Digital twin monitoring method and system for turbine blade manufacturing
By dividing areas in the manufacturing of turbine blades, expanding coefficient at set temperature and real-time digital twin model monitoring, misjudgment problems caused by thermal expansion and contraction of metal materials are solved, and monitoring accuracy and accuracy are improved.
Patent Information
- Application Number
- CN202411062130.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-22
AI Technical Summary
In the prior art, due to the thermal expansion and contraction properties of metal materials during the manufacturing process of turbine blades, the size difference collected by the sensor is easily misjudged, which affects the monitoring accuracy.
By dividing the turbine blades into several areas, obtaining the manufacturing material samples of each area, setting the expansion coefficient at different temperatures, establishing a real-time digital twin model, correcting the initial digital twin model, building the final digital twin model, and monitoring the dimension data in real time. Combining the material temperature and historical data collected by the sensors ensures monitoring accuracy.
It effectively avoids the impact of thermal expansion and contraction on monitoring, improves monitoring accuracy, reduces misjudgment, and ensures the accuracy of the digital twin model and fits into actual scenarios.
Smart Images

Figure BDA0004978228800000031 
Figure BDA0004978228800000061 
Figure FDA0004978228790000021
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of digital twin monitoring, and in particular to a digital twin monitoring method and system for manufacturing steam turbine blades. Background Art
[0002] The manufacturing of steam turbine blades is usually a complex process involving high-precision processing and material engineering, including material selection, casting or forging, precision machining, heat treatment and quality inspection. Among them, quality inspection is the most stringent step at the end of steam turbine blade manufacturing, including size inspection, material composition analysis, non-destructive testing, etc.
[0003] Digital twin monitoring refers to the use of digital twin technology to monitor, simulate and predict the operating status and performance of physical systems or processes in real time. Digital twin refers to the simulation, monitoring and optimization of actual systems by digitizing the structure, behavior and performance of physical systems into virtual models and synchronizing and interacting with the actual systems in real time.
[0004] In the prior art, the quality inspection steps of turbine blade manufacturing often adopt digital twin monitoring methods. The digital twin model is updated through real-time sensor data to reflect the current status of the actual manufacturing process. By comparing the actual data with the predicted results of the digital twin model, abnormal situations in the manufacturing process can be detected in time.
[0005] In the prior art, a Chinese invention patent document with publication number CN116644559A and publication date August 25, 2023 is proposed. The technical solution disclosed in the patent document is as follows: a method for predicting the service life of a turbine blade during its service process based on a digital twin framework. By constructing relevant digital twin sub-models and integrating them into a complete digital twin framework model, the service process of the turbine blade is monitored, and internal damage is detected and estimated in real time, thereby realizing fault warning and remaining life prediction of the turbine blade during its service process.
[0006] During the actual use of the above technical solution, the following problems will arise: Since the manufacturing material of turbine blades is often metal material, metal material has the physical property of thermal expansion and contraction. This makes the length and width of the turbine blades collected by the sensor different in manufacturing environments with different temperatures. The length and width of the digital twin model are fixed when it is established, which makes it easy to misjudge when comparing actual data with the digital twin model. Summary of the invention
[0007] In order to solve the above technical problems, the present invention proposes a digital twin monitoring method and system for turbine blade manufacturing, which can effectively solve the problem of misjudgment that is prone to occur in the prior art and improve the monitoring accuracy.
[0008] The present invention is achieved by adopting the following technical solutions:
[0009] A digital twin monitoring method for manufacturing steam turbine blades, comprising the following steps:
[0010] Step S1. Divide the turbine blade into several regions and obtain the manufacturing materials in each region;
[0011] Step S2. Selecting a manufacturing material sample of unit size;
[0012] Step S3. Setting the initial temperature and setting several material temperatures; obtaining the expansion coefficient of the manufactured material sample according to the size of the manufactured material sample at different material temperatures;
[0013] Step S4. Obtaining data characteristics and material temperature of each region of the turbine blade;
[0014] Step S5. Establishing a real-time digital twin model of each region of the steam turbine blade according to the expansion coefficient and material temperature of the manufacturing material in each region of the steam turbine blade;
[0015] Step S6. The real-time digital twin models of each region of the steam turbine blade are used to form a final digital twin model;
[0016] Step S7. Monitor the real-time dimensional data of the turbine blades according to the final digital twin model.
