Digital twinborn simulation method for lubricating oil system of gas turbine

Through digital twin simulation technology, the information management and fault positioning problems of gas turbine oil system in operation and maintenance are solved, efficient monitoring and fault prediction of the oil system are realized, and the operating reliability and maintenance level of the system are improved.

CN119047323AInactive Publication Date: 2024-11-29ANHUI UNIV OF SCI & TECH

Patent Information

Application Number
CN202411226348.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-03
Publication Date
2024-11-29
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

During operation and maintenance, the gas turbine oil system faces problems such as difficult information management, difficulty in fault location and insufficient monitoring, resulting in a decrease in system operation efficiency and reliability.

Method used

Digital twin simulation technology is adopted to collect and preprocess the data of the lubricant system, combine neural network algorithms to build a virtual model, realize the combination of virtual and real simulation, conduct state prediction and fault diagnosis, and provide real-time monitoring and prevention mechanisms.

Benefits of technology

It improves the operating efficiency and reliability of the lubricant system, realizes early prediction and intervention of faults, enhances the monitoring ability of system status, and reduces the difficulty and cost of fault handling.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a digital twinborn simulation method for a gas turbine lubricating oil system, and relates to the technical field of gas turbine construction. In order to solve the technical problems of high information management difficulty, high fault positioning difficulty and incapability of comprehensively monitoring the state of the lubricating oil system during operation and maintenance of the lubricating oil system of the gas turbine in the prior art, the technical scheme provided by the invention comprises the following steps: acquiring parameters of actual equipment of the lubricating oil system of the gas turbine; preset data are collected from actual equipment of the lubricating oil system of the gas turbine; the collected data are preprocessed; and predicting the operation state of the gas turbine lubricating oil system in combination with a neural network algorithm to obtain a virtual model. And synchronizing the obtained virtual model with an actual system in real time through a digital twinning technology, carrying out virtual-real combined simulation of the lubricating oil system of the gas turbine, and carrying out comparison verification on a simulation result and an actual operation condition according to a preset verification condition. The method is suitable for operation and maintenance of the lubricating oil system of the gas turbine.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of gas turbine construction, and in particular to digital twin simulation of a gas turbine lubricating oil system. Background Art

[0002] At present, the main problems existing in the operation and maintenance of gas turbine lubricating oil systems include:

[0003] The operation scale of gas turbine systems is constantly increasing, the functions are becoming more and more complex, and the cross-disciplinary penetration generates massive data with complex correlations, which greatly increases the difficulty of information management. With the advancement of gas turbine technology and the expansion of its application scope, the scale and complexity of the system are increasing. As a key component of the system, the lubricating oil system has a wide variety of parameters and data, including temperature, pressure, flow, and vibration. These data are not only huge in quantity, but also have complex correlations with each other. Traditional information management methods are difficult to effectively handle these complex data, resulting in a decrease in the overall operating efficiency of the system and a greatly increased difficulty in data analysis and decision support.

[0004] The gas turbine lubricating oil system is extremely complex. It is difficult to locate faults in the event of a fault. The data generated is huge, the timeliness of fault handling is poor, and it is difficult to prevent them in advance. The gas turbine lubricating oil system involves a variety of components and sensors, and its operating status is affected by many factors. The failure of any component may cause the overall performance of the system to decline or even shut down. In the event of a fault, the large amount of data generated by the lubricating oil system is often difficult to analyze and process quickly and accurately, resulting in difficulty in locating the fault and prolonged repair time. In addition, traditional fault handling methods mainly rely on post-fault repairs and lack effective prevention and prediction mechanisms. It is difficult to intervene and prevent faults before they occur, which increases the uncertainty and risk of system operation.

[0005] Insufficient monitoring and maintenance, the state of the lubricating oil system cannot be fully monitored, and manual state monitoring makes it difficult to intervene in the early stages of failures, resulting in untimely maintenance, increasing the risk of system failures and the difficulty of repair. The normal operation of the lubricating oil system has an important impact on the overall performance and life of the gas turbine, but the current monitoring and maintenance methods are insufficient, making it difficult to achieve comprehensive monitoring of the state of the lubricating oil system. Traditional manual monitoring methods are not only time-consuming and labor-intensive, but also subjective and limited, making it difficult to detect potential faults in a timely manner. During system operation, the state changes of the lubricating oil system may be gradual, and early minor anomalies are often difficult to detect. By the time the problem appears, it may have caused significant damage to the system, significantly increasing the difficulty and cost of repair.

