Gas turbine power plant equipment whole life cycle management method based on three-dimensional digital twinning

Abstract

The application relates to the field of power plant management and discloses a full-life-cycle management method for gas turbine power plant equipment based on three-dimensional digital twinning, which is used for realizing intelligent upgrading of gas turbine key equipment from timed maintenance to on-demand precise maintenance. The method comprises the following steps: stress and temperature characteristic values of key areas are extracted through finite element simulation; a stress-temperature ratio is calculated; an accumulated damage amount is obtained; actual deformation data obtained through periodic laser scanning is introduced; an equipment health index is obtained based on the accumulated damage amount; operation state evaluation and residual life prediction results are automatically matched; power plant spare parts inventory and standard maintenance operation package are linked; and a precise maintenance time window, spare parts procurement plan and maintenance scheduling scheme are output. The application realizes full-link closed-loop management of gas turbine power plant equipment from state sensing, damage quantification to operation and maintenance decision, effectively reduces unplanned shutdown risks, and supports safe and efficient self-controllable operation and maintenance of the gas turbine power plant.

Description

Technical Field

[0001] This invention relates to the field of power plant management, and in particular to a method for full life-cycle management of gas turbine power plant equipment based on three-dimensional digital twins. Background Technology

[0002] my country's gas-fired power generation industry is currently experiencing a period of rapid development. Heavy-duty gas turbines such as the 9F class have become the core main equipment for cogeneration projects in many places. However, its core thermal channel components have long relied on imports, and operation and maintenance technology has long been monopolized by overseas manufacturers. High maintenance costs and spare parts procurement cycles have become the core pain points restricting the safe and efficient operation of gas turbine power plants.

[0003] Meanwhile, the operating characteristics of gas turbine power plants place extremely high demands on equipment management: gas turbines operate under extreme conditions of high temperature, high pressure, and high speed for extended periods. Frequent deep peak shaving and rapid load changes cause critical components such as blades and combustion chambers to suffer both creep and fatigue damage. Traditional management models relying on planned maintenance are no longer suitable for the flexible operation needs of units under the new power system. Against this industry backdrop, the deep integration of 3D digital twin technology with 3D digital twin-based full lifecycle management of gas turbine power plant equipment, through virtual-real mapping, to accurately quantify equipment damage and predict remaining lifespan, has become an inevitable development direction for gas turbine power plants to achieve autonomous and controllable operation and maintenance, and reduce costs and increase efficiency.

[0004] Traditional gas turbine equipment management mostly uses the factory-designed CAD model directly for simulation calculations, without considering equipment installation deviations, initial deformation caused by long-term operation, and dynamic changes in actual boundary conditions. This results in a large deviation between the stress and temperature data obtained from the simulation and the actual operating state of the equipment, making it impossible to accurately reflect the actual load conditions in key areas, ultimately causing the calculation results of creep and fatigue damage to be distorted.

[0005] Most existing solutions can only output simple lifespan warning results. They do not deeply integrate health index, remaining lifespan prediction with power plant spare parts inventory and maintenance scheduling system. They cannot automatically generate spare parts procurement plans that match the procurement lead time, nor can they automatically output maintenance task schedules according to standard work packages. As a result, lifespan assessment results cannot be directly applied to guide on-site operation and maintenance, which can easily lead to problems such as delayed spare parts delivery and unreasonable maintenance window arrangements. It is difficult to truly achieve refined closed-loop management of the entire equipment life cycle.

[0006] Therefore, we propose a three-dimensional digital twin-based method for the full lifecycle management of gas turbine power plant equipment to address the above issues. Summary of the Invention

[0007] This invention provides a method for full life-cycle management of gas turbine power plant equipment based on three-dimensional digital twins, which is used to realize the intelligent leap from scheduled maintenance to on-demand precise maintenance of key gas turbine equipment.

