An accident early warning decision-making method for gas turbine power plants based on integrated analysis of potential hazard data

Abstract

The present invention relates to the technical field of safety monitoring of gas turbine power plants, and specifically discloses an accident early warning decision-making method for gas turbine power plants based on integrated analysis of hidden danger data. The temperature distribution and cooling efficiency of the combustion chamber wall surface are monitored in real time through a high-precision sensor network, and the collected data is deeply analyzed by using fast Fourier transform and Haar wavelet transform to evaluate the damage of the combustion chamber wall surface material and the health status of the cooling system. Combining with the random forest model to process the comprehensive feature vector, accurately judge the safety hidden danger level during the operation of the combustion chamber. Once a high-risk situation is detected, the system immediately activates an intelligent emergency plan and automatically adjusts measures such as the cooling water flow rate, fan speed, or activates additional cooling devices to prevent the hidden danger from further deteriorating.

Description

Technical Field

[0001] The present invention relates to the technical field of safety monitoring of gas turbine power plants, and particularly relates to an accident early warning decision-making method for gas turbine power plants based on integrated analysis of hidden danger data. Background Technique

[0002] As an important part of the modern power system, the operation safety and stability of gas turbine power plants have a crucial impact on the reliability of the power grid and environmental protection. The combustion chamber is one of the core components of gas turbine power plants. It works under high temperature and high pressure environments for a long time, and is prone to thermal stress damage and equipment failures due to reasons such as temperature fluctuations and decreased cooling efficiency, which may further lead to serious safety accidents. Traditional monitoring methods mainly rely on regular manual inspections and simple sensor data collection, making it difficult to achieve real-time and comprehensive monitoring of the combustion chamber state. With the development of industrial Internet of Things technology and big data analysis methods, by integrating multiple sensing devices and advanced data analysis algorithms, it is possible to more accurately evaluate the damage of the combustion chamber wall material and the health status of the cooling system, thus effectively preventing potential safety hazards.

[0003] The existing technology has the following deficiencies:

[0004] The existing technology lacks real-time monitoring of the temperature distribution and cooling efficiency of the combustion chamber wall through an integrated high-precision sensor network, and the use of advanced signal processing technologies (such as fast Fourier transform and Haar wavelet transform) to deeply analyze the collected data to accurately evaluate the damage of the combustion chamber wall material and the health status of the cooling system. By combining the random forest model to analyze the comprehensive feature vector, it is possible to accurately judge the safety hazard level during the operation of the combustion chamber. Once a high-risk situation is detected, the system will immediately activate an intelligent emergency plan and automatically adjust measures such as the cooling water flow rate, fan speed, or activate additional cooling devices to quickly reduce the temperature inside the combustion chamber and prevent the hidden danger from deteriorating further. Summary of the Invention

[0005] The purpose of the present invention is to provide an accident early warning decision-making method for gas turbine power plants based on integrated analysis of hidden danger data to solve the problems in the above background.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] An accident early warning decision-making method for gas turbine power plants based on integrated analysis of hidden danger data, comprising the following steps:

[0008] S1: During the monitoring period of the gas turbine power plant, real-time monitor the temperature distribution and cooling efficiency of the combustion chamber wall;

[0009] S2: Evaluate the damage of the combustion chamber wall material according to the degree of change in the temperature distribution of the combustion chamber wall;

[0010] S3: Determine whether the working state of the cooling system is stable according to the change range of the cooling efficiency of the combustion chamber;

[0011] S4: Conduct a comprehensive analysis of the temperature distribution on the wall surface of the combustion chamber and the cooling efficiency of the combustion chamber. According to the analysis results, determine the safety hazard level during the operation of the combustion chamber, including high-risk level, medium-risk level, and low-risk level;

[0012] S5: If it is determined that the safety hazard level during the operation of the combustion chamber is at a high-risk level, immediately activate the emergency plan, adjust the combustion mode, and increase additional cooling measures.

