Generator set hydrogen leakage risk prediction system and method

Abstract

The invention discloses a hydrogen leakage risk prediction system and method for a generator set. The method comprises the steps that S1, a hydrogen leakage detection device is additionally arranged on the generator set; s2, collecting operation parameter data of the generator, and performing data processing and data correlation analysis; s3, acquiring historical change data of the generator operation parameter data, and extracting historical curve change trend characteristics; s4, constructing a hydrogen leakage risk assessment model based on the generator operation parameter data after correlation analysis and historical curve change trend characteristics; s5, acquiring information of all sealing elements for preventing hydrogen leakage of the generator; and S6, monitoring the hydrogen leakage condition of the generator in real time through the hydrogen leakage risk assessment model and the sealing element information, judging and tracking the main cause of hydrogen leakage of the generator, giving an alarm, and generating a control processing scheme. According to the method, the generator hydrogen leakage risk assessment system is constructed, and deep mining and dynamic analysis are carried out on data, so that advanced early warning and tracking of the hydrogen leakage main cause of the generator are realized.

Description

Technical Field

[0001] This invention relates to the field of thermal power unit monitoring technology, specifically to a hydrogen leakage risk prediction system and method for generator sets. Background Technology

[0002] In the past two years, the number of coal-fired power unit starts has increased significantly, with the annual average number of starts 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 steam inlet mechanism jamming during start-ups and shutdowns, increasing maintenance costs and downtime. With the construction of new power systems, 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 hydrogen leakage risk in generator sets, comprising the following steps: S1. Install a hydrogen leak detection device on the generator set; S2. Collect generator operating parameter data, perform data processing, and conduct data correlation analysis; S3. Obtain historical change data of generator operating parameters and extract the trend characteristics of historical curve changes; S4. Based on the generator operating parameter data and historical curve trend characteristics after correlation analysis, a hydrogen leakage risk assessment model is constructed; S5. Obtain information on all hydrogen leak-proof seals of the generator; S6. Monitor the generator hydrogen leakage in real time using the hydrogen leakage risk assessment model and sealing information, identify and track the main cause of generator hydrogen leakage and issue alarms, and generate control and treatment plans. S7. When it is determined that hydrogen replenishment is required, generate specific risk warnings for the hydrogen replenishment operation based on the seal life information.

[0004] Furthermore, in step S1, the hydrogen leak detection device is specifically a hydrogen concentration sensor.

[0005] Furthermore, the generator operating parameter data in step S2 specifically includes: generator load, hydrogen pressure, hydrogen temperature, hydrogen-oil differential pressure, and generator stator cooling water temperature.

[0006] Furthermore, the data processing operations in step S2 specifically include: dimensionality reduction of high-dimensional data, nonlinear data mapping, and dynamic data time series analysis.

[0007] 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.

[0008] Furthermore, the information regarding the hydrogen leakage prevention seals in step S5 specifically includes: manufacturer code, seal lifespan, installation location, and user requirements.

[0009] Furthermore, it also includes a feedback optimization step: S8. The user selects and executes a control processing scheme, and optimizes it based on user feedback and the changes in generator operating parameters monitored in real time after the scheme is executed.

[0010] A generator set hydrogen leakage 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 generator's operating parameter data. This module is configured to perform the following steps: generator operating parameter data, historical change data of generator operating parameter data, information on all hydrogen leak-proof seals of the generator, and detection data of hydrogen leak detection device. 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 correlation analysis on the collected data and extract historical curve trend features. 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 perform decision optimization based on user feedback, generating risk warnings including the status of the sealing components. This module is configured to execute the construction of the hydrogen leakage risk assessment model and monitor the hydrogen leakage of the generator, determine the main cause of the generator hydrogen leakage, and perform the optimization based on user feedback. 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.

[0011] This invention provides a system and method for predicting hydrogen leakage risk in generator sets, which has the following beneficial effects: This invention constructs a generator hydrogen leakage risk assessment system and performs in-depth data mining and dynamic analysis to achieve early warning and tracking of the main causes of generator hydrogen leakage, realize early warning and source tracing of hidden dangers in key components, effectively identify hidden fault chains under complex operating conditions, and provide 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

[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 A flowchart of the method provided by the present invention; Figure 2 A schematic diagram showing the relationship between generator stator cooling water temperature, hydrogen pressure, and output power 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] Based on site conditions, hydrogen leak detection devices will be installed as needed to construct a generator hydrogen leak risk assessment system. Subsequently, a highly accurate hydrogen leak risk assessment model will be developed based on artificial intelligence technology. This will involve integrating advanced data access and processing technologies, employing professional methods such as multimodal data analysis, deep data fusion, and machine learning algorithms, and utilizing numerous complex data processing procedures, including but not limited to high-dimensional data dimensionality reduction, nonlinear data mapping, and dynamic data time series analysis. A mathematical model that meets business needs will be established, and in-depth data mining and dynamic analysis will be conducted to achieve proactive early warning and tracking of the main causes of generator hydrogen leaks.

[0018] like Figure 1 As shown, this invention provides a method for predicting the risk of hydrogen leakage in generator sets. It constructs a risk assessment system for hydrogen leakage in generators, develops a hydrogen leakage risk assessment model, and uses real-time monitoring of hydrogen leakage levels to track and provide early warnings of the main causes of generator hydrogen leakage. The method includes the following steps: S1. Install a hydrogen leak detection device (hydrogen concentration sensor) on the generator set. Calculate the hydrogen leakage amount using mathematical formulas and expert experience. Based on the calculation results, remind operators to replenish hydrogen in a timely manner, and provide risk warnings to operators during hydrogen replenishment.

