To study the influence mechanism of process parameters on the temperature field and the repair performance in Inconel718 nickel-base-superalloy laser additive repairing process, numerical research was carried out. A three-dimensional finite element model was established, and the finite element software ANSYS was used to simulate the temperature field. The influence of the laser power, the scanning speed on the laser additive repairing temperature distribution and the penetration depth and width of the repair zone were analyzed. The numerical result and the experimental measurement result was compared, and the result showed that as the laser power is in the range of 229~668W and the cladding speed is in the range of 6~16mm/s, the metallurgical bond was formed between the repair layer and the matrix material. The maximum temperature at the interface between the repair layer and the substrate is proportional to the laser power and inversely proportional to the scanning speed. The theoretically calculated penetration depth and penetration width of the repair zone are basically consistent with the experimental measurement results. The theoretical simulation can provide theoretical guidance for the parameter optimization in the laser additive repairing process.
Aiming at the low efficiency of manual detection of X-ray image defects in the production process of casting gearboxes, combined with the machine learning theory in computer vision recognition, a defect detection algorithm based on feature engineering and machine learning is proposed. Through image preprocessing and part X-ray image feature extraction, different feature models are established, and the algorithm is evaluated through different machine learning classifiers. Car subframe products are used for experimental verification. In general, the combination of directional gradient histogram (HOG) and Naive Bayes (GNB) can achieve the best results, with an accuracy rate of 83%. Compared with manual detection, this algorithm effectively improves the classification speed, and the classification accuracy has also been greatly improved, which proves the effectiveness of the proposed algorithm.
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.