Method and system for optimizing SSS clutch health state combined cycle unit

Abstract

The invention discloses an SSS clutch health state combined cycle unit optimization method and system, and relates to the technical field of clutches, and the method comprises the steps: collecting the multi-source data of a clutch in real time; extracting multi-dimensional fault features of the clutch from the multi-source data; obtaining a real-time health state of the clutch based on the multi-dimensional fault features and a preset health index quantitative model; inputting the real-time health state of the clutch into a preset health state prediction framework to obtain a corresponding health state grade; based on a preset virtual unit model, simulating responses of the clutch under different working conditions to obtain simulation results of the clutch under different operation working conditions; and according to the health state grade and the simulation result, the load distribution of the combined cycle unit and the engagement time sequence of the clutch are adjusted. According to the scheme, the risk of non-planned shutdown can be effectively reduced, excessive maintenance and lagged overhaul can be avoided, the maintenance cost is remarkably reduced, and the operation stability and economical efficiency of the combined cycle unit can be improved.

Description

Technical Field

[0001] This application relates to the field of clutch technology, and in particular to a method and system for optimizing the health status of an SSS clutch combined cycle unit. Background Technology

[0002] With increasing global emphasis on low-carbon emissions and renewable energy, combined cycle (CCPP) gas turbine units are gradually becoming an effective alternative to traditional coal-fired power plants due to their superior overall thermal efficiency (55%-60%). The high efficiency of CCPPs makes them play a crucial role in energy structure transformation. However, the health of its key transmission component, the Synchro-Self-Shifting (SSS) clutch, directly affects the stability and economy of the unit. Studies show that approximately 23% of unplanned CCPP downtime is caused by clutch gearbox failures, with an average repair time of 72 hours. This not only results in lost production efficiency but also affects the overall performance of the unit.

[0003] Traditional maintenance models rely on fixed-cycle overhauls, which present a dual dilemma of over-maintenance and delayed maintenance. On the one hand, over-maintenance leads to a waste of resources, with an average annual waste of up to 370,000 yuan per unit; on the other hand, delayed maintenance may trigger a series of interlocking failures, leading to serious safety accidents, such as the turbine water hammer accident caused by clutch jamming at a power plant in 2019. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for optimizing the health status of SSS clutch combined cycle units, aiming to solve the technical problems of untimely clutch status monitoring and unreasonable maintenance leading to safety hazards in the prior art.

[0005] To achieve the above objectives, this application provides a method for optimizing the health status of an SSS clutch combined cycle unit, the method comprising: Real-time acquisition of multi-source data from the clutch, including clutch vibration signals, clutch friction plate temperature field data, and lubricating oil metal particle content data; Multi-dimensional fault features of the clutch are extracted from the multi-source data. These multi-dimensional fault features include time-frequency domain features, metal particle content features, and friction plate temperature rise rate features. Based on the multi-dimensional fault characteristics and the preset health index quantification model, the real-time health status of the clutch is obtained. The real-time health status of the clutch is input into a preset health status prediction framework to obtain the corresponding health status level. Based on a pre-defined virtual machine group model, the response of the clutch under different operating conditions is simulated to obtain simulation results of the clutch under different operating conditions. Based on the health status level and the simulation results, adjust the load distribution and clutch engagement sequence of the combined cycle unit. In one embodiment, the step of obtaining the real-time health status of the clutch based on the multi-dimensional fault characteristics and a preset health index quantification model includes: The multi-dimensional fault characteristics are normalized, and a health index value within a preset range is output. The real-time health status of the clutch is obtained based on the relationship between the health index value and the health status threshold. In one embodiment, the step of inputting the real-time health status of the clutch into a preset health status prediction framework to obtain the corresponding health status level includes: The real-time health status of the clutch is input into the health status prediction framework to establish a correlation mapping relationship between the data and the remaining lifespan, and the probability distribution of the remaining lifespan is deduced and output. Based on the remaining life expectancy probability distribution and the preset health status grading standard, the corresponding health status level is determined. In one embodiment, the unit simulation model is a virtual mapping model that includes clutch dynamic characteristics and fluid coupling characteristics, wherein the dynamic characteristics are characterized by a built-in nonlinear stiffness coefficient.

