Gas turbine state intelligent perception method based on digital twinning

Abstract

This invention provides a method for intelligent state perception of gas turbines based on digital twins. It combines digital twins with gas turbines and constructs corresponding digital twin models for the design, production, use, and operation and maintenance of gas turbines through digital twin technology. This enables full life cycle management of gas turbines and achieves intelligent state perception of gas turbines, intuitively displaying the state of gas turbines throughout their entire life cycle and facilitating the analysis of their state change trends and other characteristics.

Description

Technical Field

[0001] This invention belongs to the field of intelligent manufacturing, specifically relating to a method for intelligent sensing of the state of a gas turbine based on digital twins. Background Technology

[0002] Digital twin technology is a technology that uses a physical entity as a carrier and a virtual model to create a twin. Through bidirectional mapping between physical and virtual models, digital twin technology enables interactive operations between physical and virtual entities, constructing a new human-computer environment that integrates the virtual and real worlds.

[0003] Digital models are objects or processes in the digital world, possessing physical properties such as geometric shape, size, mass, and materials. Virtual models are mappings between physical entities and virtual entities, possessing information such as spatial location, time, and attributes. Digital twin technology, through the mapping of physical and virtual entities in time and space, enables real-time monitoring, analysis, and control of the physical world, and feeds the results back to the real world, thereby achieving perception and control of the physical world.

[0004] In recent years, digital twin technology has been widely applied in aerospace, machinery manufacturing, energy, and medical fields, providing an effective method for intelligent sensing of gas turbine operating status. The U.S. Department of Energy (DOE) launched the Advanced Programming Research Program to develop advanced propulsion systems. The German Aerospace Center (FAA) conducted research on the Support Systems and New Energy projects, developing new energy technologies. my country has also conducted extensive research in digital twin technology. For example, the Fifth Academy of China Aerospace Science and Technology Corporation proposed a framework for an intelligent monitoring system for aircraft based on digital twins, realizing real-time acquisition, transmission, storage, management, and visualization of flight data. Tsinghua University has utilized digital twin technology to construct a simulation experimental platform and a comprehensive testing and verification platform for complex equipment.

[0005] Marine gas turbines are one of the most important and critical components in the marine industry. Effective monitoring and fault diagnosis of their operating status are essential means to ensure the reliable operation of marine systems and the safe and stable operation of equipment.

[0006] Traditional gas turbine condition monitoring typically employs experience-based and manual fault diagnosis methods, which are inherently subjective and limited. With the development of intelligent technologies, traditional gas turbine condition monitoring methods also face challenges such as low levels of intelligence and difficulty in sharing monitoring data. Therefore, this paper proposes an intelligent condition sensing method for gas turbines based on digital twin technology and validates this method. As digital twin technology develops, its application in gas turbine condition monitoring is increasingly being studied. For example, in aircraft engine health management, aerospace manufacturers utilize digital twin technology to simulate and analyze engine components, airframes, and fuselages, establishing engine and overall engine simulation models. These simulation models are then used to predict faults and manage the health of engine components and the entire engine, significantly improving the reliability and safety of aircraft engines. In aerospace product lifecycle management, a large amount of data is generated during the design, production, manufacturing, and use of products, including substantial amounts of condition and operational data. However, currently, the collection and management of this data primarily relies on manual collection and processing. Since product lifecycle management involves numerous business types, various types of software and tools are needed for collection, processing, and analysis, ultimately forming a comprehensive product lifecycle management solution.

[0007] Judging from the current state of research on digital twin technology at home and abroad, although most scholars have conducted some research and application exploration on digital twin technology and gas turbine condition monitoring, there is a lack of systematic and in-depth research on the combined application of digital twin technology and gas turbine full life cycle process model. Summary of the Invention

[0008] The purpose of this invention is to provide a method for intelligent sensing of the state of a gas turbine based on digital twins.

[0009] A method for intelligent sensing of gas turbine status based on digital twins, characterized by the following steps: S1, build a digital twin-based intelligent construction system for gas turbines in both the design and production stages, combining digital twin gas turbine design with manufacturing process simulation, and constructing a digital twin model of the gas turbine in the design and production process in a virtual digital space; S2, during the usage phase, collects real-time operating parameters of the gas turbine through gas turbine sensors, processes, analyzes, stores, and classifies the collected real-time data; the processed data interacts in real-time with its digital twin model through a digital twin data interface, and displays the gas turbine's operating status in real-time through 3D visualization; S3's operation and maintenance process includes two parts: fault prediction and health management. Fault prediction includes status assessment and fault diagnosis, while health management includes an expert knowledge base and predictive maintenance. By combining with the gas turbine digital twin model, the operating status is analyzed and faults are diagnosed, predicting components that may need maintenance, and calling the corresponding maintenance strategies and plans from the expert knowledge base to feed back to the terminal equipment.

