http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : Qingyu Yao (검색결과 3 건)
- 무료
- 기관 내 무료
- 유료
-
Few-shot transfer learning with attention for intelligent fault diagnosis of bearing
Yao Hu,Qingyu Xiong,Qiwu Zhu,Zhengyi Yang,Zhiyuan Zhang,Dan Wu,Zihui Wu 대한기계학회 2022 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.36 No.12
The bearing is one of the key components in modern industrial equipment. In the past few years, many studies have been carried out on bearing diagnosis through datadriven methods. However, there are two practical problems. First, under actual working conditions, the lack of fault samples is a major factor that hinders the application of these methods in industrial environments. Second, there is a lack of full utilization of a priori knowledge in the current stage of methods using relational networks for fault diagnosis. It is manifested by the incompleteness of the relational network structure. To address these problems, we present a new diagnosis method based on few-shot learning, which is suitable for the environment where the data is scarce. In this method, we train the model with the data generated by the artificial damaged bearings instead of the data from the real bearing. We experimentally validate the performance improvement of the complete relational network structure. It is able to perform the few-shot learning task better. In addition, we also reduce the global feature discrepancy by introducing an attention mechanism to improve the performance of the model. And the impact of the number of layers of the attention mechanism on the model is also discussed in detail. In this paper, our model performs better under the same experimental conditions compared with other transfer learning models.
-
Quantitative Reduction of Basilar Invagination With Atlantoaxial Dislocation by a Posterior Approach
Jian Guan,Fengzeng Jian,Qingyu Yao,Chenghua Yuan,Can Zhang,Longbing Ma,Zhenlei Liu,Wanru Duan,Xingwen Wang,Xuefeng Bo,Zan Chen 대한척추신경외과학회 2020 Neurospine Vol.17 No.3
Objective: This study evaluated the feasibility and efficacy of quantitative reduction and fixation to treat basilar invagination (BI) with atlantoaxial dislocation (AAD). Methods: Posterior occipitocervical angle (POCA), occiput–C2 angle (Oc–C2A), clivusaxial angle (CAA), and C2–7 angle (C2–7A) were considered for quantitative reduction. Twelve patients with BI complicated with AAD received posterior interarticular release and individualized cage implantation to restore vertical dislocation. The POCA was adjusted using cantilever technology to further reduce the horizontal dislocation and adjust lower cervical vertebral angle. All patients received a radiological follow-up for ≥12 months. Improvements in spinal cord function were evaluated using Japanese Orthopedic Association (JOA) score. Results: All the patients received successful quantitative reduction for BI-AAD, and bony fusion was achieved without spinal cord injury after surgery for 12 months. The JOA score was improved significantly to 15.2 ± 0.9 twelve months after surgery (p < 0.01). Radiological follow-up revealed that individualized cage and POCA play vital roles in quantitative correction: (1) distance of the dens above McRae’s line and atlantodens interval were restored to normal level, respectively; (2) changes in Oc–C2 angle (ΔOc–C2A), C2–7 angle (ΔC2–7A), clivus-axial angle (ΔCAA), and POCA (ΔPOCA) were all caused by changes in axis tilt. Based on the changes of radiological parameter we deduced the formula for quantitative reduction by linear regression analysis: -ΔPOCA = ΔOc–C2A = -ΔC2–7A = ΔCAA. Conclusion: Quantitative posterior reduction by individualized cage and adjusting ΔPOCA is feasible for treating BI with AAD.
-
Combination algorithm for cracked rotor fault diagnosis based on NOFRFs and HHR
Yang Liu,Yulai Zhao,Jiyuan Han,Qingyu Meng,Hongliang Yao 대한기계학회 2019 JOURNAL OF MECHANICAL SCIENCE AND TECHNOLOGY Vol.33 No.4
In this paper, a combination algorithm for diagnosing rotor crack fault is presented. Firstly, the nonlinear output frequency response functions (NOFRFs) are used to analyze the severity of crack damage in the rotor system qualitatively. The NOFRFs are obtained by processing the vibration signal through the nonlinear output frequency response functions. Further analysis of the NOFRFs can determine the crack depth qualitatively. Secondly, the position of the crack is then located using the crack position index (CPI) l based on the higher harmonic response (HHR) and the dynamic compliance matrix. The simulation and experimental results show that the G 2 (j2w F ) in NOFRFs is very sensitive to crack depth, and the crack position index (CPI) l can determine the shaft segment effectively where the crack is located. The advantage of this combination algorithm is that it can detect the crack faults by measuring the vibration signal of the cracked rotor at two speeds, which makes the measurement process more simplified and reduces the measurement time for real-time monitoring. At each speed only the vibration response of the two nodes need to be measured, which greatly reduces the number of sensor used in the measurement process and reduces the cost of monitoring. The combination algorithm can diagnose cracked rotor faults effectively and has certain application value in the diagnosis of cracked rotor fault.
연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
