Composite vibration reduction control method and system for excessive start-up vibration of steam generator

Abstract

The application provides a composite vibration reduction control method and system for excessive start-up vibration of a steam generator, and belongs to the technical field of steam generator vibration control. The method comprises the following steps: obtaining a vibration reduction reference parameter and installing a passive vibration reduction unit comprising a dynamic vibration absorber and a metal rubber vibration isolation pad; collecting pressure, temperature and flow data during the start-up process to construct a state perception data set; training a machine learning model using the data set to obtain an active control model; integrating the passive vibration reduction system and the active control model, optimizing the matching relationship through simulation and testing to generate a composite control strategy; and simultaneously executing passive energy dissipation and active hybrid ratio regulation during the start-up phase to suppress vibration. The application combines passive vibration reduction with active source control, realizes whole-chain collaborative vibration reduction from source suppression to transmission path isolation to receptor energy absorption, effectively reduces the structural vibration response of the steam generator during the start-up phase, and ensures the safe operation of the equipment.

Description

Technical Field

[0001] This invention relates to the field of steam generator vibration control technology, and in particular to a composite vibration reduction control method and system for excessive start-up vibration of steam generators. Background Technology

[0002] Steam generators are widely used in industrial production, aerospace, and nuclear power generation. During startup, the strong transient characteristics of the internal combustion and evaporation processes can easily lead to a mismatch in the fuel-oxidant mixture, causing severe vibrations. Actual measurements show that the vibration acceleration during the startup and shutdown phases of steam generators can reach over 1000G. Such severe vibrations can easily cause fatigue damage to steam pipes, ejector equipment, and connecting structures, seriously threatening the safe operation and service life of the equipment. Furthermore, the drastic fluctuations in steam parameters and significant flow instability during startup further exacerbate fluid pressure fluctuations and vibrations.

[0003] Currently, most existing technologies for addressing the vibration problem of steam generators employ single passive vibration reduction measures. For example, vibration isolation pads, anti-vibration rods, supports, or dampers are installed on pipes or equipment to suppress vibration transmission by changing local stiffness or increasing damping. Some solutions use dynamic vibration absorbers, which absorb vibration energy by adjusting their natural frequency to match the resonant frequency of the structure. However, these passive vibration reduction methods have the following shortcomings: (1) The vibration excitation frequency during the start-up phase is complex and variable and dynamically drifts over time, making it difficult for vibration reduction devices with fixed parameters to maintain optimal vibration reduction throughout the entire period; (2) Single passive vibration reduction measures only act on the vibration transmission path and cannot suppress the generation of vibration from the root; (3) The working environment of steam generators is harsh (high temperature, corrosion, etc.), and traditional rubber-based vibration isolation materials are prone to aging and failure, resulting in insufficient reliability.

[0004] Furthermore, current technologies lack active control methods for the combustion process, failing to adjust the fuel-oxidant mixing ratio in real time based on changes in state parameters such as pressure and temperature during the start-up transient process. Consequently, they cannot reduce vibration excitation at its source. Therefore, a comprehensive solution capable of simultaneously achieving passive vibration reduction and active source control is urgently needed to effectively suppress severe vibrations during the start-up phase of steam generators. Summary of the Invention

[0005] To address the aforementioned problems, the present invention aims to provide a composite vibration reduction control method and system that combines passive vibration reduction with active source control, so as to effectively suppress severe vibration during the start-up phase of a steam generator and ensure the safe operation of the equipment.

[0006] The first aspect of the present invention provides a composite vibration reduction control method for excessive start-up vibration of a steam generator, comprising the following steps:

[0007] Obtain vibration reduction reference parameters, and install a passive vibration reduction unit including a dynamic vibration absorber and a metal rubber vibration isolation pad according to the vibration reduction reference parameters to form an initial passive vibration reduction system;

[0008] Under the initial passive vibration reduction system operating condition, pressure, temperature and flow data during the steam generator start-up process are collected to construct a state-aware dataset;

[0009] The state-aware dataset is used to train a machine learning-based hybrid ratio control model to obtain an active control model;

[0010] The initial passive vibration reduction system is integrated with the active control model, and the matching relationship between the passive vibration reduction parameters and the active control parameters is optimized through simulation and experiment to generate a composite control strategy.

