Aero-engine tenon-connected blade disc tenon bottom crack diagnosis method based on blade tip timing signal
The blade tip timing signal technology is used to obtain the amplitude and blade spacing variation of the blade tip of the leaf disc, and the identification parameters are constructed and k-means clustering is used to solve the problem of difficult identification of the bottom cracks of the tenon and bottom, and realize the tenon and connecting the aero engine blade disc Accurate identification and distinction of mid-cracks improves the safety and reliability of the engine.
Patent Information
- Application Number
- CN202410949539.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-16
- Publication Date
- 2024-11-08
AI Technical Summary
The prior art is difficult to effectively identify and distinguish the tenon bottom cracks in the tenon and joint blades of aero engines, especially when the contact characteristics of the tenon and the tenon and grooves of the leaf root and the roulette wheel groove are similar to the contact characteristics of the crack surface, resulting in the difficult identification of the tenon bottom cracks. Impacts the normal operation and flight safety of the engine.
The blade tip timing signal technology is used to obtain the measured amplitude and blade spacing variation of the blade tip of the leaf disc. By constructing crack type identification parameters and using k-means clustering, the identification and distinction of tenon-bottom cracks are achieved.
Effectively identify whether the tenon-and-one blade discs of the aircraft engine contain cracks, and distinguish whether the cracks contained are blade cracks or tenon-bottom cracks, which improves the diagnostic accuracy of tenon-bottom cracks and enhances the safety and reliability of the engine.
Smart Images

Figure CN118916726A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the technical field of aircraft engine diagnosis, and in particular relates to a method for diagnosing cracks at the bottom of a tenon-jointed blade disk of an aircraft engine based on a blade tip timing signal. Background Art
[0002] As the core equipment of modern aviation industry, the performance of aircraft engines is directly related to the safety, reliability and economy of aircraft. In complex operating environment, the blade disk system of aircraft engines, especially the tenon-jointed blade disk, is very susceptible to various stresses, resulting in cracks and other damages. If these cracks are not discovered and handled in time, they will seriously threaten the normal operation of the engine and flight safety.
[0003] The tenon-jointed blade disk of an aircraft engine is composed of blades and disks, and is subjected to complex mechanical and thermal stresses. During long-term operation, due to factors such as material fatigue and corrosion, cracks are prone to appear in the tenon-jointed blade disk. These cracks are small and difficult to detect at the beginning, but they will gradually expand over time, eventually leading to blade failure or falling off, and may even cause the disk to break, causing serious flight accidents. Therefore, compared with blade cracks, tenon-jointed blade disk cracks are more dangerous. Compared with the integral blade disk, the contact characteristics between the blade root tenon and the disk tenon-jointed blade disk are similar to the contact characteristics between the crack surfaces, which can easily cover up the response characteristics of the newly added tenon-jointed blade disk cracks and increase the difficulty of identifying the tenon-jointed blade disk cracks. It is necessary to use a multi-parameter collaborative diagnosis method to more effectively identify whether there are cracks and whether the cracks are located in the blade or the tenon-jointed blade disk. With the continuous advancement of sensor technology, signal processing technology, and data analysis technology, the accuracy and reliability of blade tip timing technology have been significantly improved. Nowadays, blade tip timing technology has been widely used in real-time monitoring and fault diagnosis of aircraft engines. In the relevant research on blade crack diagnosis, there are signal characteristics in the blade tip timing signal that can reflect the health status of the blade, but the existing research has not proposed an effective identification method for the health status of the tenon bottom in the blade disk. In order to solve the problem that tenon bottom cracks are difficult to diagnose, the present invention summarizes the blade tip response characteristics of blade disks with tenon bottom cracks and forms a tenon bottom crack identification method based on blade tip timing technology. Summary of the invention
[0004] In order to solve the above technical problems, the present invention proposes a method for diagnosing cracks at the bottom of a tenon-jointed blade disc of an aircraft engine based on a blade tip timing signal, which can effectively identify whether the tenon-jointed blade disc contains cracks and distinguish whether the cracks are blade cracks or tenon bottom cracks.
[0005] The present invention solves the above problems through the following technical solutions:
[0006] The present invention provides a method for diagnosing cracks at the bottom of a tenon-jointed blade disk of an aircraft engine based on a blade tip timing signal, comprising the following steps:
[0007] Step S1, using blade tip timing technology to obtain the measurable amplitude of the blade tip of the blade disk to be diagnosed at a constant speed and calculate the kurtosis of the measurable amplitude of the blade tip;
[0008] Step S2, using blade tip timing technology to obtain the change in the distance between each blade of the blade disk to be diagnosed and the healthy blade disk at the same speed, and constructing crack type identification parameters according to the change in the blade distance;
[0009] Step S3, taking the crack type identification parameter and the kurtosis of the blade tip amplitude as input, and using k-means to perform clustering to achieve crack type differentiation;
[0010] In the above-mentioned method for diagnosing cracks at the bottom of the tenon-jointed blade disk of an aircraft engine based on the blade tip timing signal, the specific steps of step S1 are as follows:
[0011] S11: Using non-contact tip timing measurement technology, the blade spacing of the blade disk is monitored online throughout the entire cycle. In one rotation cycle, the blade with a smaller number passes the sensor first by default. The rotation cycle of the blade disk can be calculated based on the time interval between two consecutive arrivals of the same blade at the same sensor during the rotation process. The formula is as follows:
[0012]
[0013] Among them, T n is the rotation period of the blade disk at the nth circle, and is the time when the i-th blade passes the j-th sensor at the n+1th and nth turns.
[0014] S12: The maximum displacement and minimum displacement of the blade tip monitored by a sensor are obtained based on the difference between the actual arrival time and the theoretical arrival time of the same blade passing through the same sensor. The formula is as follows:
[0015]
[0016] in, and is the maximum and minimum displacement of blade No. b when rotating N circles under the monitoring of sensor No. s. r is the length from the tip of the blade to the center of the blade disk, t nbs and t nbs0 are the actual arrival time and theoretical arrival time of blade b in the nth circle to sensor s, respectively, T n is the blade rotation period, n is the current number of revolutions, N is the total number of revolutions, b is the blade number, and s is the blade tip timing sensor number.
[0017] Theoretical arrival time of blade t nbs0It can be calculated through the relative positions of the rotation speed sensor and the optical fiber sensor and the measured rotation speed.
[0018]
[0019] Among them, t n0 is the arrival time of the fixed mark point on the shaft recorded by the speed sensor at the nth lap, n is the current lap number, θ s and θ i is the angle between the sth sensor and the i-th blade relative to the speed sensor, f r is the blade rotation frequency.
[0020] S13: If S optical fiber sensors are equipped, the maximum and minimum values of the measurable displacement of the blade can be obtained by taking the maximum value from the maximum values obtained by the S sensors. The measurable amplitude of the blade tip can be calculated based on the measurable maximum displacement and minimum displacement. The formula is as follows:
[0021]
[0022] in, and is the maximum and minimum measurable displacement of blade b, A b is the measurable amplitude of blade b.
[0023] S14: Calculate the kurtosis of the blade tip amplitude of the entire blade disk to be diagnosed, the formula is as follows:
[0024]
[0025] Among them, k is the kurtosis, q is the number of leaves, A i is the measurable amplitude of the ith blade, is the mean of the measurable amplitudes of all leaves. If the measurable amplitudes of all leaves are equal, let k be 0.
[0026] In the above-mentioned method for diagnosing cracks at the bottom of the tenon-jointed blade disk of an aircraft engine based on the blade tip timing signal, the specific steps of step S2 are as follows:
[0027] S21: Use non-contact tip timing measurement technology to obtain the moment when the blade tip of the blade disk reaches the optical fiber sensor, calculate the time interval between two adjacent blades passing the same sensor, and calculate the spacing between adjacent blades of the blade disk. The formula is as follows:
[0028]
[0029] Among them, d i,i+1 is the distance between blades i and i+1, i and i+1 are blade numbers, r is the distance from the blade tip to the center of the blade disk, T n is the blade rotation period, Δt i,i+1is the time difference between blade i and blade i+1 arriving at the same sensor.
