A system and method for predicting the risk of water ingress into a generator turbine.

Abstract

This invention discloses a system and method for predicting the risk of water ingress into a generator turbine. The method includes the following steps: S1. Constructing a turbine water ingress risk database based on turbine operating procedures and historical experience; S2. Collecting relevant turbine parameter information, performing data processing and data correlation analysis; S3. Constructing a turbine water ingress risk assessment model; S4. Real-time monitoring of the turbine unit's operating status based on the turbine water ingress risk assessment model, identifying and tracking the main causes of turbine water ingress and issuing alarms, and providing control and processing solutions. This invention monitors turbine water ingress in real time through the constructed model, achieving advanced early warning and tracking of the main causes of turbine water ingress. It can effectively identify hidden fault chains under complex operating conditions, providing operators with closed-loop decision support of "risk threshold - adjustment direction - priority ranking," significantly improving equipment safety and operational reliability, and reducing the probability of unplanned shutdowns.

Description

Technical Field

[0001] This invention relates to the field of thermal power unit monitoring technology, specifically to a system and method for predicting the risk of water ingress into the turbine of a generator unit. Background Technology

[0002] In the past two years, the number of starts-up operations of coal-fired power units has increased significantly, with the annual average rising from about 5 times in 2022 to nearly 14 times in 2024. With the development of new energy sources, this high frequency of start-ups and shutdowns is expected to become the norm. This seriously threatens the reliability and lifespan of the unit equipment, especially older units, which are prone to a series of problems such as jamming of the steam inlet mechanism during start-ups and shutdowns, increasing maintenance costs and downtime. With the construction of new power systems and the advancement of "dual carbon" goals, frequent start-ups and shutdowns for peak shaving of thermal power units have become the norm, highlighting the risks of equipment failures and unplanned shutdowns caused by abnormal shaft vibration. Existing single vibration monitoring systems cannot integrate thermodynamic parameters for multi-dimensional diagnosis, making it difficult to meet the safety requirements under complex operating conditions. Summary of the Invention

[0003] To address the above problems, this invention provides a method for predicting the risk of water ingress into a generator turbine, comprising the following steps: S1. Based on turbine operating procedures and historical experience, construct a turbine water ingress risk database; S2. Collect relevant parameters of the steam turbine, perform data processing and data correlation analysis; S3. Construct a risk assessment model for preventing water ingress into steam turbines; S4. Based on the turbine water ingress risk assessment model, monitor the turbine unit's operating status in real time, identify and track the main causes of turbine water ingress and issue alarms, and provide control and processing solutions; The specific steps of step S1 are as follows: Based on the turbine operation procedures and historical experience, identify the risk factors and risk points of turbine water ingress, and construct a turbine water ingress risk database; The specific risk factors and risk points of water ingress into the steam turbine include: Main / Reheat Steam Factors: Main Steam Factors, Cold Section Reheat Steam Factors, Hot Section Reheat Steam Factors; Steam extraction factors: Steam extraction factors for stages 1-9; Shaft seal factors: steam extraction factors, water inlet factors, shaft injection water level high factors; Pipeline water supply and branch factors: main steam pipeline drainage and branch, reheat cold section high discharge port, reheat hot section pipeline branch, cold section drainage tank water level, high and medium pressure section program-controlled drainage, low pressure section program-controlled drainage anomaly. Body parameter evaluation: steam extraction factors, water inlet factors, shaft water level height factors.

[0004] Furthermore, the turbine-related parameters in step S2 specifically include: turbine load, cylinder temperature difference, cylinder temperature rise rate, turbine main steam pressure, turbine main steam temperature, shaft seal temperature of each cylinder, shaft seal pressure, upper and lower wall temperatures of each extraction steam pipeline, upper and lower wall temperature difference, water level of each high-pressure heater, and working status of the drain valves before each extraction steam check valve and before the cold section check valve.

[0005] Furthermore, in step S2, the data correlation analysis is specifically performed by integrating Pearson correlation analysis, cosine similarity, grey relational analysis, and mutual information to conduct data correlation analysis on the collected data; The calculation formula for Pearson correlation analysis is as follows: In the formula, R is the Pearson correlation coefficient, and Xi is the i-th sample value of parameter X. Let X be the mean of parameter X, and Yi be the i-th sample value of parameter Y. Let Y be the mean value of parameter Y; The formula for calculating cosine similarity is: , where cos(θ) is the cosine similarity between parameters A and B, Ai is the i-th sample value of parameter A, Bi is the i-th sample value of parameter B, n is the total number of samples, i=1,2,...,n; The formula for calculating grey relational analysis is: , Where x0(k) is the k-th sample value of the reference sequence x0, x i (k) is the comparison sequence x i The kth sample value; ρ is the correlation coefficient for comparing sequence i; ρ is the resolution coefficient, 0 < ρ < 1; r oi To compare the correlation of sequence i, m is the sample size; The formula for calculating mutual information is: , where I(X;Y) is the mutual information of parameters X and Y, P(x,y) is the joint probability distribution of parameters X and Y, and P(x) and P(y) are the marginal probability distributions of parameters X and Y, respectively.

[0006] Furthermore, it also includes a feedback optimization step: S5. The user selects and executes a control processing scheme, and optimizes it based on user feedback and the changes in turbine operating parameters monitored in real time after the scheme is executed.

[0007] A generator set turbine water ingress risk prediction system includes a multi-dimensional data monitoring module, a data processing and analysis module, a fault signal tracking and location module, a decision and feedback optimization module, and an interaction and visualization module; The multidimensional data monitoring module is used to monitor and collect the operating parameter data of the steam turbine. This module is configured to perform the steps of collecting steam turbine operating procedures and historical experience, as well as steam turbine-related parameter information. The data processing and analysis module is used to preprocess the collected data and perform correlation analysis. This module is configured to perform data processing and data correlation analysis on the collected data, and to sort out the risk factors and risk points of water ingress into the steam turbine based on the steam turbine operation procedures and historical experience. The fault signal tracking and location module is used to locate and track abnormal situations detected in the data processing and analysis module. The decision and feedback optimization module is used to generate control suggestions for the monitored abnormal situations and to optimize decisions based on user feedback. This module is configured to execute the turbine water ingress risk assessment model and monitor the turbine unit's operating status in real time, determine and track the main causes of turbine water ingress, and perform the optimization steps based on user feedback. The interaction and visualization module is used to display the monitored data, its correlations, abnormal situations, and the generated control and processing solutions, and to interact with the user.

[0008] Furthermore, the interaction and visualization module displays the monitored data, its correlations, and abnormal situations in the following ways: it performs data visualization monitoring by constructing a real-time trend curve of data monitoring changes, provides real-time alarms for abnormal situations, and synchronizes the corresponding diagnostic logic diagram, relevant criteria, and suggested control and processing solutions for the abnormal situations.

[0009] This invention provides a system and method for predicting the risk of water ingress into a generator turbine, which has the following beneficial effects: This invention uses a constructed model to monitor the water ingress of a steam turbine in real time, enabling early warning and tracking of the main causes of water ingress in the steam turbine, early warning and tracing of potential hazards in key components, effectively identifying hidden fault chains under complex operating conditions, providing operators with closed-loop decision support of "risk threshold - adjustment direction - priority ranking", significantly improving equipment safety and operational reliability, and reducing the probability of unplanned shutdowns. Attached Figure Description

[0010] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0011] Figure 1 The method flowchart provided by the present invention. Detailed Implementation

[0012] It should be understood that the specific embodiments described herein are for illustrative purposes only and are not intended to limit the scope of the invention.

[0013] The following detailed description of the implementation method of the present invention is in conjunction with the accompanying drawings. The description is only a partial embodiment and not all embodiments. For clarity, representations and descriptions unrelated to the present invention are omitted in the drawings and description.

[0014] To provide a clearer understanding of the technical features, objectives, and beneficial effects of this invention, the following detailed description of the technical solution is provided. Obviously, the described embodiments are only a portion of the embodiments of this invention, not all of them, and should not be construed as limiting the scope of implementation of this invention. Based on the embodiments of this invention, all other embodiments obtained by those skilled in the art without inventive effort are within the protection scope of this invention.

