Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Fast attack detection method for imbalanced data in industrial cyber-physical systems

Huang Meng, Li Tao, Li Beibei, Zhang Nian, Huang Hanyuan

Journal of Artificial Intelligence and Soft Computing Research

2023

Vol. 13, No. 4

229--245

Integrating industrial cyber-physical systems (ICPSs) with modern information technologies (5G, artificial intelligence, and big data analytics) has led to the development of industrial intelligence. Still, it has increased the vulnerability of such systems regarding cybersecurity. Traditional network intrusion detection methods for ICPSs are limited in identifying minority attack categories and suffer from high time complexity. To address these issues, this paper proposes a network intrusion detection scheme, which includes an information-theoretic hybrid feature selection method to reduce data dimensionality and the ALLKNN-LightGBM intrusion detection framework. Experimental results on three industrial datasets demonstrate that the proposed method outperforms four mainstream machine learning methods and other advanced intrusion detection techniques regarding accuracy, F-score, and run time complexity.

Probabilistic seismic performance evaluation of composite frames with concrete-filled steel tube columns and buckling-restrained braces

Li Beibei, Wang Jingfeng, Yang Jian, Wang Yuanqing

Archives of Civil and Mechanical Engineering

2021

Vol. 21, no. 2

541--562

The concrete-filled steel tube (CFT) composite frames using blind bolts and buckling-restrained braces (BRBs) have been studied with the development of building industrialization and energy dissipation technology. However, there has been no research so far on the probabilistic seismic fragility analysis for the blind-bolted end-plate CFT composite frames with BRBs (BRB-BECFT). Therefore, a total of 6-, 9-, 12- and 20-story BRB-BECFT prototype structures were designed based on the performance-based plastic design method. The results obtained from nonlinear static and dynamic analyses indicated that the four structures achieved predefined performance objectives in terms of story drift, joint rotation, and BRB ductility demand. Subsequently, fragility curves including non-collapse and collapse states were established to evaluate the behavior of the structure for a given intensity measure using the incremental dynamic analysis approach. Meanwhile, the geometric mean of spectral acceleration over a period range (Sa,avg) was selected as the intensity measure to assess the structural collapse capacity. Results showed that the adoption of Sa,avg can result in 32–42% lower data dispersion for the determination of collapse point, and simplification of the process of calculation of the collapse margin ratio of a structure. Furthermore, based on the combination of Sa,avg, residual story drift and BRB core plate strain, a framework of probabilistic seismic damage analysis of structures for combined damage evaluation at three levels of the system, subsystem, and component was summarized and conducted by the 6- and 12-story case study. This is practically useful to assess structural damage state after an earthquake because it could present more information on the probability distribution of various damage scenarios.