[0006] In one embodiment, the step of adjusting the load distribution of the combined cycle unit includes: Adjust the operating parameters of the unit's core equipment based on the aforementioned health status level; A multi-objective optimization algorithm is used to find the optimal balance between unit operating performance and clutch wear.

[0007] In addition, this application also provides an SSS clutch health status combined cycle unit optimization system, including: The data acquisition module is used to acquire multi-source data of the clutch in real time. The multi-source data includes clutch vibration signal, clutch friction plate temperature field data and lubricating oil metal particle content data. The feature extraction module is used to extract multi-dimensional fault features of the clutch from the multi-source data. The multi-dimensional fault features include time-frequency domain features, metal particle content features, and friction plate temperature rise rate features. The health status assessment module is used to obtain the real-time health status of the clutch based on the multi-dimensional fault characteristics and the preset health index quantification model. The health status prediction module inputs the real-time health status of the clutch into a preset health status prediction framework to obtain the corresponding health status level. The virtual simulation module is used to simulate the clutch response under different operating conditions based on a preset virtual machine group model, and obtain simulation results of the clutch under different operating conditions. The operation adjustment module is used to adjust the load distribution and clutch engagement sequence of the combined cycle unit based on the health status level and the simulation results.

[0008] In one embodiment, the health status assessment module includes: The normalization unit is used to normalize the multi-dimensional fault characteristics and output a health index value within a preset range. The status determination unit is used to obtain the real-time health status of the clutch based on the relationship between the health index value and the health status threshold.

[0009] In one embodiment, the health status prediction module includes: The prediction unit is used to input the real-time health status of the clutch into the health status prediction framework, establish the correlation mapping relationship between the data and the remaining life, and deduce and output the probability distribution of the remaining life. The assessment unit is used to determine the corresponding health status level based on the remaining life expectancy probability distribution and the preset health status grading standard.

[0010] In one embodiment, the virtual machine group model in the virtual simulation module is a virtual mapping model that includes clutch dynamic characteristics and fluid coupling characteristics, wherein the dynamic characteristics are characterized by a built-in nonlinear stiffness coefficient. In one embodiment, the operation adjustment module includes: The parameter adjustment unit is used to adjust the operating parameters of the unit's core equipment based on the health status level. The optimization solution unit is used to solve for the optimal balance between unit operating performance and clutch wear using a multi-objective optimization algorithm.

[0011] The above-mentioned technical solution of this application has at least the following beneficial technical effects: The technical solution of this application achieves dynamic adjustment of unit operating parameters through multi-source data acquisition, multi-dimensional fault feature extraction, quantitative assessment and prediction of health status, combined with digital twin simulation. This enables real-time monitoring of the SSS clutch health status and early warning of potential faults, effectively reducing the risk of unplanned downtime. Simultaneously, by accurately matching operating conditions with clutch health status, it avoids excessive maintenance and delayed repairs, significantly reducing maintenance costs and improving the operational stability and economy of the combined cycle unit. Attached Figure Description

[0012] Figure 1 This is a flowchart illustrating an embodiment of the SSS clutch health state combined cycle unit optimization method provided in this application; Figure 2 A block diagram of an embodiment of the SSS clutch health status combined cycle unit optimization system provided in this application. Detailed Implementation

[0013] To make the objectives, technical solutions, and advantages of this application clearer, the application will be further described in detail below with reference to specific embodiments and accompanying drawings. It should be understood that these descriptions are merely exemplary and not intended to limit the scope of this application. Furthermore, descriptions of well-known structures and technologies are omitted in the following description to avoid unnecessarily obscuring the concepts of this application.

[0014] The embodiments described in this application are only some, not all, of the embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments described herein without inventive effort are within the scope of protection of this application.

[0015] To address the aforementioned technical problems, this application provides an optimization method for SSS clutch health status combined cycle units.