[0030] S22: Calculate the blade spacing variation between the blade disk to be diagnosed and the healthy blade disk at the same speed. The formula is as follows:
[0031]
[0032] Where, Δd i,i+1 is the change in the distance between the blade i and i+1 of the blade disk to be diagnosed and the healthy blade disk, and are the distances between the blades i and i+1 of the blade disk to be diagnosed and the healthy blade disk respectively. The maximum value of the change in the distance between all blades in the same period is recorded as Δd max , the minimum value is recorded as Δd min , Δd max The corresponding leaf numbers on both sides are j max and j max+1 , Δd min The corresponding leaves on both sides are numbered j min , j min+1 , and j max and j min The two must be adjacent blade numbers, Δd min It must be a negative value, otherwise the data is invalid and needs to be collected again.
[0033] S23: It is difficult to distinguish whether the cracked mortise-jointed blade disc is a mortise bottom crack or a blade crack. The identification parameters for distinguishing mortise bottom cracks from blade cracks are constructed:
[0034] δ=Δd max -|Δd min |
[0035] When the tenon-jointed leaf disk contains a blade crack, δ approaches 0, while when there is a tenon bottom crack, δ will be significantly greater than 0.
[0036] In the above-mentioned method for diagnosing cracks at the bottom of the tenon-jointed blade disk of an aircraft engine based on the blade tip timing signal, the specific steps of step S3 are as follows:
[0037] S31: Set the number of k-means clusters to 3 and stop the iteration when the centroid of the cluster does not change.
[0038] S32: Taking the δ calculated by S23 and the k calculated by S14 as input, the data are clustered using k-means to distinguish the crack types.
[0039] The present invention provides a method for diagnosing cracks at the bottom of a tenon-jointed blade disc of an aeroengine based on a blade tip timing signal. The method comprises the following steps: step S1, using blade tip timing technology to obtain the measurable amplitude of the blade tip of the blade disc to be diagnosed at a constant speed and calculating the kurtosis of the measurable amplitude of the blade tip; step S2, using blade tip timing technology to obtain the variation of the spacing between each blade of the blade disc to be diagnosed and the healthy blade disc at the same speed, and constructing crack type identification parameters according to the variation of the spacing between the blades; step S3, using the crack type identification parameters and the kurtosis of the blade tip amplitude as input, and using k-means for clustering to achieve the distinction of crack types; in view of the problem that cracks at the bottom of a tenon-jointed blade disc of an aeroengine are difficult to diagnose, the present invention summarizes the response characteristics of the blade tip of a blade disc containing a tenon bottom crack, and forms a tenon bottom crack identification method based on blade tip timing technology, which can effectively identify whether the tenon-jointed blade disc contains cracks, and distinguish whether the cracks contained are blade cracks or tenon bottom cracks. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] The present invention is further described with the aid of the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the present invention. A person skilled in the art can obtain other accompanying drawings based on the following accompanying drawings without creative work.
[0041] Figure 1 It is a schematic diagram of the process of the present invention.
[0042] Figure 2 It is a schematic diagram of the blade tip timing principle of the present invention.
[0043] Figure 3 It is a schematic diagram of the crack at the bottom of the tenon of the mortise-jointed leaf disc of the present invention.
[0044] Figure 4 It is a schematic diagram of cracks in the blades of the tenon-jointed blade disk of the present invention.
[0045] Figure 5 It is a schematic diagram of the k-means clustering results of a healthy leaf disk, a leaf disk with different sizes of cracks, and a tenon bottom disk with different sizes of cracks of the present invention. DETAILED DESCRIPTION
[0046] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features therein can be combined with each other without conflict.
[0047] Combination Figure 1 As shown, an embodiment of the present invention provides a method for diagnosing cracks at the bottom of a tenon-jointed blade disk of an aircraft engine based on a blade tip timing signal, comprising the following steps:
[0048] S1: Use blade tip timing technology to obtain the measurable amplitude of the blade tip of the blade disk to be diagnosed at a constant speed and calculate the kurtosis of the measurable amplitude of the blade tip. The specific steps are:
[0049] S11: Using non-contact tip timing measurement technology, the blade spacing of the blade disk is monitored online throughout the entire cycle. In one rotation cycle, the blade with a smaller number passes the sensor first by default. The rotation cycle of the blade disk can be calculated based on the time interval between two consecutive arrivals of the same blade at the same sensor during the rotation process. The formula is as follows:
[0050]
[0051] Among them, T n is the rotation period of the blade disk at the nth circle, and is the time when the i-th blade passes the j-th sensor at the n+1th and nth turns.
