Porosity Characterization of Thermal Barrier Coatings by Ultrasound with Genetic Algorithm Backpropagation Neural Network

Zhang, Shuxiao; Lv, Gaolong; Guo, Shifeng; Zhang, Yanhui; Feng, Wei

doi:10.1155/2021/8869928

Cited by 5 publications

(3 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, coating applications are becoming more and more widespread, and there are various methods for detecting coatings, such as high-frequency wave packet decomposition techniques [12], scanning imaging [13], intelligent algorithmic feature recognition [14], acoustic decay properties [15,16], time-frequency joint analysis [17], multiple data fusion methods [18], and time series parameter identification [19]. However, the effectiveness of these methods for processing coating detection signals with severe degree of aliasing is yet to be verified.…”

Section: Introductionmentioning

confidence: 99%

Ultrasonic Detection of Aliased Signal Separation Based on Adaptive Feature Dictionary and K–SVD Algorithm for Protective Coatings of Assembled Steel Structure

et al. 2023

View full text Add to dashboard Cite

When using ultrasound to detect the thickness of protective coatings on assembled steel structures, the coatings are extremely thin, which can cause echo signals to overlap and impair the detection accuracy. Therefore, the study of the separation of the superimposed signals is essential for the precise measurement of the thickness of thinner coatings. A method for signal time domain feature extraction based on an adaptive feature dictionary and K–SVD is investigated. First, the wavelet transform, which is sensitive to singular signal values, is used to identify the extreme values of the signal and use them as the new signal to be processed. Then, the feature signal extracted by wavelet transform is transformed into Hankel matrix form, and the initial feature dictionary is constructed by period segmentation and random extraction. The optimized feature dictionary is subsequently obtained by enhancing the K–SVD algorithm. Finally, the time domain signal is reconstructed using the optimized feature dictionary. Simulations and experiments demonstrate that the method is more accurate in separating mixed signals and extracting signal time domain feature information than the conventional wavelet transform and Gabor dictionary-based MP algorithm, and that it is more advantageous in detecting the thickness of protective coatings.

show abstract

Section: Introductionmentioning

confidence: 99%

Ultrasonic Detection of Aliased Signal Separation Based on Adaptive Feature Dictionary and K–SVD Algorithm for Protective Coatings of Assembled Steel Structure

et al. 2023

View full text Add to dashboard Cite

show abstract

“…Until now, there have been few studies on the detection of the debonded section of the coating layer applied to the concrete structure in water immersion tests. Recent research has been based on the following methods: high-frequency wave echo decomposition [39], reflection coefficient theory [40,41], pulse-velocity-based methods [42,43], wave attenuation [44,45], the data fusion technique [46], the multifrequency method [47], and time-based parameters [48].…”

Section: Introductionmentioning

confidence: 99%

Neural-Network-Based Ultrasonic Inspection of Offshore Coated Concrete Specimens

Malikov

Kim

et al. 2022

Coatings

View full text Add to dashboard Cite

A thin layer of protective coating material is applied on the surface of offshore concrete structures to prevent its degradation, thereby extending the useful life of the structures. The main reasons for the reduction in the protective capability of coating layers are loss of adhesion to concrete and flattening of the coating layer wall. Usually, the state of the coating layer is monitored in the setting of water immersion using ultrasonic inspection methods, and the method of inspection still needs improvement in terms of speed and accuracy. In this study, the ultrasonic pulse echo method was used in a water immersion test of the coated specimens, and continuous wavelet transform (CWT) with complex Morlet wavelets was implemented to define the received waveforms’ time of flight and instantaneous center frequency. These allow one to evaluate the thickness of the coating layer during water immersion. Furthermore, phases of reflected echoes at CWT local peaks were computed using a combination of Hilbert transforms (HT) and wave parameters derived from CWT. In addition, three relative wave parameters of echoes were also used to train deep neural networks (DNN), including instantaneous center frequency ratio, CWT magnitude ratio, and phase difference. With the use of three relative waveform parameters of the DNN, the debonded layer detection accuracy of our method was 100%.

show abstract

“…To test metallic coatings, high-frequency eddy currents of several MHz [30] must be used. Similarly, crack detection and layer thickness measurements can be undertaken with high-frequency 5-25 MHz ultrasound waves [31,32]. Due to complex airfoil geometry (e.g., at LE), the measurements of blade coatings are less accurate than ones on flat surfaces.…”

Section: Introductionmentioning

confidence: 99%

Health and Durability of Protective and Thermal Barrier Coatings Monitored in Service by Visual Inspection

et al. 2022

View full text Add to dashboard Cite

Protective and Thermal Barrier Coatings (TBC) applied on gas-turbine blades gradually degrade due to oxidation, aluminum depletion and impacts of environmental particles. Among various non-destructive coating testing methods (NDT), visual inspection can be undertaken regularly in service, but it provides little quantitative information, and only surface defects can be detected. This work aims at in-service monitoring of turbine blades with multilayer coatings applied by atmospheric plasma spraying (APS) in a few variants. They were validated during a series of accelerated mission tests of a retired military turbofan engine in a test cell together with five other technologies. The fifty-hour rainbow test focused on assessing coating durability. Between engine runs, 12 borescope inspections were conducted to monitor the health of the blades. Finally, the blades were disassembled and examined using computed tomography (CT) and metallographic methods. Throughout the testing, 31 newly-coated blades (66%) withstood the tests, producing results comparable to the reference blades. However, 16 blades suffered intolerable failures observed as increased roughness, gradual loss of the topcoat, spallation and minor foreign object damage. Visual inspection results were generally in agreement with subsequent laboratory tests.

show abstract

Porosity Characterization of Thermal Barrier Coatings by Ultrasound with Genetic Algorithm Backpropagation Neural Network

Cited by 5 publications

References 40 publications

Ultrasonic Detection of Aliased Signal Separation Based on Adaptive Feature Dictionary and K–SVD Algorithm for Protective Coatings of Assembled Steel Structure

Ultrasonic Detection of Aliased Signal Separation Based on Adaptive Feature Dictionary and K–SVD Algorithm for Protective Coatings of Assembled Steel Structure

Neural-Network-Based Ultrasonic Inspection of Offshore Coated Concrete Specimens

Health and Durability of Protective and Thermal Barrier Coatings Monitored in Service by Visual Inspection

Contact Info

Product

Resources

About