Central South University

Hunan University

Xu Zhou

Zuming Liu

Bing Wei

Yake Ren

Bizhong Nong

Yongkang Ai

Bin Cao

Sizhe Lu

Quan Li

Zhuo Tang

Liang Du

Qing Liao

Chubo Liu

Kenli Li

Siyang Yu

A method for preventing cracking of nickel-based superalloy fabricated by selective laser melting (SLM) belongs to the field of additive manufacturing (AM). The method of preparing an as-built part with a high density, no crack defects, and good mechanical properties includes: reducing the content of elements Zr and B forming low melting point phase in a nickel-based superalloy, adjusting the total content of Al and Ti in the alloy to 4.5 wt % or below, and combining with the control of special SLM process parameters. The new method has the advantages of a reasonable component design, a simple preparation process, and good performance of the as-built part, and therefore is suitable for large-scale application.

Method for preventing cracking of nickel-based superalloy fabricated by selective laser melting

A method for preparing a nano spherical oxide dispersion strengthening phase using a micron oxide is proposed for the first time. First, a micron oxide is used as a raw material to prepare a nano oxide with a completely amorphous structure/matrix alloy composite powder by mechanical ball milling in stages. In the first stage, ball milling is performed, causing the oxide to break and transform in structure, and achieving nano-sizing and completely amorphization, to prepare a composite powder with a completely amorphous structure nano oxide uniformly distributed in the matrix alloy powder; and in the second stage, the composite powder obtained in the first stage and the remaining matrix alloy powder are uniformly mixed by ball milling. Then, the uniformly mixed powder is sequentially subjected to hot forming, hot rolling, and heat treatment, to obtain a nano spherical oxide dispersion strengthened alloy.

Method for preparing nano spherical oxide dispersion strengthening phase

The disclosure discloses a method for detecting an intrusion in parallel based on an unbalanced data Deep Belief Network, which reads an unbalanced data set DS; under-samples the unbalanced data set using the improved NCR algorithm to reduce the ratio of the majority type samples and make the data distribution of the data set balanced; the improved differential evolution algorithm is used on the distributed memory computing platform Spark to optimize the parameters of the deep belief network model to obtain the optimal model parameters; extract the feature of data of the data set, and then classify the intrusion detection by the weighted nuclear extreme learning machine, and finally train multiple weighted nuclear extreme learning machines of different structures in parallel by multithreading as the base classifier, and establish a multi-classifier intrusion detection model based on adaptive weighted voting for detecting the intrusion in parallel.

Method and system for detecting intrusion in parallel based on unbalanced data Deep Belief Network

Growing community of inventors

Changsha, China

Xu Zhou