Gas turbine state recovery control method based on state evaluation

Abstract

A gas turbine state recovery control method based on state evaluation, comprising the following steps: step S1, collecting external environmental parameters and monitoring parameters of a gas turbine; step S2, synchronously establishing a gas turbine simulation twin model by means of parameters of a gas turbine physical entity; step S3, on the basis of an analytic hierarchy process, numerically quantifying an operating state of the gas turbine physical entity from three levels: a parameter level, a component level, and a device level; step S4, operating the gas turbine simulation twin model, inputting the external environmental parameters and related monitoring parameters, setting an objective function on the basis of the monitoring parameters, and adjusting internal performance parameters of the gas turbine simulation twin model by means of an optimization algorithm, to achieve synchronization with the gas turbine physical entity; and step S5, operating state recovery control, selecting input control parameters of the gas turbine, and when the operating state of the gas turbine is abnormal, solving for an optimal input control quantity by means of the optimization algorithm, so as to achieve recovery of the operating state of the gas turbine.

Description

A Gas Turbine Condition Recovery Control Method Based on Condition Assessment Technical Field

[0001] This invention relates to the field of gas turbine technology, and more specifically to a gas turbine state recovery control method based on state assessment. Background Technology

[0002] Gas turbines are widely used in power generation, aviation, and industrial drives, and their performance and reliability are crucial to the overall efficiency of the system. During long-term operation, gas turbines may experience performance degradation or malfunctions due to various factors. Traditional maintenance and control methods rely primarily on periodic inspections and experience-based judgment, which cannot reflect the actual operating status of the gas turbine in real time, leading to problems such as high maintenance costs, slow fault response, and low operating efficiency.

[0003] To improve the operating efficiency and reliability of gas turbines, a recovery control method based on real-time condition assessment is urgently needed. By conducting real-time assessments of the condition of each component and the overall state of the gas turbine, and comprehensively considering the external environment, operating conditions, and historical data, input control parameters can be selected and optimized to achieve real-time monitoring and intelligent control of the gas turbine. This ensures that the gas turbine can be restored and maintained in its optimal operating state under the premise of economic efficiency, ease of operation, and environmental compliance. Summary of the Invention

[0004] The purpose of this invention is to provide a gas turbine state recovery control method based on state assessment. By real-time assessment of the state of each component and the overall state of the gas turbine, the invention enables real-time monitoring and intelligent control of the gas turbine, ensuring that the gas turbine can be restored and maintained in its optimal operating state under the premise of economic efficiency, ease of operation and environmental compliance.

[0005] The objective of this invention is achieved through the following technical solution:

[0006] A gas turbine state recovery control method based on state assessment, comprising the following steps:

[0007] Step S1: Collect and monitor external environmental parameters and monitoring parameters of the gas turbine;

[0008] Step S2: Synchronously establish a simulation twin model of the gas turbine using the parameters of the physical entity of the gas turbine;

[0009] Step S3: Based on the tomographic analysis method, the operating status of the gas turbine physical entity is evaluated by numerically quantifying the operating status of the gas turbine from three levels: parameter level, component level, and equipment level.

[0010] Step S4: Run the gas turbine simulation twin model, input external environmental parameters and relevant monitoring parameters, set the objective function with the monitoring parameters, and adjust the internal performance parameters of the gas turbine simulation twin model through optimization algorithm to achieve synchronization with the physical entity of the gas turbine;

[0011] Step S5: Operation status recovery control. Select the input control parameters of the gas turbine. When the gas turbine operation status is abnormal, the optimal input control quantity is obtained by optimization algorithm to realize the recovery of the gas turbine operation status.

[0012] The external environmental parameters of the gas turbine in step S1 include: ambient temperature, ambient pressure, and speed; the monitored parameters include: compressor inlet temperature, compressor inlet pressure, turbine outlet pressure, turbine outlet temperature, and fuel flow rate.