[0011] The composite control strategy is used to simultaneously perform passive energy dissipation and active mixing ratio regulation during the steam generator start-up phase to suppress vibration; wherein, the passive energy dissipation includes aligning the natural frequency of the dynamic vibration absorber with the resonance peak of the main system to absorb energy, and deviating the natural frequency of the metal rubber vibration isolation pad from the resonance peak to isolate it.

[0012] Furthermore, the step of obtaining the vibration reduction reference parameters includes:

[0013] The excitation frequency range of the main system during the power-on phase was determined through modal testing and spectrum analysis.

[0014] Based on the excitation frequency range, the resonant frequency of the main system is extracted;

[0015] Based on the theory of tuned mass dampers, the stiffness of the elastic element and the mass of the mass block of the dynamic vibration absorber are adjusted so that their natural frequency is aligned with the resonant frequency, and this natural frequency is used as one of the vibration reduction reference parameters.

[0016] Furthermore, the optimization of the dynamic vibration absorber also includes:

[0017] An adjustable stiffness elastic element is used to adjust the stiffness in real time according to the dynamic changes of the main system frequency during the start-up process, so that the natural frequency of the vibration absorber remains in a tuned state.

[0018] Furthermore, the optimization of the dynamic vibration absorber also includes:

[0019] The location of the node with the largest vibration displacement in the main system is determined by finite element analysis, and the node location is taken as the vibration sensitive point.

[0020] The dynamic vibration absorber is installed at the node location, or multiple small vibration absorber units are distributed and installed at multiple vibration-sensitive points to form an array-type vibration absorption structure.

[0021] Furthermore, the step of obtaining the vibration reduction reference parameters also includes:

[0022] The metal wire material is selected based on the operating temperature and corrosive environment of the steam generator. The wire diameter, weaving density and forming pressure are optimized through orthogonal experiments or response surface methodology. A mapping relationship between the natural frequency and structural parameters is established so that the natural frequency of the metal rubber vibration isolation pad avoids the resonance peak range of the main system. This natural frequency is then used as one of the vibration reduction reference parameters.

[0023] Furthermore, the optimization of the metal rubber vibration isolation pad also includes:

[0024] A three-dimensional vibration isolation structure is designed to achieve multi-directional isolation of axial, radial, and torsional vibrations by adjusting the braiding direction of the metal wires.

[0025] A multi-layer composite structure is adopted, which stacks metal and rubber pads with different stiffnesses to form a wide-band vibration isolation characteristic.

[0026] Furthermore, the installation optimization of the metal rubber vibration isolation pad includes:

[0027] The installation positions of pipes, valves and bases are determined by topology optimization method, forming a layout with multi-point support and graded vibration isolation.

[0028] Furthermore, the step of constructing the state-aware dataset includes:

[0029] Based on historical pressure and temperature data from key measuring points of the steam generator, and combined with flow characteristic parameters of liquid oxygen, alcohol, and water, a basic sample dataset was constructed.

[0030] A combustion reaction kinetic model of liquid oxygen and alcohol is established, CFD simulation calculations are carried out, and the simulation results are extended to the basic sample dataset to form the state-aware dataset.

[0031] The machine learning model is trained using the pressure and temperature at the measurement point as input features and the mixing ratio of liquid oxygen, alcohol and water as the prediction target.

[0032] Furthermore, the step of generating the composite control strategy includes:

[0033] Establish a simulation model that includes the physical characteristic parameters of the passive vibration damping unit and the output commands of the active control model;

[0034] Through simulation and experimentation, the matching relationship between passive vibration reduction parameters and active mixing ratio control commands is determined, and the composite control strategy is generated.

[0035] A second aspect of the present invention provides a composite vibration reduction control system for excessive start-up vibration of a steam generator, comprising:

[0036] The reference acquisition module is used to acquire vibration reduction reference parameters;

[0037] A passive vibration damping unit, comprising a dynamic vibration absorber and a metal rubber vibration isolation pad, is used to install and form an initial passive vibration damping system according to the vibration damping reference parameters;

[0038] The data acquisition module is used to collect pressure, temperature and flow data of the steam generator during the start-up process under the initial passive vibration reduction system operating state, and to construct a state-aware dataset.

[0039] The model training module is used to train a machine learning-based hybrid control model using the state-aware dataset to obtain an active control model.

[0040] The strategy generation module is used to integrate the initial passive vibration reduction system with the active control model, and to optimize the matching relationship between the passive vibration reduction parameters and the active control parameters through simulation and experimentation to generate a composite control strategy.

[0041] The execution module is used to simultaneously perform passive energy dissipation and active mixing ratio regulation during the steam generator start-up phase to suppress vibration; wherein, the passive energy dissipation includes absorbing energy by aligning the natural frequency of the dynamic vibration absorber with the resonance peak of the main system and isolating the natural frequency of the metal rubber vibration isolation pad by deviating it from the resonance peak.

[0042] The present invention has the following advantages or beneficial effects:

[0043] 1. By combining the dynamic vibration absorber with the metal rubber vibration isolation pad, the device achieves precise absorption of vibrations at specific frequencies and effective isolation of vibrations across a wide frequency range. At the same time, by utilizing the porous structure and friction energy dissipation mechanism of the metal rubber material, it can maintain stable vibration reduction performance even in harsh environments such as high temperature and corrosion, which significantly improves the reliability and service life of the device.

[0044] 2. A machine learning-based active mixing ratio control mechanism is introduced. By collecting state parameters such as pressure and temperature, the combustion mixture ratio is optimized in real time, reducing the excitation amplitude at the vibration source level. This organically integrates passive vibration reduction with active control, forming a composite vibration reduction scheme covering the entire chain of source suppression, transmission path isolation, and receptor energy absorption. In addition, through refined optimization of the vibration absorber frequency, damping, and vibration isolation pad material and structural parameters, the system's adaptability and vibration reduction robustness to complex start-up conditions are significantly improved. This effectively solves the technical problems of traditional single passive vibration reduction methods being unable to cope with the variable excitation frequency during the start-up phase and the lack of active intervention at the source. It significantly reduces the structural vibration response of the steam generator during the start-up phase, ensuring the operational safety of steam pipelines, ejector equipment, and other related components. Attached Figure Description

[0045] The above and other features and advantages of the present invention will become more apparent from a detailed description of exemplary embodiments thereof with reference to the accompanying drawings.

[0046] Figure 1 This is a flowchart illustrating a composite vibration reduction control method for excessive start-up vibration of a steam generator, according to an exemplary embodiment.

[0047] Figure 2 This is a structural block diagram of a composite vibration reduction control system for excessive start-up vibration of a steam generator, according to an exemplary embodiment.

[0048] Figure 3 This is a schematic diagram of the structure of an electronic device according to the present invention;

[0049] Figure 4 This is a schematic diagram of the structure of a computer-readable storage medium according to the present invention. Detailed Implementation

[0050] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar structures, and therefore their detailed description will be omitted.

[0051] The terms “a,” “one,” “the,” and “the” are used to indicate the existence of one or more elements / components / etc.; the terms “including” and “having” are used to indicate an open-ended meaning of inclusion and that other elements / components / etc. may exist in addition to the listed elements / components / etc.

[0052] In this invention, the "main system" refers to the steam generator body and its connected piping system, that is, the object on which the dynamic vibration absorber and the metal rubber vibration isolation pad act, that is, the vibration system that needs to be controlled by vibration reduction.

[0053] Example 1

[0054] like Figure 1 As shown in the figure, this embodiment discloses a composite vibration reduction control method for excessive start-up vibration of a steam generator, including the following steps.

[0055] Step S100: Obtain vibration reduction reference parameters, and install a passive vibration reduction unit including a dynamic vibration absorber and a metal rubber vibration isolation pad according to the vibration reduction reference parameters to form an initial passive vibration reduction system.

[0056] First, the key excitation frequency range of the main system during the start-up phase of the steam generator is obtained through modal testing and spectral analysis. Modal testing uses a vibrating hammer to apply pulse excitation to the main system, and accelerometers placed at key measuring points collect the response signals. The frequency response function of the system is obtained through Fast Fourier Transform, thereby identifying the main excitation frequency components and their amplitude distribution during the start-up transient process. Based on the excitation frequency range, the resonant frequency of the main system is extracted.

[0057] Based on the theory of tuned mass dampers, a matching model between the natural frequency of the vibration absorber and the frequency of the main system is established. The dynamic vibration absorber consists of a mass block, an elastic element, and a damping element. By adjusting the stiffness of the elastic element and the mass block, their natural frequencies are aligned with the resonant frequency, and this natural frequency is used as one of the vibration reduction reference parameters to achieve maximum energy absorption efficiency.