[0019] S2. Collect generator operating parameter data (generator load, hydrogen pressure, hydrogen temperature, hydrogen-oil differential pressure, generator stator cooling water temperature), perform data processing (dimensionality reduction of high-dimensional data, nonlinear data mapping, dynamic data time series analysis), and perform data correlation analysis.

[0020] 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. 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.

[0021] 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.

[0022] 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.

[0023] 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.

[0024] S3. Obtain historical change data of generator operating parameters and extract the trend characteristics of historical curve changes.

[0025] S4. Based on the generator operating parameter data and historical curve trend characteristics after correlation analysis, a hydrogen leakage risk assessment model is constructed through deep data fusion and neural network algorithm.

[0026] S5. Obtain information on all hydrogen leak-proof seals for the generator: manufacturer code, seal life, installation location, and user requirements. For each seal, it supports manual start-up timing, basic information query, and early replacement warning.

[0027] S6. Monitor the generator's hydrogen leakage in real time using a hydrogen leakage risk assessment model and sealing information, identify and track the main cause of the generator's hydrogen leakage, issue alarms, and generate control and handling solutions.

[0028] S7. When it is determined that hydrogen replenishment is required, generate specific risk warnings for the hydrogen replenishment operation based on the seal life information.

[0029] like Figure 2As shown, the real-time display shows the relationship curves between the hydrogen pressure, cooler inlet water temperature, and operating output of the hydrogen-cooled generator. When the cooler inlet water temperature and the cold air temperature exceed the rated temperature, it is determined that the generator set has a hydrogen leak and an alarm is triggered.

[0030] It also includes a feedback optimization step: S8. The user selects and executes a control processing scheme, and optimizes it based on user feedback and changes in generator operating parameters monitored in real time after the scheme is executed.

[0031] A generator set hydrogen leakage 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 multi-dimensional data monitoring module is used to monitor and collect the operating parameter data of the generator.

[0032] The data processing and analysis module is used to preprocess the collected data and perform correlation analysis.

[0033] The fault signal tracking and location module is used to locate and track abnormal signals detected by the data processing and analysis module.

[0034] The decision and feedback optimization module is used to generate control suggestions for monitored abnormal signals and to optimize decisions based on user feedback, generating risk warnings that include the status of the seals.

[0035] 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 solutions, and to allow users to interact with them.

[0036] This invention constructs a generator hydrogen leakage risk assessment system and performs in-depth data mining and dynamic analysis to achieve early warning and tracking of the main causes of generator hydrogen leakage, realize early warning and source tracing of hidden dangers in key components, effectively identify hidden fault chains under complex operating conditions, and provide 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.

[0037] 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 hydrogen leakage in a generator set, characterized in that, Includes the following steps: S1. Install a hydrogen leak detection device on the generator set; S2. Collect generator operating parameter data, perform data processing, and conduct data correlation analysis; S3. Obtain historical change data of generator operating parameters and extract the trend characteristics of historical curve changes; S4. Based on the generator operating parameter data and historical curve trend characteristics after correlation analysis, a hydrogen leakage risk assessment model is constructed; S5. Obtain information on all hydrogen leak-proof seals of the generator; S6. Monitor the generator hydrogen leakage in real time using the hydrogen leakage risk assessment model and sealing information, identify and track the main cause of generator hydrogen leakage and issue alarms, and generate control and treatment plans. S7. When it is determined that hydrogen replenishment is required, generate specific risk warnings for the hydrogen replenishment operation based on the seal life information.

2. The method for predicting hydrogen leakage risk in generator sets according to claim 1, characterized in that, In step S1, the hydrogen leak detection device is specifically a hydrogen concentration sensor.

3. The method for predicting hydrogen leakage risk in generator sets according to claim 1, characterized in that, The generator operating parameter data in step S2 specifically include: generator load, hydrogen pressure, hydrogen temperature, hydrogen-oil differential pressure, and generator stator cooling water temperature.

4. The method for predicting hydrogen leakage risk in generator sets according to claim 3, characterized in that, The data processing operations in step S2 specifically include: dimensionality reduction of high-dimensional data, nonlinear data mapping, and dynamic data time series analysis.

5. The method for predicting hydrogen leakage risk in generator sets according to claim 4, 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.

6. The method for predicting hydrogen leakage risk in generator sets according to claim 1, characterized in that, The specific information regarding the hydrogen leakage prevention seals in step S5 includes: manufacturer code, seal lifespan, installation location, and user requirements.

7. The method for predicting hydrogen leakage risk in generator sets according to claim 1, characterized in that, It also includes a feedback optimization step: S8. The user selects and executes a control processing scheme, and optimizes it based on user feedback and changes in generator operating parameters monitored in real time after the scheme is executed.

8. A generator set hydrogen leakage risk prediction system, used to implement the generator set hydrogen leakage 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 generator's operating parameter data. The module is configured to perform the steps described in claim 1: generator operating parameter data, historical change data of generator operating parameter data, information on all hydrogen leak-proof seals of the generator, and detection data from the hydrogen leak detection device. 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 extract the historical curve change trend features. 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 perform decision optimization based on user feedback, generating risk warnings including the status of the sealing components. This module is configured to execute the steps of constructing a hydrogen leakage risk assessment model as described in claim 1 and monitoring the hydrogen leakage of the generator, determining the main cause of the generator hydrogen leakage, 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.

Images