[0013] The method for creating a gas turbine simulation twin model in step S2 is to establish a gas turbine simulation model using the volumetric inertia method, and to simulate gas turbine performance degradation and faults by introducing performance degradation mechanisms and fault factors.

[0014] The parameter-level state assessment in step S3 consists of three parts. The first part establishes a benchmark model for the monitoring parameters and calculates the normal values ​​of the monitoring parameters under different states using regression prediction. The second part calculates the deviation between the normal values ​​and the actual values ​​and obtains the threshold range of the monitoring parameters using probability density statistics. The third part transforms the parameter assessment result into a number between 0 and 1 using a membership function. The selection of the membership function references trapezoidal and triangular membership functions. The specific calculation formula is as follows, and the parameter-level state assessment result is obtained.

[0015] Where, a and e are the lower and upper fault thresholds of the parameter, respectively; b and e are the lower and upper abnormal thresholds of the parameter, respectively; and c is the baseline value obtained by modeling the baseline value of the parameter.

[0016] In step S3, the component-level state assessment is performed using a radar chart method, where the area of ​​a polygon represents the current state of the component, and the state assessment results for each component are calculated.

[0017] Suppose we have a polygon where the distances from each vertex to the center point are r1, r2, ..., r. n And the angle of each vertex is 2π / n radians; the radar chart is calculated as follows:

[0018] Where n is the number of vertices, i.e., the number of monitoring parameters contained in each component; r nS1 represents the distance from each vertex to the center point, i.e., the evaluation result of each monitoring parameter; S1 represents the current polygon area of ​​the component; Smax represents the polygon area of ​​the component when the theoretical state is best; Acomp represents the state evaluation result of each component.

[0019] In step S3, the device-level state assessment integrates the state assessment results of various components through a Bayesian network to perform an overall state assessment of the device. For each node Xi in the Bayesian network, its joint probability density distribution can be expressed as:

[0020] Where Xi represents the i-th node, which includes the gas turbine and all its components to be evaluated; Pa(Xi) represents the set of parent nodes of Xi;

[0021] The internal performance parameters in step S4 refer to the internal calculation parameters of the gas turbine simulation twin model, which include flow correction factor, total pressure recovery coefficient correction factor, and efficiency correction factor, etc.

[0022] In step S4, the objective function is set based on the monitored parameters, and the internal performance parameters of the gas turbine simulation twin model are adjusted through an optimization algorithm to achieve synchronization with the physical entity of the gas turbine. Specifically, this includes:

[0023] The gas turbine collects monitoring parameters via sensors, including speed, power, exhaust temperature, and compressor outlet pressure; the calculation error c for each target monitoring parameter is... i The simulation calculation value y of the model i The actual operating parameter value yi of the gas turbine is expressed as follows:

[0024] The digital twin process of a gas turbine is described as an optimization problem that solves a set of component performance parameters to minimize the calculation error of the target monitoring parameters. The objective function is defined as a function of the calculation error of each selected target monitoring parameter.

[0025] In the formula: m is the number of target monitoring parameters; wi is the weighting coefficient of each target monitoring parameter. n is the number of performance parameters; x i For performance parameters; x k,max and x k,min These are the upper and lower limits of the correction factor for the corresponding performance parameter, respectively.

[0026] The optimization algorithm specifically includes: a particle swarm optimization algorithm based on particle exclusion zones and Lévy flight, which balances traditional PSO updates and Lévy flight updates through a probabilistic mechanism, sets particle exclusion zones to redistribute particles, and initially redistributes particles located in the exclusion zone to the position of the previous particle. During the iteration process, particles entering the exclusion zone retain the position of the previous iteration.

[0027] The selection of input control parameters for the gas turbine in step S4 specifically includes: the state recovery control of the gas turbine needs to comprehensively consider the state assessment results of each component, environmental conditions, operating conditions, historical data, economy, operability, and environmental protection; by selecting appropriate input control parameters, it is ensured that the gas turbine can resume normal operation under the premise of being economical and efficient, easy to operate, and environmentally compliant.