[0058] To address the dynamic frequency changes during startup, adjustable stiffness elastic elements (such as disc springs or piezoelectric ceramics) are employed. By adjusting the stiffness in real time, the natural frequency of the vibration absorber remains tuned according to the dynamic changes in the main system frequency during startup. Regarding damping parameter optimization, a two-degree-of-freedom dynamic model incorporating both the main system and the vibration absorber is established. Numerical simulations analyze the impact of different damping coefficients on vibration transmissibility. Optimal damping design criteria are adopted to ensure effective energy absorption by the vibration absorber while avoiding a decrease in absorption efficiency due to excessive damping. Viscous dampers or magnetorheological dampers are preferred to achieve real-time adjustable damping. For installation location and structural optimization, finite element analysis determines the node location with the largest vibration displacement in the main system. This node location is designated as a vibration-sensitive point, and the dynamic vibration absorber is installed at this location. Alternatively, multiple small vibration absorber units can be distributed and installed at multiple vibration-sensitive points to form an array-type vibration absorption structure, achieving simultaneous suppression of multi-frequency band vibrations.

[0059] Meanwhile, the metal-rubber vibration isolation pads were optimized. These pads, made from metal wires using a cold-forming process, are porous structural components installed in critical locations such as pipes and valves. Through the friction and elastic deformation of the internal metal wires, the mechanical energy of vibration is converted into heat energy for dissipation. Based on the operating temperature and corrosive environment of the steam generator, stainless steel and high-temperature alloys are preferred metal wire materials to ensure the stability of the vibration isolation pads' mechanical properties under harsh conditions. Parameters such as wire diameter, weaving density, and forming pressure were optimized using orthogonal experiments or response surface methodology to establish a mapping relationship between the natural frequency, stiffness, and damping ratio of the vibration isolation pads. This ensures that the natural frequency of the metal-rubber vibration isolation pads avoids the resonance peak range of the main system, and this natural frequency is used as one of the vibration reduction reference parameters, while ensuring sufficient static stiffness to support equipment loads. Topology optimization methods were used to determine the installation positions on pipes, valves, and bases, forming a multi-point support and graded vibration isolation layout. Furthermore, a three-dimensional vibration isolation structure is designed to achieve multi-directional isolation of axial, radial, and torsional vibrations by adjusting the weaving direction of the metal wires; a multi-layer composite structure is adopted to stack metal rubber pads of different stiffnesses to form a wide-band vibration isolation characteristic, effectively covering the complex vibration spectrum during the start-up phase.

[0060] Based on the vibration reduction reference parameters obtained above, a dynamic vibration absorber is installed on the main vibration system, and metal rubber vibration isolation pads are installed on the key vibration transmission paths such as pipes and valves of the steam generator to form an initial passive vibration reduction system.

[0061] Step S200: Under the initial passive vibration reduction system operating state, collect pressure, temperature and flow data during the steam generator start-up process to construct a state-aware dataset.

[0062] Based on pressure and temperature sensors at key measuring points of the steam generator, historical pressure and temperature data during startup are collected. Combined with flow rate characteristics of liquid oxygen, alcohol, and water, a basic sample dataset is constructed. Specifically, pressure and temperature sensors are installed at key measuring points of the steam generator, and flow meters are installed on the supply pipelines for liquid oxygen, alcohol, and water. During startup, these parameters are continuously collected at a preset sampling frequency, covering the complete transient process from startup to reaching stable operating conditions.

[0063] To further enrich the dataset and improve the model's generalization ability, a combustion reaction kinetic model of liquid oxygen and alcohol was established, and CFD simulation calculations were conducted. Specifically, based on the principles of chemical reaction kinetics, component transport equations, energy equations, and momentum equations were established for the combustion process of liquid oxygen and alcohol. The pressure field and temperature field distributions under different mixing ratios and their time-varying characteristics were obtained through numerical solutions. The CFD simulation results were then extended to the aforementioned basic sample dataset to form a complete state-aware dataset. This dataset covers the state parameters under various operating conditions during the steam generator start-up process, providing ample data support for the subsequent training of machine learning models.

[0064] Step S300: Use the state-aware dataset to train a machine learning-based hybrid control model to obtain an active control model.

