This paper proposes an imaging analysis technique based on a concatenated convolutional neural network to improve and standardize the assessment procedure of laser cleaning 7075 aluminium alloy. First, an orthogonal experiment based on the pairwise algorithm is designed to analyze the cleaning effect variation under different laser processing parameters. Based on the data augmentation of experimental image datasets, sufficient datasets can be input into several deep convolutional neural networks to realize the automatic and quick assessment procedure for laser cleaning quality. The results show that the classification performance of the concatenated network based on Xception and ResNet50v2 networks is best, the average accracy of the proposed network for detecting surface roughness is 99.50%, and the overall average accuracy for all classes is 98.40%.
To effectively produce solar hydrogen through the two step water decomposition cycle, a CeO2-NiO (Ce: Ni = 9:1) solid solution was synthesized by the coprecipitation method. CeO2-NiO was coated on ceramic (Al2O3) substrate and sintered at 90-150°C inorganic adhesive. In order to quickly increase the reaction surface area emitted by O2, laser material treatment was used, and the delicate laser texture pattern was confirmed by laser treatment on CeO2-NiO. In the periodic two step water decomposition process at 1200 – 800°C, the O2 gas produced in the O2 emission reaction with CeO2-NiO substrate with suitable laser treatment is almost twice that of the untreated substrate.
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.