[0016] In one embodiment of this application, please refer to Figure 1 The optimization method for the health status of the SSS clutch combined cycle unit includes the following steps: Step S1 involves real-time acquisition of multi-source data from the clutch, including clutch vibration signals, clutch friction plate temperature field data, and lubricating oil metal particle content data. Specifically, high-frequency vibration characteristics are monitored using an accelerometer to obtain vibration signals and identify abnormal gear wear; infrared thermal imaging captures the temperature rise of the clutch friction plate, providing an early warning of overheating risks; and the lubricating oil metal particle content is detected, and oil analysis is performed to quantify the degree of mechanical wear. In this step S1, 0-20kHz high-frequency accelerometers are placed at key stress points on the clutch housing, and an infrared thermal imaging array with ±0.5℃ accuracy is deployed in the corresponding area of ​​the friction plate. An oil spectrometer is installed in the lubricating oil circulation pipeline to collect high-frequency vibration signals, full-area friction plate temperature field data, and the concentration of Fe, Cu, and Al element particles in the lubricating oil in real time. Simultaneously, gear meshing vibration characteristics, friction plate temperature rise curves, and metal particle size distribution are recorded. Through simultaneous acquisition and precise monitoring of multi-source data, the core characteristics of gear wear, friction plate overheating, and mechanical wear are comprehensively captured, providing comprehensive and high-precision raw data for subsequent fault identification and significantly improving the ability to detect early fault symptoms.

[0017] Step S2: Extract multi-dimensional fault features of the clutch from multi-source data. These features include time-frequency domain features, metal particle content features, and friction plate temperature rise rate features. In step S2, the vibration signal acquired in step S1 is decomposed using an improved EEMD algorithm and combined with WPD and PCA noise reduction to extract time-frequency domain features such as kurtosis and entropy. Metal particle content and particle size distribution are statistically analyzed using oil spectrometer data. The friction plate temperature rise rate and temperature difference distribution features per unit time are calculated based on infrared thermal imaging data. This multi-dimensional feature extraction comprehensively uncovers the clutch's operating status correlation information, effectively distinguishing between normal fluctuations and fault characteristics, laying a solid foundation for health status assessment.

[0018] Step S3: Based on multi-dimensional fault characteristics and a preset health index quantification model, the real-time health status of the clutch is obtained. In this step S3, the multi-dimensional fault characteristics extracted in step S2, such as time-frequency domain, metal particle content, and temperature rise rate, are input into the preset health index quantification model. The real-time health index is calculated by integrating the weights of each feature. Through the comprehensive judgment of multi-source features by the model, the current health level of the clutch is accurately quantified, avoiding the one-sidedness of single feature evaluation, and providing an intuitive and reliable status basis for subsequent operation and maintenance decisions.

[0019] In one embodiment, step S3 further includes the following specific steps: Step S31: Normalize the multi-dimensional fault features and output a health index value within a preset range. In this step S31, the Min-Max normalization method is used to process the multi-dimensional fault features, mapping the time-frequency domain features, metal particle content features, and temperature rise rate features to the preset range [0,1], and outputting standardized health index values. Feature normalization eliminates the dimensional differences of data from different dimensions, ensuring that the weight of each feature in the model is reasonable, and improving the accuracy and comparability of the health index calculation.

[0020] Step S32: Based on the relationship between the health index value and the health status threshold, the real-time health status of the clutch is obtained. In this step S32, a preset health index ≥ 0.8 indicates a good health status; a preset health index between 0.6 and 0.8 indicates a moderate health status; and a preset health index < 0.6 indicates a warning status. The health index value output in S31 is compared with the threshold to determine the real-time health status of the clutch. Clear threshold divisions make health status determination more operational, facilitating maintenance personnel to quickly identify risk levels.

[0021] Step S4: Input the real-time health status of the clutch into a preset health status prediction framework to obtain the corresponding health status level. In this step S4, the real-time health index of the clutch and the corresponding multi-dimensional feature data obtained in S3 are input into the health status prediction framework built on an LSTM neural network. The framework outputs the corresponding health status level through its built-in training model. Deep learning algorithms are used to mine the state evolution law and predict the trend of health status changes in advance, providing forward-looking guidance for preventive maintenance.

[0022] In one embodiment, step S4 further includes the following specific steps: Step S41: Input the real-time health status of the clutch into the health status prediction framework, establish a correlation mapping relationship between the data and the remaining life, and deduce the probability distribution of the remaining life. In this step S41, the real-time health status data of the clutch, along with multi-source data such as historical operating temperature, load, and vibration, are input into the health status prediction framework. Through model training, a nonlinear correlation mapping relationship between the data and the remaining life is established, and the probability distribution of the remaining life with a confidence interval of ±5% is deduced and output. Through accurate remaining life prediction, a scientific time reference is provided for maintenance plan formulation, avoiding over-maintenance or maintenance delays.