[0008] The first aspect of this invention provides a method for full lifecycle management of gas turbine power plant equipment based on three-dimensional digital twins. The method includes: constructing a digital twin of the target equipment; acquiring stress and temperature parameters of key areas of the target equipment based on the digital twin; calculating the cumulative damage of the target equipment during each operating period based on the stress parameters, the temperature parameters, and initial lifespan data; acquiring actual deformation data of the key areas to determine deformation damage, and correcting the initial lifespan data based on the deviation between the deformation damage and the cumulative damage; determining the health status of the target equipment based on the cumulative damage, and outputting a corresponding operation and maintenance strategy.

[0009] Optionally, in a first implementation of the first aspect of the present invention, constructing a digital twin of the target device includes: Obtain the design model and material property data of the target device; Obtain the spatial morphological data of the key area, and fuse the spatial morphological data with the design model to obtain the corrected geometric model; By coupling the modified geometric model with the boundary conditions acquired in real time, a digital twin reflecting the actual state is obtained.

[0010] Optionally, in a second implementation of the first aspect of the present invention, the method includes: Based on the digital twin, finite element simulation is performed on the key area, and the actual stress value and actual temperature value of the key area are extracted from the simulation results. The stress ratio obtained by comparing the actual stress value with the design stress value is used as the stress parameter, and the temperature ratio obtained by comparing the actual temperature value with the design temperature value is used as the temperature parameter.

[0011] Optionally, in a third implementation of the first aspect of the present invention, the method includes: When the operating conditions of the target equipment change by a preset magnitude, the finite element simulation is triggered to extract the nodal stress and nodal temperature values ​​of all mesh nodes in the key area. Based on the volume ratio of the grid nodes, the stress values ​​of the nodes are weighted and summed to obtain the overall stress characterization value as the actual stress value, and the temperature values ​​of the nodes are weighted and summed to obtain the overall temperature characterization value as the actual temperature value.

[0012] Optionally, in a fourth implementation of the first aspect of the present invention, the method includes: The initial life data includes creep life data and fatigue life data; Based on the stress parameters, the temperature parameters, and the creep life data, calculate the creep damage amount for each of the operating time periods; The fatigue damage amount for each of the operating time periods is calculated based on the stress parameters, the temperature parameters, and the fatigue life data. The creep damage amount and the fatigue damage amount are added together to obtain the damage increment within the corresponding operating time period. The damage increments of each operating time period are then accumulated to obtain the cumulative damage amount.

[0013] Optionally, in a fifth implementation of the first aspect of the present invention, the method includes: The actual operating state of the target device during each operating time period is divided into a stable operating phase and a variable operating condition phase. For each stable operation phase, the creep life value is retrieved based on the stress and temperature parameters of that phase, and the creep damage amount is calculated in combination with the actual operating time of that phase. For each of the variable working condition stages, the fatigue life value is obtained based on the change range of the stress parameters in that stage, and the fatigue damage is calculated in combination with the actual number of start-stop cycles in that stage.

[0014] Optionally, in a sixth implementation of the first aspect of the present invention, the method includes: The actual deformation value of the key area is obtained by non-contact measurement as the actual deformation data. The actual deformation value is compared with the design allowable deformation value to determine the amount of deformation damage. When the deviation result exceeds the preset deviation threshold multiple times consecutively, the material parameters in the initial life data are adjusted so that the deviation between the cumulative damage amount and the deformation damage amount recalculated by substituting the adjusted material parameters is reduced, thereby obtaining the corrected life data.

[0015] Optionally, in a seventh implementation of the first aspect of the present invention, the step of obtaining the actual deformation value of the critical area through non-contact measurement as the actual deformation data, and comparing the actual deformation value with the design allowable deformation value to determine the amount of deformation damage, includes: The critical region is divided into multiple sub-regions, and the actual deformation value of each sub-region is obtained, and the deformation damage amount of each sub-region is determined. Calculate the regional deviation between the deformation damage amount and the cumulative damage amount in each sub-region in the corresponding sub-region; When the deviation result of any sub-region exceeds the preset deviation threshold multiple times consecutively, the material parameters corresponding to that sub-region are adjusted individually, and the adjusted material parameters of each sub-region are combined according to their spatial position to obtain a partitioned material parameter correction table, which is used as the corrected life data.

