Kemin Li, Zhifu Huang, Hanwen Ma, Shaofei Wang, Chaofeng Qin and Pengcheng Liu
The purpose of this study was to investigate the tribological properties of bulk Fe2B with pre-oxidation treatment.
Abstract
Purpose
The purpose of this study was to investigate the tribological properties of bulk Fe2B with pre-oxidation treatment.
Design/methodology/approach
Bulk Fe2B was oxidized in an electric box furnace with a soaking time of 9 min under 750°C in air. Then, the tribological experiments were carried out on an UMT-Tribolab tester.
Findings
The oxide layer was composed of Fe, Fe2O3, Fe3O4, B2O3 and H3BO3. The oxidative direction of bulk Fe2B was perpendicular to the sample surface. But, the oxidative direction of Fe2B crystals was irregular. At 0.1 m/s, the friction coefficient was the lowest. The effects of shortening the running-in period of friction and reducing the friction coefficient by pre-oxidation treatment at 0.1 m/s were remarkable. Nevertheless, the effect of pre-oxidation treatment was futile at 0.2 m/s. Wear mechanisms of oxidized Fe2B mainly were adhesive and abrasive wear.
Originality/value
The effects of shortening the running-in period of friction and reducing the friction coefficient by pre-oxidation treatment were remarkable.
Details
Keywords
Previous knowledge base question answering (KBQA) models only consider the monolingual scenario and cannot be directly extended to the cross-lingual scenario, in which the…
Abstract
Purpose
Previous knowledge base question answering (KBQA) models only consider the monolingual scenario and cannot be directly extended to the cross-lingual scenario, in which the language of questions and that of knowledge base (KB) are different. Although a machine translation (MT) model can bridge the gap through translating questions to the language of KB, the noises of translated questions could accumulate and further sharply impair the final performance. Therefore, the authors propose a method to improve the robustness of KBQA models in the cross-lingual scenario.
Design/methodology/approach
The authors propose a knowledge distillation-based robustness enhancement (KDRE) method. Specifically, first a monolingual model (teacher) is trained by ground truth (GT) data. Then to imitate the practical noises, a noise-generating model is designed to inject two types of noise into questions: general noise and translation-aware noise. Finally, the noisy questions are input into the student model. Meanwhile, the student model is jointly trained by GT data and distilled data, which are derived from the teacher when feeding GT questions.
Findings
The experimental results demonstrate that KDRE can improve the performance of models in the cross-lingual scenario. The performance of each module in KBQA model is improved by KDRE. The knowledge distillation (KD) and noise-generating model in the method can complementarily boost the robustness of models.
Originality/value
The authors first extend KBQA models from monolingual to cross-lingual scenario. Also, the authors first implement KD for KBQA to develop robust cross-lingual models.
Details
Keywords
Shaofei Chen, Hongfu Liu, Jing Chen and Lincheng Shen
The purpose of this paper is to plan the penetration trajectory for unmanned aerial vehicle (UAV) in the presence of radar‐guided surface to air missiles (SAMs).
Abstract
Purpose
The purpose of this paper is to plan the penetration trajectory for unmanned aerial vehicle (UAV) in the presence of radar‐guided surface to air missiles (SAMs).
Design/methodology/approach
The penetration trajectory planning problem is modelled based on four aspects of radar tracking features. As penetration just utilizes the low observability of radar cross section (RCS) to satisfy temporal constraints of tracking, the problem is formulated as multi‐phase trajectory planning with detected probability (MTP‐DP). While utilizing both the low observability of RCS and the radial velocity blind area of radar, the problem is formulated as multi‐phase trajectory planning with detected probability and radial velocity (MTP‐DP&RV). The pseudospectral multi‐phase optimal control based trajectory planning algorithm is proposed.
Findings
The results of the examples illustrate that the multi‐phase trajectory planning method can finely utilize the radar tracking features to optimize the comprehensive efficiency of penetration. The pseudospectral multi‐phase optimal control based trajectory planning algorithm could effectively solve the trajectory planning problem.
Originality/value
This paper provides new structured method to plan UAV penetration trajectory for military application and academic study.