Blade regulating system based on damage monitoring and adaptive surface strengthening process

Abstract

The application discloses a blade regulation system based on damage monitoring and an adaptive surface strengthening process, and belongs to the technical field of steam turbine blade life management. The system is based on the settings of a damage monitoring unit, a data processing and decision unit, an adaptive strengthening execution unit, a system control and interaction unit and a feedback optimization unit. Through multi-dimensional damage monitoring, intelligent evaluation driven by machine learning, dynamic parameter generation, closed-loop regulation and system iterative optimization, the system realizes intelligent regulation and control of the whole process from damage perception, strategy generation, accurate execution to effect verification. The system can not only capture the damage state of the blade in all directions and dynamically generate optimal strengthening parameters, but also can improve the system model and knowledge base through continuous feedback iteration, effectively improve the efficiency and reliability of blade strengthening repair, effectively prolong the service life of the blade, and reduce the maintenance cost and downtime risk of industrial equipment.

Description

Technical Field

[0001] This invention belongs to the field of turbine blade life management technology, specifically involving a blade control system based on damage monitoring and an adaptive surface strengthening process. Background Technology

[0002] The turbine blades are among the most delicate and critical components of a steam turbine. They withstand extremely harsh conditions, including high temperature, high pressure, immense centrifugal force, steam force, steam excitation force, corrosion and vibration, and the erosion caused by water droplets in the wet steam zone. Their aerodynamic performance, machining geometry, surface roughness, installation clearance, operating conditions, and scaling all affect the turbine's efficiency and output; their structural design, vibration intensity, and operating mode have a decisive impact on the unit's safety and reliability.

[0003] Steam turbine blades are subjected to multiple types of damage during operation, including high-cycle fatigue, low-cycle fatigue, water erosion, scaling, and wear. Existing monitoring technologies only provide life assessment or alarms, failing to directly drive adjustments to strengthening process parameters. Furthermore, traditional surface strengthening processes often employ fixed parameter modes, making it difficult to dynamically optimize strengthening strategies based on the real-time damage status of the blades. This results in poor strengthening effects or over-strengthening, wasting resources and potentially affecting the original performance of the blades. In addition, the lack of an integrated control system prevents real-time interaction between damage monitoring data and the strengthening execution unit, leading to delayed damage response and failing to meet the dynamic maintenance requirements of steam turbine blades under complex operating conditions. Therefore, this invention provides a blade control system based on damage monitoring and an adaptive surface strengthening process. Summary of the Invention

[0004] In view of the above-mentioned problems in the prior art, the purpose of this invention is to provide a blade control system based on damage monitoring and an adaptive surface strengthening process.

[0005] This invention provides the following technical solution: a blade control system based on damage monitoring, comprising: Damage monitoring unit, used to collect multi-dimensional damage data of the blade in real time; The data processing and decision-making unit, which is connected to the damage monitoring unit, is used to extract features and classify damage levels from the collected damage data. It combines the preset blade material performance database and strengthening process knowledge base to generate surface strengthening parameters that are adapted to the current damage state. An adaptive enhancement execution unit, connected to a data processing and decision-making unit, is used to adjust the enhancement process parameters in real time based on the parameters output by the data processing and decision-making unit. The system control and interaction unit is used to build a real-time data transmission link between the damage monitoring unit, the data processing and decision-making unit and the adaptive reinforcement execution unit, and to provide a visual human-machine interface. The feedback optimization unit is bidirectionally connected to the adaptive reinforcement execution unit and the data processing and decision-making unit. By collecting data on the damage repair effect of the reinforced blades and the deviation information during the process execution, it verifies and iteratively optimizes the adaptability of the reinforcement process parameters.

[0006] Furthermore, the damage monitoring unit includes: Vibration sensors are used to capture high-cycle / low-cycle fatigue characteristic signals; An ultrasonic testing module is used to identify internal microcracks and damage depth. A water erosion monitoring component that uses image recognition technology to quantify the size and distribution of surface erosion pits; The scale condition sensor detects the thickness of scale on the surface by measuring changes in dielectric constant.