[0016] Optionally, in an eighth implementation of the first aspect of the present invention, the method includes: The health index is determined based on the result of subtracting the cumulative damage amount from one; The health index is compared with multiple preset threshold ranges to determine the operating status level of the target device and the corresponding remaining life prediction range, which is taken as the health status. When the health index is lower than the preset maintenance trigger threshold, a maintenance suggestion including a suggested maintenance time window is obtained as an operation and maintenance strategy.

[0017] Optionally, in a ninth implementation of the first aspect of the present invention, the step of obtaining a maintenance suggestion including a suggested maintenance time window as the operation and maintenance strategy when the health index is lower than a preset maintenance trigger threshold further includes: By combining the health index, the remaining life prediction range, and the current spare parts inventory information, a spare parts procurement recommendation is obtained, which includes the procurement quantity and procurement time window. The spare parts procurement recommendation determines the ordering time by comparing the remaining life prediction range with the spare parts procurement lead time, and calculates the procurement quantity based on the minimum safety stock and the current inventory quantity. Based on the operating status level, a corresponding standard maintenance work package is matched to obtain a maintenance task schedule that includes the maintenance work type, required human resources, and estimated downtime.

[0018] Beneficial effects: The modeling method of registering and fusing laser point clouds with design models, and superimposing real-time sensor boundary conditions to obtain dynamic twins, improves the simulation accuracy of stress and temperature in key areas of equipment compared with traditional solutions, and fundamentally solves the common industry problem of simulation results being out of sync with actual working conditions; By introducing laser scanning deformation data into the damage calculation closed loop, the creep and fatigue material parameters are dynamically and iteratively corrected by the deviation between the deformation damage amount and the cumulative damage amount. This changes the defect of long-term solidification of material performance parameters in traditional technology and greatly improves the reliability of long-term operation and maintenance. The equipment operation is divided into two independent stages: stable operation and variable operating conditions. Differentiated calculation logics for creep and fatigue damage are matched respectively. At the same time, the node volume weighting method is used to statistically analyze the overall stress and temperature characterization values ​​of key areas, accurately capturing local concentrated damage under extreme operating conditions such as deep peak shaving and rapid load change, avoiding the problem of missing early local hidden dangers in traditional averaging calculations. By deeply linking equipment health index and remaining life prediction results with power plant spare parts inventory system and standard maintenance work packages, the system can automatically generate spare parts procurement plans that are adapted to the procurement lead time and maintenance task schedules that match the operating conditions. This allows life assessment results to be directly transformed into implementable solutions, achieving refined and intelligent management and control of the entire equipment life cycle. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of an embodiment of the gas turbine power plant equipment lifecycle management method based on three-dimensional digital twins in this invention. Detailed Implementation

[0020] This invention provides a method for full lifecycle management of gas turbine power plant equipment based on three-dimensional digital twins, enabling a smart leap from scheduled maintenance to precise on-demand maintenance of key gas turbine equipment. The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein. Furthermore, the terms "comprising" or "having" and any variations thereof are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or devices.

[0021] For ease of understanding, the specific process of the embodiments of the present invention is described below. Please refer to [link / reference]. Figure 1 One embodiment of the gas turbine power plant equipment lifecycle management method based on three-dimensional digital twins in this invention includes: 101. Construct a three-dimensional digital twin model of the equipment, which includes the equipment's geometric dimensions, material properties, and real-time boundary conditions, to obtain the equipment's three-dimensional digital twin.

[0022] It is understood that the executing entity of this invention can be a gas turbine power plant equipment lifecycle management device based on three-dimensional digital twins, or it can be a terminal or a server; the specific implementation is not limited here. This embodiment of the invention will be described using a server as an example.

[0023] Specifically, the design CAD model and material property data of the equipment are acquired, and laser point cloud data of key areas of the equipment are collected. The laser point cloud data is registered and fused with the design CAD model to obtain a corrected geometric model. The corrected geometric model is then coupled with the boundary conditions obtained from the sensors in real time to obtain a three-dimensional digital twin that can dynamically reflect the actual state of the equipment.

[0024] It should be noted that the design CAD 3D solid model of the first-stage turbine blade was retrieved from the power plant equipment asset management system. The blade has a complex internal cooling channel structure. The system reads the material property data of the blade from the factory: the blade material is a directionally solidified nickel-based superalloy with a room temperature yield strength of 850 MPa. It also includes key thermodynamic data such as the thermal conductivity, specific heat capacity, and coefficient of thermal expansion of the alloy under different temperature gradients.

[0025] During equipment downtime for maintenance, technicians used a high-precision 3D laser scanner to scan the blade, particularly key areas such as the leading edge and root tenon, to acquire point cloud data of its actual physical shape. The server then used a registration algorithm to spatially align and fuse the point cloud data with the original design CAD model. System comparison revealed a 0.15mm profile deviation between the actual physical blade's inlet leading edge and the theoretical design. Based on this deviation, the server fine-tuned the mesh nodes of the original CAD model, resulting in a corrected geometric model that closely matches the current actual dimensions of the physical entity.

[0026] During stable grid-connected operation of the gas turbine, the server reads sensor parameters in real time through the distributed control system: the gas temperature at the turbine inlet is 1380℃, the rotor speed is 3000rpm, the cooling air pressure is 2.5MPa, and the cooling airflow temperature is 380℃. The server converts these real-time operating conditions into physical field boundary conditions and applies them to the model.

[0027] 102. Based on the three-dimensional digital twin, calculate the ratio of actual stress to design stress and the ratio of actual temperature to design temperature in the key areas of the equipment to obtain the stress ratio and temperature ratio.

[0028] Specifically, based on a three-dimensional digital twin, finite element simulation is performed on the key areas of the equipment, and the maximum equivalent stress and the highest temperature value of the area are extracted from the simulation results. The maximum equivalent stress value is then divided by the equipment design stress value to obtain the stress ratio, and the highest temperature value is divided by the equipment design temperature value to obtain the temperature ratio.

[0029] Furthermore, the finite element simulation is triggered when the equipment's operating conditions undergo a preset amplitude change. From each simulation result, the stress and temperature values ​​of all mesh nodes in the critical area of ​​the equipment are extracted. The stress values ​​of the nodes within this area are weighted and summed according to their volume ratio to obtain the overall stress characterization value for that area. The node temperature values ​​are weighted in the same way to obtain the overall temperature characterization value. The stress ratio is obtained by dividing the overall stress characterization value by the equipment's design stress value, and the temperature ratio is obtained by dividing the overall temperature characterization value by the equipment's design temperature value. The stress ratio and temperature ratio obtained from each simulation trigger together constitute a state parameter pair for a given operating point, and a runtime label corresponding to that operating point is attached. This state parameter pair is used to subsequently calculate the damage increment based on the actual runtime corresponding to the operating point.

[0030] It should be noted that the server database pre-stores the basic design extreme value data of the turbine blade root tenon transition zone: the design limit stress is set to 250MPa, and the design limit temperature is set to 1000℃. The system sets a dynamic trigger threshold for finite element simulation, that is, when the unit load variation exceeds 10% of the rated load, the simulation calculation is automatically triggered.

[0031] When the unit performs peak-shaving tasks to reduce load, the sensor detects that the fluctuation reaches 15%, exceeding the preset threshold. The server then performs a fluid-solid-thermal multi-field coupled finite element simulation of the region based on the 3D digital twin updated in step 101.

[0032] After the simulation was completed, in order to more accurately reflect the dangerous nodes that may induce fatigue fracture and high-temperature creep, the server abandoned the volume-weighted average method, which easily smooths out local extreme values, and instead directly extracted the peak point of the maximum equivalent stress and the highest local temperature extreme point in the region where the load was most severe.

[0033] The system extracted a maximum equivalent stress of 200 MPa and a maximum local temperature of 920 °C for the region. The server divided the extracted actual peak stress (200 MPa) by the design stress (250 MPa) to obtain a stress ratio of 0.80; and divided the actual peak temperature (920 °C) by the design temperature (1000 °C) to obtain a temperature ratio of 0.92. The stress ratio of 0.80 and the temperature ratio of 0.92 together constitute the state parameter pair at this operating point. The system adds a "120h" duration label for the actual operation to provide standard input for subsequent damage increments.