[0013] As a further solution of the present invention: Evaluate the damage of the combustion chamber wall material according to the change degree of the temperature distribution on the combustion chamber wall surface, specifically including:

[0014] During the monitoring period of the gas turbine power plant, divide the combustion chamber wall surface into several regions, collect the temperature data of the combustion chamber wall surface in each region respectively, analyze the fluctuation degree of the temperature data in each region of the combustion chamber wall surface respectively, and calculate the thermal stress distribution characteristic value of the combustion chamber wall surface according to the abnormal distribution of the temperature data. Determine whether the thermal stress distribution characteristic value of the combustion chamber wall surface is greater than or equal to the preset threshold. If so, there is damage to the combustion chamber wall material; if not, there is no damage to the combustion chamber wall material.

[0015] As a further solution of the present invention: The process of obtaining the thermal stress distribution characteristic value is as follows:

[0016] Obtain the temperature measurement value at the position and time in each region, where represents the position coordinate on the combustion chamber wall surface, and represents time;

[0017] Preprocess the obtained temperature data, including removing outliers and smoothing;

[0018] Apply the fast Fourier transform algorithm to the temperature time series in each region to obtain the frequency domain representation; calculate the modulus square of the frequency domain expression obtained after conversion by the fast Fourier transform algorithm to obtain the energy of each frequency component;

[0019] Calculate the thermal stress at the corresponding position by multiplying the elastic modulus of the material by its coefficient of thermal expansion and the product of the energy of all frequency components at the corresponding position;

[0020] For each region divided on the combustion chamber wall surface, calculate the thermal stress distribution characteristic value of the entire wall surface according to its average thermal stress value.

[0021] As a further solution of the present invention: judging whether the working state of the cooling system is stable according to the change range of the cooling efficiency of the combustion chamber, specifically including:

[0022] During the monitoring period of the gas turbine power plant, the cooling efficiency of the combustion chamber is monitored in real time. According to the change range of the cooling efficiency of the combustion chamber, the abnormal change characteristic value of the cooling efficiency is calculated, and it is judged whether the abnormal change characteristic value of the cooling efficiency is greater than or equal to the preset threshold. If so, it is judged that the working state of the cooling system is stable; if not, it is judged that the working state of the cooling system is unstable.

[0023] As a further solution of the present invention: the obtaining process of the abnormal change characteristic value of the cooling efficiency is as follows:

[0024] Obtain the cooling efficiency measurement value at each monitoring period of time;

[0025] Decompose the cooling efficiency time series into wavelet coefficients of different scales through Haar wavelet transform;

[0026] Take the detail coefficients as the main fluctuation components;

[0027] Calculate the sum of the squares of all detail coefficients to obtain the total energy of the detail coefficients at the corresponding scale, obtain the detail coefficients of the highest frequency, and calculate the ratio of the energy of the detail coefficients of the highest frequency to the average value of the energies of the detail coefficients at all scales to obtain the abnormal change characteristic value of the cooling efficiency.

[0028] As a further solution of the present invention: comprehensively analyzing the temperature distribution of the wall surface of the combustion chamber and the cooling efficiency of the combustion chamber, specifically including:

[0029] Obtain the thermal stress distribution characteristic value and the abnormal change characteristic value of the cooling efficiency of the combustion chamber during the monitoring period of the gas turbine power plant, construct the thermal stress distribution characteristic value and the abnormal change characteristic value of the cooling efficiency into a comprehensive characteristic vector as the input of the machine learning model, the output of the model is the safety hazard score, and determine the safety hazard level of the combustion chamber during operation according to the safety hazard score output by the model. The machine learning model is a random forest model.

[0030] As a further solution of the present invention: the training process of the machine learning model is as follows:

[0031] Obtain multiple groups of historical thermal stress distribution characteristic values, abnormal change characteristic values of cooling efficiency and safety hazard scores of the combustion chamber as the training data set, and train the random forest model. During the training process, the random forest determines the finally output safety hazard score by constructing multiple decision trees and voting on the results of each tree.

[0032] As a further solution of the present invention: The determination of the safety hazard level during the operation of the combustion chamber specifically includes:

[0033] Compare the safety hazard score of the combustion chamber of the gas turbine power plant during operation with a preset first threshold. If the safety hazard score is greater than or equal to the preset first threshold, it is recorded as a high-risk level. If the safety hazard score is less than the preset first threshold and greater than the preset second threshold, it is recorded as a medium-risk level. If the safety hazard score is less than or equal to the safety hazard score, it is recorded as a low-risk level.

