Search

KR-102964276-B1 - DEVICE FOR LAMINATED COMPOSITE ULTRASONIC INTERLAYER SIGNALS CANCELLATION AND METHOD THEREOF

KR102964276B1KR 102964276 B1KR102964276 B1KR 102964276B1KR-102964276-B1

Abstract

The present invention relates to a blade diagnostic system and method capable of automatically diagnosing abnormalities and/or damage to a blade by detecting vibration of the blade. The blade diagnostic system comprises a plurality of sensors installed spaced apart from each other around the blade and capable of detecting the tip of the blade; a measuring unit that measures the arrival time at which the tip of each of the plurality of blades is detected by the plurality of sensors and measures the RPM (revolution per minute) of the rotor; a signal processing unit that processes the arrival time information measured by the sensors and removes a signal determined to be an unusual signal and/or noise; a vibration prediction unit that determines whether vibration is present and, if vibration is present, whether the vibration type is synchronous vibration or asynchronous vibration based on the arrival time information processed by the signal processing unit; a feature extraction unit that extracts a stack pattern and blade dynamic characteristics based on the presence of vibration and the vibration type determined by the vibration prediction unit; It includes a diagnostic unit that diagnoses abnormalities and/or damage to the blade using artificial intelligence that takes the stack pattern and blade dynamic characteristics as input.

Inventors

  • 김정찬
  • 주영호

Assignees

  • 두산에너빌리티 주식회사

Dates

Publication Date
20260513
Application Date
20230823

Claims (19)