[0065] Using pressure and temperature at measurement points as input features, and the mixing ratio of liquid oxygen, alcohol, and water as the prediction target, the parameters of a machine learning control model are trained using the state-aware dataset constructed in step S200. The machine learning model can employ algorithms such as neural networks, support vector regression, or random forests, establishing a nonlinear mapping relationship from pressure and temperature inputs to the mixing ratio output through supervised learning. During model training, the dataset is divided into training and validation sets, and cross-validation is used to optimize the model's hyperparameters and prevent overfitting. After training, an active control model is obtained that can output optimal mixing ratio control commands based on real-time pressure and temperature at measurement points. This model achieves real-time control of the mixing ratio, reducing vibration excitation at its source.

[0066] Step S400: Integrate the initial passive vibration reduction system with the active control model, and optimize the matching relationship between the passive vibration reduction parameters and the active control parameters through simulation and experimentation to generate a composite control strategy.

[0067] A simulation model is established that includes the physical characteristic parameters of the passive vibration damping unit and the output commands of the active control model. Specifically, a dynamic model of the main system of the steam generator is constructed in the simulation environment, and the frequency-damping characteristics of the dynamic vibration absorber, the stiffness-damping characteristics of the metal rubber vibration isolation pad, and the mixing ratio control logic of the active control model are incorporated into the same simulation framework.

[0068] Through simulation and experimentation, the matching relationship between passive vibration reduction parameters and active mixing ratio control commands is determined. For example, the variation law of vibration transmissibility under different damper damping coefficients and the attenuation effect of vibration excitation amplitude under different mixing ratio control response speeds are analyzed. The optimal synergy point between passive vibration reduction and active control is found through multi-condition simulation. Based on this, a composite control strategy is generated.

[0069] Step S500: The composite control strategy is used to simultaneously perform passive energy dissipation and active mixing ratio regulation during the steam generator start-up phase in order to suppress vibration; wherein, the passive energy dissipation includes absorbing energy by aligning the natural frequency of the dynamic vibration absorber with the resonance peak of the main system and isolating the natural frequency of the metal rubber vibration isolation pad by deviating it from the resonance peak.

[0070] During the actual start-up of the steam generator, vibration reduction control is executed according to the composite control strategy generated in step S400. On one hand, the natural frequency of the dynamic vibration absorber is aligned with the resonance peak of the main system, generating reverse vibration using the principle of resonance to absorb and dissipate the vibration energy of the main system; the metal rubber vibration isolation pad converts the mechanical energy of vibration into heat energy dissipation through the friction and elastic deformation of the internal metal wires, while its natural frequency has deviated from the resonance range of the main system, achieving effective isolation of vibration transmission. On the other hand, the active control model outputs mixing ratio control commands for liquid oxygen, alcohol, and water based on real-time collected pressure and temperature data from measuring points, adjusting the mixing ratio in real time to reduce vibration excitation from the source.

[0071] The aforementioned composite control strategy achieves coordinated vibration reduction across the entire chain of "source suppression - transmission path isolation - receptor energy absorption," effectively reducing the structural vibration response during the steam generator's start-up phase and ensuring the operational safety of steam pipelines, ejector equipment, and other related components.

[0072] During the system integration and debugging phase, after integrating the vibration reduction device and control algorithm, the vibration reduction parameters and control strategy are optimized through simulation and experimentation to ensure stable system operation during startup. Specifically, the vibration reduction effect of the composite control strategy under different startup conditions is verified in a simulation environment. Based on the simulation results, passive vibration reduction parameters (such as damper damping ratio, vibration isolation pad stiffness, etc.) and active control parameters (such as model output response speed, control threshold, etc.) are fine-tuned. Then, experimental verification is conducted on an actual steam generator to finally determine the optimal combination of composite control strategy parameters.

[0073] Example 2

[0074] like Figure 2 As shown, this embodiment discloses a composite vibration reduction control system for excessive start-up vibration of a steam generator, including:

[0075] The reference acquisition module is used to acquire vibration reduction reference parameters;

[0076] A passive vibration damping unit, comprising a dynamic vibration absorber and a metal rubber vibration isolation pad, is used to install and form an initial passive vibration damping system according to the vibration damping reference parameters;

[0077] The data acquisition module is used to collect pressure, temperature and flow data of the steam generator during the start-up process under the initial passive vibration reduction system operating state, and to construct a state-aware dataset.

[0078] The model training module is used to train a machine learning-based hybrid control model using the state-aware dataset to obtain an active control model.

[0079] The strategy generation module is used to integrate the initial passive vibration reduction system with the active control model, and to optimize the matching relationship between the passive vibration reduction parameters and the active control parameters through simulation and experimentation to generate a composite control strategy.

[0080] The execution module is used to simultaneously perform passive energy dissipation and active mixing ratio regulation during the steam generator start-up phase to suppress vibration; wherein, the passive energy dissipation includes absorbing energy by aligning the natural frequency of the dynamic vibration absorber with the resonance peak of the main system and isolating the natural frequency of the metal rubber vibration isolation pad by deviating it from the resonance peak.

[0081] The specific methods by which the modules in the above embodiments perform their operations have been described in detail in Embodiment 1, and will not be elaborated upon here.

[0082] Example 3

[0083] like Figure 3 As shown, the present invention also provides an electronic device, including a processor 101, a communication interface 102, a memory 103, and a communication bus 104. The processor 101, communication interface 102, and memory 103 communicate with each other via the communication bus 104. The memory 103 is used to store computer programs. In this embodiment, when the processor 101 executes the program stored in the memory 103, it implements the steps of the method in Embodiment 1.

[0084] The electronic device provided in this embodiment of the invention has a similar implementation principle and technical effect to the above embodiments, and will not be described again here.

[0085] The aforementioned memory 103 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. Memory 103 has storage space for program code used to perform any of the method steps described above. For example, the storage space for program code may include individual program codes for implementing the various steps in the methods described above. This program code can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, optical discs (CDs), memory cards, or floppy disks. Such computer program products are typically portable or fixed storage units. The storage unit may have storage segments or storage spaces arranged similarly to memory 103 in the aforementioned electronic device. The program code may be compressed, for example, in a suitable form. Typically, the storage unit includes programs for performing the method steps according to embodiments of the invention, i.e., code that can be read by a processor such as 101, which, when run by the electronic device, causes the electronic device to perform the various steps in the methods described above.

[0086] Example 4

[0087] like Figure 4 As shown, the present invention also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the method described above.

[0088] The computer-readable storage medium may be included in the device / apparatus described in the above embodiments; or it may exist independently and not assembled into the device / apparatus. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of the present invention.

[0089] According to embodiments of the present invention, the computer-readable storage medium may be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In the present invention, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0090] In this embodiment of the invention, the term "multiple" refers to two or more, unless otherwise explicitly defined. The terms "install," "connect," and "fix" should be interpreted broadly. For example, "connect" can mean a fixed connection, a detachable connection, or an integral connection. Those skilled in the art can understand the specific meaning of the above terms in this embodiment of the invention based on the specific circumstances.

[0091] In the description of the embodiments of the present invention, it should be understood that the terms "upper" and "lower" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or unit referred to must have a specific orientation or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of the present invention.

[0092] In the description of this specification, the terms "an embodiment," "a preferred embodiment," etc., refer to a specific feature, structure, material, or characteristic described in connection with that embodiment or example, which is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0093] The above are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. For those skilled in the art, the embodiments of the present invention can have various modifications and variations. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the embodiments of the present invention should be included within the protection scope of the embodiments of the present invention.

Claims

1. A composite vibration reduction control method for excessive start-up vibration of a steam generator, characterized in that, Includes the following steps: Obtain vibration reduction reference parameters, and install a passive vibration reduction unit including a dynamic vibration absorber and a metal rubber vibration isolation pad according to the vibration reduction reference parameters to form an initial passive vibration reduction system; Under the initial passive vibration reduction system operating condition, pressure, temperature and flow data during the steam generator start-up process are collected to construct a state-aware dataset; The state-aware dataset is used to train a machine learning-based hybrid ratio control model to obtain an active control model; The initial passive vibration reduction system is integrated with the active control model, and the matching relationship between the passive vibration reduction parameters and the active control parameters is optimized through simulation and experiment to generate a composite control strategy. The composite control strategy is used to simultaneously perform passive energy dissipation and active mixing ratio regulation during the steam generator start-up phase to suppress vibration; wherein, the passive energy dissipation includes aligning the natural frequency of the dynamic vibration absorber with the resonance peak of the main system to absorb energy, and deviating the natural frequency of the metal rubber vibration isolation pad from the resonance peak to isolate it.