[0017] The step S1 of dividing the steam turbine blade into a plurality of regions specifically refers to dividing the steam turbine blade into a plurality of regions according to the difference in manufacturing materials of various parts of the steam turbine blade and the difference in manufacturing processes of various parts.
[0018] Setting a number of material temperatures in step S2 specifically refers to: setting a temperature interval threshold, starting with the initial temperature, increasing upward and decreasing downward, recording every other temperature interval threshold as a material temperature, and obtaining a number of material temperatures; wherein the setting range of the temperature interval threshold is (0°C, 4°C).
[0019] The calculation method of the expansion coefficient Lec in step S3 is:
[0020] Lec=ΔL / (L×ΔT)
[0021] Where ΔL is the dimensional change of the manufactured material sample at different material temperatures compared to the initial size, L is the initial size, and ΔT is the temperature change of different material temperatures compared to the initial temperature.
[0022] The step S3 specifically comprises the following steps:
[0023] Step S 31. Obtain the dimensions of all manufactured material samples at the initial temperature and record them as initial dimensions;
[0024] Step S 32 . Obtain the changes in the dimensions of all manufactured material samples at different material temperatures compared to the initial dimensions: {ΔL1, ΔL2, ..., ΔL n},
[0025] Among them, ΔL n Indicates the change in the size of the nth manufactured material sample compared to the initial size, where n is the total number of manufactured material samples; ΔL n =L n -L,L n is the size of the nth manufactured material sample at the current material temperature, and L is the initial size;
[0026] Step S 33 .Get the size change ΔL and temperature change ΔT:
[0027]
[0028] ΔT=T0-T
[0029] Where i∈[1,n] and i is a positive integer; T is the initial temperature, and T0 is the current material temperature.
[0030] The step S5 specifically comprises the following steps:
[0031] Step S 51 . According to the material temperature and expansion coefficient at this time, calculate the size L of each area of the turbine blade at this time 实际 :
[0032] L 实际 =ΔL+L=Lec×L×(T0-T)+L
[0033] In the formula, ΔL is the dimensional change, L is the initial size, Lec is the expansion coefficient, T0 is the material temperature at this time, and T is the initial temperature;
[0034] Step S 52 .The initial digital twin model of each area of the turbine blade is modified, and the size of the initial digital twin model of each area of the turbine blade is adjusted to ΔL+L to obtain the real-time digital twin model of each area of the turbine blade.
[0035] The step S7 specifically includes: selecting a number of monitoring points at equal intervals in the turbine blade, obtaining the dimensions at the monitoring points, recording them as actual dimensions Ad, and obtaining the dimensions of the corresponding monitoring points on the digital twin model, recording them as reference dimensions Rd; setting an error threshold E, when |Rd-Ad|≤E, it is recorded that there is no abnormality in the dimensions at the monitoring points; when |Rd-Ad|>E, it is prompted that there is an abnormality in the monitoring points.
[0036] The step S4 of obtaining the material temperature of each region of the turbine blade specifically refers to:
[0037] Obtain historical manufacturing data, and establish a corresponding relationship between material temperature and ambient temperature based on the historical manufacturing data; collect material temperature and ambient temperature through sensors respectively; calculate the predicted material temperature based on the collected ambient temperature; determine whether the difference between the predicted material temperature and the material temperature collected by the sensor is within a preset threshold, and if so, the material temperature of each area of the turbine blade is the material temperature collected by the sensor.
[0038] A digital twin monitoring system for steam turbine blade manufacturing, comprising:
[0039] an expansion coefficient determination module for obtaining expansion coefficients of manufacturing material samples of various regions in a steam turbine blade;
[0040] Data acquisition module, used to obtain data characteristics and material temperature of each area of the turbine blade;
[0041] A digital twin modeling module is used to establish a real-time digital twin model of each area of the steam turbine blade according to the expansion coefficient and material temperature of the manufacturing material in each area of the steam turbine blade, and the real-time digital twin model of each area of the steam turbine blade constitutes the final digital twin model;
[0042] The real-time monitoring module is used to monitor the real-time dimensional data of the turbine blades according to the final digital twin model.
[0043] It also includes a blockchain module for storing historical manufacturing data and monitoring data of turbine blades.
[0044] Compared with the prior art, the beneficial effects of the present invention are as follows:
[0045] 1. In the present invention, the dimensional changes of the manufacturing materials in each area of the turbine blade at different material temperatures are determined according to the expansion coefficient, and then the real-time digital twin models of each area of the turbine blade are established, and finally the final digital twin model is combined to monitor the real-time dimensional data of the turbine blade. The monitoring method of the present invention avoids the influence of thermal expansion and contraction of the manufacturing materials on the size of the turbine blade by the existing digital twin model during the manufacturing of the turbine blade, which can improve the monitoring accuracy and reduce the situation of misjudgment.
[0046] 2. Since different manufacturing materials have different physical properties and different manufacturing processes result in different material temperatures of turbine blades during manufacturing, the present invention divides the turbine blades into several areas according to the different manufacturing materials and manufacturing processes of various parts of the turbine blades. This helps to accurately analyze the changes in the size of the turbine blades with temperature, making the final digital twin model more accurate and in line with the actual scenario.
[0047] 3. Since the manufacturing material of the turbine blade may be an alloy or other composite material, the expansion coefficient cannot be determined. The present invention obtains the dimensional change of the manufacturing material at different material temperatures by setting different material temperatures, and obtains the expansion coefficient of the manufacturing material through simulation experiments, and the obtained data is accurate.
[0048] 4. In the present invention, the initial digital twin model of each area is first constructed, and then the dimensional change of the manufacturing material at each material temperature in the turbine blade is determined according to the expansion coefficient, and the initial digital twin model is further corrected. The obtained digital twin model is accurate and the construction method is simple.
[0049] 5. When obtaining the material temperature of each area of the turbine blade, we not only rely on the correspondence between the material temperature and the ambient temperature in the historical manufacturing data, but also collect the material temperature through sensors. Through the mutual cooperation of the two, the final material temperature is more accurate, and the judgment of the dimensional changes of the manufacturing materials in each area of the turbine blade is more accurate.
[0050] 6. The mutual cooperation of various modules in this monitoring system can avoid the influence of thermal expansion and contraction of manufacturing materials on monitoring and improve the monitoring accuracy.
[0051] 7. This monitoring system also includes a blockchain module, which can store the historical manufacturing data and monitoring data of turbine blades and ensure the integrity and credibility of the data. DETAILED DESCRIPTION
[0052] Example 1
[0053] As a basic embodiment of the present invention, the present invention includes a digital twin monitoring method for steam turbine blade manufacturing, comprising the following steps:
[0054] Step S1. Divide the steam turbine blade into several regions and obtain the manufacturing material in each region.
[0055] Step S2: Select a manufacturing material sample of unit size.
[0056] Step S3. Setting an initial temperature and setting a number of material temperatures; obtaining the expansion coefficient of the manufactured material sample according to the size of the manufactured material sample at different material temperatures.
[0057] Step S4: Obtain data characteristics and material temperature of each region of the turbine blade.
[0058] Step S5. A real-time digital twin model of each region of the steam turbine blade is established based on the expansion coefficient and material temperature of the manufacturing material in each region of the steam turbine blade.
[0059] Step S6. The final digital twin model is constructed by the real-time digital twin models of each area of the turbine blade.
[0060] Step S7. Monitor the real-time dimensional data of the turbine blades according to the final digital twin model.
[0061] Example 2
[0062] As a preferred embodiment of the present invention, the present invention includes a digital twin monitoring method for steam turbine blade manufacturing, comprising the following steps:
[0063] Step S1. Divide the steam turbine blade into several regions and obtain the manufacturing materials in each region. More specifically, the steam turbine blade can be divided into several regions according to the different manufacturing materials and manufacturing processes of various parts of the steam turbine blade.
[0064] Step S2: Select a manufacturing material sample of unit size.
[0065] Step S3. Set the initial temperature and set several material temperatures. According to the size of the material sample manufactured at different material temperatures, the expansion coefficient Lec of the manufactured material sample is obtained. Among them, setting several material temperatures specifically refers to: setting the temperature interval threshold, starting with the initial temperature as the starting value, starting to increase upward and decrease downward, and recording every other temperature interval threshold as a material temperature to obtain several material temperatures. Among them, the setting range of the temperature interval threshold is (0°C, 4°C).