[0007] Furthermore, the data processing and decision-making unit includes: The damage feature extraction subunit is used to analyze the damage type and damage level. The machine learning-based damage assessment subunit predicts damage development trends based on machine learning models. The enhanced parameter optimization sub-unit is based on a multi-objective optimization algorithm, which dynamically generates suitable surface enhancement parameters according to the damage state.

[0008] Furthermore, the multi-objective optimization algorithm is a genetic algorithm or a particle swarm optimization algorithm.

[0009] Furthermore, the adaptive reinforcement execution unit includes: The high-precision motion control subunit achieves micron-level positioning of the actuator on the blade surface through a servo drive system; The dynamic process parameter adjustment subunit adjusts process variables in real time based on the enhancement parameters output by the data processing and decision-making unit. The targeted reinforcement actuator integrates a laser cladding module and a plasma spraying component, which is used to select between laser cladding or plasma spraying operations based on the type of damage. The real-time status feedback subunit is used to collect the temperature field distribution and the contact force of the actuator during the strengthening process.

[0010] Furthermore, laser cladding modules are used to repair microcrack damage, and plasma spraying components are used to strengthen erosion pit damage.

[0011] Furthermore, the system control and interaction unit includes: The real-time data communication subunit is used to realize data interaction between the damage monitoring unit, the data processing and decision-making unit, and the adaptive reinforcement execution unit. The visual human-computer interaction interface sub-unit can visualize the damage distribution, reinforcement area and dynamic changes of process parameters, and enable human-computer interaction; The manual intervention and strategy adjustment subunit allows authorized operators to manually modify enhancement parameters or pause the enhancement process under set operating conditions. The system status monitoring and alarm subunit collects the hardware operating status of each unit in real time, triggers fault alarms, and pushes diagnostic reports of the alarm faults. The data storage and traceability subunit is used to store damage monitoring data, strengthening process parameters, and effect verification results throughout the blade's entire life cycle.

[0012] Furthermore, the feedback optimization unit includes: The reinforcement effect verification subunit is used to quantify the reinforcement layer thickness, bonding strength and surface roughness of the damaged area, and to evaluate whether the reinforcement effect meets the preset repair standards. The process deviation analysis subunit compares the deviation values ​​between the actual process parameters and the theoretical output parameters during the enhancement process, identifies the causes of deviation, and generates targeted deviation compensation strategies. The model parameter iterative update sub-unit inputs the reinforcement effect data back into the machine learning model of the machine learning damage assessment sub-unit, and dynamically adjusts the model weight matrix through the gradient descent algorithm; The knowledge base is dynamically supplemented by a sub-unit, which stores the parameters generated by the enhanced parameter optimization sub-unit, the damage features extracted by the damage feature extraction sub-unit, and the deviation compensation strategy generated by the process deviation analysis sub-unit into the enhanced process knowledge base.

[0013] The system-based adaptive surface strengthening process includes the following steps: S1. Damage Data Acquisition: The damage monitoring unit continuously monitors the blades to obtain multi-dimensional damage information such as vibration, cracks, erosion, and scaling. S2. Data Analysis and Damage Assessment: The data processing and decision-making unit extracts features from the collected data, uses machine learning models to determine the damage type and severity, and predicts the damage evolution trend. S3. Dynamic generation of enhancement parameters: Based on the damage assessment results, the enhancement parameter optimization sub-unit matches the preset enhancement strategy library to generate targeted process parameters. S4. Enhanced Execution and Feedback: The adaptive enhanced execution unit executes the enhanced operation according to the generated parameters, and at the same time collects the enhanced damage data in real time and feeds it back to the data processing unit to form a closed-loop control. S5. System Dynamic Adjustment: The feedback optimization unit evaluates the enhancement effect based on the feedback data. If the expected results are not achieved, the parameters are re-optimized until the blade performance maintenance requirements are met.