2. The method according to claim 1, characterized in that, The steps for obtaining the vibration reduction reference parameters include: The excitation frequency range of the main system during the power-on phase was determined through modal testing and spectrum analysis. Based on the excitation frequency range, the resonant frequency of the main system is extracted; Based on the theory of tuned mass dampers, the stiffness of the elastic element and the mass of the mass block of the dynamic vibration absorber are adjusted so that their natural frequency is aligned with the resonant frequency, and this natural frequency is used as one of the vibration reduction reference parameters.

3. The method according to claim 2, characterized in that, The optimization of the dynamic vibration absorber also includes: An adjustable stiffness elastic element is used to adjust the stiffness in real time according to the dynamic changes of the main system frequency during the start-up process, so that the natural frequency of the vibration absorber remains in a tuned state.

4. The method according to claim 2, characterized in that, The optimization of the dynamic vibration absorber also includes: The location of the node with the largest vibration displacement in the main system is determined by finite element analysis, and the node location is taken as the vibration sensitive point. The dynamic vibration absorber is installed at the node location, or multiple small vibration absorber units are distributed and installed at multiple vibration-sensitive points to form an array-type vibration absorption structure.

5. The method according to claim 1, characterized in that, The step of obtaining the vibration reduction reference parameters also includes: The metal wire material is selected based on the operating temperature and corrosive environment of the steam generator. The wire diameter, weaving density and forming pressure are optimized through orthogonal experiments or response surface methodology. A mapping relationship between the natural frequency and structural parameters is established so that the natural frequency of the metal rubber vibration isolation pad avoids the resonance peak range of the main system. This natural frequency is then used as one of the vibration reduction reference parameters.

6. The method according to claim 5, characterized in that, The optimization of the metal rubber vibration isolation pad also includes: A three-dimensional vibration isolation structure is designed to achieve multi-directional isolation of axial, radial, and torsional vibrations by adjusting the braiding direction of the metal wires. A multi-layer composite structure is adopted, which stacks metal and rubber pads with different stiffnesses to form a wide-band vibration isolation characteristic.

7. The method according to claim 1, characterized in that, The installation optimization of the metal rubber vibration isolation pad includes: The installation positions of pipes, valves and bases are determined by topology optimization method, forming a layout with multi-point support and graded vibration isolation.

8. The method according to claim 1, characterized in that, The steps for constructing the state-aware dataset include: Based on historical pressure and temperature data from key measuring points of the steam generator, and combined with flow characteristic parameters of liquid oxygen, alcohol, and water, a basic sample dataset was constructed. A combustion reaction kinetic model of liquid oxygen and alcohol is established, CFD simulation calculations are carried out, and the simulation results are extended to the basic sample dataset to form the state-aware dataset. The machine learning model is trained using the pressure and temperature at the measurement point as input features and the mixing ratio of liquid oxygen, alcohol and water as the prediction target.

9. The method according to claim 1, characterized in that, The steps for generating the composite control strategy include: Establish a simulation model that includes the physical characteristic parameters of the passive vibration damping unit and the output commands of the active control model; Through simulation and experimentation, the matching relationship between passive vibration reduction parameters and active mixing ratio control commands is determined, and the composite control strategy is generated.

10. A composite vibration reduction control system for excessive start-up vibration of a steam generator, characterized in that, include: The reference acquisition module is used to acquire vibration reduction reference parameters; A passive vibration damping unit, comprising a dynamic vibration absorber and a metal rubber vibration isolation pad, is used to install and form an initial passive vibration damping system according to the vibration damping reference parameters; The data acquisition module is used to collect pressure, temperature and flow data of the steam generator during the start-up process under the initial passive vibration reduction system operating state, and to construct a state-aware dataset. The model training module is used to train a machine learning-based hybrid control model using the state-aware dataset to obtain an active control model. The strategy generation module is used to integrate the initial passive vibration reduction system with the active control model, and to optimize the matching relationship between the passive vibration reduction parameters and the active control parameters through simulation and experimentation to generate a composite control strategy. The execution module is used to simultaneously perform passive energy dissipation and active mixing ratio regulation during the steam generator start-up phase to suppress vibration; wherein, the passive energy dissipation includes absorbing energy by aligning the natural frequency of the dynamic vibration absorber with the resonance peak of the main system and isolating the natural frequency of the metal rubber vibration isolation pad by deviating it from the resonance peak.

Images