[0015] An efficient and accurate water ingress risk assessment system is constructed based on artificial intelligence technology. This leads to the development of an advanced steam turbine water ingress risk assessment model, utilizing cutting-edge data acquisition and processing technologies. Professional methods such as deep data fusion strategies, high-order feature extraction algorithms, and complex pattern recognition techniques are employed to conduct comprehensive and in-depth analysis and processing of multi-source data. By constructing a mathematical model tailored to business needs, and comprehensively considering various aspects such as the steam turbine's operating status, the system accurately assesses water ingress risk and abnormal temperature variations, providing real-time tracking and early warning of steam turbine water ingress risks.

[0016] This invention provides a method for predicting the risk of water ingress into the turbine of a generator set, such as... Figure 1 As shown, it includes the following steps: S1. Based on turbine operation procedures and historical experience, construct a turbine water ingress risk database: Based on turbine operation procedures and historical experience, identify turbine water ingress risk factors and risk points, and construct a turbine water ingress risk database.

[0017] The specific risk factors and risk points of water ingress into the steam turbine include: Main / Reheat Steam Factors: Main Steam Factors, Cold Section Reheat Steam Factors, Hot Section Reheat Steam Factors; Steam extraction factors: Steam extraction factors for stages 1-9; Shaft seal factors: steam extraction factors, water inlet factors, shaft injection water level high factors; Pipeline water supply and branch factors: main steam pipeline drainage and branch, reheat cold section high discharge port, reheat hot section pipeline branch, cold section drainage tank water level, high and medium pressure section program-controlled drainage, low pressure section program-controlled drainage anomaly. Body parameter evaluation: steam extraction factors, water inlet factors, shaft water level height factors.

[0018] S2. Collect relevant turbine parameter information (turbine load, cylinder temperature difference, cylinder temperature rise rate, turbine main steam pressure, turbine main steam temperature, shaft seal temperature of each cylinder, shaft seal pressure, upper and lower wall temperatures of each extraction pipe, upper and lower wall temperature difference, water level of each high-pressure heater, working status of drain valves before each extraction check valve and before the cold section check valve), and perform data processing and data correlation analysis.

[0019] S3. Construct a risk assessment model for preventing water ingress into steam turbines through deep data fusion and machine learning algorithms.

[0020] S4. Based on the turbine water ingress risk assessment model, monitor the turbine unit's operating status in real time, identify and track the main causes of turbine water ingress and issue alarms, and provide control and processing solutions.

[0021] In step S2, data correlation analysis is performed by integrating Pearson correlation analysis, cosine similarity, grey relational analysis, and mutual information to conduct data correlation analysis on the collected data.

[0022] The calculation formula for Pearson correlation analysis is as follows: In the formula, R is the Pearson correlation coefficient, and Xi is the i-th sample value of parameter X. Let X be the mean of parameter X, and Yi be the i-th sample value of parameter Y. Let Y be the mean value of parameter Y.

[0023] The formula for calculating cosine similarity is: , Where cos(θ) is the cosine similarity between parameters A and B, Ai is the i-th sample value of parameter A, Bi is the i-th sample value of parameter B, n is the total number of samples, i=1,2,...,n.

[0024] The formula for calculating grey relational analysis is: , , Where x0(k) is the k-th sample value of the reference sequence x0, x i (k) is the comparison sequence x i The kth sample value; ρ is the correlation coefficient for comparing sequence i; ρ is the resolution coefficient, 0 < ρ < 1; r oi To compare the correlation of sequence i, m is the sample size.

[0025] The formula for calculating mutual information is: , where I(X;Y) is the mutual information of parameters X and Y, P(x,y) is the joint probability distribution of parameters X and Y, and P(x) and P(y) are the marginal probability distributions of parameters X and Y, respectively.

[0026] It also includes a feedback optimization step: S5. The user selects and executes a control processing scheme, and optimizes it based on user feedback and the changes in turbine operating parameters monitored in real time after the scheme is executed.