[0014] By employing the above-described technology, the beneficial effects of the present invention compared to the prior art are as follows: 1) In this invention, the intelligent control of the entire process from damage perception, strategy generation, precise execution to effect verification is realized through the setting of damage monitoring unit, data processing and decision-making unit, adaptive reinforcement execution unit, system control and interaction unit and feedback optimization unit. It can not only capture the blade damage state in all aspects and dynamically generate the optimal reinforcement parameters, but also improve the system model and knowledge base through continuous feedback iteration, effectively improve the efficiency and reliability of blade reinforcement and repair, effectively extend the service life of blades, and reduce the maintenance cost and downtime risk of industrial equipment. 2) In this invention, through a full-process adaptive mechanism of multi-dimensional damage monitoring, machine learning-driven intelligent assessment, dynamic parameter generation, closed-loop control and system iterative optimization, the accurate identification, customized repair and continuous protection of blade damage are achieved, which effectively makes up for the defects of traditional processes, effectively improves the service life of blades and operation and maintenance efficiency, and reduces long-term operating costs. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of a blade control system based on damage monitoring. Figure 2 This is the connection logic diagram of a blade control system based on damage monitoring; Figure 3 This is a flowchart of the adaptive surface strengthening process based on damage monitoring. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention.

[0017] Conversely, this invention encompasses any substitutions, modifications, equivalent methods, and solutions made within the spirit and scope of the invention as defined in the claims. Furthermore, to provide a better understanding of the invention, certain specific details are described in detail below. However, those skilled in the art will fully understand the invention even without these detailed descriptions.

[0018] Please see Figure 1-2 The blade control system based on damage monitoring includes: a damage monitoring unit, a data processing and decision-making unit, an adaptive enhancement execution unit, a system control and interaction unit, and a feedback optimization unit. Among them: The damage monitoring unit is used to collect multi-dimensional damage data of the blade in real time, enabling dynamic perception of the damage status of the blade throughout its entire life cycle.

[0019] The data processing and decision-making unit is connected to the damage monitoring unit. Based on a deep learning-based damage assessment model, it extracts features and classifies damage levels from the monitoring data. Combined with a pre-set blade material performance database and a strengthening process knowledge base, it generates surface strengthening parameters that are adapted to the current damage state.

[0020] The adaptive strengthening execution unit is connected to the data processing and decision-making unit. Based on the parameters output by the data processing and decision-making unit, the strengthening process parameters are adjusted in real time to achieve precise targeted strengthening of the damaged area of ​​the blade, avoiding over-strengthening or under-strengthening.

[0021] The system control and interaction unit is used to build a real-time data transmission link to achieve seamless communication between the damage monitoring unit, the data processing and decision-making unit, and the adaptive reinforcement execution unit. It also provides a visual human-machine interface to allow operators to view damage data, reinforcement parameters, and process execution status, and to manually intervene and adjust strategies.

[0022] The feedback optimization unit is used to connect bidirectionally with the adaptive reinforcement execution unit and the data processing and decision-making unit. By collecting data on the damage repair effect of the reinforced blade and the deviation information during the process execution, it verifies and iteratively optimizes the adaptability of the reinforcement process parameters, continuously improves the damage assessment model and reinforcement process knowledge base, and enhances the system's ability to handle complex damage scenarios.

[0023] Specifically, the damage monitoring unit can achieve comprehensive and high-precision dynamic perception of the damage state of the blade surface and interior, both macroscopically and microscopically. It can not only simultaneously acquire information on multiple types of damage such as fatigue damage, internal cracks, surface erosion, and scaling, but also improve the accuracy and reliability of damage identification through cross-validation of multi-source data, providing comprehensive and reliable raw monitoring data support for subsequent data processing and decision-making units.

[0024] It includes a vibration sensor, an ultrasonic detection module, a water erosion monitoring component, and a scaling condition sensor; among which: Vibration sensors are used to capture high-cycle / low-cycle fatigue characteristic signals; The ultrasonic testing module is used to identify internal microcracks and damage depth; The water erosion monitoring component uses image recognition technology to quantify the size and distribution of surface erosion pits. The scaling condition sensor detects the thickness of surface scale by measuring changes in dielectric constant.

[0025] Specifically, the data processing and decision-making unit enables end-to-end intelligent transformation from multi-source damage data to precise reinforcement strategies. It includes a damage feature extraction subunit, a machine learning damage assessment subunit, and a reinforcement parameter optimization subunit; wherein: The damage feature extraction subunit is used to analyze the damage type and damage level. It first performs denoising, fusion and feature engineering on multimodal monitoring data such as vibration, ultrasound, image and dielectric, and transforms the unstructured raw signal into a structured feature vector containing damage type, level, location and development rate. The machine learning damage assessment subunit is used to predict the damage development trend. The machine learning model is based on deep learning algorithms (such as convolutional neural networks, long short-term memory networks, etc.), combined with fatigue life curves, fracture toughness parameters and historical cases in the strengthening process knowledge base of the blade material performance database, to analyze the damage feature vector and accurately predict the short-term evolution trend and long-term failure risk of damage. The strengthening parameter optimization subunit dynamically generates suitable surface strengthening parameters based on the damage state. Through multi-objective optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.), the strengthening parameter optimization subunit dynamically generates the optimal strengthening scheme, which includes key parameters such as laser power, scanning speed, strengthening depth and coverage, under the premise of meeting the material strengthening threshold, process equipment constraints and cost-effectiveness.

[0026] Specifically, the adaptive strengthening execution unit can accurately locate the damaged area of ​​the blade, adapt dynamic parameters, and intelligently switch between multi-modal strengthening methods. This ensures high stability and consistency in the strengthening process and allows for personalized strengthening treatment for different types and locations of damage. It effectively avoids material performance degradation caused by over-strengthening or repair failure caused by insufficient strengthening, providing a reliable execution guarantee for efficient repair of blade damage.

[0027] It includes a high-precision motion control subunit, a dynamic process parameter adjustment subunit, a targeted enhancement actuator, and a real-time status feedback subunit; wherein: The high-precision motion control subunit achieves micron-level positioning of the actuator on the blade surface through a servo drive system, accurately covering the damaged area; The dynamic process parameter adjustment subunit can adjust core process variables such as laser power, scanning rate, and spraying pressure in real time based on the enhancement parameters output by the data processing and decision-making unit. The targeted strengthening actuator integrates a laser cladding module and a plasma spraying component, allowing for the selection of appropriate strengthening methods for different damage types (such as microcracks and erosion pits). The real-time status feedback subunit collects the temperature field distribution and the contact force of the actuator during the strengthening process through infrared temperature sensors and force sensors, ensuring the stability and consistency of the strengthening process.

[0028] Specifically, the system control and interaction unit can ensure low-latency coordination and stable operation of core components such as damage monitoring, data processing and adaptive enhancement, and can also achieve efficient complementarity between human and machine intelligence through an intuitive visual interface and a flexible manual intervention mechanism. At the same time, through real-time monitoring of system status and traceable storage of data throughout the entire life cycle, it provides solid support for the safe and reliable operation and continuous optimization of the system, effectively improving the usability, controllability and maintainability of the entire blade control system.

[0029] It includes a real-time data communication subunit, a visual human-computer interaction interface subunit, a manual intervention and strategy adjustment subunit, a system status monitoring and alarm subunit, and a data storage and traceability subunit; among which: The real-time data communication subunit adopts a 5G+industrial Ethernet converged architecture to realize low-latency, high-bandwidth data interaction between the damage monitoring unit, data processing and decision-making unit and adaptive reinforcement execution unit, ensuring that the collaborative response of each unit does not exceed 100ms. The visual human-machine interface sub-unit uses a 3D blade model to visually display the damage distribution, reinforcement area and dynamic changes of process parameters, and supports operators to query parameters, preview strategies and compare historical data through a touch screen or mouse. The manual intervention and strategy adjustment subunit allows authorized operators to manually modify enhancement parameters or pause the enhancement process under special working conditions, while recording intervention operation logs for traceability. The system status monitoring and alarm subunit collects the hardware operating status of each unit in real time. When an abnormality is detected, it triggers a graded audible and visual alarm and pushes a diagnostic report containing the fault location, cause speculation and emergency handling suggestions. The data storage and traceability subunit stores damage monitoring data, strengthening process parameters, and effect verification results throughout the entire life cycle of the blade based on a distributed cloud database. It supports multi-dimensional retrieval by blade number, damage type, or strengthening time, providing data support for subsequent process optimization.

[0030] Specifically, the feedback optimization unit can realize a complete closed loop for enhancing the process, from verifying the execution effect to parameter iteration, model optimization, and knowledge base update.