[0006] In summary, the main problems faced by the current gas turbine lubricating oil system in the operation and maintenance process are concentrated in information management, fault location and processing, monitoring and maintenance, etc. These problems seriously affect the operation efficiency and reliability of the system. Therefore, there is an urgent need for a new technical solution that can effectively process complex data, realize early fault prediction and intervention, and comprehensively monitor the status of the lubricating oil system, so as to improve the operation and maintenance level of the gas turbine lubricating oil system and ensure the safe and reliable operation of the system. Summary of the invention

[0007] In order to solve the technical problems existing in the prior art, such as the difficulty in information management and fault location during operation and maintenance of the gas turbine lubricating oil system, and the inability to fully monitor the state of the lubricating oil system, the present invention provides the following technical solutions:

[0008] A method for constructing a digital twin simulation virtual model of a gas turbine lubricating oil system, comprising:

[0009] Steps for collecting parameters of actual equipment in a gas turbine lubricating oil system;

[0010] Steps for collecting preset data from actual equipment of a gas turbine lubricating oil system;

[0011] The step of preprocessing the collected data;

[0012] The operation status of the gas turbine lubricating oil system is predicted by combining the neural network algorithm to obtain the steps of the virtual model.

[0013] Furthermore, a preferred embodiment is provided, wherein the preset data includes temperature, pressure, flow and vibration data.

[0014] Furthermore, a preferred embodiment is provided, wherein the preprocessing includes operations of data cleaning, outlier detection and elimination, data smoothing and data transformation.

[0015] Furthermore, a preferred embodiment is provided, which also includes the step of constructing a lubricating oil system mechanism model based on the collected parameters of the actual equipment of the gas turbine lubricating oil system as the basis of the virtual model.

[0016] Based on the same inventive concept, the present invention also provides a digital twin simulation virtual model building device for a gas turbine lubricating oil system, comprising:

[0017] A module for collecting parameters of actual equipment in the gas turbine lubricating oil system;

[0018] A module for collecting preset data from actual equipment in the gas turbine lubricating oil system;

[0019] A module for preprocessing the collected data;

[0020] The operating status of the gas turbine lubricating oil system is predicted by combining the neural network algorithm to obtain the module of the virtual model.

[0021] Based on the same inventive concept, the present invention also provides a digital twin simulation method for a gas turbine lubricating oil system, comprising:

[0022] Through digital twin technology, the virtual model is synchronized with the actual system in real time, and a virtual-reality simulation of the gas turbine lubricating oil system is carried out. According to the preset verification conditions, the simulation results are compared and verified with the actual operating conditions.

[0023] Based on the same inventive concept, the present invention also provides a digital twin simulation device for a gas turbine lubricating oil system, comprising:

[0024] Through digital twin technology, the virtual model is synchronized with the actual system in real time, and a virtual-reality simulation of the gas turbine lubricating oil system is carried out. According to the preset verification conditions, the simulation results are compared with the actual operating conditions to verify the module.

[0025] Based on the same inventive concept, the present invention also provides a computer storage medium for storing a computer program. When the computer program is read by a computer, the computer executes the method described.

[0026] Based on the same inventive concept, the present invention also provides a computer, including a processor and a storage medium. When the processor reads a computer program stored in the storage medium, the computer executes the method described.

[0027] Based on the same inventive concept, the present invention also provides a computer program product, which is a computer program. When the computer program is executed, the method described above is implemented.

[0028] The digital twin simulation method of a gas turbine lubricating oil system provided by the present invention can accurately reflect the actual operating conditions of the gas turbine lubricating oil system by constructing a lubricating oil system mechanism model. This method improves the accuracy and reliability of the system model, making the simulation results closer to reality, thereby more effectively guiding actual operation and maintenance. Such high-precision modeling is difficult to achieve in the prior art, especially when the system complexity increases.

[0029] The digital twin simulation method of a gas turbine lubricating oil system provided by the present invention can effectively eliminate noise and outliers and ensure the accuracy and reliability of data by real-time acquisition and preprocessing of key data, including temperature, pressure, flow rate, vibration and other information. This data preprocessing step makes the subsequent state prediction and simulation more accurate and reliable. Compared with the data inaccuracy problem that may exist in the prior art, the preprocessing step of the present invention greatly improves the data quality.

[0030] The digital twin simulation method of a gas turbine lubricating oil system provided by the present invention combines a neural network algorithm to predict the operating status of the lubricating oil system, and can make full use of deep learning technology to extract the complex characteristics of the system and accurately evaluate the operating status and potential faults of the system. This method improves the accuracy and timeliness of fault diagnosis and can perform preventive maintenance before the system fails. Compared with traditional fault diagnosis methods based on experience and rules, the present invention provides a more intelligent and efficient solution.