[0034] 103. Substitute the stress ratio and temperature ratio into the creep life data and fatigue life data of the material at the time of manufacture, calculate the damage increment in each operating time period, and sum up the damage increments in each time period to obtain the cumulative damage.

[0035] Specifically, the stress ratio and temperature ratio are substituted into the creep life curve and fatigue life curve of the material at the time of manufacture, respectively, to obtain the corresponding creep life value and fatigue life value; the creep damage is calculated based on the actual running time and creep life value within the current operating period; the fatigue damage is calculated based on the actual number of start-stop cycles and fatigue life value within the current operating period; the creep damage is added to the fatigue damage to obtain the damage increment within the operating period; and the damage increments of each operating period are summed to obtain the cumulative damage.

[0036] Furthermore, the actual operating state of the equipment within each operating time period is divided into a stable operating phase and a variable operating condition phase. The operating time of the stable operating phase is taken as the actual operating time, and the number of start-stop cycles in the variable operating condition phase is taken as the actual start-stop cycle. For each stable operating phase, the creep life value is retrieved based on the stress ratio and temperature ratio corresponding to that phase, and the creep damage amount for that phase is calculated. For each variable operating condition phase, the fatigue life value is retrieved based on the stress ratio change range corresponding to that phase, and the fatigue damage amount for that phase is calculated. The creep damage amount of each stable operating phase and the fatigue damage amount of each variable operating condition phase within the same time period are added together to obtain the damage increment for that time period. At the same time, the stress ratio, temperature ratio, creep damage amount, and fatigue damage amount corresponding to each operating time period are all tagged with a time stamp and stored in the historical operating condition database. This historical operating condition database is used as the basis for correcting material parameters when tracing abnormal operating conditions based on deviation results.

[0037] It should be noted that the operating condition parameter pair obtained in the previous step (i.e., the peak stress ratio of 0.80 and the peak temperature ratio of 0.92) is substituted into the standard creep and low-cycle fatigue life curves of the directionally solidified nickel-based superalloy at the time of its manufacture for interpolation addressing. It is found that under this harsh level, the theoretical limit creep life of the material is 24,000 hours, and the theoretical limit fatigue life is 10,000 cycles.

[0038] This operation was precisely divided into a variable operating condition phase and a stable operating phase for calculation: Fatigue damage calculation: This load reduction operation is counted as one variable operating condition cycle. One actual cycle divided by the theoretical limit fatigue life of 10,000 cycles results in a single fatigue damage of 0.0001.

[0039] Creep damage calculation: The status label shows that the unit has been running stably for 120 hours. Dividing the actual 120 hours of operation by the theoretical limit creep life of 24,000 hours, the creep damage is 0.005.

[0040] Incremental merging: The creep damage (0.005) and fatigue damage (0.0001) are added together, and the total damage increment for this operating period is 0.0051.

[0041] After completing the current calculation, the server retrieves the historical cumulative damage of the moving blade since its commissioning (currently recorded as 0.1500). The system adds the newly added damage (0.0051) to the historical baseline value, updating the latest cumulative damage to 0.1551. The system then structures and packages the timestamp, stress ratio, temperature ratio, and updated cumulative damage into the power plant's historical operating condition feature database.

[0042] 104. Regularly perform laser scanning on key areas of the equipment to obtain deformation data, and convert the deformation data into deformation damage amount; compare the deviation between the deformation damage amount and the cumulative damage amount, and correct the material parameters in the creep life data and fatigue life data according to the deviation to obtain the corrected material parameters.

[0043] Specifically, the actual deformation value of the key area is obtained by using a laser scanning device; the actual deformation value is compared with the maximum allowable deformation value to determine the deformation damage; the deviation between the deformation damage and the cumulative damage is calculated to obtain the deviation result; when the deviation result exceeds the preset deviation threshold multiple times consecutively, the material parameters in the creep life data and fatigue life data are adjusted so that the deviation between the cumulative damage and the deformation damage is reduced after substituting the adjusted material parameters, thereby obtaining the corrected material parameters, which are used to calculate the damage increment in subsequent operating periods.