[0034] As a further solution of the present invention: If it is determined that the safety hazard level of the combustion chamber during operation is a high-risk level, immediately initiate an emergency plan, which specifically includes:

[0035] If it is determined that the safety hazard level of the combustion chamber during operation is a high-risk level, the system will immediately initiate an early warning mechanism, send notifications to the operators and the emergency response team, adjust the cooling water flow rate, fan speed, and activate additional cooling devices to rapidly reduce the temperature inside the combustion chamber.

[0036] Advantages of the present invention:

[0037] (1) By integrating advanced sensing technologies and signal processing methods, the present invention realizes real-time and high-precision monitoring of the temperature distribution on the wall of the combustion chamber and the cooling efficiency of the gas turbine power plant. The fast Fourier transform is used to analyze the temperature data on the wall of the combustion chamber, and the spectral characteristics are extracted to evaluate the thermal stress distribution and its impact on material damage. At the same time, the Haar wavelet transform is used to decompose the time series of the cooling efficiency to identify local abnormal changes, ensuring that the health status of the cooling system is comprehensively monitored. Based on these in-depth analysis results, a comprehensive feature vector is constructed and input into the random forest model. This model accurately judges the safety hazard level during the operation of the combustion chamber through the voting mechanism of multiple decision trees. Once a high-risk situation is detected, the system immediately initiates an intelligent emergency plan, automatically adjusts the cooling water flow rate, fan speed, or activates additional cooling measures to rapidly reduce the temperature inside the combustion chamber and prevent the potential hazard from deteriorating further. This full-process closed-loop management from real-time data acquisition, advanced signal processing, intelligent data analysis to automated emergency response not only significantly improves the safety and reliability of the gas turbine power plant, but also effectively prevents major safety accidents caused by equipment failures, safeguards the safety of personnel and equipment, and provides an efficient, flexible and adaptive technical solution for industrial safety. In addition, the system ensures long-term stable operation by continuously optimizing the control strategy, reduces the maintenance cost, extends the service life of the equipment, and has important practical application value and broad promotion prospects.

[0038] (2) The present invention can not only accurately identify potential safety hazards at an early stage, but also achieve efficient and flexible emergency response and optimization control through an integrated intelligent decision-making support module. When a high-risk situation is detected, the system can automatically adjust measures such as the cooling water flow rate, fan speed, or activate additional cooling devices to quickly reduce the temperature inside the combustion chamber and effectively prevent the further expansion of potential hazards. The system has excellent adaptability and can dynamically adjust parameter settings according to real-time working conditions to ensure the best cooling effect and system stability. Compared with traditional manual monitoring and adjustment methods, the automated solution provided by the present invention significantly shortens the response time and greatly improves the ability and efficiency to handle emergencies. In addition, the built-in continuous monitoring and feedback mechanism of the system can continuously optimize the cooling strategy to ensure the long-term efficient operation of the cooling system, thereby reducing maintenance costs and extending the service life of the equipment. Through this full-process closed-loop management from data collection, intelligent analysis to dynamic adjustment, the present invention provides an efficient, reliable and highly adaptable technical means for industrial safety. Its advanced algorithms and intelligent design not only improve the safety and reliability of gas turbine power plants, but also have broad applicability and promotion value, and are applicable to a variety of complex industrial environments, providing solid technical support for ensuring the safe and stable operation of key equipment. Brief Description of the Drawings

[0039] The present invention will be further described below in conjunction with the accompanying drawings.

[0040] Figure 1 It is a specific step flow block diagram of an accident early warning decision-making method for a gas turbine power plant based on integrated analysis of potential hazard data of the present invention. Detailed Embodiments

[0041] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0042] Please refer to Figure 1 As shown, the present invention is an accident early warning decision-making method for a gas turbine power plant based on integrated analysis of potential hazard data, including the following steps:

[0043] S1: During the monitoring period of the gas turbine power plant, the temperature distribution and cooling efficiency of the combustion chamber wall are monitored in real time;

[0044] S2: Evaluate the damage of the combustion chamber wall material according to the degree of change in the temperature distribution of the combustion chamber wall;

[0045] S3: Determine whether the working state of the cooling system is stable according to the change range of the cooling efficiency of the combustion chamber;

[0046] S4: Conduct a comprehensive analysis of the temperature distribution on the wall surface of the combustion chamber and the cooling efficiency of the combustion chamber. According to the analysis results, determine the safety hazard level during the operation of the combustion chamber, including high-risk level, medium-risk level, and low-risk level;

[0047] S5: If it is determined that the safety hazard level during the operation of the combustion chamber is at the high-risk level, immediately activate the emergency plan, adjust the combustion mode, and increase additional cooling measures.

