Metal wear detection is an essential aspect of metal materials research. However, obtaining wear data for certain metals can be challenging, impacting detection accuracy. This paper proposes expanding the metal wear sample library using an improved CycleGAN. This method optimizes the composite model by replacing the L2 paradigm of the cycle loss function with the LPIPS function. This enables the generated images to have the fundamental outlines of metal wear samples and additional detail variability while enhancing the training network's resolution and stability. Experimental results demonstrate that the CycleGAN network with the improved loss function significantly improves the quality of the generated images from the metal wear dataset compared to the primary CycleGAN network. Specifically, the SSIM and PSNR values enhanced by 6.38% and 9.34%, respectively.
The railroad switch is one of the most vulnerable components of railway tracks, and the slide bed bears the non-contact force of the train wheelset, serving as a crucial part of the switch. Due to constant exposure to harsh environmental conditions, the slide bed is susceptible to corrosion, leading to fractures and significantly reducing its lifespan. This issue poses a serious threat to the operational safety of high-speed trains. In this study, addressing the current deficiencies in corrosion detection methods, such as the use of approximate exponential functions, non-linearity, data disturbance, and complex trend changes in corrosion data due to salt spray, we employ the Long Short-Term Memory (LSTM) model to predict corrosion information on the slide bed. This approach provides a reliable method for predicting metal corrosion damage caused by salt spray. The results of the prediction model indicate that when using LSTM to predict four types of characteristic values, the error functions MSE, MAE, RMSE, and MAPE are all close to 0, demonstrating high prediction accuracy.
This article introduces a novel infrared image enhancement algorithm, Heat-HE, which combines the histogram equalization algorithm with the laser cladding thermal field distribution law. By applying the grayscale world, automatic white balance, and Heat-HE algorithms to infrared images, the algorithm’s performance is evaluated using two evaluation indicators: average peak signal-to- noise ratio and average structural similarity. The experimental results demonstrate that the Heat-HE algorithm outperforms the comparison algorithm in terms of average peak signal-to-noise ratio, average structural similarity, and average running time. The Heat-HE algorithm efficiently removes noise and non-defective areas in infrared images, resulting in more intuitive and clear defect contours.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.