[0052] S12: The maximum displacement and minimum displacement of the blade tip monitored by a sensor are obtained based on the difference between the actual arrival time and the theoretical arrival time of the same blade passing through the same sensor. The formula is as follows:
[0053]
[0054] in, and is the maximum and minimum displacement of blade No. b when rotating N circles under the monitoring of sensor No. s. r is the length from the tip of the blade to the center of the blade disk, t nbs and t nbs0 are the actual arrival time and theoretical arrival time of the blade b in the nth circle to the sensor s, respectively, T n is the blade rotation period, n is the current number of revolutions, N is the total number of revolutions, b is the blade number, and s is the blade tip timing sensor number.
[0055] Theoretical arrival time of blade t nbs0 It can be calculated through the relative positions of the rotation speed sensor and the optical fiber sensor and the measured rotation speed.
[0056]
[0057] Among them, t n0 is the arrival time of the fixed mark point on the shaft recorded by the speed sensor at the nth lap, n is the current lap number, θ s and θ i is the angle between the sth sensor and the i-th blade relative to the speed sensor, f r is the blade rotation frequency.
[0058] S13: If S optical fiber sensors are equipped, the maximum and minimum values of the measurable displacement of the blade can be obtained by taking the maximum value from the maximum values obtained by the S sensors. The measurable amplitude of the blade tip can be calculated based on the measurable maximum displacement and minimum displacement. The formula is as follows:
[0059]
[0060] in, and is the maximum and minimum measurable displacement of blade b, A b is the measurable amplitude of blade b.
[0061] S14: Calculate the kurtosis of the blade tip amplitude of the entire blade disk to be diagnosed, the formula is as follows:
[0062]
[0063] Among them, k is the kurtosis, q is the number of leaves, A i is the measurable amplitude of the ith blade, is the mean of the measurable amplitudes of all leaves. If the measurable amplitudes of all leaves are equal, let k be 0.
[0064] Step S2: Use blade tip timing technology to obtain the change in the distance between each blade of the blade disk to be diagnosed and the healthy blade disk at the same speed, and construct crack type identification parameters based on the change in the blade distance. The specific steps are:
[0065] S21: Use non-contact tip timing measurement technology to obtain the moment when the blade tip of the blade disk reaches the optical fiber sensor, calculate the time interval between two adjacent blades passing the same sensor, and calculate the spacing between adjacent blades of the blade disk. The formula is as follows:
[0066]
[0067] Among them, d i,i+1 is the distance between blades i and i+1, i and i+1 are blade numbers, r is the distance from the blade tip to the center of the blade disk, T n is the blade rotation period, Δt i,i+1 is the time difference between blade i and blade i+1 arriving at the same sensor.
[0068] S22: Calculate the blade spacing variation between the blade disk to be diagnosed and the healthy blade disk at the same speed. The formula is as follows:
[0069]
[0070] Where, Δd i,i+1 is the change in the distance between the blade i and i+1 of the blade disk to be diagnosed and the healthy blade disk, and are the distances between the blades i and i+1 of the blade disk to be diagnosed and the healthy blade disk respectively. The maximum value of the change in the distance between all blades in the same period is recorded as Δd max , the minimum value is recorded as Δd min , Δd max The corresponding leaf numbers on both sides are j max and j max+1 , Δd min The corresponding leaves on both sides are numbered j min , j min+1 , and j max and j min The two must be adjacent blade numbers, Δd min It must be a negative value, otherwise the data is invalid and needs to be collected again.
[0071] S23: It is difficult to distinguish whether the cracked mortise-jointed blade disc is a mortise bottom crack or a blade crack. The identification parameters for distinguishing mortise bottom cracks from blade cracks are constructed:
[0072] δ=Δd max -|Δd min |
[0073] When the tenon-jointed leaf disk contains a blade crack, δ approaches 0, while when there is a tenon bottom crack, δ will be significantly greater than 0.
[0074] Step S3: Taking the crack type identification parameter and the kurtosis of the blade tip amplitude as input, k-means is used for clustering to distinguish the crack types. The specific steps are:
[0075] S31: Set the number of k-means clusters to 3 and stop the iteration when the centroid of the cluster does not change.