[0028] In step S5, when the gas turbine operating state becomes abnormal, the optimal input control quantity is obtained by solving an optimization algorithm to restore the gas turbine operating state.

[0029] Specifically, this includes adjusting the input control quantities to maximize the gas turbine operating status assessment result, calculated as follows: Obj=min{1-Assessment[gasturbin(ΔIN1,ΔIN2,...,ΔIN n )]}

[0030] In the formula, gasturbine is the gas turbine twin model, with inputs being the gas turbine input control variables and outputs being the real-time monitoring parameters of the gas turbine; Assessment is the operating condition evaluation model, with inputs being the gas turbine monitoring parameters and outputs being the current gas turbine condition evaluation result; ΔIN n This is the input control quantity.

[0031] The beneficial effects of this invention are as follows:

[0032] A gas turbine simulation twin model was established using the volumetric inertia method. This model incorporates performance degradation mechanisms and fault factors to simulate gas turbine performance degradation and faults. An optimization algorithm was used to adjust the internal performance parameters of the gas turbine simulation twin model, synchronizing them with the physical gas turbine entity. This achieved a virtual-real integration, enhancing the practicality and reliability of the simulation model. The twin mechanism fully considers the direct reflection of performance parameters on the gas turbine's operating state. State assessment was conducted at three levels: parameter level, component level, and equipment level, delving deeper and comprehensively covering all aspects of the gas turbine to ensure the comprehensiveness and reliability of the assessment results. The gas turbine control recovery parameters were clearly defined. When an abnormal gas turbine operating state occurs, the optimal input control quantity was solved using an optimization algorithm, with the input control quantity as the independent variable and the state assessment result as the dependent variable, thus optimizing the gas turbine's operating state. Attached Figure Description

[0033] The present invention will now be described in further detail with reference to the accompanying drawings and specific implementation methods.

[0034] Figure 1 is a schematic diagram of the steps of a gas turbine state recovery control method based on state assessment according to the present invention;

[0035] Figure 2 is a flowchart of a gas turbine state recovery control method based on state assessment according to the present invention;

[0036] Figure 3 is a schematic diagram of the gas turbine state recovery result of the present invention. Detailed Implementation

[0037] The present invention will now be described in further detail with reference to the accompanying drawings.

[0038] As shown in Figures 1 to 3, in order to achieve the technical effect of "real-time monitoring and intelligent control of the gas turbine by real-time evaluation of the status of each component and the overall status of the gas turbine, and to ensure that the gas turbine can be restored and maintained in its optimal operating state under the premise of economic efficiency, ease of operation and environmental compliance", the steps and functions of the gas turbine status recovery control method based on status evaluation are explained in detail below.

[0039] As shown in Figure 1, a gas turbine state recovery control method based on state assessment includes the following steps:

[0040] Step S1: Data acquisition, collecting external environmental parameters and monitoring parameters of the gas turbine;

[0041] In practice, the gas turbine control system data acquisition unit and the sensors installed on the gas turbine are used to dynamically acquire and monitor the external environmental parameters and monitoring parameters of the gas turbine.

[0042] Taking a certain type of three-shaft gas turbine as an example, the collected external environmental parameters and monitoring parameters mainly include: ambient temperature, ambient pressure, low-pressure compressor inlet temperature, low-pressure compressor inlet pressure, low-pressure compressor outlet temperature, low-pressure compressor outlet pressure, high-pressure compressor outlet temperature, high-pressure compressor outlet pressure, low-pressure turbine outlet temperature, low-pressure turbine outlet temperature, power turbine outlet temperature, power turbine outlet pressure, low-pressure turbine speed, high-pressure turbine speed, power turbine speed, fuel flow rate, throttle opening, etc.