[0044] Furthermore, when performing laser scanning on the critical area of ​​the equipment, the critical area is divided into multiple sub-regions. The actual deformation value of each sub-region is obtained, and the deformation damage amount corresponding to each sub-region is calculated. The deviation between the deformation damage amount of each sub-region and the corresponding value of the cumulative damage amount in the same sub-region is calculated to obtain the deviation result of each sub-region. When the deviation result of a certain sub-region exceeds the preset deviation threshold multiple times consecutively, only the material parameters corresponding to that sub-region are adjusted individually to obtain the corrected material parameters of that sub-region. The corrected material parameters of each sub-region are combined according to their spatial position relationship to form a partitioned material parameter correction table for the critical area of ​​the equipment. This partitioned material parameter correction table is used for subsequent calculation of the damage increment at the location of that sub-region.

[0045] It should be noted that during routine maintenance, a laser scanner is used to scan the blades, and the data is divided into Zone A (high-temperature zone at the blade leading edge), Zone B, and Zone C. Taking Zone A, which is subject to the most severe heating, as an example, the actual deformation value (creep elongation) obtained from the scan is 0.6 mm. The system confirms that the maximum allowable deformation limit for this zone is 2.0 mm.

[0046] To convert physical geometric elongation into damage life dimension, the system divides the actual deformation value (0.6 mm) by the maximum deformation limit value (2.0 mm) and multiplies it by the "deformation and damage equivalent conversion coefficient" specific to this nickel-based alloy (set to a linear mapping coefficient of 1.0 in this example) to calculate the deformation damage amount characterizing the current macroscopic state as 0.30.

[0047] The server retrieves the theoretical cumulative damage amount for area A, calculated daily in step 103, which is currently recorded as 0.25. The system compares the deformation damage amount (0.30) with the theoretical damage amount (0.25) and finds a deviation of 20%. Given that the internal allowable deviation threshold is 10%, the current 20% has exceeded the limit, and historical records show that this area has exceeded the limit three times consecutively, thus meeting the correction trigger condition.

[0048] The actual damage exceeded the theoretical calculation, indicating that the factory parameters overestimated the creep resistance of the material in area A under the actual micro-environment of the power plant. The server used a reverse optimization algorithm to lower the basic creep life coefficient bound to area A by 15%, and recalculated using historical data, resulting in a new theoretical cumulative damage of 0.29. At this point, the deviation from the actual deformation damage (0.30) was reduced to approximately 3.3%, achieving the correction objective. The system then combined the corrected parameters for area A with the uncorrected parameters for areas B and C.

[0049] 105. Determine the health index of the equipment based on the cumulative damage amount, compare the health index with the preset threshold, output the equipment's operating status assessment and remaining life prediction, and obtain maintenance recommendations based on the comparison results.

[0050] Specifically, the result of subtracting the cumulative damage amount from the health index is used as the health index; the health index is compared with multiple preset threshold intervals, each threshold interval corresponding to a device operating status level; the current operating status level of the device is determined based on the comparison results, and the corresponding remaining life prediction interval is output based on the status level; at the same time, when the health index is lower than the preset maintenance trigger threshold, maintenance recommendations including suggested maintenance time windows are obtained.

[0051] It should be noted that the server retrieves the latest cumulative damage value of the high-temperature region at the leading edge of the turbine blade from the historical operating condition database. After long-term and complex operation and material coefficient correction, the system records that the current cumulative damage value has reached 0.62. The server subtracts this cumulative damage value of 0.62 from the value to obtain the current health index of the blade as 0.38.

[0052] The server has a built-in health index evaluation matrix. The calculated value of 0.38 is compared with the following preset threshold range, as shown in Table 1 below: Table 1

[0053] Based on the table analysis, the health index of 0.38 falls into the "dangerous (severe damage)" range. The server output status assessment is "dangerous," with a remaining lifespan prediction range of less than 3000 EOH. Since 0.38 is lower than the preset maintenance trigger threshold (0.40 safety red line), the system receives a high-priority maintenance recommendation: there is a risk of severe creep and microcrack fracture at the leading edge of the blade. It is recommended to schedule a Level C overhaul within the next 1500~2000 EOH (approximately 3 months of actual operation) to perform comprehensive flaw detection and replacement of the damaged blade.