[0031] It includes a reinforcement effect verification subunit, a process deviation analysis subunit, a model parameter iterative update subunit, and a knowledge base dynamic supplementation subunit; among which: The reinforcement effect verification subunit uses high-precision three-dimensional morphology scanning and microhardness testing to quantify the thickness of the reinforcement layer, bonding strength and surface roughness of the damaged area, and evaluate whether the reinforcement effect meets the preset repair standards, providing an objective basis for process adaptability. The process deviation analysis subunit compares the deviation values ​​between the actual process parameters and the theoretical output parameters during the reinforcement process, identifies deviation causes such as material property fluctuations and environmental temperature changes, and generates targeted deviation compensation strategies. In other words, by using the cause identification and compensation strategy generation of the process deviation analysis subunit, the uncertainty in the execution process can be effectively eliminated. The model parameter iterative update subunit inputs the reinforcement effect data back into the machine learning model in the machine learning damage assessment subunit. The model weight matrix is ​​dynamically adjusted through the gradient descent algorithm to improve the accuracy of damage development trend prediction and reinforcement parameter generation. Through the reverse training of the model parameter iterative update subunit, the accuracy of damage assessment and parameter generation is continuously improved. The knowledge base dynamic supplementation subunit stores verified new reinforcement parameter combinations, special damage treatment cases, and deviation compensation strategies into the reinforcement process knowledge base, enriching the system's process adaptation scenario library and providing more efficient decision support for subsequent similar damage conditions. Relying on the scenario expansion of the knowledge base dynamic supplementation subunit, the system's experience in handling special damage conditions is continuously enriched.

[0032] The working principle of the system of this invention: The damage monitoring unit, through the collaborative operation of vibration sensors, ultrasonic detection modules, water erosion monitoring components, and scaling condition sensors, simultaneously collects multi-dimensional damage data on the blade, including fatigue characteristic signals, internal microcrack depth, surface erosion pit distribution, and scaling thickness. This data is transmitted in real-time to the data processing and decision-making unit via a low-latency communication link from the system control and interaction unit. The data processing and decision-making unit first performs denoising, fusion, and feature engineering on the multimodal raw data to generate a structured feature vector containing damage type, level, location, and development rate. Then, it uses a deep learning-based damage assessment model to predict the short-term evolution trend and long-term failure risk of the damage. Combining fatigue life curves, fracture toughness parameters, and historical cases from the blade material performance database and the strengthening process knowledge base, it uses multi-objective optimization algorithms such as genetic algorithms or particle swarm optimization to generate key strengthening parameters such as laser power, scanning speed, and strengthening depth adapted to the current damage state. Subsequently, the adaptive strengthening execution unit receives the strengthening parameters and achieves micron-level damage area positioning through a high-precision motion control subunit, while the dynamic process parameter adjustment subunit... The system adjusts core process variables in real time, and the targeted strengthening actuator selects laser cladding or plasma spraying methods to complete precise repair based on the damage type. Simultaneously, the real-time status feedback subunit collects temperature field distribution and contact force data during the strengthening process to ensure process stability. After strengthening, the feedback optimization unit performs 3D morphology scanning and microhardness testing on the blade through the strengthening effect verification subunit, quantifying the performance of the strengthening layer and evaluating the repair effect. The process deviation analysis subunit identifies the causes of deviations between actual and theoretical parameters and generates compensation strategies. The model parameter iteration update subunit inputs the effect data back into the damage assessment model to adjust the weight matrix. The knowledge base dynamic supplementation subunit stores verified new parameter combinations, special cases, and compensation strategies into the process knowledge base. The system control and interaction unit ensures seamless communication between all units throughout the process, providing a visual human-machine interface to allow operators to view real-time data and intervene in adjustment strategies. Ultimately, this achieves intelligent control of the entire lifecycle of blade damage, from dynamic monitoring, intelligent decision-making, targeted strengthening to closed-loop optimization, continuously improving the system's ability to handle complex damage scenarios and the reliability of blade service.