[0048] In S1, during the monitoring period of the gas turbine power plant, the temperature distribution and cooling efficiency of the combustion chamber wall surface are monitored in real time, specifically including:

[0049] During the monitoring period of the gas turbine power plant, first, the temperature distribution on the wall surface of the combustion chamber is monitored in real time. This step is achieved through a high-precision temperature sensor network deployed at key positions of the combustion chamber. These sensors can continuously collect temperature data at different points on the combustion chamber wall surface. The acquisition of temperature data not only includes the absolute temperature value but also involves the change trend of temperature over time and the temperature difference between different regions. To ensure the accuracy and reliability of the data, all temperature sensors need to be calibrated regularly, and a redundant design is adopted to avoid single-point failures. In addition, through the integrated data acquisition system, these scattered temperature information can be summarized and transmitted to the central control system for subsequent analysis and processing.

[0050] The inlet temperature of the cooling medium before entering the combustion chamber cooling system and the outlet temperature after heat exchange are measured respectively by high-precision temperature sensors. At the same time, the flow rate of the cooling medium is accurately recorded by a flow meter. These data are transmitted to the central monitoring system for processing. Based on these original data, first, the heat actually removed by the cooling system is calculated, and the calculation expression is: , where represents the mass flow rate converted according to the flow rate, represents the specific heat capacity of the cooling medium, represents the inlet temperature, represents the outlet temperature, represents the heat load. The cooling efficiency is calculated based on the proportional relationship between the actual heat load and the theoretical maximum heat load, where the theoretical maximum heat load is estimated according to the design parameters of the combustion chamber. The obtained cooling efficiency data will also be integrated into the central control system to provide a basis for subsequent safety hazard analysis.

[0051] In S2, evaluate the damage of the combustion chamber wall material according to the change degree of the thermal stress distribution on the combustion chamber wall surface, specifically including:

[0052] During the monitoring period of the gas turbine power plant, the combustion chamber wall surface is divided into several regions, and the temperature data of the combustion chamber wall surface in each region are collected respectively. The fluctuation degree of the temperature data in each region of the combustion chamber wall surface is analyzed respectively, and according to the abnormal distribution of the temperature data, the characteristic value of the thermal stress distribution of the combustion chamber wall surface is calculated, and it is judged whether the characteristic value of the thermal stress distribution of the combustion chamber wall surface is greater than or equal to the preset threshold. If so, the material of the combustion chamber wall surface is damaged; if not, the material of the combustion chamber wall surface is not damaged.

[0053] The process of obtaining the characteristic value of the thermal stress distribution is as follows:

[0054] Obtain the temperature measurement values at the position and time in each region, where represents the position coordinate on the combustion chamber wall surface, and represents the time;

[0055] Preprocess the obtained temperature data, including removing outliers and smoothing;

[0056] Apply the fast Fourier transform algorithm to the temperature time series in each region to obtain the frequency domain representation , where represents the frequency variable;

[0057] Calculate the modulus square of the spectral density function: , where represents the energy of each frequency component. According to the thermal stress theory, calculate the thermal stress, and the calculation expression is: , where represents the thermal stress, represents the elastic modulus, and represents the coefficient of thermal expansion;

[0058] For each divided region, calculate its average thermal stress. According to the average thermal stress of each divided region, calculate the average thermal stress in all regions to obtain the characteristic value of the thermal stress distribution of the entire combustion chamber wall surface.

[0059] It should be noted that: the characteristic value of the thermal stress distribution reflects the thermal stress distribution characteristics of the combustion chamber wall surface, and the higher the characteristic value of the thermal stress distribution, the higher the degree of material damage to the corresponding combustion chamber wall surface.