[0054] 106. Based on the health index and remaining life prediction range, and combined with the power plant's current spare parts inventory information, we obtain the procurement quantity recommendations and procurement time windows for key spare parts of the equipment; at the same time, based on the equipment operating status level corresponding to the health index, we obtain a maintenance task schedule that includes maintenance operation type, required human resources, and expected downtime.

[0055] Furthermore, the spare parts inventory information includes the spare parts name, current inventory quantity, procurement lead time, and minimum safety stock level. The procurement quantity recommendation is determined by comparing the remaining life forecast range with the procurement lead time to determine the spare parts ordering time, and the required procurement quantity is calculated based on the minimum safety stock level and the current inventory quantity. The maintenance task scheduling table matches pre-compiled standard maintenance work packages according to the equipment operating status level corresponding to the health index. Each standard maintenance work package includes the corresponding maintenance procedures, the required number of trades, and the estimated working hours.

[0056] It should be noted that real-time data from the ERP system shows that the current inventory of the core material "first-level turbine blades" is 1 set, the minimum safety stock is 1 set, and the procurement lead time is as long as 6 months.

[0057] The system simulation showed that the equipment needed a major overhaul within three months, consuming one set of existing inventory. At that point, the inventory would drop below the safety threshold to zero, while new purchases would take six months to arrive, resulting in a three-month "spare-free period." Given this critical risk, the system not only immediately received an order to expedite the purchase of one set of spare parts but also automatically triggered a degraded operation intervention strategy.

[0058] Based on the health index, the server matches a "Hot Aisle Component Special C-Level Maintenance Work Package" from the standard operation library. The system integrates material scheduling, operational intervention, and maintenance scheduling, and outputs the following intuitive guidance to the production department (see Table 2 below): Table 2

[0059] The present invention also provides a gas turbine power plant equipment lifecycle management device based on three-dimensional digital twins. The gas turbine power plant equipment lifecycle management device based on three-dimensional digital twins includes a memory and a processor. The memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor performs the steps of the gas turbine power plant equipment lifecycle management method based on three-dimensional digital twins in the above embodiments.

[0060] The present invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when the instructions are executed on a computer, cause the computer to perform the steps of the method for full life cycle management of gas turbine power plant equipment based on three-dimensional digital twin.

[0061] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0062] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0063] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for full lifecycle management of gas turbine power plant equipment based on three-dimensional digital twins, characterized in that, include: Construct a digital twin of the target device; Based on the digital twin, obtain the stress and temperature parameters of the key areas of the target equipment; Based on the stress parameters, the temperature parameters, and the initial life data, calculate the cumulative damage to the target equipment during each operating period. The actual deformation data of the key area is obtained to determine the amount of deformation damage, and the initial lifetime data is corrected based on the deviation between the amount of deformation damage and the amount of cumulative damage. The health status of the target device is determined based on the cumulative damage amount, and the corresponding operation and maintenance strategy is output.

2. The method for full lifecycle management of gas turbine power plant equipment based on three-dimensional digital twins according to claim 1, characterized in that, The construction of the digital twin of the target device includes: Obtain the design model and material property data of the target device; Obtain the spatial morphological data of the key area, and fuse the spatial morphological data with the design model to obtain the corrected geometric model; By coupling the modified geometric model with the boundary conditions acquired in real time, a digital twin reflecting the actual state is obtained.

3. The method for full life-cycle management of gas turbine power plant equipment based on three-dimensional digital twins according to claim 1, characterized in that, include: Based on the digital twin, finite element simulation is performed on the key area, and the actual stress value and actual temperature value of the key area are extracted from the simulation results. The stress ratio obtained by comparing the actual stress value with the design stress value is used as the stress parameter, and the temperature ratio obtained by comparing the actual temperature value with the design temperature value is used as the temperature parameter.

4. The method for full life-cycle management of gas turbine power plant equipment based on three-dimensional digital twins according to claim 3, characterized in that, include: When the operating conditions of the target equipment change by a preset magnitude, the finite element simulation is triggered to extract the nodal stress and nodal temperature values ​​of all mesh nodes in the key area. Based on the volume ratio of the grid nodes, the stress values ​​of the nodes are weighted and summed to obtain the overall stress characterization value as the actual stress value, and the temperature values ​​of the nodes are weighted and summed to obtain the overall temperature characterization value as the actual temperature value.

5. The method for full life-cycle management of gas turbine power plant equipment based on three-dimensional digital twins according to claim 1, characterized in that, include: The initial life data includes creep life data and fatigue life data; Based on the stress parameters, the temperature parameters, and the creep life data, calculate the creep damage amount for each of the operating time periods; The fatigue damage amount for each of the operating time periods is calculated based on the stress parameters, the temperature parameters, and the fatigue life data. The creep damage amount and the fatigue damage amount are added together to obtain the damage increment within the corresponding operating time period. The damage increments of each operating time period are then accumulated to obtain the cumulative damage amount.

6. The method for full life-cycle management of gas turbine power plant equipment based on three-dimensional digital twins according to claim 5, characterized in that, include: The actual operating state of the target device during each operating time period is divided into a stable operating phase and a variable operating condition phase. For each stable operation phase, the creep life value is retrieved based on the stress and temperature parameters of that phase, and the creep damage amount is calculated in combination with the actual operating time of that phase. For each of the variable working condition stages, the fatigue life value is obtained based on the change range of the stress parameters in that stage, and the fatigue damage is calculated in combination with the actual number of start-stop cycles in that stage.

7. The method for full life-cycle management of gas turbine power plant equipment based on three-dimensional digital twins according to claim 1, characterized in that, include: The actual deformation value of the key area is obtained by non-contact measurement as the actual deformation data. The actual deformation value is compared with the design allowable deformation value to determine the amount of deformation damage. When the deviation result exceeds the preset deviation threshold multiple times consecutively, the material parameters in the initial life data are adjusted so that the deviation between the cumulative damage amount and the deformation damage amount recalculated by substituting the adjusted material parameters is reduced, thereby obtaining the corrected life data.

8. The method for full life-cycle management of gas turbine power plant equipment based on three-dimensional digital twins according to claim 7, characterized in that, The step of obtaining the actual deformation value of the key area through non-contact measurement as the actual deformation data, and comparing the actual deformation value with the design allowable deformation value to determine the amount of deformation damage includes: The critical region is divided into multiple sub-regions, and the actual deformation value of each sub-region is obtained, and the deformation damage amount of each sub-region is determined. Calculate the regional deviation between the deformation damage amount and the cumulative damage amount in each sub-region in the corresponding sub-region; When the deviation result of any sub-region exceeds the preset deviation threshold multiple times consecutively, the material parameters corresponding to that sub-region are adjusted individually, and the adjusted material parameters of each sub-region are combined according to their spatial position to obtain a partitioned material parameter correction table, which is used as the corrected life data.

9. The method for full life-cycle management of gas turbine power plant equipment based on three-dimensional digital twins according to claim 1, characterized in that, include: The health index is determined based on the result of subtracting the cumulative damage amount from one; The health index is compared with multiple preset threshold ranges to determine the operating status level of the target device and the corresponding remaining life prediction range, which is taken as the health status. When the health index is lower than the preset maintenance trigger threshold, a maintenance suggestion including a suggested maintenance time window is obtained as an operation and maintenance strategy.

10. The method for full life-cycle management of gas turbine power plant equipment based on three-dimensional digital twins according to claim 9, characterized in that, When the health index falls below a preset maintenance trigger threshold, a maintenance recommendation including a suggested maintenance time window is obtained as the operation and maintenance strategy, which further includes: By combining the health index, the remaining life prediction range, and the current spare parts inventory information, a spare parts procurement recommendation is obtained, which includes the procurement quantity and procurement time window. The spare parts procurement recommendation determines the ordering time by comparing the remaining life prediction range with the spare parts procurement lead time, and calculates the procurement quantity based on the minimum safety stock and the current inventory quantity. Based on the operating status level, a corresponding standard maintenance work package is matched to obtain a maintenance task schedule that includes the maintenance work type, required human resources, and estimated downtime.

Images