A steam turbine shafting vibration risk prediction system and method
By constructing a turbine shaft system stability risk database and a multi-dimensional assessment model, the problem of shaft vibration that cannot be diagnosed from multiple dimensions in existing technologies has been solved, enabling early warning and fault tracing of turbine shaft systems, and improving equipment safety and operational reliability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HUADIAN LAIZHOU POWER GENERATION
- Filing Date
- 2026-03-10
- Publication Date
- 2026-06-02
AI Technical Summary
Existing single vibration monitoring systems cannot integrate thermodynamic parameters for multi-dimensional diagnosis, making it difficult to meet the safety requirements of thermal power units under complex operating conditions with frequent start-ups and shutdowns. In particular, older units are prone to abnormal shaft vibration during start-ups and shutdowns, leading to a high risk of equipment failure and unplanned shutdowns.
A turbine shaft system stability risk database is constructed, operating parameters are acquired and data are processed and correlation analysis is performed. Through grayscale correlation analysis with the shaft system stability risk database, a shaft system vibration risk assessment model is established, and real-time monitoring and early warning schemes are generated. The system combines multi-dimensional data monitoring modules, data processing and analysis modules, fault signal tracking and location modules, decision and feedback optimization modules, and interaction and visualization modules.
It enables multi-dimensional assessment of turbine shaft vibration, provides early warning and fault tracing, improves equipment safety and operational reliability, and reduces the probability of unplanned downtime.
Smart Images
Figure CN122129328A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of thermal power unit monitoring technology, specifically to a turbine shaft vibration risk prediction system and method. 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 vibration risk of a steam turbine shaft system, comprising the following steps: S1. Construct a turbine shaft system stability risk database based on turbine operating procedures and historical experience; S2. Obtain turbine operating parameters; S3. Process the turbine operating parameters and perform data correlation analysis; S4. Perform correlation analysis between the processed data and the data in the turbine shaft system stability risk database to construct a shaft system vibration risk assessment model; S5. Real-time monitoring of turbine shaft vibration is achieved through a shaft vibration risk assessment model and a turbine shaft stability risk database. Abnormal situations are tracked and warned in advance, and corresponding control and processing schemes are generated.
[0004] Furthermore, the turbine operating parameters in step S2 specifically include: load, turbine speed, bearing vibration, bearing temperature, return oil temperature, lubricating oil pressure, oil temperature, cylinder temperature difference, jacking oil pressure, turning gear current, turbine main steam pressure, turbine main steam temperature, cylinder left and right expansion, cylinder expansion difference, axial displacement, and eccentricity.
[0005] Furthermore, the data correlation analysis in step S3 specifically involves calculating the correlation coefficients between each pair of data in the turbine operating parameters, using the following formula: In the formula, R is the Pearson correlation coefficient, and X... i Let X be the i-th sample value. Let X be the mean of parameter X, and Y be the mean of parameter X. i Let Y be the i-th sample value. Let Y be the mean value of parameter Y; A correlation coefficient of 1 indicates that the two data points are perfectly correlated; a correlation coefficient between 0.8 and 1 indicates a strong correlation; a correlation coefficient between 0.3 and 0.8 indicates a weak correlation; and a correlation coefficient of 0 indicates that the two data points are independent.
[0006] Furthermore, in step S3, data processing is performed on the turbine operating parameters: handling missing data values, data denoising, numerical filtering, and rationality judgment; wherein, the rationality judgment specifically involves: performing logical pattern judgment on the monitored data based on generator-related knowledge, and identifying and alarming data that violates the principle of thermal balance.
[0007] Furthermore, the correlation analysis between the processed data and the data in the turbine shaft system stability risk database in step S4 specifically involves: analyzing the processed data and the data in the turbine shaft system stability risk database using grayscale correlation, including the following sub-steps: S41. Set m data sequences to generate an analysis index matrix: , where n is the number of processed data indicators; S42. Determine the reference data column, denoted as: ; S43. Dimensionlessize the processed data indicators to form a comparison sequence matrix: ; S44. Calculate the absolute difference between corresponding elements of the comparison sequence matrix and the reference data column one by one. Where k = 1,2,…,m; i = 1,2,…,n; S45. Calculate the correlation coefficient between corresponding elements of each comparison sequence and the reference sequence. The formula is as follows: , Where k = 1,2,…,m; i = 1,2,…,n; ρ is the correlation coefficient of the comparison sequence i; ρ is the resolution coefficient, 0 < ρ < 1; S46. Calculate the mean of the correlation coefficients between the data indicators of each comparison sequence and the corresponding elements of the reference sequence, denoted as the correlation degree: , where r oi To compare the correlation of sequence i; S47. Obtain the correlation analysis results between the processed data and the data in the turbine shaft system stability risk database based on the correlation degree.
