Multiscale Image Fusion-Based Thermal Fatigue Damage Detection Method for Cylinder Head Inner Wall

Fig. 2. Inner wall images reconstructed by traditional association imaging. (a) Images of original object; (b)-(d) reconstructed images when N=500, 1000, 3000, respectively

Download full size

Fig. 3. Reconstructed images of cylinder head inner wall at different scales. (a)-(c) Reconstructed images with pixel size of $1 p i x e l \times 1 p i x e l$ , $2 p i x e l \times 2 p i x e l$ ,and $3 p i x e l \times 3 p i x e l$ when N=500, respectively; (d)-(f) reconstructed images with pixel size of $1 p i x e l \times 1 p i x e l$ , $2 p i x e l \times 2 p i x e l$ , and $3 p i x e l \times 3 p i x e l$ when N=1000, respectively

Download full size

Fig. 4. Principle of multi-scale image fusion method

Download full size

Fig. 5. Speckle patterns of thermal field on inner wall at different scales. (a)-(c) Inner wall thermal field speckle patterns with pixel size of $1 p i x e l \times 1 p i x e l$ , $2 p i x e l \times 2 p i x e l$ , and $3 p i x e l \times 3 p i x e l$ respectively

Download full size

Fig. 6. Images of cracked cylinder head inner wall. (a)(d) Images of the original object; (b)(e) images reconstructed by traditional association and differential association when N=500, respectively; (d)(f) images fused by traditional association and differential association respectively when the fusion weight is $1 ∶ 1 ∶ 1$

Download full size

Fig. 7. Fused inner wall images with different weight proportions. (a) $2 ∶ 1 ∶ 1$ ; (b) $3 ∶ 1 ∶ 1$ ; (c) $4 ∶ 1 ∶ 1$ ; (d) $1 ∶ 1 ∶ 2$ ; (e) $1 ∶ 1 ∶ 3$ ; (f) $1 ∶ 1 ∶ 4$

Download full size

Fig. 8. Change curves of quantitative index for images under different measurement times. (a) Average SSIM value; (b) average PSNR value; (c) average V value

Download full size

Table 1. Performance parameters of a single-cylinder four-valve internal combustion engine
View table
Table 1. Performance parameters of a single-cylinder four-valve internal combustion engine
Parameter Value
Cylinder diameter /mm 120
Cylinder head stroke /mm 150
Total emissions /L 10.45
Nominal power /kW 162
Calibrated power speed /（r·min^-1） 2200
Maximum torque /（N·m） 844

Table 2. Comparison of evaluation indexes between traditional association imaging and multi-scale fusion images
View table
Table 2. Comparison of evaluation indexes between traditional association imaging and multi-scale fusion images
Evaluation index Traditional association Multi-scale fusion
PSNR 6.6073 7.2429
SSIM 0.9745 0.9790
V 0.1795 0.2264

Table 3. Comparison of evaluation indexes between differential association imaging and multi-scale fusion images
View table
Table 3. Comparison of evaluation indexes between differential association imaging and multi-scale fusion images
Evaluation index Differential association Multi-scale fusion
PSNR 6.9603 7.4523
SSIM 0.9759 0.9812
V 0.2155 0.2436

Table 4. Evaluation indexes under different weight proportion

View table

Table 4. Evaluation indexes under different weight proportion

Weight proportion	PSNR	SSIM	V
$2 ∶ 1 ∶ 1$	7.1358	0.9798	0.2148
$3 ∶ 1 ∶ 1$	7.0536	0.9809	0.2078
$4 ∶ 1 ∶ 1$	6.9917	0.9813	0.2031
$1 ∶ 1 ∶ 1$	7.2429	0.9790	0.2264
$1 ∶ 1 ∶ 2$	7.1960	0.9777	0.2356
$1 ∶ 1 ∶ 3$	7.1462	0.9768	0.2412
$1 ∶ 1 ∶ 4$	7.1043	0.9767	0.2449

Tools

Get Citation

Copy Citation Text

Quanliang Li, Xiaoxia Wang, Fengbao Yang. Multiscale Image Fusion-Based Thermal Fatigue Damage Detection Method for Cylinder Head Inner Wall[J]. Laser & Optoelectronics Progress, 2023, 60(6): 0612002

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Instrumentation, Measurement and Metrology

Received: Oct. 31, 2022

Accepted: Nov. 8, 2022

Published Online: Mar. 16, 2023

The Author Email: Xiaoxia Wang (wangxiaoxia@nuc.edu.cn)

DOI:10.3788/LOP222923

Topics

laser devices and laser physics

Lasers and Laser Optics

Laser physics

laser manufacturing

Instrumentation, Measurement and Metrology

Table 1. Performance parameters of a single-cylinder four-valve internal combustion engine

Table 1. Performance parameters of a single-cylinder four-valve internal combustion engine

Table 2. Comparison of evaluation indexes between traditional association imaging and multi-scale fusion images

Table 2. Comparison of evaluation indexes between traditional association imaging and multi-scale fusion images

Table 3. Comparison of evaluation indexes between differential association imaging and multi-scale fusion images

Table 3. Comparison of evaluation indexes between differential association imaging and multi-scale fusion images

Table 4. Evaluation indexes under different weight proportion

Table 4. Evaluation indexes under different weight proportion