Intelligent diagnosis and preventive maintenance method of steam turbine system and related device

Abstract

The invention discloses an intelligent diagnosis and preventive maintenance method of a steam turbine system and a related device. Comprising the steps that a three-dimensional thermodynamic model of a steam turbine system is established through digital twin modeling, virtual sensor nodes are implanted into the three-dimensional thermodynamic model, and operation data of the steam turbine system are collected in real time; based on the collected operation data, an AI defect pre-judgment algorithm is adopted to analyze the health state of the steam turbine system, and prediction defect information is output; according to the predicted defect information, a modular maintenance process is executed, a maintenance result is obtained, and the modular maintenance process comprises rotor system detection, sealing system regulation and control and thermodynamic system diagnosis; an augmented reality (AR) auxiliary operation system is adopted, and maintenance operation is guided in real time and a safety range is monitored based on a modular maintenance process; and based on the maintenance result and the operation data, verifying the steam turbine system performance and generating a health index report. Diagnosis accuracy and maintenance efficiency are remarkably improved, operation and maintenance cost is reduced, and stable and efficient operation of the system is guaranteed.

Description

Technical Field

[0001] The present invention belongs to the technical field of equipment maintenance, and in particular relates to an intelligent diagnosis and preventive maintenance method and related devices for a steam turbine system. Background Art

[0002] In industries such as energy, power, and chemicals, steam turbines serve as core power equipment, and their operational stability and reliability are crucial to the entire production process. Traditional steam turbine system maintenance relies primarily on scheduled inspections and post-fault repairs. Scheduled inspections fail to accurately identify the equipment's true health, leading to over- or under-maintenance. This not only wastes resources but can also impact equipment performance due to frequent disassembly and assembly. Post-fault repairs, performed only after equipment failures occur, are a reactive approach that can lead to prolonged downtime, significant economic losses, and potentially secondary safety incidents.

[0003] With the digital transformation of industry, some companies have begun using sensors to monitor equipment operating data. However, traditional data processing methods struggle to effectively mine the data's value, and their ability to predict potential faults is limited. Furthermore, existing maintenance operations lack intuitive guidance, forcing maintenance personnel to rely on experience, which is inefficient, prone to errors, and presents a high safety risk. Furthermore, each maintenance step is relatively independent and lacks systematic integration, making comprehensive and efficient maintenance of steam turbine systems impossible. Therefore, there is an urgent need for an intelligent diagnosis and preventive maintenance method and system for steam turbine systems that can achieve accurate diagnosis, efficient maintenance, and safety assurance. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent diagnosis and preventive maintenance method and related devices for a steam turbine system, so as to overcome the shortcomings of the existing technology in which the judgment of the health status of the steam turbine is mostly dependent on experience, the ability to predict potential faults is weak, the various links of traditional maintenance are scattered, there is a lack of systematic planning and efficient technical means, the maintenance time is long and the cost is high, the maintenance personnel rely on experience and are prone to mistakes, and the safety risks are high.

[0005] In order to achieve the above object, the present invention provides the following technical solutions: In a first aspect, the present invention provides an intelligent diagnosis and preventive maintenance method for a steam turbine system, comprising the following steps: Step 1: Establish a three-dimensional thermodynamic model of the steam turbine system through digital twin modeling, and implant virtual sensor nodes in the three-dimensional thermodynamic model to collect operating data of the steam turbine system in real time; Step 2: Based on the collected operating data, an AI defect prediction algorithm is used to analyze the health status of the steam turbine system and output predicted defect information; Step 3: According to the predicted defect information, execute the modular maintenance process to obtain the maintenance result. The modular maintenance process includes rotor system detection, seal system regulation, and thermal system diagnosis; Step 4: Adopt an augmented reality (AR) assisted operation system to guide the maintenance operation in real time based on the modular maintenance process and monitor the safety range; Step 5: Based on the maintenance result of Step 3 and the operation data of Step 4, verify the performance of the steam turbine system and generate a health index report.

[0006] Further, in Step 1, the three-dimensional thermodynamic model includes an aerodynamic performance model, a rotor dynamics model, and a thermal stress model. The implantation positions of the virtual sensor nodes include the inlets and outlets of the high-pressure cylinder, the inlets and outlets of the intermediate-pressure cylinder, the bearing pedestals, and the gland clearances; The operation data is synchronously collected by physical sensors and virtual sensor nodes, and wavelet transform is used for noise elimination processing.

[0007] Further, in Step 2, the health state is quantified by the comprehensive health index HI, which is calculated by weighting the steam turbine system efficiency, vibration margin, and seal leakage rate; The quantification calculation process of the comprehensive health index HI includes: obtaining the current efficiency of the steam turbine system design efficiency vibration margin[[ID=−19]] and seal leakage rate ; The comprehensive health index HI is calculated by the following formula: ; where α, β, and γ are dynamic weight coefficients, and α + β + γ = 1; The dynamic weight coefficients α, β, and γ are periodically adjusted based on the SHAP value analysis method.

[0008] Further, in Step 3, the rotor system detection includes online dynamic balance correction and blade defect detection. The online dynamic balance correction generates a counterweight plan through a phase compensation algorithm; The formula for generating the counterweight plan is: ; where is the counterweight mass, is the counterweight radius, is the initial vibration amplitude, is the vibration phase angle, k is the rotor stiffness coefficient, and ω is the current rotational speed.

[0009] Further, in the step 3, the sealing system regulation includes an intelligent adjustable steam seal and a closed-loop control of the leakage rate; The output value of the PID algorithm for the closed-loop control of the leakage rate is: ; wherein, , is the upper limit of the designed leakage rate, , , are the parameters tuned by the Ziegler-Nichols method.

[0010] Further, in the step 3, the thermal system diagnosis includes the identification of condenser fouling, and the identification of condenser fouling is realized through a relationship model between the heat transfer coefficient and the circulating water flow rate.

[0011] Further, the specific process in the step 4 includes: Collect the real-time images of the maintenance site, and obtain the environmental three-dimensional point cloud data through the ToF depth sensor; Perform spatial registration on the operation instructions in the modular maintenance process and the three-dimensional thermodynamic model in the digital twin model to generate AR visual guidance content; Compare the tactile signal of the force feedback glove with the safety range threshold, and issue an alarm when it does not match the safety range threshold.

[0012] Further, the AR visual guidance content specifically includes the animation overlay of the disassembly and assembly sequence of key components; the real-time numerical display of the bolt tightening torque; the infrared temperature warning boundary of the dangerous area.

[0013] In a second aspect, the present invention provides an intelligent diagnosis and preventive maintenance system for a steam turbine system, including: An acquisition module, which establishes a three-dimensional thermodynamic model of the steam turbine system through digital twin modeling, and implants virtual sensor nodes in the three-dimensional thermodynamic model to collect the operation data of the steam turbine system in real time; A prediction module, which analyzes the health status of the steam turbine system based on the collected operation data by using an AI defect prediction algorithm and outputs prediction defect information; A maintenance module, which executes a modular maintenance process according to the prediction defect information to obtain a maintenance result, and the modular maintenance process includes rotor system detection, sealing system regulation and thermal system diagnosis; A visual monitoring module, which adopts an augmented reality AR-assisted operation system to guide the maintenance operation in real time based on the modular maintenance process and monitor the safety range; A generation module, which verifies the performance of the steam turbine system and generates a health index report based on the maintenance result of the maintenance module and the operation data of the visual monitoring module.

[0014] In a third aspect, the present invention provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of an intelligent diagnosis and preventive maintenance method for a steam turbine system are implemented.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the steps of an intelligent diagnosis and preventive maintenance method for a steam turbine system are implemented.

[0016] Compared with the prior art, the present invention has the following beneficial technical effects: The present invention provides an intelligent diagnosis and preventive maintenance method for a steam turbine system. By establishing a three-dimensional thermodynamic model of the steam turbine system through digital twin modeling and implanting virtual sensor nodes to work in cooperation with physical sensors, comprehensive and real-time acquisition of the operation data of the steam turbine system is achieved. The AI defect prediction algorithm is used to analyze the health status of the steam turbine system, which can quickly identify potential fault hazards and output predicted defect information. According to the predicted defect information, a modular maintenance process is executed, and an augmented reality (AR) assisted operation system is adopted to guide the maintenance operation in real time. The modular maintenance process disassembles complex maintenance tasks into multiple professional modules such as rotor system detection, seal system regulation, and thermodynamic system diagnosis. Each module specifically solves a particular problem, making the maintenance process more systematic and standardized, and reducing unnecessary maintenance steps. Based on the maintenance results and operation data, the performance of the steam turbine system is verified and a health index report is generated, which can comprehensively and scientifically quantify the evaluation of the maintenance effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention, and thus should not be regarded as limiting the scope. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts. Figure 1 It is a schematic flow chart of an intelligent diagnosis and preventive maintenance method for a steam turbine system in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0018] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention usually described and illustrated in the accompanying drawings here can be arranged and designed in various different configurations.

[0019] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the claimed present invention, but merely represents selected embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0020] It should be noted that like reference numerals and letters denote like items in the following drawings. Therefore, once an item is defined in one drawing, it does not require further definition and explanation in subsequent drawings.

[0021] In the description of the embodiments of the present invention, it should be noted that if terms such as "upper", "lower", "horizontal", "inner", etc. indicate the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, or the orientation or positional relationship in which the inventive product is usually placed during use, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be construed as a limitation of the present invention. In addition, terms such as "first", "second", etc. are only used for descriptive distinction and cannot be construed as indicating or implying relative importance.

[0022] In addition, if the term "horizontal" appears, it does not mean that the component is required to be absolutely horizontal, but it can be slightly inclined. For example, "horizontal" only means that its direction is more horizontal relative to "vertical", and does not mean that the structure must be completely horizontal, but it can be slightly inclined.

[0023] In the description of the embodiments of the present invention, it should also be noted that unless otherwise clearly specified and limited, if terms such as "set", "installed", "connected", "connected" are understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the communication inside two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0024] The following further describes the present invention in detail with reference to the accompanying drawings: Refer to Figure 1, an intelligent diagnosis and preventive maintenance method for a steam turbine system, comprising the following steps: Step 1, establish a three-dimensional thermodynamic model of the steam turbine system through digital twin modeling, and implant virtual sensor nodes in the three-dimensional thermodynamic model to collect the operation data of the steam turbine system in real time; The three-dimensional thermodynamic model includes an aerodynamic performance model, a rotor dynamics model, and a thermal stress model. The implantation positions of the virtual sensor nodes include the inlets and outlets of the high-pressure cylinder, the inlets and outlets of the intermediate-pressure cylinder, the bearing pedestals, and the gland clearances; The specific process of implanting virtual sensor nodes in the three-dimensional thermodynamic model is as follows: Mark the key monitoring positions corresponding to the physical structure of the steam turbine system in the geometric grid of the three-dimensional thermodynamic model. The key monitoring positions at least include the inlets and outlets of the high-pressure cylinder, the inlets and outlets of the intermediate-pressure cylinder, the bearing pedestals, and the gland clearances; Align the CAD coordinate system of the actual steam turbine system with the coordinate system of the three-dimensional thermodynamic model through affine transformation. The transformation parameters include the rotation matrix R and the translation vector T; Bind the output variables of the corresponding physical field solver to each virtual sensor node. Among them, the nodes at the inlets and outlets of the high-pressure cylinder and the intermediate-pressure cylinder are bound with the pressure, temperature, and flow rate data of the aerodynamic performance model; the bearing pedestal nodes are bound with the vibration displacement and phase angle data of the rotor dynamics model; the gland clearance nodes are bound with the temperature gradient and thermal strain data of the thermal stress model; Establish a data channel between the physical sensor and the virtual sensor through the OPC UA protocol, and adopt a timestamp synchronization mechanism to achieve millisecond-level data fusion.

[0025] The operation data is synchronously collected through the physical sensor and the virtual sensor nodes, and wavelet transform is used for noise elimination processing. For example, the vibration data collected during a certain period is processed to effectively remove the noise signals generated by environmental electromagnetic interference.

[0026] By combining virtual and physical sensors to collect data and perform noise reduction processing, compared with the traditional single data collection method, the data accuracy can be improved, avoiding misjudgment of faults caused by data errors, overcoming the problem of insufficient accuracy in traditional diagnosis, and reflecting the advantage of accurate diagnosis of the present invention.

[0027] Step 2, based on the collected operation data, adopt an AI defect prediction algorithm to analyze the health status of the steam turbine system and output predicted defect information; The health status is quantified by the comprehensive health index HI. The comprehensive health index HI is obtained by weighted calculation of the steam turbine system efficiency, vibration margin, and seal leakage rate; The quantification calculation process of the comprehensive health index HI includes: obtaining the current efficiency of the steam turbine system Design efficiency 、vibration margin and seal leakage rate ; Calculate the comprehensive health index HI through the following formula: ; where α, β, and γ are dynamic weight coefficients and satisfy α + β + γ = 1; Periodically adjust the dynamic weight coefficients α, β, and γ based on the SHAP value analysis method.

[0028] Utilize the AI algorithm and the quantified comprehensive health index, combined with dynamic weight adjustment, to predict potential faults in advance. Compared with traditional empirical judgment, the accuracy of fault prediction is improved, achieving a precise assessment of the health status of the steam turbine, promptly discovering potential problems, and effectively avoiding shutdown losses caused by sudden failures.

[0029] Step 3, according to the predicted defect information, execute the modular maintenance process to obtain the maintenance result. The modular maintenance process includes rotor system detection, seal system regulation, and thermal system diagnosis; Rotor system detection includes online dynamic balance correction and blade defect detection. The online dynamic balance correction generates a counterweight plan through the phase compensation algorithm; The formula for generating the counterweight plan is: ; where is the counterweight mass, is the counterweight radius, is the initial vibration amplitude, is the vibration phase angle, k is the rotor stiffness coefficient, and ω is the current rotational speed; Seal system regulation includes intelligent adjustable steam seals and closed-loop control of the leakage rate. The intelligent adjustable steam seals drive the radial displacement of the steam seal teeth through piezoelectric ceramics; In the rotor system detection, when abnormal vibration of the steam turbine is detected, a counterweight plan is generated through the phase compensation algorithm In this embodiment, the initial vibration amplitude is 10 μm, the vibration phase angle is 45°, the rotor stiffness coefficient k is 50 N / μm, and the current rotational speed ω is 3000 r / min; Calculate the counterweight mass and the counterweight radius for online dynamic balance correction, and use online vibration monitoring for blade defect detection.

[0030] In this example, the upper limit of the designed leakage rate is set to 0.03, and the PID algorithm is tuned by the Ziegler-Nichols method Kp = 0.5, Ki = 0.1, Kd = 0.2; According to Perform calculations and adjust the sealing system to control the leakage within a reasonable range.

[0031] In the diagnosis of the thermal system, the fouling of the condenser is identified through the relationship model between the heat transfer coefficient and the circulating water flow rate. If it is found that the heat transfer coefficient drops by more than the set threshold, it is judged that the condenser is fouled, and the cleaning operation is arranged in a timely manner.

[0032] The output value of the PID algorithm for closed-loop control of the leakage rate is: ; Among them, , is the upper limit of the designed leakage rate, , , are the parameters tuned by the Ziegler-Nichols method; The modular overhaul process adopts professional technologies for different systems, and each module works in coordination to improve the overhaul efficiency. At the same time, the application of technologies such as online dynamic balance correction and intelligent seal regulation avoids overhauls and repeated overhauls, reducing the overhaul cost.

[0033] Step 4: Adopt an augmented reality (AR) assisted operation system to guide the overhaul operation in real time based on the modular overhaul process and monitor the safety range; The specific process in Step 4 includes: Adopt an augmented reality (AR) assisted operation system to collect real-time images of the overhaul site through a ToF depth sensor to obtain three-dimensional point cloud data of the environment; register the operation instructions in the modular overhaul process with the three-dimensional thermodynamic model in the digital twin model to generate AR visual guidance content. For example, when disassembling the bolts of the steam turbine cylinder block, the correct disassembly and assembly sequence is displayed by overlaying an animation, and the bolt tightening torque value is displayed in real time. At the same time, compare the tactile signal of the force feedback glove with the safety range threshold. When the overhaul personnel's operation approaches the dangerous area, the AR system issues an infrared temperature warning to ensure the safety of the overhaul operation. For example, when the tool enters the high-temperature warning area, T > 150 °C; when the tightening torque exceeds the limit, > the design value ± 10%; when the limb approaches the live body, the distance < 0.5 m.

[0034] The AR assisted operation system provides intuitive visual guidance for overhaul personnel, avoiding damage to equipment due to improper operation and effectively solving the problem of lack of safety guarantee in traditional overhauls.

[0035] Step 5: Verify the performance of the steam turbine system based on the overhaul results of the modular overhaul process and the operation data of the AR assisted operation system. Recalculate the comprehensive health index HI , compare the operating parameters before and after the overhaul, and finally generate a health index report, which details the overhaul process, overhaul effect and the current health status of the system.

[0036] In a second aspect, the present invention provides an intelligent diagnosis and preventive maintenance system for a steam turbine system, comprising: An acquisition module that establishes a three-dimensional thermodynamic model of the steam turbine system through digital twin modeling, implants virtual sensor nodes in the three-dimensional thermodynamic model, and collects the operation data of the steam turbine system in real time; A prediction module that analyzes the health status of the steam turbine system using an AI defect prediction algorithm based on the collected operation data and outputs predicted defect information; A maintenance module that executes a modular maintenance process according to the predicted defect information to obtain a maintenance result. The modular maintenance process includes rotor system detection, seal system regulation, and thermodynamic system diagnosis; A visual monitoring module that uses an augmented reality (AR) assisted operation system to guide maintenance operations in real time based on the modular maintenance process and monitor the safety range; A generation module that verifies the performance of the steam turbine system and generates a health index report based on the maintenance result of the maintenance module and the operation data of the visual monitoring module.

[0037] In an embodiment of the present invention, a computer device is provided. The computer device includes a processor and a memory. The memory is used to store a computer program, and the computer program includes program instructions. The processor is used to execute the program instructions stored in the computer storage medium. The processor may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, and is suitable for implementing one or more instructions. Specifically, it is suitable for loading and executing one or more instructions in the computer storage medium to implement the corresponding method flow or corresponding function. The processor described in the embodiment of the present invention can be used for the operation of an intelligent diagnosis and preventive maintenance method for a steam turbine system.

[0038] The present invention also provides a storage medium, specifically a computer-readable storage medium (Memory). The computer-readable storage medium is a memory device in a computer device and is used to store programs and data. It can be understood that the computer-readable storage medium here can include both the built-in storage medium in the computer device and, of course, the extended storage medium supported by the computer device. The computer-readable storage medium provides a storage space, and this storage space stores the operating system of the terminal. Moreover, in this storage space, there is also stored one or more instructions suitable for being loaded and executed by a processor, and these instructions can be one or more computer programs (including program codes). It should be noted that the computer-readable storage medium here can be a high-speed RAM memory or a non-volatile memory, such as at least one disk memory. The one or more instructions stored in the computer-readable storage medium can be loaded and executed by the processor to implement the corresponding steps of the intelligent diagnosis and preventive maintenance method for a steam turbine system in the above embodiments.

[0039] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0040] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, such that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the functions specified in Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0041] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, such that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the functions in Figure 1 one flow or multiple flows and / or blocks Figure 1The functions specified in one or more boxes.

[0042] These computer program instructions can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate a computer-implemented process. Thus, the instructions executed on the computer or other programmable device provide for implementing the steps of the functions specified in one Figure 1 One process or more processes and / or boxes Figure 1 The steps of the functions specified in one or more boxes.

[0043] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the specific implementation manners of the present invention can still be modified or equivalently replaced, and any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. An intelligent diagnosis and preventive maintenance method for a steam turbine system, characterized in that, It includes the following steps: Step 1, establish a three-dimensional thermodynamic model of the steam turbine system through digital twin modeling, and implant virtual sensor nodes in the three-dimensional thermodynamic model to collect the operation data of the steam turbine system in real time; Step 2, based on the collected operation data, use the AI defect prediction algorithm to analyze the health status of the steam turbine system and output the predicted defect information; Step 3, according to the predicted defect information, execute the modular maintenance process to obtain the maintenance result. The modular maintenance process includes rotor system detection, seal system regulation and thermodynamic system diagnosis; Step 4, adopt the augmented reality AR-assisted operation system to guide the maintenance operation in real time based on the modular maintenance process and monitor the safety range; Step 5, based on the maintenance result of Step 3 and the operation data of Step 4, verify the performance of the steam turbine system and generate a health index report.