[0008] Furthermore, in step S5, the real-time monitoring of turbine shaft vibration is specifically achieved by constructing a turbine shaft characteristic curve to monitor the turbine shaft vibration value and its trend.
[0009] Furthermore, it also includes a feedback optimization step: S6. 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.
[0010] A turbine shaft vibration 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 the operating parameter data of the steam turbine. This module is configured to execute the steps of collecting steam turbine operating procedures and historical experience, and steam turbine operating parameters. 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, as well as to perform correlation analysis between the processed data and the data in the turbine shaft system stability risk database. The fault signal tracking and location module is used to locate and track abnormal signals monitored in the data processing and analysis module. The decision and feedback optimization module is used to generate control suggestions for the monitored abnormal signals and to optimize decisions based on user feedback. This module is configured to execute the steps of building a shaft vibration risk assessment model and monitoring the turbine shaft vibration in real time, performing early warning and corresponding control processing schemes for abnormal situations, and optimizing based on user feedback. The interaction and visualization module is used to display the monitored data and its correlation, locate abnormal signals, and generate control suggestions, and to interact with the user.
[0011] This invention provides a system and method for predicting the vibration risk of a steam turbine shaft system, which has the following beneficial effects: This invention constructs a multi-dimensional integrated assessment model that comprehensively considers parameters such as shaft speed and vibration amplitude to assess risks, enabling early warning and tracing of potential hazards in key components. 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 downtime. Attached Figure Description
[0012] 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.
[0013] Figure 1 The method flowchart provided by the present invention. Detailed Implementation
[0014] 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.
[0015] 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.
[0016] 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.
[0017] A multi-parameter fusion assessment model is employed to comprehensively consider parameters such as shaft speed and vibration amplitude to evaluate risk. Multiple characteristic curves, including shaft vibration, speed, and load curves, are used to aid in judgment. At critical speeds, the vibration value and its trend are closely monitored; once an anomaly is detected, the operating condition is locked and an alert is issued. This assessment can analyze the causes of vibration, demonstrate bearing jacking, and indicate the correlation with TSI shaft vibration protection. An assessment model is established based on data such as cylinder block temperature distribution, displaying cylinder temperature measurement point distribution diagrams and related temperature difference and rate of change data. Simultaneously, by combining inlet steam temperature, cylinder temperature difference, cylinder expansion, and other indicators with multi-dimensional data such as the sliding pin system diagram, the risk of unit expansion jamming is comprehensively assessed, and the pattern of axial displacement variation is identified.
[0018] Based on site conditions, exciter bearing vibration monitoring points are installed as needed. Research on turbine generator shaft vibration is conducted, and an advanced technology and method are employed to construct a shaft vibration risk assessment system. A shaft vibration risk assessment model is developed, utilizing professional methods such as high-order data fusion strategies, deep signal processing algorithms, and complex data analysis models to comprehensively and deeply mine and analyze multi-source data. By constructing mathematical models and advanced algorithms that meet business requirements, the shaft stability state is accurately assessed. Real-time tracking and early warning of turbine shaft stability risks are implemented.
[0019] like Figure 1 As shown, the present invention provides a method for predicting the vibration risk of a steam turbine shaft system, comprising the following steps: S1. Based on turbine operating procedures and historical experience, construct a turbine shaft system stability risk database.
[0020] S2. Obtain turbine operating parameters, including: load, main turbine speed, bearing vibration, bearing temperature, return oil temperature, lubricating oil pressure, oil temperature, cylinder temperature difference, jacking oil pressure, turning gear current, turbine main steam pressure, turbine main steam temperature, cylinder left and right expansion, cylinder expansion difference, axial displacement, and eccentricity.
[0021] S3. Process the turbine operating parameters and perform data correlation analysis: Calculate the correlation coefficients between each pair of data in the turbine operating parameters. The calculation formula is as follows: In the formula, R is the Pearson correlation coefficient, and X... i Let X be the i-th sample value. Let X be the mean of parameter X, and Y be the mean of parameter X. i Let Y be the i-th sample value. Let Y be the mean value of parameter Y; A correlation coefficient of 1 indicates that the two data points are perfectly correlated; a correlation coefficient between 0.8 and 1 indicates a strong correlation; a correlation coefficient between 0.3 and 0.8 indicates a weak correlation; and a correlation coefficient of 0 indicates that the two data points are independent.
[0022] The process includes data processing for turbine operating parameters: handling missing data values, data denoising, numerical filtering, and rationality judgment. Specifically, the rationality judgment involves: performing logical pattern judgment on the monitored data based on generator-related knowledge, and identifying and issuing alarms for data that violates the principle of thermal balance.
[0023] S4. Perform correlation analysis between the processed data and the data in the turbine shaft system stability risk database, and construct a shaft system vibration risk assessment model through deep data fusion and neural network algorithms.
[0024] Specifically, the correlation analysis between the processed data and the data in the turbine shaft system stability risk database involves: using grayscale correlation to analyze the processed data and the data in the turbine shaft system stability risk database, including the following sub-steps: S41. Set m data sequences to generate an analysis index matrix: , where n is the number of processed data indicators; S42. Determine the reference data column, denoted as: ; S43. Dimensionlessize the processed data indicators to form a comparison sequence matrix: ; S44. Calculate the absolute difference between corresponding elements of the comparison sequence matrix and the reference data column one by one. Where k = 1,2,…,m; i = 1,2,…,n; S45. Calculate the correlation coefficient between corresponding elements of each comparison sequence and the reference sequence. The formula is as follows: , Where k = 1,2,…,m; i = 1,2,…,n; ρ is the correlation coefficient of the comparison sequence i; ρ is the resolution coefficient, 0 < ρ < 1; S46. Calculate the mean of the correlation coefficients between the data indicators of each comparison sequence and the corresponding elements of the reference sequence, denoted as the correlation degree: , where r oi To compare the correlation of sequence i; S47. Obtain the correlation analysis results between the processed data and the data in the turbine shaft system stability risk database based on the correlation degree.
[0025] S5. Real-time monitoring of turbine shaft vibration is achieved through a shaft vibration risk assessment model and a turbine shaft stability risk database. Abnormal situations are proactively tracked and warned of, and corresponding control and processing schemes are generated. Specifically, real-time monitoring of turbine shaft vibration is achieved by constructing turbine shaft characteristic curves to monitor the turbine shaft vibration values and their trends.
[0026] It also includes a feedback optimization step: S6. 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] A turbine shaft vibration 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.
[0028] 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 signals detected by the data processing and analysis module.
[0031] The decision and feedback optimization module is used to generate control suggestions for monitored abnormal signals and to optimize decisions based on user feedback.
[0032] The interaction and visualization module is used to display the monitored data and its correlations, locate abnormal signals, and generate control suggestions, and to allow users to interact with the data.
[0033] This invention constructs a multi-dimensional integrated assessment model that comprehensively considers parameters such as shaft speed and vibration amplitude to assess risks, enabling early warning and tracing of potential hazards in key components. 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 downtime.
[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 vibration risk of a steam turbine shaft system, characterized in that, Includes the following steps: S1. Construct a turbine shaft system stability risk database based on turbine operating procedures and historical experience; S2. Obtain turbine operating parameters; S3. Process the turbine operating parameters and perform data correlation analysis; S4. Perform correlation analysis between the processed data and the data in the turbine shaft system stability risk database to construct a shaft system vibration risk assessment model; S5. Real-time monitoring of turbine shaft vibration is achieved through a shaft vibration risk assessment model and a turbine shaft stability risk database. Abnormal situations are tracked and warned in advance, and corresponding control and processing schemes are generated.