[0010] Furthermore, the status assessment comprehensively evaluates the gas turbine based on historical data in the database and provides a comprehensive evaluation curve for the gas turbine; the fault judgment judges abnormal data, and if a fault occurs, the alarm information is fed back to the terminal device in the form of a pop-up window.

[0011] Furthermore, the expert knowledge base stores diagnostic solutions for various faults; predictive maintenance compares and judges historical data with actual operation and maintenance data to predict the parts that need to be repaired, and recommends the best solution based on the expert knowledge base, and feeds back the solution and the key fault information that needs to be repaired to the terminal equipment.

[0012] Furthermore, the intelligent construction system for gas turbines digitizes every step of the factory production line, enabling real-time monitoring and analysis of the production process. It matches parameters from the virtual model with data from the actual production line, performing real-time analysis and adjustments to optimize each stage of the production process. This digital twin-based intelligent factory digitizes every step of the factory production line, allowing for real-time monitoring and analysis of the production process, and optimization through algorithms.

[0013] Furthermore, the digital twin model of the gas turbine in the design and manufacturing process includes digital twin models of various components of the gas turbine and an overall digital twin model of the gas turbine.

[0014] Furthermore, the modeling data includes design drawings and equipment drawings of the gas turbine.

[0015] Furthermore, the gas turbine sensors include a temperature sensor, a pressure sensor, a speed sensor, a crankshaft position sensor, and an acceleration sensor. The data collected by the sensors includes real-time data on engine lubricating oil temperature, coolant temperature, transmission lubricating oil temperature, power-end lubricating oil temperature, fuel pressure, intake manifold pressure, brake pressure, lubricating oil pressure, lubricating oil pressure at the hydraulic end of the plunger pump, power-end lubricating oil pressure, plunger pump discharge pressure, engine speed, crankshaft position, and acceleration.

[0016] Furthermore, the underlying state data of various parts of the gas turbine collected by the sensors are preprocessed, classified, and redundancy cleaned, including: a. Perform signal filtering, signal enhancement, feature extraction, data compression, data analysis, and pattern recognition; b. Divide the collected data into real-time data and historical data, and store them accordingly; c. Clean up redundant data; Real-time data is used to monitor the operating status of the gas turbine and diagnose faults in real time; historical data includes basic information data of the gas turbine, operating status data, maintenance record data, etc., and its function is to obtain the comprehensive evaluation curve of the gas turbine based on historical data.

[0017] Furthermore, the digital twin data interface adopts a CAN-OBD interface and transmits data through the CAN protocol. This interface is used to connect the real gas turbine entity and the digital twin body, thereby realizing data information interaction between the digital twin body and the real gas turbine entity.

[0018] Furthermore, the 3D visualization includes a real-time information display module and an operation log viewing module; the real-time information display module can read the real-time status information of the actual gas turbine through a data interface; the historical data query module can read the historical status information of the actual gas turbine through a data interface; and the operation log viewing module can read the operation log information of the actual gas turbine through a data interface, thereby realizing real-time and accurate monitoring of the operating status of the actual gas turbine.

[0019] The beneficial effects of this invention are as follows: (1) By building a digital twin-based intelligent construction system for gas turbines, this invention can realize real-time monitoring, digital management and process optimization of the site. At the same time, it can assist workers in operation in the form of three-dimensional process files and transform workers' assembly experience and knowledge into a knowledge base, which can be used for subsequent process guidance and simulation training.

[0020] (2) Based on digital twin technology, this invention realizes intelligent perception of the gas turbine's full life cycle status by constructing a gas turbine full life cycle model, making the gas turbine status monitoring more intuitive and improving monitoring efficiency.

[0021] (3) It realizes real-time and accurate monitoring of the operating status of gas turbines, provides an effective method for gas turbine operating status assessment and fault diagnosis, and provides strong support for gas turbine operating status prediction, life assessment and health management, and has important engineering application value.

[0022] (4) The embodiments of the present invention are simple and easy to implement and can achieve accurate monitoring of the actual operating status of gas turbines. Attached Figure Description

[0023] Figure 1This is a schematic diagram of the data interface interaction of the present invention; Figure 2 This is a schematic diagram of the structure of the present invention; Figure 3 This is a flowchart of the present invention. Detailed Implementation

[0024] The present invention will now be further described with reference to the accompanying drawings.

[0025] like Figures 1-3 As shown, a method for intelligent sensing of gas turbine status based on digital twins is characterized by the following steps: S1, build a digital twin-based intelligent construction system for gas turbines in both the design and production stages, combining digital twin gas turbine design with manufacturing process simulation, and constructing a digital twin model of the gas turbine in the design and production process in a virtual digital space; The intelligent construction system for gas turbines digitizes every step of the factory production line, enabling real-time monitoring and analysis of the production process. It matches parameters from the virtual model with data from the actual production line, performing real-time analysis and adjustments to optimize each stage of the production process. Similarly, the intelligent factory based on digital twins digitizes every step of the factory production line, allowing for real-time monitoring and analysis of the production process and optimization through algorithms.

[0026] The digital twin model of a gas turbine in the design and manufacturing process includes digital twin models of individual components of the gas turbine and an overall digital twin model of the gas turbine.

[0027] The modeling data includes design drawings and equipment drawings of the gas turbine.

[0028] S2, during the usage phase, collects real-time operating parameters of the gas turbine through gas turbine sensors, processes, analyzes, stores, and classifies the collected real-time data; the processed data interacts in real-time with its digital twin model through a digital twin data interface, and displays the gas turbine's operating status in real-time through 3D visualization; Gas turbine sensors include temperature sensors, pressure sensors, speed sensors, crankshaft position sensors, and acceleration sensors. The data collected by the sensors includes real-time data on engine lubricating oil temperature, coolant temperature, transmission lubricating oil temperature, power-end lubricating oil temperature, fuel pressure, intake manifold pressure, brake pressure, lubricating oil pressure, lubricating oil pressure, plunger pump hydraulic end lubricating oil pressure, power-end lubricating oil pressure, plunger pump discharge pressure, engine speed, crankshaft position, and acceleration.

[0029] The underlying state data of various parts of the gas turbine collected by sensors are preprocessed, classified, and redundancy removed, including: a. Perform signal filtering, signal enhancement, feature extraction, data compression, data analysis, and pattern recognition; b. Divide the collected data into real-time data and historical data, and store them accordingly; c. Clean up redundant data; Real-time data is used to monitor the operating status of the gas turbine and diagnose faults in real time; historical data includes basic information data of the gas turbine, operating status data, maintenance record data, etc., and its function is to obtain the comprehensive evaluation curve of the gas turbine based on historical data.

[0030] The digital twin data interface adopts the CAN-OBD interface and transmits data through the CAN protocol. This interface is used to connect the real gas turbine entity and the digital twin body, thereby realizing the data information interaction between the digital twin body and the real gas turbine entity.

[0031] The 3D visualization includes a real-time information display module and an operation log viewing module. The real-time information display module can read the real-time status information of the actual gas turbine through the data interface. The historical data query module can read the historical status information of the actual gas turbine through the data interface. The operation log viewing module can read the operation log information of the actual gas turbine through the data interface, thereby realizing real-time and accurate monitoring of the operating status of the actual gas turbine.

[0032] S3's operation and maintenance process includes two parts: fault prediction and health management. Fault prediction includes status assessment and fault diagnosis, while health management includes an expert knowledge base and predictive maintenance. By combining with the gas turbine digital twin model, the operating status is analyzed and faults are diagnosed, predicting components that may need maintenance, and calling the corresponding maintenance strategies and plans from the expert knowledge base to feed back to the terminal equipment.

[0033] The condition assessment comprehensively evaluates the gas turbine based on historical data in the database and provides a comprehensive evaluation curve for the gas turbine; the fault diagnosis judges abnormal data, and if a fault occurs, the alarm information is fed back to the terminal equipment in the form of a pop-up window.

[0034] The expert knowledge base stores diagnostic solutions for various faults; predictive maintenance compares and judges historical data with actual operation and maintenance data to predict the parts that need to be repaired, and recommends the best solution based on the expert knowledge base, and feeds back the solution and the key fault information that needs to be repaired to the terminal equipment.

[0035] Terminal devices include PCs and mobile devices.