[0066] The expansion coefficient Lec is calculated as:
[0067] Lec=ΔL / (L×ΔT)
[0068] Where ΔL is the dimensional change of the manufactured material sample at different material temperatures compared to the initial size, L is the initial size, and ΔT is the temperature change of different material temperatures compared to the initial temperature.
[0069] Step S4. Obtain data features and material temperature of each region of the steam turbine blade. Specifically, the data features of each region of the steam turbine blade can be obtained using a 3D scanning module. The data features include size and shape. The material temperature of each region of the steam turbine blade can be obtained using a sensor module.
[0070] Step S5. A real-time digital twin model of each region of the steam turbine blade is established based on the expansion coefficient and material temperature of the manufacturing material in each region of the steam turbine blade.
[0071] Step S6. The final digital twin model is constructed by the real-time digital twin models of each area of the turbine blade.
[0072] Step S7. Monitor the real-time dimensional data of the turbine blades according to the final digital twin model.
[0073] Example 3
[0074] As another preferred embodiment of the present invention, the present invention includes a digital twin monitoring method for steam turbine blade manufacturing, comprising the following steps:
[0075] Step S1. Divide the steam turbine blade into several regions and obtain the manufacturing material in each region.
[0076] Step S2: Select a manufacturing material sample of unit size.
[0077] Step S3. Set the initial temperature and several material temperatures; obtain the expansion coefficient of the manufactured material sample according to the size of the manufactured material sample at different material temperatures. Specifically, the following steps are included:
[0078] Step S 31 . Obtain the dimensions of all manufactured material samples at the initial temperature and record them as initial dimensions;
[0079] Step S 32 . Obtain the changes in the dimensions of all manufactured material samples at different material temperatures compared to the initial dimensions as {ΔL1, ΔL2, ..., ΔL n},
[0080] Where, ΔL n Indicates the change in the size of the nth manufactured material sample compared to the initial size, where n is the total number of manufactured material samples; ΔL n =L n -L,L nis the size of the nth manufactured material sample at the current material temperature, and L is the initial size;
[0081] Step S 33 .Get the size change ΔL and temperature change ΔT:
[0082]
[0083] ΔT=T0-T
[0084] Where i∈[1,n] and i is a positive integer; T is the initial temperature, and T0 is the current material temperature.
[0085] Step S4: Obtain data characteristics and material temperature of each region of the turbine blade.
[0086] Step S5. According to the expansion coefficient and material temperature of the manufacturing material in each area of the steam turbine blade, a real-time digital twin model of each area of the steam turbine blade is established. Specifically, the following steps are included:
[0087] Step S 51 . According to the material temperature and expansion coefficient at this time, calculate the size L of each area of the turbine blade at this time 实际 :
[0088] L 实际 =ΔL+L=Lec×L×(T0-T)+L
[0089] In the formula, ΔL is the dimensional change, L is the initial size, Lec is the expansion coefficient, T0 is the material temperature at this time, and T is the initial temperature;
[0090] Step S 52 .The initial digital twin model of each area of the turbine blade is modified, and the size of the initial digital twin model of each area of the turbine blade is adjusted to ΔL+L to obtain the real-time digital twin model of each area of the turbine blade.
[0091] Step S6. The final digital twin model is constructed by the real-time digital twin models of each area of the turbine blade.
[0092] Step S7. Monitor the real-time dimensional data of the turbine blades according to the final digital twin model.
[0093] Example 4
[0094] As another preferred embodiment of the present invention, the present invention includes a digital twin monitoring system for manufacturing steam turbine blades, comprising:
[0095] The expansion coefficient determination module is used to obtain the expansion coefficient of the manufacturing material samples of each area in the turbine blade.
[0096] The data acquisition module is used to obtain the data characteristics and material temperature of each area of the turbine blade.
[0097] The digital twin modeling module is used to establish a real-time digital twin model of each area of the steam turbine blade according to the expansion coefficient and material temperature of the manufacturing material in each area of the steam turbine blade, and the real-time digital twin model of each area of the steam turbine blade constitutes the final digital twin model.
[0098] The real-time monitoring module is used to monitor the real-time dimensional data of the turbine blades according to the final digital twin model.