[0027] The system utilizes a constructed model to monitor turbine water ingress in real time, enabling proactive early warning and tracking of the main causes of turbine water ingress. Detailed system diagrams of the turbine's condensate drain system, shaft sealing system, and extraction steam regeneration system are visualized, clearly presenting the real-time operating status of each system. Regarding parameter monitoring, the page updates and displays key real-time parameters of each turbine system, such as the status of drain valves, heater water levels, and drain tank water levels, while also providing historical trend curves to help operators understand equipment status changes. For alarm events, the page not only displays real-time alarm information, including drain valve malfunctions, excessively high water levels, and abnormal pressure and temperature, but also supports historical event queries for easy analysis of accident causes and patterns. Whenever an alarm event occurs, the system automatically and synchronously displays the corresponding diagnostic logic diagram, relevant criteria, and detailed handling suggestions, providing comprehensive technical guidance to operators.

[0028] A generator turbine water ingress risk prediction system includes a multi-dimensional data monitoring module, a data processing and analysis module, a fault signal tracking and location module, a decision-making and feedback optimization module, and an interaction and visualization module. The multidimensional data monitoring module is used to monitor and collect operating parameter data of the steam turbine.

[0029] The data processing and analysis module is used to preprocess the collected data and perform correlation analysis.

[0030] The fault signal tracking and location module is used to locate and track abnormal situations detected by the data processing and analysis module.

[0031] The decision and feedback optimization module is used to generate control suggestions for monitored anomalies and to optimize decisions based on user feedback.

[0032] The interaction and visualization module is used to display the monitored data, its correlations, anomalies, and the generated control and processing solutions, and to interact with the user: it visualizes and monitors data by constructing real-time trend curves for data monitoring, provides real-time alarms for anomalies, and synchronizes the corresponding diagnostic logic diagrams, relevant criteria, and suggested control and processing solutions for the anomalies.

[0033] This invention uses a constructed model to monitor the water ingress of a steam turbine in real time, enabling early warning and tracking of the main causes of water ingress in the steam turbine, early warning and tracing of potential hazards in key components, effectively identifying hidden fault chains under complex operating conditions, providing operators with closed-loop decision support of "risk threshold - adjustment direction - priority ranking", significantly improving equipment safety and operational reliability, and reducing the probability of unplanned shutdowns.

[0034] The above description is merely a preferred embodiment of the present invention. It should be understood that the present invention is not limited to the forms disclosed herein and should not be construed as excluding other embodiments. It can be used in various other combinations, modifications, and environments, and can be altered within the scope of the concept described herein through the above teachings or related technologies or knowledge. Modifications and variations made by those skilled in the art that do not depart from the spirit and scope of the present invention should be within the protection scope of the appended claims.

Claims

1. A method for predicting the risk of water ingress into a generator turbine, characterized in that, Includes the following steps: S1. Based on turbine operating procedures and historical experience, construct a turbine water ingress risk database; S2. Collect relevant parameters of the steam turbine, perform data processing and data correlation analysis; S3. Construct a risk assessment model for preventing water ingress into steam turbines; S4. Based on the turbine water ingress risk assessment model, monitor the turbine unit's operating status in real time, identify and track the main causes of turbine water ingress and issue alarms, and provide control and processing solutions; The specific steps of step S1 are as follows: Based on the turbine operation procedures and historical experience, identify the risk factors and risk points of turbine water ingress, and construct a turbine water ingress risk database; The specific risk factors and risk points of water ingress into the steam turbine include: Main / Reheat Steam Factors: Main Steam Factors, Cold Section Reheat Steam Factors, Hot Section Reheat Steam Factors; Steam extraction factors: Steam extraction factors for stages 1-9; Shaft seal factors: steam extraction factors, water inlet factors, shaft injection water level high factors; Pipeline water supply and branch factors: main steam pipeline drainage and branch, reheat cold section high discharge port, reheat hot section pipeline branch, cold section drainage tank water level, high and medium pressure section program-controlled drainage, low pressure section program-controlled drainage anomaly. Body parameter evaluation: steam extraction factors, water inlet factors, shaft water level height factors.