[0043] Step S2: Establish a simulation model by synchronously establishing a simulation twin model of the gas turbine using the parameters of the physical entity of the gas turbine;

[0044] In a specific embodiment, a gas turbine simulation model is established using the volumetric inertia method. Taking a certain type of three-shaft gas turbine gas circuit components as an example, it includes a low-pressure compressor, a high-pressure compressor, a combustion chamber, a high-pressure turbine, a low-pressure turbine, a power turbine, etc.

[0045] Step S3: Operational status assessment. Based on the analytic hierarchy process (AHP), the operational status of the gas turbine is assessed by numerically quantifying the physical entity of the gas turbine at three levels: parameter level, component level, and equipment level.

[0046] In a specific embodiment, a baseline model for monitoring parameters is established through a long short-term memory network. The input parameters of the baseline model are ambient temperature, ambient pressure, and calculated torque. The normal values ​​of the monitoring parameters under different conditions are calculated by a regression prediction method based on LSTM.

[0047] In specific examples, the parameters are normalized using the maximum-minimum method. i,j The original data, Let be the i-th normalized value of parameter j. and The maximum and minimum values ​​of parameter j are given. Data preprocessing normalizes the data to the range [0,1] to reduce the influence of operating conditions and environment.

[0048] In a specific embodiment, historical data of the input window size is used for prediction. Let the window length be n. Therefore, the two-dimensional input dimension of the constructed three input parameters is (3, n), and the corresponding output dimension is (1, p). That is, using historical data of n steps, the trend is predicted p steps ahead. Here, n = 3, p = 1. This data is input into the LSTM model to train the LSTM baseline prediction model, enabling the prediction of the baseline value for the next step.

[0049] In this specific embodiment, the baseline model consists of two LSTM layers and one fully connected layer. Low-pressure turbine exhaust temperature time-series features are extracted from the hidden layers of the LSTM, and then the fully connected layer performs regression from the features to the predicted values. The model employs the tanh activation function, L2 regularization (coefficient 0.001), Adam optimizer (learning rate 0.01), and MSE loss function, with 300 training iterations.

[0050] In a specific embodiment, the threshold range of the monitoring parameters is calculated by the kernel density estimation method. The threshold range can be set by confidence intervals, wherein the upper and lower limit abnormal thresholds are 95% confidence intervals and the upper and lower limit fault thresholds are 99% confidence intervals.

[0051] In a specific embodiment, the parameter evaluation result is transformed into a number between 0 and 1 through a membership function. The selection of the membership function is based on trapezoidal and triangular membership functions. The specific calculation formula is as follows, and the parameter-level state evaluation result is calculated.

[0052] Where a and e are the lower and upper fault thresholds of the parameter, respectively; b and e are the lower and upper abnormal thresholds, respectively; and c is the baseline value obtained by modeling the baseline value of the parameter.

[0053] In a specific embodiment, the gas turbine comprises four components, represented by four vertices on a radar chart. The distances from each vertex to the center point are r1, r2, r3, and r4, respectively, and the angle of each vertex is 90 degrees. The radar chart calculation is as follows.

[0054] In a specific embodiment, the gas turbine is divided into four components: gas path, fuel system, lubricating oil system, and cooling system. The Bayesian network contains five nodes, and its joint probability density distribution can be expressed as: P(T,G,O,F,C)=P(TG,O,F,C)·P(G)·P(O)·P(F)·P(C)

[0055] Where T represents the gas turbine, and G, O, F, and C represent the four components: gas path, fuel system, lubricating oil system, and cooling system, respectively.

[0056] Step S4: Run the gas turbine simulation twin model, input external environmental parameters and relevant monitoring parameters, set the objective function with the monitoring parameters, and adjust the internal performance parameters of the gas turbine simulation twin model through optimization algorithm to achieve synchronization with the physical entity of the gas turbine;

[0057] In a specific embodiment, taking the gas path component as an example, the internal performance parameters include: low-pressure compressor flow correction factor, low-pressure compressor efficiency correction factor, high-pressure compressor flow correction factor, high-pressure compressor efficiency correction factor, combustion chamber total pressure recovery coefficient correction factor, high-pressure turbine flow correction factor, high-pressure turbine efficiency correction factor, low-pressure turbine flow correction factor, low-pressure turbine efficiency correction factor, power turbine flow correction factor, and power turbine efficiency correction factor.

