterize the performance degradation trend of the target gas turbine caused by compressor fouling. Based on the performance degradation trend characteristics caused by the fouling of the gas compressor, the pre-constructed exponential function characterizing the heat consumption degradation rate of the target gas turbine is modified to obtain the modified exponential function; The combined cycle power generation revenue loss caused by the performance degradation of the target gas turbine is calculated based on the two-stage exponential function and the modified exponential function. The economic objective function for water washing is constructed by combining the combined cycle power generation revenue loss and the downtime water washing cost.

6. The method according to claim 5, characterized in that, The construction of the water washing economic objective function based on the basic parameters, economic parameters, and performance degradation parameters of the target gas turbine includes: The time-load mapping relationship is obtained based on the historical load data of the target gas turbine. A load curve is constructed based on the mapping relationship, and the periodic average load rate is calculated using the load curve. The load rate of the target gas turbine at each time point is obtained based on the load curve and the periodic average load rate, so as to determine the load fluctuation of the target gas turbine; The water washing economic objective function is constructed based on the impact of the load fluctuation on the economic parameters.

7. The method according to claim 1, characterized in that, After calculating the target water washing cycle of the target gas turbine using a pre-built water washing economic objective function, the process further includes: Based on the target water washing cycle, determine whether the power degradation rate of the target gas turbine has reached a preset degradation threshold; If the preset degradation threshold is reached, the target washing cycle is adjusted based on the preset weight.

8. The method according to claim 1, characterized in that, After determining whether the target gas turbine meets the preset warning conditions, the method further includes: If the preset warning conditions are met, the water washing maintenance action of the target gas turbine will be performed.

9. A gas turbine intelligent maintenance decision-making device based on inverse fitting of component characteristics, characterized in that, include: The acquisition module is used to acquire the current operating data of the target gas turbine; The input module is used to input the current operating data into a pre-built gas turbine performance degradation simulation model to obtain flow degradation data and efficiency degradation data; The judgment module is used to determine whether the target gas turbine meets the preset early warning conditions based on the flow degradation data and the efficiency degradation data; The maintenance module is used to calculate the target water washing cycle of the target gas turbine using a pre-built water washing economic objective function if the preset early warning conditions are not met, so as to perform water washing maintenance actions on the target gas turbine based on the target water washing cycle.

10. An electronic device, characterized in that, include: The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the intelligent maintenance decision-making method for gas turbines based on inverse fitting of component characteristics as described in any one of claims 1-7.

Images