2. The method for predicting the vibration risk of a steam turbine shaft system according to claim 1, characterized in that, The turbine operating parameters in step S2 specifically include: load, turbine speed, bearing vibration, bearing temperature, return oil temperature, lubricating oil pressure, oil temperature, cylinder temperature difference, jacking oil pressure, turning gear current, turbine main steam pressure, turbine main steam temperature, cylinder left and right expansion, cylinder expansion difference, axial displacement, and eccentricity.
3. The method for predicting the vibration risk of a steam turbine shaft system according to claim 1, characterized in that, The data correlation analysis in step S3 specifically involves calculating the correlation coefficients between each pair of data in the turbine operating parameters. The calculation formula is as follows: In the formula, R is the Pearson correlation coefficient, and X... i Let X be the i-th sample value. Let X be the mean of parameter X, and Y be the mean of parameter X. i Let Y be the i-th sample value. Let Y be the mean value of parameter Y; A correlation coefficient of 1 indicates that the two data points are perfectly correlated; a correlation coefficient between 0.8 and 1 indicates a strong correlation; a correlation coefficient between 0.3 and 0.8 indicates a weak correlation; and a correlation coefficient of 0 indicates that the two data points are independent.
4. The method for predicting the vibration risk of a steam turbine shaft system according to claim 3, characterized in that, In step S3, the turbine operating parameters are processed: missing data handling, data denoising, numerical filtering, and rationality judgment. Specifically, the rationality judgment involves: performing logical pattern judgment on the monitored data based on generator-related knowledge, and identifying and issuing alarms for data that violate the principle of thermal balance.
5. The method for predicting the vibration risk of a steam turbine shaft system according to claim 1, characterized in that, Step S4, which involves performing a correlation analysis between the processed data and the data in the turbine shaft system stability risk database, specifically involves using grayscale correlation to analyze the processed data against the data in the turbine shaft system stability risk database, including the following sub-steps: S41. Set m data sequences to generate an analysis index matrix: , where n is the number of processed data indicators; S42. Determine the reference data column, denoted as: ; S43. Dimensionlessize the processed data indicators to form a comparison sequence matrix: ； S44. Calculate the absolute difference between corresponding elements of the comparison sequence matrix and the reference data column one by one. Where k = 1,2,…,m; i = 1,2,…,n; S45. Calculate the correlation coefficient between corresponding elements of each comparison sequence and the reference sequence. The formula is as follows: Where k = 1,2,…,m; i = 1,2,…,n; ρ is the correlation coefficient of the comparison sequence i; ρ is the resolution coefficient, 0 < ρ < 1; S46. Calculate the mean of the correlation coefficients between the data indicators of each comparison sequence and the corresponding elements of the reference sequence, denoted as the correlation degree: , where r oi To compare the correlation of sequence i; S47. Obtain the correlation analysis results between the processed data and the data in the turbine shaft system stability risk database based on the correlation degree.
6. The method for predicting the vibration risk of a steam turbine shaft system according to claim 1, characterized in that, In step S5, the real-time monitoring of turbine shaft system vibration is specifically achieved by constructing a turbine shaft system characteristic curve to monitor the turbine shaft system vibration value and its trend.
7. The method for predicting the vibration risk of a steam turbine shaft system according to claim 1, characterized in that, It also includes a feedback optimization step: S6. 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.
8. A turbine shaft system vibration risk prediction system, used to implement the turbine shaft system vibration risk prediction method according to any one of claims 1 to 7, 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. The module is configured to perform the steps described in claim 1 to collect the steam turbine operating procedures and historical experience, and the steam turbine operating parameters. 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 as described in claim 1, and to perform correlation analysis on the processed data and the data in the turbine shaft system stability risk database. The fault signal tracking and location module is used to locate and track abnormal signals monitored in the data processing and analysis module. The decision and feedback optimization module is used to generate control suggestions for the monitored abnormal signals and to optimize decisions based on user feedback. The module is configured to execute the steps of constructing a shaft vibration risk assessment model as described in claim 1 and monitoring the turbine shaft vibration in real time, performing early warning and corresponding control processing schemes for abnormal situations, and optimizing based on user feedback as described in claim 7. The interaction and visualization module is used to display the monitored data and its correlation, the location of abnormal signals, and the generated control and processing schemes, and to interact with the user.