[0058] In a specific embodiment, the optimization algorithm has a particle swarm size N of 30, an iteration count iter of 500, a search space dimension dim of 10, an inertia weight w of 0.7, a cognitive coefficient c1 of 1.2, a social coefficient c2 of 1.5, and a Levy flight stride RL of 0.15*levy(N,dim,1.5), where 1.5 is the β parameter of the Levy distribution.

[0059] Step S5: Operation status recovery control. Select the input control parameters of the gas turbine. When the gas turbine operation status is abnormal, the optimal input control quantity is obtained by optimization algorithm to realize the recovery of the gas turbine operation status.

[0060] Specifically, this includes adjusting the input control quantities to maximize the gas turbine operating status assessment result, calculated as follows: Obj=min{1-Assessment[gasturbin(ΔIN1,ΔIN2,...,ΔIN n )]}

[0061] In the formula, gasturbine is the gas turbine twin model, with inputs being the gas turbine input control variables and outputs being the real-time monitoring parameters of the gas turbine; Assessment is the operating condition evaluation model, with inputs being the gas turbine monitoring parameters and outputs being the current gas turbine condition evaluation result; ΔIN n For input control quantity;

[0062] In a specific embodiment, the control speed and intake air flow rate are selected as the input control quantities.

[0063] In a specific embodiment, since the speed range of the gas turbine power turbine is between 3000 r / min and 3600 r / min, the upper and lower limits of the variation of the gas turbine control speed parameter are determined to be [-600, 600], in r / min. Due to the limitations of the adjustable guide vanes, the variation of the intake flow rate should be controlled within 10%. Under the 0.95 operating condition, the intake flow rate is around 80 kg / s, and the upper and lower limits of the variation of the intake flow rate parameter are determined to be [-6, 6], in kg / s.

[0064] In specific embodiments, the recovery states achievable under different fault conditions vary. Fault 5 showed the best recovery effect, recovering from an initial health level of 0.5846 to 0.9795. Fault 15 showed the worst recovery effect, recovering from an initial health level of 0.4602 to 0.4921, only slightly improving gas turbine performance. Overall, the recovery results improved under all different conditions.

[0065] In a specific embodiment, the optimized input control values ​​are shown in the table below:

[0066] Table 5.3 Fault Status Input Control Quantities

[0067] It should be noted that the steps shown in the above process or in the flowchart of the accompanying figures can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0068] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A gas turbine state recovery control method based on state assessment, characterized in that: The method includes the following steps: Step S1: Collect and monitor external environmental parameters and monitoring parameters of the gas turbine; Step S2: Synchronously establish a simulation twin model of the gas turbine using the parameters of the physical entity of the gas turbine; Step S3: Based on the tomographic analysis method, the operating status of the gas turbine physical entity is numerically quantified from three levels: parameter level, component level, and equipment level, to evaluate the operating status of the gas turbine. Step S4: Run the gas turbine simulation twin model, input external environmental parameters and relevant monitoring parameters, set the objective function with the monitoring parameters, and adjust the internal performance parameters of the gas turbine simulation twin model through optimization algorithm to achieve synchronization with the physical entity of the gas turbine; In step S4, the objective function is set based on the monitored parameters, and the internal performance parameters of the gas turbine simulation twin model are adjusted through an optimization algorithm to achieve synchronization with the physical entity of the gas turbine. Specifically, this includes: The gas turbine collects monitoring parameters via sensors, including speed, power, exhaust temperature, and compressor outlet pressure; the calculation error c for each target monitoring parameter is... i The simulation calculation value y of the model i ′ and actual gas turbine operating parameter values ​​y i Represented as: The digital twin process of a gas turbine is described as an optimization problem that solves a set of component performance parameters to minimize the calculation error of the target monitoring parameters. The objective function is defined as a function of the calculation error of each selected target monitoring parameter. In the formula: m is the number of target monitoring parameters; w i These are the weighting coefficients for the monitoring parameters of each target. n is the number of performance parameters; x i For performance parameters; x k,max and x k,min These are the upper and lower limits of the correction factor for the corresponding performance parameter, respectively. Step S5: Operation status recovery control. Select the input control parameters of the gas turbine. When the gas turbine operation status is abnormal, the optimal input control quantity is obtained by optimization algorithm to realize the recovery of the gas turbine operation status. In step S5, when the gas turbine operating state becomes abnormal, the optimal input control quantity is obtained by solving an optimization algorithm to restore the gas turbine operating state. Specifically, this includes adjusting the input control quantities to maximize the gas turbine operating status assessment results, as calculated below: Obj=min{1-Assessment[gasturbin(ΔIN1,ΔIN2,…,ΔIN n )]}; In the formula, gasturbin is the gas turbine twin model, with inputs being the gas turbine input control variables and outputs being the real-time monitoring parameters of the gas turbine; Assessment is the operating condition assessment model, with inputs being the gas turbine monitoring parameters and outputs being the current gas turbine condition assessment result; ΔIN n This is the input control quantity.