[0023] Step S42: Determine the corresponding health status level based on the remaining lifetime probability distribution and the preset health status grading standard. In step S42, a preset remaining lifetime > 8000 hours corresponds to health status level A; a preset remaining lifetime > 4000 hours and < 8000 hours corresponds to health status level B; a preset remaining lifetime > 2000 hours and < 4000 hours corresponds to health status level C; and a preset remaining lifetime < 2000 hours corresponds to health status level D. By comparing the remaining lifetime probability distribution output in S41 with the grading standard, the corresponding health status level is determined. This clear grading clarifies the degree of equipment risk, facilitating the development of targeted operation and maintenance strategies.

[0024] Step S5: Based on a preset virtual machine group model, simulate the clutch response under different operating conditions to obtain simulation results for different clutch operating conditions. In one embodiment, the unit simulation model is a virtual mapping model that includes the clutch dynamic characteristics and fluid coupling characteristics, with the dynamic characteristics characterized by a built-in nonlinear stiffness coefficient. Specifically, in step S5, a 1:1 virtual mapping model including the clutch dynamic characteristics (built-in nonlinear stiffness coefficient) and fluid coupling characteristics is constructed based on digital twin technology. This model simulates the clutch vibration response, temperature changes, and wear under different loads, speeds, and ambient temperatures, outputting simulation results for more than 2,000 operating conditions. Virtual simulation comprehensively covers complex operating scenarios, allowing for the understanding of the impact of different operating conditions on the clutch without physical testing, thus reducing testing costs and risks.

[0025] Step S6: Adjust the load distribution and clutch engagement timing of the combined cycle unit based on the health status level and simulation results. In step S6, based on the health status level determined in S4 and combined with the operating condition simulation results in S5, dynamically adjust the pressure and timing parameters of the gas turbine load distribution ratio and clutch engagement. Through targeted adjustments, overload operation under poor health conditions is avoided, the wear of the clutch due to impact loads is reduced, and the coordinated optimization of unit operation and equipment protection is achieved. In one embodiment, step S6 further includes the following specific steps: Step S61: Adjust the operating parameters of the core equipment of the unit based on the health status level. In this step S61, the operating parameters of the core equipment are dynamically adjusted according to the health status level: under the A-level status, the gas turbine power generation efficiency is maintained at ≥58%; under the B / C-level status, the inlet guide vane angle is adjusted with an accuracy of ±3°; under the D-level status, the load is appropriately reduced and the engagement time is shortened. By adjusting the graded parameters, the unit can be adapted to different health statuses, thereby reducing equipment wear while ensuring unit operation.

[0026] Step S62: A multi-objective optimization algorithm is used to find the optimal balance between unit operating performance and clutch wear. In this step S62, the NSGA-Ⅲ multi-objective optimization algorithm is used, with constraints of power generation efficiency ≥58%, NOx emissions ≤50mg / m³, and clutch wear rate ≤0.01mm / thousand-hour, to find the Pareto optimal balance between unit operating performance and clutch wear. Through multi-objective collaborative optimization, a win-win situation of economic benefits, environmental benefits, and equipment health is achieved, thereby enhancing the overall operating value of the unit.

[0027] The technical solution of this application achieves dynamic adjustment of unit operating parameters through multi-source data acquisition, multi-dimensional fault feature extraction, quantitative assessment and prediction of health status, combined with digital twin simulation. This enables real-time monitoring of the SSS clutch health status and early warning of potential faults, effectively reducing the risk of unplanned downtime. Simultaneously, by accurately matching operating conditions with clutch health status, it avoids excessive maintenance and delayed repairs, significantly reducing maintenance costs and improving the operational stability and economy of the combined cycle unit.

[0028] In addition, this application also provides an SSS clutch health status combined cycle unit optimization system, please refer to [link / reference]. Figure 2 The system includes: The data acquisition module is used to collect multi-source data from the clutch in real time. This multi-source data includes clutch vibration signals, clutch friction plate temperature field data, and lubricating oil metal particle content data. Specifically, by capturing multi-source core data on clutch vibration, temperature field, and lubricating oil metal particles in real time, comprehensive and accurate raw data can be provided for subsequent fault analysis. This helps avoid the limitations of single-data monitoring and ensures the reliability of condition assessment. Specifically, the data acquisition module can be a high-frequency accelerometer, an infrared thermal imager, or an online oil spectrometer; no restrictions are placed on this.