[0060] In S3, according to the change range of the cooling efficiency of the combustion chamber, judge whether the working state of the cooling system is stable, specifically including:

[0061] Obtain the time ​Measured cooling efficiency values; perform preprocessing operations on the obtained cooling efficiency data, including removing outliers and smoothing, to ensure the data quality for subsequent analysis;

[0062] Decompose the cooling efficiency time series into wavelet coefficients of different scales through Haar wavelet transform. Specifically, for a given time series, the Haar wavelet transform can decompose the original signal into a series of approximation coefficients and detail coefficients; the approximation coefficients represent the general trend of the signal, while the detail coefficients capture the local changes or abnormal fluctuations in the signal. "Scale" refers to the level of decomposition.

[0063] Calculate the energy of each detail coefficient. The calculation expression is: ,

[0064] where, represents the total energy of the detail coefficients at the th layer, represents the number of layers of the Haar wavelet transform, represents the th detail coefficient, represents the th detail coefficient of the th layer of the Haar wavelet transform;

[0065] For the detail coefficients of the highest frequency, calculate the total energy, and calculate the ratio of the total energy to the average value of the energies of the detail coefficients at all scales to obtain the characteristic value of abnormal changes in cooling efficiency.

[0066] It should be noted that: By using the Haar wavelet transform to analyze the time series data of cooling efficiency and evaluating the health status of the cooling system according to the calculated characteristic value of abnormal changes in cooling efficiency. This method can not only effectively detect abnormal changes in cooling efficiency but also provide a scientific basis for preventing equipment damage caused by cooling system failures.

[0067] In S4, comprehensively analyze the temperature distribution on the wall of the combustion chamber and the cooling efficiency of the combustion chamber. According to the analysis results, determine the safety hazard level during the operation of the combustion chamber, including high-risk level, medium-risk level, and low-risk level. Specifically, it includes:

[0068] Obtain the characteristic value of the thermal stress distribution and the characteristic value of abnormal changes in cooling efficiency of the combustion chamber during the monitoring period of the gas turbine power plant. Construct the characteristic value of the thermal stress distribution and the characteristic value of abnormal changes in cooling efficiency into a comprehensive characteristic vector as the input of the machine learning model. The output of the model is the safety hazard score. According to the safety hazard score output by the model, determine the safety hazard level during the operation of the combustion chamber. The machine learning model is a random forest model;

[0069] Obtain the characteristic values of the thermal stress distribution, the abnormal change characteristic values of the cooling efficiency, and the safety hazard scores of multiple historical combustion chambers as the training data set, and train the random forest model. During the training process, the random forest determines the finally output safety hazard score by constructing multiple decision trees and voting on the results of each tree. When splitting nodes each time, the algorithm selects the best splitting attribute based on information gain (such as Gini impurity or entropy), so as to ensure that the constructed model has good generalization ability.

[0070] After completing the model training, it is necessary to strictly evaluate the random forest model to verify its performance on unseen data. This usually includes calculating evaluation metrics such as the accuracy, recall rate, and F1 score of the model using cross-validation techniques. Once the model is confirmed to be accurate, it can be applied to real-time monitoring, and the safety hazard score is output according to the input comprehensive feature vector. Based on a preset first threshold and a preset second threshold, the safety hazard score can be mapped to different safety hazard levels, including: low risk level, medium risk level, and high risk level. This grading mechanism helps operators quickly identify potential hazards during the operation of the combustion chamber and take corresponding preventive measures, thus ensuring the safe and stable operation of the equipment.

[0071] In S5, if it is determined that the safety hazard level of the combustion chamber during operation is the high risk level, immediately start the emergency plan and adjust the combustion mode and increase additional cooling measures, specifically including:

[0072] When the random forest model analyzes that the safety hazard level of the combustion chamber operation is the high risk level, the system will immediately start the warning mechanism and send emergency notifications to the operators and the emergency response team to ensure that relevant personnel can be informed in time and respond quickly. Immediately afterwards, the intelligent decision support module automatically intervenes, and based on the combustion chamber temperature data collected in real time, adjusts the cooling water flow rate, fan speed, or activates additional cooling devices to quickly reduce the temperature in the combustion chamber and prevent the hazard from deteriorating further. The whole process not only realizes the seamless connection from warning to response, but also ensures the timeliness and effectiveness of the cooling measures through intelligent means, maximizing the safety and stable operation of the gas turbine power plant. This comprehensive response plan is significantly different from the traditional manual monitoring and adjustment methods, providing a more efficient and reliable automated solution.