[0076] S32: Taking the δ calculated by S23 and the k calculated by S14 as input, the data are clustered using k-means to distinguish the crack types.
[0077] Example
[0078] For the model of the blisk to be diagnosed, through simulation analysis, Figure 3 The radial cracks with sizes of 1.11mm, 1.48mm, 1.85mm, 2.22mm, 2.59mm, 2.96mm, 3.33mm and 3.70mm are implanted at the tenon bottom of the blade 7, respectively. Figure 4 The blade 7 shown has blade cracks with sizes of 1.11 mm, 1.48 mm, 1.85 mm, 2.22 mm, 2.59 mm, 2.96 mm, 3.33 mm and 3.70 mm implanted near the blade root.
[0079] The normalized value of the kurtosis k of the measurable amplitude of the blade tip of the healthy tenon-jointed blade disk calculated based on S1 and S2 is 0, and the crack type identification parameter δ is 0 mm.
[0080] According to S1, the kurtosis k of the measurable amplitude of the blade tip of the tenon bottom crack containing 1.11mm, 1.48mm, 1.85mm, 2.22mm, 2.59mm, 2.96mm, 3.33mm and 3.70mm are 1.942, 1.965, 1.973, 1.934, 1.919, 1.981, 2.072 and 2.055 respectively.
[0081] According to S2, the crack type identification parameters δ of the tenon bottom cracks containing 1.11mm, 1.48mm, 1.85mm, 2.22mm, 2.59mm, 2.96mm, 3.33mm and 3.70mm are: 0.01469mm, 0.0189mm, 0.01988mm, 0.02346mm, 0.02568mm, 0.03012mm, 0.03399mm and 0.03603mm respectively.
[0083] According to S1, the kurtosis k of the measurable amplitude of the crack tip of the blade with 1.11mm, 1.48mm, 1.85mm, 2.22mm, 2.59mm, 2.96mm, 3.33mm and 3.70mm are 8.8694, 9.4705, 9.7195, 9.916, 10.0113, 10.0448, 10.0845 and 10.0734 respectively.
[0084] According to S2, the crack type identification parameters δ of blade cracks containing 1.11mm, 1.48mm, 1.85mm, 2.22mm, 2.59mm, 2.96mm, 3.33mm and 3.70mm are: -0.005683333mm, 0.004086667mm, -0.001313333mm, -0.006503333mm, 0.002046667mm, 0.004176667mm, -0.002003333mm and -0.005303333mm.
[0085] According to S3, the number of k-means clusters is set to 3, and the iteration is stopped when the centroid of the cluster does not change.
[0086] The calculated kurtosis k of the measurable amplitude of the blade tip and the crack type identification parameter δ are used as input, and k-means is used to cluster the data. The results are as follows: Figure 5 As shown, it is effective to identify whether the tenon-jointed blade disc contains cracks, and distinguish whether the cracks are blade cracks or tenon bottom cracks.
Claims
1. A method for diagnosing cracks at the bottom of a tenon-jointed blade disk of an aircraft engine based on a blade tip timing signal, comprising the following steps: Step S1: using blade tip timing technology to obtain the measurable amplitude of the blade tip of the blade disk to be diagnosed at a constant speed and calculate the kurtosis of the measurable amplitude of the blade tip. Step S2: using blade tip timing technology to obtain the variation of the spacing between each blade of the blade disk to be diagnosed and the healthy blade disk at the same rotation speed, and constructing crack type identification parameters according to the variation of the blade spacing. Step S3: Taking the crack type identification parameter and the kurtosis of the blade tip amplitude as input, the input data is clustered using k-means to achieve the distinction of crack types.