[0099] Example 5
[0100] In the prior art, the quality inspection steps of steam turbine blade manufacturing often adopt a digital twin monitoring method. The digital twin model is updated through real-time sensor data to reflect the current status of the actual manufacturing process. By comparing the actual data with the predicted results of the digital twin model, abnormal conditions in the manufacturing process can be detected in time. However, steam turbine blades are often made of metal materials. Metal materials have the physical property of thermal expansion and contraction. This makes the length and width of the steam turbine blades collected by the sensor different in manufacturing environments with different temperatures. The length and width of the digital twin model are fixed when it is established, which makes it easy to misjudge when comparing the actual data with the digital twin model.
[0101] Based on this, the present invention includes a digital twin monitoring system for turbine blade manufacturing, including: an expansion coefficient determination module, a data acquisition module, a digital twin modeling module, a real-time monitoring module, a user interface module, a data management module, a security and compliance module, and a maintenance and support module.
[0102] Among them, the expansion coefficient determination module is used to obtain the expansion coefficient of the manufacturing material sample in each area of the turbine blade. More specifically, the turbine blade can be divided into several areas, and the manufacturing material in each area can be obtained. Select a manufacturing material sample of unit size. Conduct a simulation experiment, set the initial temperature, and set several material temperatures. Adjust the temperature of the manufacturing material sample to the initial temperature and the corresponding different material temperatures, and obtain the size of the manufacturing material sample at the initial temperature, which is recorded as the initial size. Obtain the dimensional change of the manufacturing material sample at different material temperatures compared to the initial size, and obtain the temperature change of the material temperature compared to the initial temperature. According to the size of the manufacturing material sample at different material temperatures, obtain the expansion coefficient Lec of the manufacturing material sample:
[0103] Lec=ΔL / (L×ΔT),
[0104] Where ΔL is the dimensional change of the manufactured material sample at different material temperatures compared to the initial size, L is the initial size, and ΔT is the temperature change of different material temperatures compared to the initial temperature.
[0105] Among them, different materials are used in different parts of the turbine blades during manufacturing; the differentiated use of such materials is to ensure that each part can achieve the best performance and longest life under the high temperature and high pressure working environment of the turbine. Specifically for turbine blades, they can be mainly divided into three parts: blade shape, blade root and blade tip. Each part uses materials of different properties and compositions due to its different functions and stress conditions, and different manufacturing materials have different physical properties. In addition, different manufacturing processes have different effects on manufacturing materials. For example, for turbine blades that need to be polished, the temperature of the manufacturing material inside the turbine blades will increase when the turbine blades are polished. Therefore, according to the different manufacturing materials of various parts of the turbine blades and the different manufacturing processes of various parts, the turbine blades are divided into several areas.
[0106] More specifically, the initial temperature may be 25°C. The method for setting several material temperatures may be: setting a temperature interval threshold, wherein the setting range of the temperature interval threshold is (0°C, 4°C). Taking the initial temperature as the starting value, increasing upward and decreasing downward from the starting value, and recording every other temperature interval threshold as a material temperature, several material temperatures are obtained. Among them, when adjusting the temperature of the manufacturing material sample itself to the corresponding material temperature, several detection points may be selected in the manufacturing material sample to obtain the temperature of each detection point. When the average value of the temperature of each detection point is the corresponding material temperature, the manufacturing material sample is recorded as having been adjusted to the corresponding material temperature.
[0107] More specifically, the process of obtaining the expansion coefficient includes:
[0108] The changes in the dimensions of all the manufactured material samples obtained at different material temperatures compared to the initial dimension L are {ΔL1, ΔL2, ..., ΔL n}. Among them, ΔL1 represents the change in the size of the first manufactured material sample compared to the initial size, ΔL n Indicates the change in the size of the nth manufactured material sample compared to the initial size, where n is the total number of manufactured material samples. ΔL n =L n -L,L n is the size of the nth manufactured material sample at the current material temperature.
[0109] The size change Where i∈[1,n] and i is a positive integer.
[0110] The temperature change ΔT=T0-T, wherein T is the initial temperature and T0 is the current material temperature.
[0111] It is understandable that when the simulation experiment is actually carried out, although the materials used to manufacture the material samples are the same, there are still errors. At the same material temperature, the dimensional changes collected from different manufacturing material samples are different. Therefore, the change in the size of all manufacturing material samples compared to the initial size at different material temperatures is taken as the dimensional change. The expansion coefficient is always greater than 0. When ΔL<0, ΔT<0 at the same time; that is, ΔL and ΔT have the same sign.