[0073] Working principle of the present invention: During the monitoring period of a gas turbine power plant, the temperature distribution of the combustion chamber wall is real-time monitored through a high-precision temperature sensor network deployed at key positions of the combustion chamber, and the inlet temperature, outlet temperature and flow rate of the cooling medium are monitored by using a flow meter and a temperature sensor, so as to calculate the actual heat load and cooling efficiency of the cooling system. These original data are transmitted to the central control system for processing. For the combustion chamber wall, it is divided into several regions, and the fast Fourier transform algorithm is applied to the temperature data in each region to obtain the frequency domain representation and calculate the modulus square of the spectral density function. Furthermore, the characteristic value of the thermal stress distribution is estimated according to the thermal stress theory, so as to evaluate the damageability of the combustion chamber wall material. At the same time, the Haar wavelet transform is used to decompose the cooling efficiency time series, and the energy of the detail coefficient is calculated to identify the change range of the cooling efficiency and determine whether the working state of the cooling system is stable. The characteristic value of the thermal stress distribution of the combustion chamber and the characteristic value of the abnormal change of the cooling efficiency are constructed into a comprehensive characteristic vector as the input of the random forest model, and the model outputs a safety hazard score. The random forest model is trained through a historical data set, and the cross-validation technology is used to evaluate the performance of the model to ensure its good generalization ability. According to the safety hazard score output by the model and combined with a preset threshold, the safety hazard level during the operation of the combustion chamber can be determined. Once it is determined to be at a high-risk level, the system immediately activates the early warning mechanism, notifies relevant personnel, and automatically adjusts measures such as the cooling water flow rate, fan speed or activates additional cooling devices, etc., to quickly reduce the temperature in the combustion chamber and prevent the hazard from further deteriorating. Throughout the process, not only the full-process automated management from data collection to safety hazard assessment and then to emergency response is realized, but also the timeliness and effectiveness of the cooling measures are ensured through the intelligent decision support module, significantly improving the ability to respond to emergencies. Compared with the traditional manual monitoring and adjustment method, the present invention provides an efficient and reliable automated solution, greatly improving the safety and stability of the gas turbine power plant, reducing accidental shutdowns and economic losses caused by equipment failures, and providing a solid technical guarantee for industrial safety. In addition, this method can also flexibly adjust parameters according to the actual situation to adapt to different working conditions, and has strong practicality and popularization value.

[0074] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data for software simulation to get a formula closest to the real situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0075] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wired or wireless (such as infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that contains one or more sets of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0076] It should be understood that the term "and / or" in this document is merely a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Here, A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the associated objects before and after, but it may also represent an "and / or" relationship, which can be specifically understood by referring to the context before and after.

[0077] It should be understood that in various embodiments of the present application, the magnitudes of the sequence numbers of the above processes do not imply the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0078] The above has described in detail one embodiment of the present invention, but the content described is only a preferred embodiment of the present invention and cannot be considered as limiting the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the application of the present invention should still fall within the scope covered by the patent of the present invention.