[0033] Please see Figure 3 The adaptive surface strengthening process based on damage monitoring includes the following steps: S1. Damage Data Acquisition: The damage monitoring unit continuously monitors the blades to obtain multi-dimensional damage information such as vibration, cracks, erosion, and scaling; thus providing comprehensive and real-time data source support for subsequent quantitative assessment of damage status.

[0034] S2. Data Analysis and Damage Assessment: The data processing and decision-making unit extracts features from the collected data, uses machine learning models to determine the damage type and severity, and predicts the damage evolution trend. This provides a scientific and reliable basis for the optimization and precise control of parameters in the adaptive surface strengthening process, ensuring that the subsequent strengthening strategy is not only consistent with the current actual damage situation of the blade, but also addresses potential damage development risks in advance, laying a key decision-making foundation for the generation of strengthening process parameters in the next step.

[0035] S3. Dynamic Generation of Strengthening Parameters: Based on the damage assessment results, the strengthening parameter optimization sub-unit matches the preset strengthening strategy library to generate targeted process parameters (such as using low-energy-density laser shock strengthening for mild water erosion, and using plasma spraying repair combined with laser remelting for severe fatigue cracks). This enables precise adaptation to different damage types and severity of the blade, avoiding material performance loss due to over-strengthening or damage aggravation caused by insufficient strengthening. At the same time, it provides clear operational guidance for the automated execution of subsequent strengthening processes, ensuring the efficiency and reliability of the strengthening process. It can quickly restore the structural integrity and functional stability of the blade, and enhance the fatigue resistance and erosion resistance of the damaged area through customized parameters, effectively extending the service life of the blade, reducing operation and maintenance costs, and laying a solid foundation of core parameters for the implementation of adaptive surface strengthening processes.

[0036] S4. Enhanced Execution and Feedback: The adaptive enhancement execution unit executes enhancement operations according to the generated parameters, while simultaneously collecting enhanced damage data in real time and feeding it back to the data processing unit to form a closed-loop control; thus, the effectiveness of the enhancement operation can be verified in real time, ensuring that the repair effect of the damaged area meets the expected standards.

[0037] S5. System Dynamic Adjustment: The feedback optimization unit evaluates the strengthening effect based on feedback data. If the expected results are not achieved, the parameters are re-optimized until the blade performance maintenance requirements are met. This enables dynamic tracking and iterative optimization of the strengthening process, ensuring that blade performance is always maintained within the preset safe operating threshold. Through this cyclical control mechanism, not only can the shortcomings of a single strengthening operation be made up in a timely manner, but the strategy can also be continuously adjusted according to the dynamic trend of blade damage, maximizing the blade's damage resistance and service life. At the same time, it accumulates more strengthening experience under actual working conditions for the system, continuously enriches the preset strengthening strategy library, and further enhances the intelligence and adaptability of the adaptive surface strengthening process, providing dynamic protection for the long-term stable operation of the blade throughout its entire life cycle.

[0038] Furthermore, any content not described in detail in this specification is existing technology known to those skilled in the art.

Claims

1. A blade control system based on damage monitoring, characterized in that, include: Damage monitoring unit, used to collect multi-dimensional damage data of the blade in real time; The data processing and decision-making unit, which is connected to the damage monitoring unit, is used to extract features and classify damage levels from the collected damage data. It combines the preset blade material performance database and strengthening process knowledge base to generate surface strengthening parameters that are adapted to the current damage state. An adaptive enhancement execution unit, connected to a data processing and decision-making unit, is used to adjust the enhancement process parameters in real time based on the parameters output by the data processing and decision-making unit. The system control and interaction unit is used to build a real-time data transmission link between the damage monitoring unit, the data processing and decision-making unit and the adaptive reinforcement execution unit, and to provide a visual human-machine interface. The feedback optimization unit is bidirectionally connected to the adaptive reinforcement execution unit and the data processing and decision-making unit. By collecting data on the damage repair effect of the reinforced blades and the deviation information during the process execution, it verifies and iteratively optimizes the adaptability of the reinforcement process parameters.

2. The system according to claim 1, characterized in that, The damage monitoring unit includes: Vibration sensors are used to capture high-cycle / low-cycle fatigue characteristic signals; An ultrasonic testing module is used to identify internal microcracks and damage depth. A water erosion monitoring component that uses image recognition technology to quantify the size and distribution of surface erosion pits; The scale condition sensor detects the thickness of scale on the surface by measuring changes in dielectric constant.