[0029] The feature extraction module is used to extract multi-dimensional fault features of the clutch from multi-source data. These multi-dimensional fault features include time-frequency domain features, metal particle content features, and friction plate temperature rise rate features. Specifically, by deeply mining the time-frequency domain, metal particle content, and temperature rise rate features in the multi-source data, it is possible to accurately distinguish between normal fluctuations and fault signals, which helps to highlight early fault symptoms and lay a solid foundation for health status assessment. Specifically, the feature extraction module can be an embedded data processor, an FPGA chip, or an industrial control computer; there are no restrictions.

[0030] The health status assessment module is used to obtain the real-time health status of the clutch based on multi-dimensional fault characteristics and a preset health index quantification model. Specifically, by comprehensively evaluating multi-dimensional characteristics through the preset health index quantification model, the real-time health status of the clutch can be output intuitively and accurately, which is conducive to quickly identifying the equipment risk level and providing a direct basis for operation and maintenance decisions. Specifically, the health status assessment module can be an edge computing gateway, PLC controller, or industrial server, without limitation.

[0031] The health status prediction module inputs the real-time health status of the clutch into a preset health status prediction framework to obtain the corresponding health status level. Specifically, by associating the real-time health status with the remaining lifespan through the preset prediction framework, it is possible to predict the performance degradation trend of the equipment in advance, which helps to avoid delayed or excessive maintenance and reduce operation and maintenance costs. Specifically, the health status prediction module can be an AI inference server, a deep learning accelerator card, or a cloud computing platform, without any restrictions.

[0032] The virtual simulation module is used to simulate the clutch response under different operating conditions based on a preset virtual machine group model, obtaining simulation results for different clutch operating conditions. Specifically, by simulating the equipment response under different operating conditions through the virtual machine group model, it is possible to comprehensively understand the impact of complex operating conditions on the clutch, which is beneficial for verifying optimization schemes without physical testing, reducing experimental risks and costs. Specifically, the virtual simulation module can be a high-performance workstation, a cloud simulation platform, or a dedicated digital twin server, without any restrictions.

[0033] The operation adjustment module is used to adjust the load distribution and clutch engagement timing of the combined cycle unit based on the health status level and simulation results. Specifically, dynamically adjusting the unit's operating parameters according to the health status level and simulation results can achieve optimal adaptation of load distribution and clutch engagement timing, which helps reduce equipment impact losses and improve the unit's power generation efficiency and operational stability. Specifically, the operation adjustment module can be the unit's PLC control system, variable frequency drive, or intelligent actuator; there are no restrictions.

[0034] In one embodiment, the health status assessment module includes: The normalization unit is used to normalize multi-dimensional fault characteristics and output a health index value within a preset range. Specifically, by standardizing multi-dimensional fault characteristics, the differences in the dimensions of different characteristics can be eliminated, ensuring that the weight ratio of each characteristic is reasonable. This is beneficial to improving the accuracy and comparability of health index calculation and providing reliable data support for subsequent status determination. Specifically, the normalization unit can be a data preprocessing chip, an embedded algorithm module, or an industrial data acquisition terminal; no restrictions are placed here.

[0035] The status determination unit is used to obtain the real-time health status of the clutch based on the relationship between the health index value and the health status threshold. Specifically, by accurately comparing the health index value with the preset threshold, the clutch health status level can be quickly and clearly classified. This helps maintenance personnel to intuitively identify the degree of equipment risk, providing a direct basis for formulating targeted maintenance strategies and improving decision-making efficiency. Specifically, the status determination unit can be a logic control module, a PLC processing unit, or an intelligent determination gateway; there are no restrictions here.

[0036] In one embodiment, the health status prediction module includes: The prediction unit is used to input the real-time health status of the clutch into the health status prediction framework, establish a correlation mapping between the data and the remaining lifespan, and deduce the probability distribution of the remaining lifespan. Specifically, by inputting the real-time health status into the prediction framework, establishing a correlation mapping between the data and the remaining lifespan, and deduce the probability distribution, the performance degradation trend of the clutch can be accurately predicted, potential failure risks can be identified in advance, and economic losses caused by unplanned downtime can be avoided, providing a scientific time reference for maintenance planning. Specifically, the prediction unit can be an AI inference chip, a deep learning module, or an edge computing server, without limitation.