[0031] The digital twin simulation method of a gas turbine lubricating oil system provided by the present invention synchronizes the virtual model with the actual system in real time through virtual-real combination simulation, and compares and verifies the simulation results with the actual operation conditions, thereby realizing accurate simulation and prediction of the operation status of the lubricating oil system. This virtual-real combination simulation method not only improves the accuracy and reliability of the simulation, but also enables operators to intuitively understand the system operation status. Compared with simple physical experiments or single simulation methods, the two-way interactive method of the present invention significantly enhances the system monitoring and fault handling capabilities.

[0032] The present invention provides a digital twin simulation method for a gas turbine lubricating oil system, and the visualization of simulation results is displayed through two-dimensional and three-dimensional simulation animation views and parameter curve views, so that complex system operation data and prediction results can be presented in an intuitive and easy-to-understand form. This method greatly improves the interpretability and operability of data, helping operators to better understand system status and decision-making. Compared with traditional data presentation in text or table form, the visualization of the present invention provides a more user-friendly experience.

[0033] The present invention provides a digital twin simulation method for a gas turbine lubricating oil system, which is suitable for application in the operation and maintenance of a gas turbine lubricating oil system. DETAILED DESCRIPTION

[0034] In order to make the advantages and benefits of the technical solution provided by the present invention more clearly reflected, the technical solution provided by the present invention is now further clearly and completely described, specifically:

[0035] Embodiment 1: This embodiment provides a method for constructing a digital twin simulation virtual model of a gas turbine lubricating oil system, including:

[0036] Steps for collecting parameters of actual equipment in a gas turbine lubricating oil system;

[0037] Steps for collecting preset data from actual equipment of a gas turbine lubricating oil system;

[0038] The step of preprocessing the collected data;

[0039] The operation status of the gas turbine lubricating oil system is predicted by combining the neural network algorithm to obtain the steps of the virtual model.

[0040] Embodiment 2: This embodiment further limits the method for constructing a digital twin simulation virtual model of a gas turbine lubricating oil system provided in Embodiment 1, and the preset data includes temperature, pressure, flow and vibration data.

[0041] Implementation method three: This implementation method is a further limitation of the method for constructing a digital twin simulation virtual model of a gas turbine lubricating oil system provided in implementation method one, and the preprocessing includes data cleaning, outlier detection and elimination, data smoothing and data transformation operations.

[0042] Implementation method 4. This implementation method is a further limitation of the method for constructing a digital twin simulation virtual model of a gas turbine lubricating oil system provided in implementation method 1, and also includes a step of constructing a lubricating oil system mechanism model based on the collected parameters of the actual equipment of the gas turbine lubricating oil system as the basis of the virtual model.

[0043] Embodiment 5: This embodiment provides a digital twin simulation virtual model building device for a gas turbine lubricating oil system, including:

[0044] A module for collecting parameters of actual equipment in the gas turbine lubricating oil system;

[0045] A module for collecting preset data from actual equipment in the gas turbine lubricating oil system;

[0046] A module for preprocessing the collected data;

[0047] The operating status of the gas turbine lubricating oil system is predicted by combining the neural network algorithm to obtain the module of the virtual model.

[0048] Embodiment 6: This embodiment provides a digital twin simulation method for a gas turbine lubricating oil system, including:

[0049] Through digital twin technology, the virtual model obtained in implementation mode one is synchronized with the actual system in real time, and a virtual-reality simulation of the gas turbine lubricating oil system is carried out. According to preset verification conditions, the simulation results are compared and verified with the actual operating conditions.

[0050] Specifically, they include:

[0051] Step 1: Establish the lubricating oil system mechanism model

[0052] Input: Parameters and characteristics of actual equipment in the gas turbine lubricating oil system.

[0053] A lubricating oil system mechanism model library is constructed based on the Modelica language, and the model library contains multiple component models.

[0054] The component models (such as the lubricating oil pump group model, pipeline model, circulating lubricating oil tank model, etc.) are connected to obtain the overall lubricating oil system mechanism model.

[0055] The test data of the actual gas turbine lubricating oil system is injected for iteration, verification and optimization.

[0056] Output: Lubricating oil system mechanism model that can accurately reflect the actual operating conditions of the system.

[0057] Step 2: Collect operating data

[0058] Input: Actual equipment of gas turbine lubricating oil system.

[0059] Receive real-time operating data of the physical gas turbine lubricating oil system.

[0060] Preprocess the operating data, including data cleaning, outlier detection and elimination, data smoothing, data transformation, etc.