3. The system according to claim 1, characterized in that, The data processing and decision-making unit includes: The damage feature extraction subunit is used to analyze the damage type and damage level. The machine learning-based damage assessment subunit predicts damage development trends based on machine learning models. The enhanced parameter optimization sub-unit is based on a multi-objective optimization algorithm, which dynamically generates suitable surface enhancement parameters according to the damage state.

4. The system according to claim 3, characterized in that, The multi-objective optimization algorithm is either a genetic algorithm or a particle swarm optimization algorithm.

5. The system according to claim 1, characterized in that, The adaptive enhanced execution unit includes: The high-precision motion control subunit achieves micron-level positioning of the actuator on the blade surface through a servo drive system; The dynamic process parameter adjustment subunit adjusts process variables in real time based on the enhancement parameters output by the data processing and decision-making unit. The targeted reinforcement actuator integrates a laser cladding module and a plasma spraying component, which is used to select between laser cladding or plasma spraying operations based on the type of damage. The real-time status feedback subunit is used to collect the temperature field distribution and the contact force of the actuator during the strengthening process.

6. The system according to claim 5, characterized in that, For microcrack damage, laser cladding modules are used for repair; for erosion pit damage, plasma spraying components are used for reinforcement.

7. The system according to claim 1, characterized in that, The system control and interaction unit includes: The real-time data communication subunit is used to realize data interaction between the damage monitoring unit, the data processing and decision-making unit, and the adaptive reinforcement execution unit. The visual human-computer interaction interface sub-unit can visualize the damage distribution, reinforcement area and dynamic changes of process parameters, and enable human-computer interaction; The manual intervention and strategy adjustment subunit allows authorized operators to manually modify enhancement parameters or pause the enhancement process under set operating conditions. The system status monitoring and alarm subunit collects the hardware operating status of each unit in real time, triggers fault alarms, and pushes diagnostic reports of the alarm faults. The data storage and traceability subunit is used to store damage monitoring data, strengthening process parameters, and effect verification results throughout the blade's entire life cycle.

8. The system according to claim 3, characterized in that, The feedback optimization unit includes: The reinforcement effect verification subunit is used to quantify the reinforcement layer thickness, bonding strength and surface roughness of the damaged area, and to evaluate whether the reinforcement effect meets the preset repair standards. The process deviation analysis subunit compares the deviation values ​​between the actual process parameters and the theoretical output parameters during the enhancement process, identifies the causes of deviation, and generates targeted deviation compensation strategies. The model parameter iterative update sub-unit inputs the reinforcement effect data back into the machine learning model of the machine learning damage assessment sub-unit, and dynamically adjusts the model weight matrix through the gradient descent algorithm; The knowledge base is dynamically supplemented by a sub-unit, which stores the parameters generated by the enhanced parameter optimization sub-unit, the damage features extracted by the damage feature extraction sub-unit, and the deviation compensation strategy generated by the process deviation analysis sub-unit into the enhanced process knowledge base.

9. An adaptive surface strengthening process based on the system according to any one of claims 1-8, characterized in that, Includes the following steps: S1. Damage Data Acquisition: The damage monitoring unit continuously monitors the blades to obtain multi-dimensional damage information such as vibration, cracks, erosion, and scaling. S2. Data Analysis and Damage Assessment: The data processing and decision-making unit extracts features from the collected data, uses machine learning models to determine the damage type and severity, and predicts the damage evolution trend. S3. Dynamic generation of enhancement parameters: Based on the damage assessment results, the enhancement parameter optimization sub-unit matches the preset enhancement strategy library to generate targeted process parameters. S4. Enhanced Execution and Feedback: The adaptive enhanced execution unit executes the enhanced operation according to the generated parameters, and at the same time collects the enhanced damage data in real time and feeds it back to the data processing unit to form a closed-loop control. S5. System Dynamic Adjustment: The feedback optimization unit evaluates the enhancement effect based on the feedback data. If the expected results are not achieved, the parameters are re-optimized until the blade performance maintenance requirements are met.

Images