[0037] The assessment unit is used to determine the corresponding health status level based on the remaining lifetime probability distribution and preset health status grading standards. Specifically, by comparing the remaining lifetime probability distribution with the preset grading standards, the health status level can be clearly defined, allowing maintenance personnel to intuitively understand the degree of equipment risk. This facilitates the development of targeted maintenance strategies, balancing maintenance costs and equipment reliability, and improving the accuracy and efficiency of maintenance decisions. Specifically, the assessment unit can be a logic operation module, a PLC control unit, or an intelligent decision gateway; there are no restrictions.

[0038] In one embodiment, the virtual machine group model in the virtual simulation module is a virtual mapping model that includes the clutch's dynamic characteristics and fluid coupling characteristics. The dynamic characteristics are characterized by a built-in nonlinear stiffness coefficient. Specifically, by constructing a virtual mapping model that includes the clutch's dynamic characteristics (built-in nonlinear stiffness coefficient) and fluid coupling characteristics, the actual operating response of the clutch under complex working conditions can be accurately replicated, and the dynamic interaction law of the equipment can be restored. This facilitates a comprehensive understanding of the impact of different working conditions on the clutch without physical testing, significantly reducing testing costs and safety risks, and providing accurate simulation support for operational optimization. Specifically, the virtual simulation module can be a dedicated digital twin server, a high-performance simulation workstation, or a cloud-native simulation platform, and there are no restrictions on its implementation. In one embodiment, the operation adjustment module includes: The parameter adjustment unit is used to adjust the operating parameters of the unit's core equipment based on the health status level. Specifically, by dynamically adjusting the operating parameters of the unit's core equipment according to the health status level, the unit's operating state can be precisely matched with the clutch's health level, avoiding overload operation when the health status is poor. This helps reduce equipment impact losses, extend clutch life, and ensure the unit's basic operating performance. Specifically, the parameter adjustment unit can be an intelligent PID controller, a unit PLC regulation module, or a variable frequency speed control device; there are no restrictions.

[0039] The optimization and solution unit is used to find the optimal balance between unit operating performance and clutch wear using a multi-objective optimization algorithm. Specifically, by employing a multi-objective optimization algorithm to find the optimal balance between unit operating performance and clutch wear, it is possible to minimize clutch wear while ensuring power generation efficiency and controlling pollutant emissions. This facilitates a synergistic improvement in economic benefits, environmental benefits, and equipment health, thereby enhancing the overall operating value of the unit. Specifically, the optimization and solution unit can be an embedded optimization computing module, an AI decision chip, or a high-performance industrial server; there are no restrictions on its specific capabilities. This application aims to protect a method and system for optimizing the health status of a combined cycle power unit using an SSS clutch. The technical solution of this application achieves dynamic adjustment of unit operating parameters through multi-source data acquisition, multi-dimensional fault feature extraction, quantitative assessment and prediction of health status, combined with digital twin simulation. This allows for real-time monitoring of the SSS clutch health status and early warning of potential faults, effectively reducing the risk of unplanned downtime. Simultaneously, by accurately matching operating conditions with clutch health status, it avoids excessive maintenance and delayed repairs, significantly reducing maintenance costs and improving the operational stability and economy of the combined cycle power unit.

[0040] It should be understood that the specific embodiments described above are merely illustrative or explanatory of the principles of this application and do not constitute a limitation thereof. Therefore, any modifications, equivalent substitutions, improvements, etc., made without departing from the spirit and scope of this application should be included within the protection scope of this application. Furthermore, the appended claims are intended to cover all variations and modifications falling within the scope and boundaries of the appended claims, or equivalent forms of such scope and boundaries.

Claims

1. A method for optimizing the health status of a combined cycle power unit with an SSS clutch, characterized in that, include: Real-time acquisition of multi-source data from the clutch, including clutch vibration signals, clutch friction plate temperature field data, and lubricating oil metal particle content data; Multi-dimensional fault features of the clutch are extracted from the multi-source data. These multi-dimensional fault features include time-frequency domain features, metal particle content features, and friction plate temperature rise rate features. Based on the multi-dimensional fault characteristics and the preset health index quantification model, the real-time health status of the clutch is obtained. The real-time health status of the clutch is input into a preset health status prediction framework to obtain the corresponding health status level. Based on a pre-defined virtual machine group model, the response of the clutch under different operating conditions is simulated to obtain simulation results of the clutch under different operating conditions. Based on the health status level and the simulation results, adjust the load distribution and clutch engagement sequence of the combined cycle unit.