  1. In a system for diagnosing a plurality of blades provided at equal intervals on a rotor rotating in a circumferential direction, A measuring unit comprising a plurality of sensors installed spaced apart from each other around the blade and capable of detecting the tip of the blade, measuring the arrival time at which the tip of each of the plurality of blades is detected by the plurality of sensors, and measuring the RPM (revolution per minute) of the rotor; A signal processing unit that processes arrival time information measured by the plurality of sensors above and removes signals determined to be unusual signals and/or noise; A vibration prediction unit that determines whether vibration exists and, if vibration exists, whether the vibration type is synchronous vibration or asynchronous vibration based on arrival time information processed by the signal processing unit above; A feature extraction unit that extracts a stack pattern and blade dynamic characteristics based on the presence or absence of vibration and the type of vibration determined by the vibration prediction unit above; and It includes a diagnostic unit that diagnoses abnormalities and/or damage to the blade using artificial intelligence that takes the stack pattern and blade dynamic characteristics as input, and The above feature extraction unit is, If it is determined that no vibration occurred or if it is determined that the vibration type is asynchronous vibration, the above stack pattern is extracted, and A blade diagnostic system that extracts the blade dynamic characteristics when the vibration type is determined to be synchronous vibration.
  2. In paragraph 1, A blade diagnostic system in which the plurality of sensors are installed at equal intervals along the circumference of the circle formed by the blades.
  3. In paragraph 1, The above vibration prediction unit is, In the absence of vibration, each of the plurality of blades obtains vibration information based on a reference time detected by each of the plurality of sensors and the arrival time, and Vibration information for each of the above plurality of blades is accumulated and summed over a certain period to generate a stack pattern, and A blade diagnostic system that determines the presence or absence of vibration based on the above stack pattern.
  4. In paragraph 3, The above vibration prediction unit is, A blade diagnostic system that determines that there is vibration if the magnitude of the accumulated vibration of at least one of the plurality of blades is greater than a preset first threshold value.
  5. In paragraph 3, The above vibration prediction unit is, Normalized vibration information is obtained by multiplying the value obtained by subtracting the reference time from the above arrival time by the RPM at the time the above arrival time is obtained, and A blade diagnostic system that extracts phase information from normalized vibration information obtained at the same RPM among the above normalized vibration information, and determines whether it is synchronous vibration or asynchronous vibration based on the extracted phase information.
  6. In paragraph 5, The above vibration prediction unit is, A blade diagnostic system that sets multiple phase intervals, determines the phase interval to which the normalized vibration information belongs among the multiple phase intervals, increases the frequency of the determined phase interval by 1, and determines whether the vibration is synchronous or asynchronous based on the frequency of the multiple phase intervals.
  7. In paragraph 6 The above vibration prediction unit is, A blade diagnostic system that determines synchronous vibration if the frequency of the plurality of phase intervals has a value similar to a normal distribution, having a large value in one specific phase interval and gradually decreasing as it progresses in both directions, or if the frequency of the plurality of phase intervals has a value similar to a normal distribution, having a large value in two phase intervals and gradually decreasing as it progresses in both directions.
  8. In paragraph 6, The above vibration prediction unit is, A blade diagnostic system that determines asynchronous vibration when the frequency of each of the above-mentioned plurality of phase intervals is within a certain range.
  9. delete
  10. In paragraph 1, The above diagnostic unit is, A blade diagnosis system comprising a first artificial intelligence that takes only the stack pattern as input and a second artificial intelligence that takes the blade dynamic characteristics as input, wherein the first artificial intelligence and the second artificial intelligence independently diagnose abnormalities and/or damage to the blade.
  11. A blade diagnosis method of a system for diagnosing a plurality of blades provided at equal intervals on a rotor rotating in a circumferential direction, An operation to measure the arrival time at which the tip of each of the plurality of blades is detected using a plurality of sensors installed spaced apart from each other around the blade; Operation of measuring the RPM (revolution per minute) of the above rotor; An operation to process arrival time information measured by the plurality of sensors above and remove signals determined to be unusual signals and/or noise; An operation to determine whether vibration is present and, if vibration occurs, whether the vibration type is synchronous or asynchronous vibration based on the above-mentioned processed arrival time information; An operation to extract a stack pattern and blade dynamic characteristics based on the determined vibration occurrence status and vibration type; and It includes an operation to diagnose abnormalities and/or damage to the blade using artificial intelligence that takes the stack pattern and blade dynamic characteristics as input, and The operation of extracting a stack pattern and blade dynamic characteristics based on the above-determined vibration occurrence status and vibration type is, An operation to extract the stack pattern when it is determined that no vibration occurred or when it is determined that the vibration type is asynchronous vibration; and A blade diagnosis method comprising the operation of extracting the blade dynamic characteristics when the vibration type is determined to be synchronous vibration.
  12. In Paragraph 11, The operation of determining whether vibration occurs and, if vibration occurs, whether the vibration type is synchronous or asynchronous based on the above-mentioned processed arrival time information is, An operation to obtain vibration information based on a reference time detected by each of the plurality of sensors and the arrival time when there is no vibration, for each of the plurality of blades; The operation of generating a stack pattern by accumulating and summing vibration information for each of the plurality of blades over a certain period; and A blade diagnosis method comprising an operation to determine the presence or absence of vibration based on the stack pattern above.
  13. In Paragraph 12, The operation of determining the presence or absence of vibration based on the above stack pattern is, A blade diagnosis method comprising determining that vibration exists if the magnitude of the accumulated sum of vibrations of at least one of the plurality of blades in the stack pattern is greater than a preset first threshold value.
  14. In Paragraph 12, The operation of determining whether vibration occurs and, if vibration occurs, whether the vibration type is synchronous or asynchronous based on the above-mentioned processed arrival time information is, An operation to obtain normalized vibration information by multiplying the value obtained by subtracting the reference time from the arrival time by the RPM at the time of acquiring the arrival time; A blade diagnosis method comprising the operation of extracting phase information from normalized vibration information obtained at the same RPM among the normalized vibration information, and determining whether the vibration is synchronous or asynchronous based on the extracted phase information.
  15. In Paragraph 14, The operation of extracting phase information from normalized vibration information obtained at the same RPM among the above normalized vibration information, and determining whether it is synchronous vibration or asynchronous vibration based on the extracted phase information, Operation of setting multiple phase intervals; An operation to determine the phase section to which the normalized vibration information belongs among the plurality of phase sections above; An operation to increase the frequency of the determined phase interval by 1; and A blade diagnosis method comprising an operation to determine whether the vibration is synchronous or asynchronous based on the frequency of each of the plurality of phase intervals.
  16. In paragraph 15 The operation of determining whether it is synchronous oscillation or asynchronous oscillation based on the frequency of each of the aforementioned plurality of phase intervals is, A blade diagnosis method comprising an operation of determining synchronous vibration if the frequency of the plurality of phase intervals has a value similar to a normal distribution that has a large value in one specific phase interval and gradually decreases as it progresses in both directions, or if the frequency of the plurality of phase intervals has a value that has a large value in two phase intervals and gradually decreases as it progresses in both directions.
  17. In paragraph 15, The operation of determining whether it is synchronous oscillation or asynchronous oscillation based on the frequency of each of the aforementioned plurality of phase intervals is, A blade diagnosis method further comprising an operation of determining asynchronous vibration when the frequency of each of the above plurality of phase intervals is within a certain range.
  18. delete
  19. In Paragraph 11, The operation of diagnosing abnormalities and/or damage to the blade using artificial intelligence that takes the above stack pattern and blade dynamic characteristics as input, A blade diagnosis method comprising a first artificial intelligence that takes only the stack pattern as input and a second artificial intelligence that takes the blade dynamic characteristics as input, and wherein the first artificial intelligence and the second artificial intelligence independently diagnose abnormalities and/or damage to the blade.