[0061] Output: pre-processed lubricating oil system operating status information.

[0062] Step 3: State prediction

[0063] Input: Lubricating oil system operating status information after pretreatment.

[0064] Combined with neural network algorithm, the operating status of gas turbine lubricating oil system is predicted.

[0065] Use deep learning technology to extract complex features of the system and assess its operating status and potential failures.

[0066] Output: Status prediction results of gas turbine lubricating oil system.

[0067] Step 4: Virtual and real combination simulation

[0068] Input: lubricating oil system mechanism model, actual test parameters of the physical gas turbine lubricating oil system.

[0069] The actual test parameters are substituted into the lubricating oil system mechanism model for simulation.

[0070] The simulation results are compared with the actual operation of the physical gas turbine lubricating oil system.

[0071] The control parameters of the lubricating oil system mechanism model are substituted into the actual gas turbine lubricating oil system to control its operating state.

[0072] Visualize the simulation results and display them in 2D or 3D simulation animation view and parameter curve view.

[0073] Output: comparative analysis of simulation results and actual operation conditions, and simulation visualization results.

[0074] Embodiment 7: This embodiment provides a digital twin simulation device for a gas turbine lubricating oil system, including:

[0075] Through digital twin technology, the virtual model obtained in implementation mode five is synchronized with the actual system in real time, and a virtual-reality simulation of the gas turbine lubricating oil system is carried out. According to the preset verification conditions, the simulation results and the actual operating conditions are compared and verified.

[0076] Embodiment 8: This embodiment provides a computer storage medium for storing a computer program. When the computer program is read by a computer, the computer executes the method described in embodiment 1.

[0077] Embodiment 9: This embodiment provides a computer, including a processor and a storage medium. When the processor reads the computer program stored in the storage medium, the computer executes the method described in embodiment 1.

[0078] Embodiment 10: This embodiment provides a computer program product, which is a computer program. When the computer program is executed, the method described in Embodiment 1 is implemented.

[0079] Implementation eleven: This implementation further describes the above technical solution in detail through specific examples, specifically:

[0080] It includes: constructing a lubricating oil system mechanism model that can accurately reflect the actual operating conditions of the system based on the parameters and characteristics of the actual equipment of the gas turbine lubricating oil system; collecting key data such as temperature, pressure, flow, vibration, etc. from the actual equipment of the gas turbine lubricating oil system; using data cleaning technology to perform data cleaning, outlier detection and elimination, data smoothing and other pre-processing to eliminate the influence of noise and outliers; combining neural network algorithms to predict the operating status of the gas turbine lubricating oil system; through digital twin technology, the virtual model and the actual system are synchronized in real time, and virtual-reality combined simulation of the gas turbine lubricating oil system is carried out, and the simulation results are compared and verified with the actual operating conditions to achieve accurate simulation and prediction of the operating status of the lubricating oil system.

[0081] Specifically, the lubricating oil system mechanism model is established according to the parameters of the physical gas turbine lubricating oil system, including: constructing a lubricating oil system mechanism model library based on the Modelica language, the lubricating oil system mechanism model library includes multiple component models, and each of the component models is connected to obtain an overall lubricating oil system mechanism model.

[0082] The component models at least include a lubricating oil pump group model, a pipeline model, a circulating lubricating oil tank model, a motor model, a heat exchanger model, a relief valve model, a regulating valve model, a check valve model and a three-way model.

[0083] The method further comprises: injecting test data of a real gas turbine lubricating oil system into the lubricating oil system mechanism model for iteration, verification and optimization.

[0084] The test data at least include: the lubricating oil pressure, flow and temperature of the lubricating oil system at different regulating valve openings; the changes in the lubricating oil pressure, flow and temperature of the lubricating oil system under different load conditions; the pressure, temperature and flow of the lubricating oil outlet when the speed of the electric lubricating oil pump changes; the pressure of the lubricating oil main pipe at different pressure regulating valve openings; the pressure of the lubricating oil main pipe when different electric lubricating oil pumps are switched; the pressure and flow of the lubricating oil system inlet when the lubricating oil delivery pump is started; the temperature of the lubricating oil at different lubricating oil cooling water inlet flows; the temperature and viscosity of the lubricating oil when the power of the lubricating oil heater changes.

[0085] The collecting of the operating data of the gas turbine lubricating oil system comprises: receiving the operating data of the physical gas turbine lubricating oil system in real time, performing data preprocessing on the received operating data, and processing the preprocessed operating data into operating status information identifiable by a lubricating oil system mechanism model.