2. The method for diagnosing cracks at the bottom of a tenon-jointed blade disk of an aircraft engine based on blade tip timing signals according to claim 1, characterized in that: The specific steps of step S1 are: S11: Using non-contact tip timing measurement technology, the blade spacing of the blade disk is monitored online throughout the entire cycle. In one rotation cycle, the blade with a smaller number passes the sensor first by default. The rotation cycle of the blade disk can be calculated based on the time interval between two consecutive arrivals of the same blade at the same sensor during the rotation process. The formula is as follows: Among them, T n is the rotation period of the blade disk at the nth circle, is the time when the i-th blade passes the j-th sensor at the n+1th and nth turns. S12: The maximum displacement and minimum displacement of the blade tip monitored by a sensor are obtained based on the difference between the actual arrival time and the theoretical arrival time of the same blade passing through the same sensor. The formula is as follows: in, and is the maximum and minimum value of the vibration displacement of blade No. b measured by sensor No. s when blade No. b rotates N times at a constant speed. r is the length from the blade tip to the center of the blade disk, t nbs and t nbs0 are the actual arrival time and theoretical arrival time of blade b in the nth circle to sensor s, respectively, T n is the blade rotation period, n is the current number of revolutions, N is the total number of revolutions, b is the blade number, and s is the blade tip timing sensor number. Theoretical arrival time of blade t nbs0 It can be calculated from the relative positions of the rotation speed sensor and the optical fiber sensor and the measured rotation speed. Among them, t n0 is the arrival time of the fixed mark point on the shaft recorded by the speed sensor at the nth lap. n is the current lap number, θ s and θ i is the angle between the sth sensor and the i-th blade relative to the speed sensor, f r is the blade rotation frequency. S13: If S optical fiber sensors are equipped, the maximum and minimum values of the measurable displacement of the blade can be obtained by taking the maximum value of the displacement obtained by the S sensors. The measurable amplitude of the blade tip can be calculated based on the measurable maximum displacement and minimum displacement. The formula is as follows: in, and is the maximum and minimum measurable displacement of blade b, A b is the measurable amplitude of blade b. S14: Calculate the kurtosis of the blade tip amplitude of the entire blade disk to be diagnosed, the formula is as follows: Among them, k is the kurtosis, q is the number of leaves, A i is the measurable amplitude of the ith blade, is the mean of the measurable amplitudes of all leaves. If the measurable amplitudes of all leaves are equal, let k be 0.
3. The method for diagnosing cracks at the bottom of a tenon-jointed blade disk of an aircraft engine based on blade tip timing signals according to claim 1, characterized in that: The specific steps of step S2 are: S21: Use non-contact tip timing measurement technology to obtain the moment when the blade tip reaches the optical fiber sensor, calculate the time interval between two adjacent blades passing the same sensor, and calculate the spacing between adjacent blades. The formula is as follows: Among them, d i,i+1 is the distance between blades i and i+1, i and i+1 are blade numbers, r is the distance from the blade tip to the center of the blade disk, T n is the blade rotation period, Δt i,i+1 is the time difference between blade i and blade i+1 arriving at the same sensor. S22: Calculate the blade spacing variation between the blade disk to be diagnosed and the healthy blade disk at the same speed. The formula is as follows: Where, Δd i,i+1 is the change in the distance between the blade i and i+1 of the blade disk to be diagnosed and the healthy blade disk, and are the distances between the blades i and i+1 of the blade disk to be diagnosed and the healthy blade disk respectively. The maximum value of the change in the distance between all blades in the same period is recorded as Δd max , the minimum value is recorded as Δd min , Δd max The corresponding leaf numbers on both sides are j max and j max+1 , Δd min The corresponding leaves on both sides are numbered j min , j min+1 , and j max and j min The two must be adjacent blade numbers, Δd min It must be a negative value, otherwise the data is invalid and needs to be collected again. S23: It is difficult to distinguish whether the cracked mortise-jointed blade disc is a mortise bottom crack or a blade crack. The identification parameters for distinguishing mortise bottom cracks from blade cracks are constructed: δ=Δd max -|Δd min | When the tenon-jointed leaf disk contains a blade crack, δ approaches 0, while when there is a tenon bottom crack, δ will be significantly greater than 0.
4. The method for diagnosing cracks at the bottom of a tenon-jointed blade disk of an aircraft engine based on blade tip timing signals according to claim 1, characterized in that: The specific steps of step S3 are: S31: Set the number of k-means clusters to 3 and stop the iteration when the centroid of the cluster does not change. S32: Taking the δ calculated by S23 and the k calculated by S14 as input, the data are clustered using k-means to distinguish the crack types.
Citation Information
Cited By
Blade crack identification method for mistuned blisk
CN119761110A