Description

Blade Diagnosis System and Method {DEVICE FOR LAMINATED COMPOSITE ULTRASONIC INTERLAYER SIGNALS CANCELLATION AND METHOD THEREOF} This specification relates to a blade diagnostic system and method capable of automatically diagnosing abnormalities and/or damage to a blade by detecting vibrations of the blade. Power generation equipment is a device that converts the energy of fluids such as water, gas, and steam into mechanical work; it can be described as a turbo-type device that typically has multiple blades embedded in the circumference of a rotating body and rotates it at high speed using impulse or reaction force by blowing steam or gas onto them. A gas turbine, which is a type of power generation equipment, includes a compressor, a combustor, a turbine, and a rotor. It operates on the principle of compressing air using a compressor, generating energy by burning fuel in the combustor with the compressed air, and using the generated energy to power the turbine. Here, the compressor compresses air by rotating a rotating body equipped with multiple blades on its circumference, and the turbine can also generate electricity by rotating the blades using energy, equipped with multiple blades on its circumference. Because blades rotate at high speeds under heavy forces, even the slightest factor can cause defects such as breakage or deformation. If defects occur in some of the multiple blades, the turbine's performance can be significantly degraded, and the imbalance of the rotor caused by the defective blades can lead to catastrophic failure of the entire system. Accordingly, it is crucial to rapidly and accurately detect the presence and location of abnormalities or damage to the blades; however, conventional visual detection methods using personnel or equipment make it difficult to identify damage while the equipment is in operation, and accurate inspection is only possible when the equipment has been shut down. Furthermore, in the case of turbines where a large number of blades are installed in multiple stages, it is extremely difficult to determine the presence and location of damage even when the operation is stopped, and verification may only be possible by disassembling the equipment. This poses a problem that significantly increases equipment maintenance costs. FIG. 1 is a block diagram of a blade diagnostic system according to one embodiment of the present invention. FIG. 2 is a diagram illustrating an example in which a measuring unit of a blade diagnostic system according to one embodiment of the present invention measures tip timing. Figure 3 is a diagram illustrating an example of a process for measuring the arrival time of each of a plurality of blades using a plurality of tip timing sensors. Figure 4 is a diagram illustrating an example of a time series pattern generated by the vibration prediction unit. Figure 5 is a diagram illustrating bias information derived from a time series pattern. Figures 6 and 7 illustrate an example of a stack pattern generated by a vibration prediction unit. Figure 8 is a diagram illustrating an example showing the frequency count obtained for each phase interval. FIG. 9 is a flowchart of a blade diagnosis method of a blade diagnosis system according to various embodiments of the present invention. Figure 10 is a diagram illustrating the flow of a blade diagnostic system predicting vibration. Specific structural or functional descriptions regarding embodiments according to the concept of the present invention disclosed herein are provided merely for the purpose of explaining embodiments according to the concept of the present invention, and embodiments according to the concept of the present invention may be implemented in various forms and are not limited to the embodiments described herein. Embodiments according to the concept of the present invention may be subject to various modifications and may take various forms; therefore, embodiments are illustrated in the drawings and described in detail in this specification. However, this is not intended to limit the embodiments according to the concept of the present invention to specific disclosed forms, and includes all modifications, equivalents, or substitutions that fall within the spirit and scope of the present invention. Terms such as "first" or "second" may be used to describe various components, but said components should not be limited by said terms. For the sole purpose of distinguishing one component from another, for example, without departing from the scope of rights according to the concept of the present invention, the first component may be named the second component, and similarly, the second component may be named the first component. When it is stated that one component is "connected" or "connected" to another component, it should be understood that while it may be directly connected or connected to that other component, there may also be other components in between. Conversely, when it is stated that