[0112] The data acquisition module is used to obtain data features and material temperature of each area of the turbine blade. More specifically, the data acquisition module includes a 3D scanning module and a sensor module. The 3D scanning module is used to obtain data features of the turbine blade, and the data features include size and shape. The 3D scanning module is any one of a laser three-dimensional scanner, a structured light scanner, a photogrammeter, an ultrasonic scanner, and a mobile scanner. The sensor module may include an infrared temperature sensor for obtaining the material temperature of the turbine blade, and the material temperature is the temperature of the manufacturing material of the turbine blade.
[0113] Furthermore, in order to improve the accuracy of the final digital twin model, the data acquisition module also includes a blockchain module, which is used to ensure the integrity and credibility of the data and store the historical manufacturing data and monitoring data of the turbine blades. The historical manufacturing data includes the ambient temperature and material temperature of the turbine blades when the turbine blades are manufactured. When the structure of the turbine blades is processed, the manufacturing material of the turbine blades will change with the ambient temperature. According to the historical manufacturing data, a curve of the relationship between the material temperature and the ambient temperature is obtained. Specifically, a rectangular coordinate system can be established with the ambient temperature as the horizontal coordinate and the material temperature as the vertical coordinate; the material temperature of the turbine blades at different ambient temperatures is converted into the coordinate points of the corresponding positions in the rectangular coordinate system, and each coordinate point is connected with a smooth curve, and the curve is recorded as the curve of the relationship between the material temperature and the ambient temperature. Therefore, the material temperature of the turbine blades at different ambient temperatures can be obtained according to the historical manufacturing data.
[0114] Based on this, the sensor module may also include a digital temperature sensor for obtaining the air temperature at preset distances at several different directions of the turbine blades, and recording the average value of each air temperature as the ambient temperature of the turbine blades. The predicted material temperature is calculated based on the collected ambient temperature and the correspondence between the material temperature and the ambient temperature in the historical manufacturing data. Determine whether the difference between the predicted material temperature and the material temperature collected by the infrared temperature sensor is within a preset threshold. If so, the material temperature of each area of the turbine blade is the material temperature collected by the sensor. If not, the infrared temperature sensor and the digital temperature sensor can be used to re-collect data and repeat the above judgment steps; alternatively, the infrared temperature sensor and the digital temperature sensor can be replaced and re-tested.
[0115] The digital twin modeling module may include an AR module, and the AR module is used to establish and combine superimposed digital twin models. An initial digital twin model of the turbine blade at the initial temperature is established; according to the expansion coefficient and material temperature of the manufacturing material in each area of the turbine blade, the initial digital twin model is corrected to establish a real-time digital twin model of each area of the turbine blade, and the real-time digital twin models of each area of the turbine blade constitute the final digital twin model.
[0116] Among them, correcting the initial digital twin model specifically includes: recording the material temperature at this time as T0, and obtaining ΔL=Lec×L×(T0-T) according to the expansion coefficient. Then the size of the manufacturing material in the turbine blade at this time is ΔL+L, and adjusting the size of the initial digital twin model of the turbine blade to ΔL+L.
[0117] It can be understood that when ΔL<0, the size is reduced, and when ΔL>0, the size is expanded. The definition of the size is determined according to the shape of the manufacturing material, which is the two-dimensional linear size of a certain surface of the manufacturing material. For example, for a rectangular manufacturing material, when it is necessary to reduce its size, the reduction amount of the length, width and height is obtained respectively, and the reduction is performed simultaneously; when the manufacturing material is spherical, the size of its radius is reduced.
[0118] Among them, the method for obtaining the final digital twin model can be: obtaining several complete turbine blades as samples, and obtaining the three-dimensional model of the samples; using the skeleton shape feature extraction method to obtain the structural characteristics of the three-dimensional model of the samples; the skeleton shape feature extraction method is to describe the structural characteristics of the three-dimensional model by extracting the connectivity relationship between different components; the structural characteristics include the spatial topological relationship of the three-dimensional model, which can not only identify models with different topologies, but also three-dimensional models with similar topologies but different geometric structures, so it has good stability; according to the structural characteristics, the real-time digital twin models are combined and superimposed to obtain the final digital twin model of the turbine blade.