2. The method for predicting the risk of water ingress into the turbine of a generator set according to claim 1, characterized in that, The turbine-related parameters in step S2 specifically include: turbine load, cylinder temperature difference, cylinder temperature rise rate, turbine main steam pressure, turbine main steam temperature, shaft seal temperature of each cylinder, shaft seal pressure, upper and lower wall temperatures of each extraction steam pipeline, upper and lower wall temperature difference, high pressure heater water level, and the working status of the drain valves before each extraction steam check valve and before the cold section check valve.

3. The method for predicting the risk of water ingress into the turbine of a generator set according to claim 2, characterized in that, In step S2, the data correlation analysis is specifically performed by integrating Pearson correlation analysis, cosine similarity, grey relational analysis, and mutual information to conduct data correlation analysis on the collected data. The calculation formula for Pearson correlation analysis is as follows: In the formula, R is the Pearson correlation coefficient, and Xi is the i-th sample value of parameter X. Let X be the mean of parameter X, and Yi be the i-th sample value of parameter Y. Let Y be the mean value of parameter Y; The formula for calculating cosine similarity is: , where cos(θ) is the cosine similarity between parameters A and B, Ai is the i-th sample value of parameter A, Bi is the i-th sample value of parameter B, n is the total number of samples, i=1,2,...,n; The formula for calculating grey relational analysis is: , Where x0(k) is the k-th sample value of the reference sequence x0, x i (k) is the comparison sequence x i The kth sample value; ρ is the correlation coefficient for comparing sequence i; ρ is the resolution coefficient, 0 < ρ < 1; r oi To compare the correlation of sequence i, m is the sample size; The formula for calculating mutual information is: , where I(X;Y) is the mutual information of parameters X and Y, P(x,y) is the joint probability distribution of parameters X and Y, and P(x) and P(y) are the marginal probability distributions of parameters X and Y, respectively.

4. The method for predicting the risk of water ingress into the turbine of a generator set according to claim 1, characterized in that, It also includes a feedback optimization step: S5. The user selects and executes a control processing scheme, and optimizes it based on user feedback and the changes in turbine operating parameters monitored in real time after the scheme is executed.

5. A generator set turbine water ingress risk prediction system, used to implement the generator set turbine water ingress risk prediction method according to any one of claims 1 to 4, characterized in that, It includes a multi-dimensional data monitoring module, a data processing and analysis module, a fault signal tracking and location module, a decision-making and feedback optimization module, and an interaction and visualization module; The multidimensional data monitoring module is used to monitor and collect the operating parameter data of the steam turbine. This module is configured to perform the steps described in claim 1, which involve collecting steam turbine operating procedures and historical experience, as well as steam turbine-related parameter information. The data processing and analysis module is used to preprocess the collected data and perform correlation analysis. The module is configured to perform data processing and data correlation analysis on the collected data as described in claim 1, and to sort out the risk factors and risk points of steam turbine water ingress based on steam turbine operating procedures and historical experience. The fault signal tracking and location module is used to locate and track abnormal situations detected in the data processing and analysis module. The decision and feedback optimization module is used to generate control suggestions for the monitored abnormal situation and to optimize the decision based on user feedback. The module is configured to execute the turbine water ingress risk assessment model described in claim 1 and monitor the turbine unit operation status in real time, determine and track the main cause of turbine water ingress, and perform the optimization based on user feedback as described in claim 4. The interaction and visualization module is used to display the monitored data, its correlations, abnormal situations, and the generated control and processing solutions, and to interact with the user.

6. The generator set turbine water ingress risk prediction system according to claim 5, characterized in that, The interaction and visualization module displays the monitored data, its correlations, and anomalies in the following ways: it visualizes and monitors data by constructing a real-time trend curve for data monitoring, provides real-time alerts for anomalies, and synchronizes the corresponding diagnostic logic diagrams, relevant criteria, and suggested control and processing solutions for the anomalies.

Images