Deep Learning-Based Models for Porosity Measurement in Thermal Barrier Coating Images

Deep Learning-Based Models for Porosity Measurement in Thermal Barrier Coating Images

Yongjin Lu, Wei-Bang Chen, Xiaoliang Wang, Zanyah Ailsworth, Melissa Tsui, Huda Al-Ghaib, Ben Zimmerman
DOI: 10.4018/IJMDEM.2020070102
OnDemand:
(Individual Articles)
Available
$37.50
No Current Special Offers
TOTAL SAVINGS: $37.50

Abstract

This work trained convolutional neural networks (CNNs) to identify microstructure characteristics and then provide a measurement of porosity in the topcoat layer (TCL) of thermal barrier coatings using digital images captured by an inverted optical microscope. Porosity in a coating is related to thermal compensation and the longevity of the parts protected by the coating. The approach employs pixel-wise classification and transfer learning accompanied by data augmentation to expedite the training process and increase classification accuracy. The authors evaluate CNN-based models globally on the entire TCL of 159 high resolution raw images of three types (Type A, B, C) that are generated from three different types of powders and exhibit different physical and visual properties. The experimental results show that the CNN-based models outperform adaptive local thresholding-based porosity measurement (ALTPM) approach that this paper proposed in the previous work by 7.76%, 10.82%, and 12.10% respectively for Type A, Type B, and Type C images in terms of the average classification accuracy.
Article Preview
Top

1. Introduction

Thermal plasma spray coating, which provides significant improvement towards wear resistance, heat resistance, corrosion resistance and electrical properties of fabricated parts, has been regarded as an important process in modern manufacturing industry (Davis, 2004; Pawlowski, 2008). The thermal barrier coating technology has been widely used in the aerospace manufacturing industry to deposit coating materials such as metals and ceramic onto gas turbine parts. These coatings play an important role in protecting the underlying parts as they can be exposed to harsh, corrosive, as well as high temperature environments during service (Odhiambo, Li, Zhao, & Li, 2019). Although thermal barrier coatings are designed to provide friction, wear, environmental, and thermal protection, it is important to note that defects such as cracks, partially melted particles and volume fraction of porosity must be realized within acceptable range before service as they can alter the performance of the coatings (Odhiambo, Li, Zhao, & Li, 2019).

In a typical atmospheric plasma spay process, powder feedstock is carried in an inert gas stream into the plasma spray gun where it is heated and accelerated to deposit onto the substrate. Due to the high-temperature nature of the plasma jet, the feedstock coating powder is being melted as droplets which solidify rapidly when deposited onto the substrates. As a result, the rapid solidification introduces defects in the microstructures, such as partially melted particles, and cracks into the coatings. These defects have a huge impact on the performance, quality, and durability of the thermal barrier coatings (TBC). In this research, we mainly focus on quantifying microstructures, specifically, porosity measurement, as it is a feature that is commonly characterized in thermal plasma spray coatings. Porosity in a coating is directly related to the powder feedstock and spray process parameters (Kulkarni et al., 2003; Oliker, Gridasova, & Pritulyak, 2008). In the case for thermal barrier coatings, porosity provides thermal compensation in parts from temperature changes, however, excessive porosity can accelerate the deterioration of turbine parts in a corrosive environment (Moskal, 2007).

To measure porosity in the top coat layer of thermal barrier coating, a high-resolution digital image of the cross section of a sample is captured using optical microscope. Figure 1 demonstrates a typical image of the thermal barrier coating, which consists of four layers, including substrate, bond coat layer (BCL), top coat layer (TCL), and mount material. In the bond coat layer and the top coat layer, the dark areas, which are void spaces, represent microstructures in the coatings as shown in Figure 1. In this research, porosity assessment of thermal barrier coatings is defined as the quantification of microstructures in the top coat layer.

Figure 1.

Thermal barrier coating image

IJMDEM.2020070102.f01

Complete Article List

Search this Journal:
Reset
Volume 15: 1 Issue (2024)
Volume 14: 1 Issue (2023)
Volume 13: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 12: 4 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing