Search

With the development of Materials Genome Initiative (MGI) and data mining technology, machine learning (ML) has emerged as an important tool in the research of materials science. For the heat resistant alloys used in furnace tubes, the rapid prediction of the high-temperature properties is critical but difficult until now. In this work, the ML method based on the deep learning algorithm is developed to establish the direct correlation between microstructure inputs and output stress rupture properties of Fe-Cr-Ni based heat resistant alloys. Two simple convolutional neural networks (CNN) and the complex network with VGG16 architecture are implemented and evaluated. The simple CNN and VGG16 models are trained from scratch and pre-trained, respectively. Due to the relatively few training samples in the dataset, the data augmentation configuration and the improved architecture are effective to mitigate overfitting in simple CNN models. The result also shows that in the case of transfer learning, the features extracted from other datasets can be used directly to this new visual task. It is demonstrated that both the simple CNN and VGG16 models reach the high prediction accuracies (more than 90 %) of high-temperature properties with a wide range of microstructures. In addition, the good prediction performance achieved in the small dataset also reveals the deep learning approaches can be used to construct powerful vision models in engineering practice, where very limited data is the common situation.

The influence of Ti element with the content from 0.018 wt.% to 0.112 wt.% on microstructure and mechanical properties of centrifugally cast 25Cr-35Ni-Nb alloy was investigated in this paper. The experiments were carried out by optical emission spectrometer, metallographic image analyzer, field emission gun scanning electron microscopy (FEG-SEM) equipped with an Oxford INCA energy dispersive X-ray spectrometer (EDS), tensile testing machine and creep testing machine. The results show that the microstructure and high temperature creep rupture properties of as-cast 25Cr-35Ni-Nb alloy are significantly affected by the addition of Ti. No precipitation of Ti carbides was observed in the alloy with the Ti content of 0.018 wt.%, whereas the skeleton (Nb, Ti) C were precipitated at grain boundaries when increasing the Ti content. Under the creep rupture condition of 1100 °C and 17 MPa, the rupture lives of 25Cr-35Ni-Nb alloy with Ti contents ranging from 0.04 wt.% to 0.112 wt.% were relatively higher. In addition, the role of Ti in ethylene pyrolysis furnace tube was also discussed in this paper.

Centrifugal cast HP40Nb alloys are commonly used as ethylene pyrolysis and reformer furnace tube materials. The actual wall temperature can usually reach 1423 K. The technical specifications require that the rupture life shall be at least 120 h under test condition of 1373 K at 17 MPa. The effects of amounts of Lead on the creep and stress rupture performance of the centrifugal cast HP40Nb alloy have been investigated at the temperature of 1373 K and the constant stress of 17 MPa. In this paper, HP40Nb alloy tubes with different contents of Lead element by centrifugal casting were selected, by high temperature stress rupture test and microscopic observation of creep damage, relationship between the content of Lead and high temperature stress rupture lives was given, as well as the threshold value of Lead element. It could provide the basis for ethylene pyrolysis furnace tubes manufacturers and design specifications.Copyright © 2012 by ASME