[0119] The real-time monitoring module is used to monitor the real-time dimensional data of the turbine blade according to the final digital twin model, including: selecting a number of monitoring points at equal intervals in the turbine blade, obtaining the dimensions at the monitoring points, recorded as the actual dimensions Ad, and obtaining the dimensions of the corresponding monitoring points on the digital twin model, recorded as the reference dimensions Rd; setting an error threshold E, when |Rd-Ad|≤E, it is recorded that there is no abnormality in the dimensions at the monitoring points; when |Rd-Ad|>E, it is prompted that there is an abnormality in the monitoring point.
[0120] The process of selecting the monitoring points includes obtaining the size Tsa of the turbine blade, setting the selection interval threshold St, and setting the standard number N of monitoring points, where N>10, and the selection interval threshold St. Wherein α is a preset coefficient and α>1.
[0121] Furthermore, the real-time monitoring module also includes an alarm module and a data analysis module. The alarm module is used to prompt that the monitoring point is abnormal, and is also used to automatically trigger an alarm when the real-time monitoring module detects that there is a difference between the turbine blade in the manufacturing process and the digital twin model. The alarm of the alarm module is any one of an audible and visual alarm, a text message alarm, and a telephone alarm. The data analysis module is used to predict the performance and life of the turbine blade.
[0122] The user interface module includes an operator interface and an engineer interface, which are used for monitoring, data analysis and decision support. The operator interface and the engineer interface both include a login module, which can be logged in through any one of face recognition login and account password login. The data management module is used to store, transmit and process data. The security and compliance module includes security measures and compliance monitoring to ensure the security and compliance of the system. The maintenance and support module is used for system maintenance and upgrades.
[0123] Based on the above monitoring system, the present invention also proposes a digital twin monitoring method for steam turbine blade manufacturing, comprising the following steps:
[0124] Step S1. Divide the steam turbine blade into several regions and obtain the manufacturing material in each region.
[0125] Step S2: Select a manufacturing material sample of unit size.
[0126] Step S3. Setting an initial temperature and setting a number of material temperatures; obtaining the expansion coefficient of the manufactured material sample according to the size of the manufactured material sample at different material temperatures.
[0127] Step S4: Obtain data characteristics and material temperature of each region of the turbine blade.
[0128] Step S5. A real-time digital twin model of each region of the steam turbine blade is established based on the expansion coefficient and material temperature of the manufacturing material in each region of the steam turbine blade.
[0129] Step S6. The final digital twin model is constructed by the real-time digital twin models of each area of the turbine blade.
[0130] Step S7. Monitor the real-time dimensional data of the turbine blades according to the final digital twin model.
[0131] In summary, after reading the present invention document, ordinary technicians in this field can make various other corresponding transformation schemes based on the technical scheme and technical concept of the present invention without creative mental labor, which all fall within the scope of protection of the present invention.
Claims
1. A digital twin monitoring method for steam turbine blade manufacturing, characterized in that: The following steps are involved: Step S1. Divide the turbine blade into several regions and obtain the manufacturing materials in each region; Step S2. Selecting a manufacturing material sample of unit size; Step S3. Setting the initial temperature and setting several material temperatures; obtaining the expansion coefficient of the manufactured material sample according to the size of the manufactured material sample at different material temperatures; Step S4. Obtaining data characteristics and material temperature of each region of the turbine blade; Step S5. Establishing a real-time digital twin model of each region of the steam turbine blade according to the expansion coefficient and material temperature of the manufacturing material in each region of the steam turbine blade; Step S6. The real-time digital twin models of each region of the steam turbine blade are used to form a final digital twin model; Step S7. Monitor the real-time dimensional data of the turbine blades according to the final digital twin model.
2. A digital twin monitoring method for steam turbine blade manufacturing according to claim 1, characterized in that: The step S1 of dividing the steam turbine blade into a plurality of regions specifically refers to dividing the steam turbine blade into a plurality of regions according to the difference in manufacturing materials of various parts of the steam turbine blade and the difference in manufacturing processes of various parts.