[0086] The preprocessing includes: data cleaning, outlier detection and elimination, data smoothing, data transformation, etc., to eliminate the influence of noise and outliers.

[0087] The state prediction includes: combining a neural network algorithm to predict the operating state of the gas turbine lubricating oil system, and using deep learning technology to extract the complex characteristics of the system, so as to accurately evaluate its operating status and potential failures.

[0088] The virtual-reality interactive simulation of the gas turbine lubricating oil system includes: substituting the actual test parameters of the physical gas turbine lubricating oil system into the lubricating oil system mechanism model for simulation, and comparing the simulation results with the actual operating conditions of the physical gas turbine lubricating oil system.

[0089] The virtual-reality interactive simulation of the gas turbine lubricating oil system includes: substituting the control parameters of the lubricating oil system mechanism model into the physical gas turbine lubricating oil system to control the operating state of the physical gas turbine lubricating oil system.

[0090] The virtual-reality interactive simulation of the gas turbine lubricating oil system also includes visualizing the simulation results.

[0091] The visualization includes: displaying the simulation results in a two-dimensional simulation animation view, a three-dimensional simulation animation view, and a parameter curve view.

[0092] The technical solution provided by the present invention is further described in detail above through several specific implementation modes in order to highlight the advantages and benefits of the technical solution provided by the present invention. However, the several specific implementation modes described above are not intended to be used as limitations on the present invention. Any reasonable modification and improvement of the present invention, combination of implementation modes and equivalent substitution within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for constructing a digital twin simulation virtual model of a gas turbine lubricating oil system, characterized in that: include: Steps for collecting parameters of actual equipment in a gas turbine lubricating oil system; Steps for collecting preset data from actual equipment of a gas turbine lubricating oil system; The step of preprocessing the collected data; The operation status of the gas turbine lubricating oil system is predicted by combining the neural network algorithm to obtain the steps of the virtual model.

2. The method for constructing a digital twin simulation virtual model of a gas turbine lubricating oil system according to claim 1, characterized in that: The preset data includes temperature, pressure, flow and vibration data.

3. The method for constructing a digital twin simulation virtual model of a gas turbine lubricating oil system according to claim 1, characterized in that: The preprocessing includes data cleaning, outlier detection and elimination, data smoothing and data transformation operations.

4. The method for constructing a digital twin simulation virtual model of a gas turbine lubricating oil system according to claim 1, characterized in that: The method also includes the step of constructing a lubricating oil system mechanism model based on the collected parameters of the actual equipment of the gas turbine lubricating oil system as the basis of the virtual model.

5. A digital twin simulation virtual model building device for a gas turbine lubricating oil system, characterized in that: include: A module for collecting parameters of actual equipment in the gas turbine lubricating oil system; A module for collecting preset data from actual equipment in the gas turbine lubricating oil system; A module for preprocessing the collected data; The operating status of the gas turbine lubricating oil system is predicted by combining the neural network algorithm to obtain the module of the virtual model.

6. A digital twin simulation method for a gas turbine lubricating oil system, characterized in that: include: Through the digital twin technology, the virtual model obtained in claim 1 is synchronized with the actual system in real time, and a virtual-real simulation of the gas turbine lubricating oil system is carried out. According to the preset verification conditions, the simulation results are compared and verified with the actual operating conditions.

7. A digital twin simulation device for a gas turbine lubricating oil system, characterized in that: include: Through digital twin technology, the virtual model obtained in claim 5 is synchronized with the actual system in real time, and a virtual-real simulation of the gas turbine lubricating oil system is carried out. According to preset verification conditions, the simulation results and the actual operating conditions are compared and verified.

8. A computer storage medium for storing a computer program, characterized in that: When the computer program is read by a computer, the computer executes the method of claim 1 .

9. A computer, comprising a processor and a storage medium, characterized in that: When the processor reads the computer program stored in the storage medium, the computer executes the method of claim 1 .

10. A computer program product, being a computer program, characterized in that When the computer program is executed, the method of claim 1 is implemented.

Citation Information

Patent Citations

  • Digital twinborn modeling method for bearing test bench

    CN114925558A

  • Digital twin simulation method for ship lubricating oil system

    CN116579241A

  • Description method for digital twin functional behaviors of industrial equipment

    CN117709191A

  • Aero-engine performance mechanism analogue simulation method based on digital twinning

    CN118194707A

  • Methods and systems for monitoring lubricant oil condition using photoacoustic modelling

    US20240068934A1

Cited By

  • Gas turbine state recovery control method based on state evaluation

    CN119644796A

  • Semi-physical test system, method and program for gas turbine capable of reversing and storage medium

    CN119739041A