2. The intelligent diagnosis and preventive maintenance method of a steam turbine system according to claim 1, characterized in that In Step 1, the three-dimensional thermodynamic model includes an aerodynamic performance model, a rotor dynamics model and a thermal stress model. The implantation positions of the virtual sensor nodes include the inlets and outlets of the high-pressure cylinder, the inlets and outlets of the intermediate-pressure cylinder, the bearing pedestals and the gland clearances; The operation data is collected synchronously by physical sensors and virtual sensor nodes, and wavelet transform is used for noise elimination processing.

3. The intelligent diagnosis and preventive maintenance method for a steam turbine system according to claim 1, characterized in that In Step 2, the health status is quantified by the comprehensive health index HI, and the comprehensive health index HI is calculated by weighted calculation of the steam turbine system efficiency, vibration margin and seal leakage rate; The process of quantitatively calculating the comprehensive health index HI includes: obtaining the current efficiency of the steam turbine system , design efficiency , vibration margin and seal leakage rate ; The comprehensive health index HI is calculated by the following formula: ； where α, β, γ are dynamic weight coefficients and satisfy α + β + γ = 1; The dynamic weight coefficients α, β, γ are periodically adjusted based on the SHAP value analysis method.

4. The intelligent diagnosis and preventive maintenance method for a steam turbine system according to claim 1, characterized in that, In Step 3, the rotor system detection includes online dynamic balance correction and blade defect detection, and the online dynamic balance correction generates a counterweight scheme through a phase compensation algorithm; The formula for generating the counterweight scheme is: ； Among them, is the counterweight mass, is the counterweight radius, is the initial vibration amplitude, is the vibration phase angle, k is the rotor stiffness coefficient, and ω is the current rotational speed.

5. The intelligent diagnosis and preventive maintenance method for a steam turbine system according to claim 1, characterized in that, In Step 3, the seal system regulation includes intelligent adjustable gland and closed-loop control of the leakage amount; The output value of the PID algorithm for the closed-loop control of the leakage amount is: ； Among them, , is the upper limit of the designed leakage flow rate, , , are the parameters tuned by the Ziegler-Nichols method.

6. The intelligent diagnosis and preventive maintenance method for a steam turbine system according to claim 1, characterized in that, The specific process in Step 4 includes: Collect the real-time images of the maintenance site and obtain the three-dimensional point cloud data of the environment through a ToF depth sensor; Register the operation instructions in the modular maintenance process with the three-dimensional thermodynamic model in the digital twin model to generate AR visualization guidance content; Compare the tactile signal of the force feedback glove with the safety range threshold, and issue an alarm when it does not match the safety range threshold.

7. The intelligent diagnosis and preventive maintenance method of a steam turbine system according to claim 6, characterized in that, The AR visualization guidance content specifically includes the animation overlay of the disassembly and assembly sequence of key components; the real-time numerical display of the bolt tightening torque; the infrared temperature warning boundary of the dangerous area.

8. An intelligent diagnosis and preventive maintenance system for a steam turbine system, characterized in that, It includes: A collection module, which establishes a three-dimensional thermodynamic model of the steam turbine system through digital twin modeling, and implants virtual sensor nodes in the three-dimensional thermodynamic model to collect the operation data of the steam turbine system in real time; A prediction module, which based on the collected operation data, uses the AI defect prediction algorithm to analyze the health status of the steam turbine system and output the predicted defect information; The maintenance module executes a modular maintenance process based on the predicted defect information to obtain a maintenance result. The modular maintenance process includes rotor system detection, seal system regulation, and thermal system diagnosis; The visual monitoring module uses an augmented reality (AR) assisted operation system to guide the maintenance operation in real time based on the modular maintenance process and monitor the safety range; The generation module verifies the performance of the steam turbine system and generates a health index report based on the maintenance result of the maintenance module and the operation data of the visual monitoring module.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1-7.

Images