2. The method for optimizing the health status of a combined cycle unit with an SSS clutch according to claim 1, characterized in that, The step of obtaining the real-time health status of the clutch based on the multi-dimensional fault characteristics and the preset health index quantification model includes: The multi-dimensional fault characteristics are normalized, and a health index value within a preset range is output. The real-time health status of the clutch is obtained based on the relationship between the health index value and the health status threshold.

3. The method for optimizing the health status of a combined cycle unit with an SSS clutch according to claim 1, characterized in that, The step of inputting the real-time health status of the clutch into a preset health status prediction framework to obtain the corresponding health status level includes: The real-time health status of the clutch is input into the health status prediction framework to establish a correlation mapping relationship between the data and the remaining lifespan, and the probability distribution of the remaining lifespan is deduced and output. Based on the remaining life expectancy probability distribution and the preset health status grading standard, the corresponding health status level is determined.

4. The method for optimizing the health status of a combined cycle unit with an SSS clutch according to claim 1, characterized in that, The unit simulation model is a virtual mapping model that includes clutch dynamic characteristics and fluid coupling characteristics, and the dynamic characteristics are characterized by a built-in nonlinear stiffness coefficient.

5. The method for optimizing the health status of a combined cycle unit with an SSS clutch according to any one of claims 1 to 4, characterized in that, The steps for adjusting the load distribution of the combined cycle unit include: Adjust the operating parameters of the unit's core equipment based on the aforementioned health status level; A multi-objective optimization algorithm is used to find the optimal balance between unit operating performance and clutch wear.

6. An optimization system for the health status of an SSS clutch combined cycle unit, characterized in that, include: The data acquisition module is used to acquire multi-source data of the clutch in real time. The multi-source data includes clutch vibration signal, clutch friction plate temperature field data and lubricating oil metal particle content data. The feature extraction module is used to extract multi-dimensional fault features of the clutch from the multi-source data. The multi-dimensional fault features include time-frequency domain features, metal particle content features, and friction plate temperature rise rate features. The health status assessment module is used to obtain the real-time health status of the clutch based on the multi-dimensional fault characteristics and the preset health index quantification model. The health status prediction module inputs the real-time health status of the clutch into a preset health status prediction framework to obtain the corresponding health status level. The virtual simulation module is used to simulate the clutch response under different operating conditions based on a preset virtual machine group model, and obtain simulation results of the clutch under different operating conditions. The operation adjustment module is used to adjust the load distribution and clutch engagement sequence of the combined cycle unit based on the health status level and the simulation results.

7. The SSS clutch health status combined cycle unit optimization system according to claim 6, characterized in that, The health status assessment module includes: The normalization unit is used to normalize the multi-dimensional fault characteristics and output a health index value within a preset range. The status determination unit is used to obtain the real-time health status of the clutch based on the relationship between the health index value and the health status threshold.

8. The SSS clutch health status combined cycle unit optimization system according to claim 7, characterized in that, The health status prediction module includes: The prediction unit is used to input the real-time health status of the clutch into the health status prediction framework, establish the correlation mapping relationship between the data and the remaining life, and deduce and output the probability distribution of the remaining life. The assessment unit is used to determine the corresponding health status level based on the remaining life expectancy probability distribution and the preset health status grading standard.

9. The SSS clutch health status combined cycle unit optimization system according to claim 8, characterized in that, The virtual machine group model in the virtual simulation module is a virtual mapping model that includes clutch dynamic characteristics and fluid coupling characteristics. The dynamic characteristics are characterized by a built-in nonlinear stiffness coefficient.

10. The SSS clutch health status combined cycle unit optimization system according to any one of claims 6 to 9, characterized in that, The operation adjustment module includes: The parameter adjustment unit is used to adjust the operating parameters of the unit's core equipment based on the health status level. The optimization solution unit is used to solve for the optimal balance between unit operating performance and clutch wear using a multi-objective optimization algorithm.

Images