[0036] The above description is merely a preferred embodiment of the present invention and is not intended to limit the invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for intelligent sensing of gas turbine status based on digital twins, characterized in that, Includes the following steps: S1, build a digital twin-based intelligent construction system for gas turbines in both the design and production stages, combining digital twin gas turbine design with manufacturing process simulation, and constructing a digital twin model of the gas turbine in the design and production process in a virtual digital space; S2, during the usage phase, collects real-time operating parameters of the gas turbine through gas turbine sensors, processes, analyzes, stores, and classifies the collected real-time data; the processed data interacts in real-time with its digital twin model through a digital twin data interface, and displays the gas turbine's operating status in real-time through 3D visualization; S3's operation and maintenance process includes two parts: fault prediction and health management. Fault prediction includes status assessment and fault diagnosis, while health management includes an expert knowledge base and predictive maintenance. By combining with the gas turbine digital twin model, the operating status is analyzed and faults are diagnosed, predicting components that may need maintenance, and calling the corresponding maintenance strategies and plans from the expert knowledge base to feed back to the terminal equipment.

2. The intelligent sensing method for gas turbine status based on digital twin as described in claim 1, characterized in that, The status assessment comprehensively evaluates the gas turbine based on historical data in the database and provides a comprehensive evaluation curve for the gas turbine; the fault judgment judges abnormal data, and if a fault occurs, the alarm information is fed back to the terminal device in the form of a pop-up window.

3. The intelligent sensing method for gas turbine status based on digital twin as described in claim 1, characterized in that, The expert knowledge base stores diagnostic solutions for various faults; predictive maintenance compares and judges historical data with actual operation and maintenance data to predict the parts that need to be repaired, and recommends the best solution based on the expert knowledge base, and feeds back the solution and the key fault information that needs to be repaired to the terminal equipment.

4. The intelligent sensing method for gas turbine status based on digital twin as described in claim 1, characterized in that, The intelligent construction system for gas turbines digitizes every step of the factory production line, enabling real-time monitoring and analysis of the production process. It matches parameters from the virtual model with data from the actual production line, performing real-time analysis and adjustments to optimize each stage of the production process. This digital twin-based intelligent factory digitizes every step of the factory production line, allowing for real-time monitoring and analysis of the production process and optimization through algorithms.

5. The intelligent sensing method for gas turbine status based on digital twin according to claim 1, characterized in that, The digital twin model of the gas turbine in the design and manufacturing process includes digital twin models of various components of the gas turbine and an overall digital twin model of the gas turbine.

6. The intelligent sensing method for gas turbine status based on digital twin according to claim 1, characterized in that, The modeling data includes design drawings and equipment drawings of the gas turbine.

7. The intelligent sensing method for gas turbine status based on digital twin according to claim 1, characterized in that, The gas turbine sensors include a temperature sensor, a pressure sensor, a speed sensor, a crankshaft position sensor, and an acceleration sensor. The data collected by the sensors includes real-time data on engine lubricating oil temperature, coolant temperature, transmission lubricating oil temperature, power-end lubricating oil temperature, fuel pressure, intake manifold pressure, brake pressure, lubricating oil pressure, lubricating oil pressure, plunger pump hydraulic end lubricating oil pressure, power-end lubricating oil pressure, plunger pump discharge pressure, engine speed, crankshaft position, and acceleration.

8. The intelligent sensing method for gas turbine status based on digital twin according to claim 1, characterized in that, The underlying state data of various parts of the gas turbine collected by sensors are preprocessed, classified, and redundancy removed, including: a. Perform signal filtering, signal enhancement, feature extraction, data compression, data analysis, and pattern recognition; b. Divide the collected data into real-time data and historical data, and store them accordingly; c. Clean up redundant data; Real-time data is used to monitor the operating status of the gas turbine and diagnose faults in real time; historical data includes basic information data of the gas turbine, operating status data, maintenance record data, etc., and its function is to obtain the comprehensive evaluation curve of the gas turbine based on historical data.

9. The intelligent sensing method for gas turbine status based on digital twin according to claim 1, characterized in that, The digital twin data interface adopts the CAN-OBD interface and transmits data through the CAN protocol. This interface is used to connect the real gas turbine entity and the digital twin body, thereby realizing data information interaction between the digital twin body and the real gas turbine entity.

10. The intelligent sensing method for gas turbine status based on digital twin according to claim 1, characterized in that, The 3D visualization includes a real-time information display module and an operation log viewing module. The real-time information display module can read the real-time status information of the actual gas turbine through a data interface. The historical data query module can read the historical status information of the actual gas turbine through a data interface. The operation log viewing module can read the operation log information of the actual gas turbine through a data interface, thereby realizing real-time and accurate monitoring of the operating status of the actual gas turbine.

Images