3. A digital twin monitoring method for steam turbine blade manufacturing according to claim 2, characterized in that: Setting a number of material temperatures in step S2 specifically refers to: setting a temperature interval threshold, starting with the initial temperature, increasing upward and decreasing downward, recording every other temperature interval threshold as a material temperature, and obtaining a number of material temperatures; wherein the setting range of the temperature interval threshold is (0°C, 4°C).
4. A digital twin monitoring method for steam turbine blade manufacturing according to claim 2, characterized in that: The calculation method of the expansion coefficient Lec in step S3 is: Lec=ΔL / (L×ΔT) Where ΔL is the dimensional change of the manufactured material sample at different material temperatures compared to the initial size, L is the initial size, and ΔT is the temperature change of different material temperatures compared to the initial temperature.
5. A digital twin monitoring method for steam turbine blade manufacturing according to claim 4, characterized in that: The step S3 specifically comprises the following steps: Step S 31 . Obtain the dimensions of all manufactured material samples at the initial temperature and record them as initial dimensions; Step S 32 . Obtain the changes in the dimensions of all manufactured material samples at different material temperatures compared to the initial dimensions: {ΔL1, ΔL2, ..., ΔL n }, Where, ΔL n Indicates the change in the size of the nth manufactured material sample compared to the initial size, where n is the total number of manufactured material samples; ΔL n =L n -L,L n is the size of the nth manufactured material sample at the current material temperature, and L is the initial size; Step S 33 .Get the size change ΔL and temperature change ΔT: ΔT=T0-T Where i∈[1,n] and i is a positive integer; T is the initial temperature, and T0 is the current material temperature.
6. A digital twin monitoring method for steam turbine blade manufacturing according to claim 1, characterized in that: The step S5 specifically comprises the following steps: Step S 51 . According to the material temperature and expansion coefficient at this time, calculate the size L of each area of the turbine blade at this time 实际 : L 实际 =ΔL+L=Lec×L×(T0-T)+L In the formula, ΔL is the dimensional change, L is the initial size, Lec is the expansion coefficient, T0 is the material temperature at this time, and T is the initial temperature; Step S 52 .The initial digital twin model of each area of the turbine blade is modified, and the size of the initial digital twin model of each area of the turbine blade is adjusted to ΔL+L to obtain the real-time digital twin model of each area of the turbine blade.
7. A digital twin monitoring method for steam turbine blade manufacturing according to claim 2, characterized in that: The step S7 specifically includes: selecting a number of monitoring points at equal intervals in the turbine blade, obtaining the dimensions at the monitoring points, recording them as actual dimensions Ad, and obtaining the dimensions of the corresponding monitoring points on the digital twin model, recording them as reference dimensions Rd; setting an error threshold E, when |Rd-Ad|≤E, it is recorded that there is no abnormality in the dimensions at the monitoring points; when |Rd-Ad|>E, it is prompted that there is an abnormality in the monitoring points.
8. A digital twin monitoring method for steam turbine blade manufacturing according to claim 2, characterized in that: The step S4 of obtaining the material temperature of each region of the turbine blade specifically includes: obtaining historical manufacturing data, and establishing a corresponding relationship between the material temperature and the ambient temperature according to the historical manufacturing data; The material temperature and the ambient temperature are collected by sensors respectively; the predicted material temperature is calculated based on the collected ambient temperature; it is determined whether the difference between the predicted material temperature and the material temperature collected by the sensor is within a preset threshold, and if so, the material temperature of each area of the turbine blade is the material temperature collected by the sensor.
9. A digital twin monitoring system for steam turbine blade manufacturing, characterized in that: include: an expansion coefficient determination module for obtaining expansion coefficients of manufacturing material samples of various regions in a steam turbine blade; Data acquisition module, used to obtain data characteristics and material temperature of each area of the turbine blade; A digital twin modeling module is used to establish a real-time digital twin model of each area of the steam turbine blade according to the expansion coefficient and material temperature of the manufacturing material in each area of the steam turbine blade, and the real-time digital twin model of each area of the steam turbine blade constitutes the final digital twin model; The real-time monitoring module is used to monitor the real-time dimensional data of the turbine blades according to the final digital twin model.
10. A digital twin monitoring system for steam turbine blade manufacturing according to claim 9, characterized in that: It also includes a blockchain module for storing historical manufacturing data and monitoring data of turbine blades.