2. The gas turbine state recovery control method based on state assessment according to claim 1, characterized in that: The external environmental parameters of the gas turbine in step S1 include: ambient temperature, ambient pressure, and rotational speed; the monitored parameters include: compressor inlet temperature, compressor inlet pressure, turbine outlet pressure, turbine outlet temperature, and fuel flow rate.

3. The gas turbine state recovery control method based on state assessment according to claim 1, characterized in that: The method for creating a gas turbine simulation twin model in step S2 involves establishing a gas turbine simulation model using the volumetric inertia method. By introducing performance degradation mechanisms and fault factors, the simulation of gas turbine performance degradation and faults is achieved.

4. The gas turbine state recovery control method based on state assessment according to claim 1, characterized in that: The parameter-level state assessment in step S3 consists of three parts. The first part is to establish a benchmark model for monitoring parameters and calculate the normal values ​​of monitoring parameters under different states through regression prediction. The second part calculates the deviation between the normal value and the actual value, and obtains the threshold range of the monitoring parameter by using probability density statistics. The third part calculates the parameter-level state evaluation results using the membership function.

5. The gas turbine state recovery control method based on state assessment according to claim 1, characterized in that: In step S3, the component-level state assessment is performed using a radar chart method, where the area of ​​a polygon represents the current state of the component, and the state assessment results for each component are calculated. Suppose we have a polygon where the distances from each vertex to the center point are r1, r2, ..., r. n And the angle of each vertex is 2π / n radians; the radar chart is calculated as follows: Where n is the number of vertices, i.e., the number of monitoring parameters contained in each component; r n S1 represents the distance from each vertex to the center point, which is the evaluation result of each monitoring parameter; S1 represents the current polygon area of ​​the component; Smax represents the polygon area of ​​the component when the theoretical state is best; and Acomp represents the state evaluation result of each component.

6. The gas turbine state recovery control method based on state assessment according to claim 1, characterized in that: In step S3, the device-level status assessment integrates the status assessment results of various components through a Bayesian network to perform an overall status assessment of the device.

7. The gas turbine state recovery control method based on state assessment according to claim 1, characterized in that: In step S4, the internal performance parameters refer to the internal calculation parameters of the gas turbine simulation twin model, which include the flow correction factor, the total pressure recovery coefficient correction factor, and the efficiency correction factor.

8. The gas turbine state recovery control method based on state assessment according to claim 1, characterized in that: The selection of input control parameters for the gas turbine in step S4 specifically includes: the state recovery control of the gas turbine needs to comprehensively consider the state assessment results of each component, environmental conditions, operating conditions, historical data, economy, operability and environmental protection.

Images