Claims

1. An accident early warning and decision-making method for a gas turbine power plant based on integrated analysis of potential hazard data, characterized in that, It includes the following steps: S1: During the monitoring period of the gas turbine power plant, the temperature distribution and cooling efficiency of the combustion chamber wall are monitored in real time; S2: According to the degree of change in the temperature distribution of the combustion chamber wall, the damage of the combustion chamber wall material is evaluated, specifically including: During the monitoring period of the gas turbine power plant, the combustion chamber wall is divided into several regions, the temperature data of the combustion chamber wall in each region are collected respectively, the fluctuation degree of the temperature data in each region of the combustion chamber wall is analyzed respectively, and according to the abnormal distribution of the temperature data, the characteristic value of the thermal stress distribution of the combustion chamber wall is calculated, and it is judged whether the characteristic value of the thermal stress distribution of the combustion chamber wall is greater than or equal to the preset threshold. If so, the combustion chamber wall material is damaged; if not, the combustion chamber wall material is not damaged; The process of obtaining the characteristic value of the thermal stress distribution is as follows: Obtain the positions within each region and the time under which the temperature measurement values are obtained, where represents the position coordinates on the combustion chamber wall represents the time; Preprocess the obtained temperature data, including removing outliers and smoothing; Apply the fast Fourier transform algorithm to the temperature time series in each region to obtain the frequency domain representation; calculate the squared modulus of the frequency domain expression obtained by the fast Fourier transform algorithm to obtain the energy of each frequency component; Obtain the thermal stress at the corresponding position by calculating the product of the elastic modulus of the material multiplied by its coefficient of thermal expansion and the energy of all frequency components at the corresponding position; For each region divided on the combustion chamber wall, calculate the characteristic value of the thermal stress distribution of the entire wall according to its average thermal stress value; S3: According to the change range of the cooling efficiency of the combustion chamber, judge whether the working state of the cooling system is stable, specifically including: During the monitoring period of the gas turbine power plant, the cooling efficiency of the combustion chamber is monitored in real time. According to the change range of the cooling efficiency of the combustion chamber, calculate the characteristic value of the abnormal change of the cooling efficiency, and judge whether the characteristic value of the abnormal change of the cooling efficiency is greater than or equal to the preset threshold. If so, it is judged that the working state of the cooling system is stable; if not, it is judged that the working state of the cooling system is unstable; The process of obtaining the characteristic value of the abnormal change of the cooling efficiency is as follows: Obtain the time within each monitoring period of the measured cooling efficiency value; Decompose the cooling efficiency time series into wavelet coefficients of different scales through Haar wavelet transform; Take the detail coefficients as the main fluctuation components; Calculate the sum of the squares of all detail coefficients to obtain the total energy of the detail coefficients at the corresponding scale, obtain the detail coefficients of the highest frequency, and calculate the ratio of the energy of the detail coefficients of the highest frequency to the average value of the energies of the detail coefficients at all scales to obtain the characteristic of the abnormal change of the cooling efficiency; S4: Conduct a comprehensive analysis of the temperature distribution of the combustion chamber wall and the cooling efficiency of the combustion chamber, specifically including: Obtain the characteristic value of the thermal stress distribution of the combustion chamber and the characteristic value of the abnormal change of the cooling efficiency during the monitoring period of the gas turbine power plant. Construct the characteristic value of the thermal stress distribution and the characteristic value of the abnormal change of the cooling efficiency into a comprehensive characteristic vector as the input of the machine learning model. The output of the model is the safety hazard score. According to the safety hazard score output by the model, determine the safety hazard level of the combustion chamber during operation. The machine learning model is a random forest model; According to the analysis results, determine the safety hazard level of the combustion chamber during operation, including high risk level, medium risk level and low risk level; S5: If it is determined that the safety hazard level of the combustion chamber during operation is a high-risk level, immediately activate the emergency plan, adjust the combustion mode and increase additional cooling measures.

2. The accident early warning decision-making method for a gas turbine power plant based on integrated analysis of potential hazard data according to claim 1, characterized in that The training process of the machine learning model is as follows: Obtain the thermal stress distribution characteristic values, abnormal change characteristic values of cooling efficiency, and safety hazard scores of multiple historical combustion chambers as the training data set, and train the random forest model. During the training process, the random forest determines the finally output safety hazard score by constructing multiple decision trees and voting on the results of each tree.

3. A method for accident early warning decision-making of a gas turbine power plant based on integrated analysis of potential hazard data, characterized in that, The determination of the safety hazard level of the combustion chamber during operation specifically includes: Compare the safety hazard score of the combustion chamber of the gas turbine power plant during operation with a preset first threshold. If the safety hazard score is greater than or equal to the preset first threshold, it is recorded as a high-risk level. If the safety hazard score is less than the preset first threshold and greater than the preset second threshold, it is recorded as a medium-risk level. If the safety hazard score is less than or equal to the safety hazard score, it is recorded as a low-risk level.

4. A method for accident early warning decision-making of a gas turbine power plant based on integrated analysis of potential hazard data, characterized in that If it is determined that the safety hazard level of the combustion chamber during operation is a high-risk level, immediately activate the emergency plan, specifically including: If it is determined that the safety hazard level of the combustion chamber during operation is a high-risk level, the system will immediately activate the warning mechanism, send notifications to the operators and the emergency response team, adjust the cooling water flow rate, fan speed, and activate additional cooling devices to quickly reduce the temperature inside the combustion chamber.

Images