DATCN: Deep Attention fused Temporal Convolution Network for the prediction of monitoring indicators in the tunnel

Junchen Ye,Bowen Du,Zhixin Zhang,Xuyan Tan,Wentao Li,Weizhong Chen 국제구조공학회 2022 Smart Structures and Systems, An International Jou Vol.30 No.6

The prediction of structural mechanical behaviors is vital important to early perceive the abnormal conditions and avoid the occurrence of disasters. Especially for underground engineering, complex geological conditions make the structure more prone to disasters. Aiming at solving the problems existing in previous studies, such as incomplete consideration factors and can only predict the continuous performance, the deep attention fused temporal convolution network (DATCN) is proposed in this paper to predict the spatial mechanical behaviors of structure, which integrates both the temporal effect and spatial effect and realize the cross-time prediction. The temporal convolution network (TCN) and self-attention mechanism are employed to learn the temporal correlation of each monitoring point and the spatial correlation among different points, respectively. Then, the predicted result obtained from DATCN is compared with that obtained from some classical baselines, including SVR, LR, MLP, and RNNs. Also, the parameters involved in DATCN are discussed to optimize the prediction ability. The prediction result demonstrates that the proposed DATCN model outperforms the state-of-the-art baselines. The prediction accuracy of DATCN model after 24 hours reaches 90 percent. Also, the performance in last 14 hours plays a domain role to predict the short-term behaviors of the structure. As a study case, the proposed model is applied in an underwater shield tunnel to predict the stress variation of concrete segments in space.

Renal surface reconstruction and segmentation for image‑guided surgical navigation of laparoscopic partial nephrectomy

Xiaohui Zhang,Xuquan Ji,Junchen Wang,Yubo Fan,Chunjing Tao 대한의용생체공학회 2023 Biomedical Engineering Letters (BMEL) Vol.13 No.2

real-time for laparoscopic image-guided navigation. The stereo vision method for intraoperative tissue 3D reconstructionhas the most potential for clinical development benefiting from its high reconstruction accuracy and laparoscopy compatibility. However, existing stereo vision methods have difficulty in achieving high reconstruction accuracy in real time. Also,intraoperative tissue reconstruction results often contain complex background and instrument information that preventsclinical development for image-guided systems. Taking laparoscopic partial nephrectomy (LPN) as the research object, thispaper realizes a real-time dense reconstruction and extraction of the kidney tissue surface. The central symmetrical Censusbased semi-global block stereo matching algorithm is proposed to generate a dense disparity map. A GPU-based pixel-bypixelconnectivity segmentation mechanism is designed to segment the renal tissue area. An in-vitro porcine heart, in-vivoporcine kidney and offline clinical LPN data were performed to evaluate the accuracy and effectiveness of our approach. The algorithm achieved a reconstruction accuracy of ± 2 mm with a real-time update rate of 21 fps for an HD image size of960 × 540, and 91.0% target tissue segmentation accuracy even with surgical instrument occlusions. Experimental resultshave demonstrated that the proposed method could accurately reconstruct and extract renal surface in real-time in LPN. Themeasurement results can be used directly for image-guided systems. Our method provides a new way to measure geometricinformation of target tissue intraoperatively in laparoscopy surgery.

Analysis on the Dynamic Responses of an Overlapped Circular Shield Tunnel under the Different Vibration Loads

Qixiang Yan,Junchen Zhang,Wenyu Chen,Chaofan Yao,Wenbo Yang,Hang Chen,Xirui Liu 대한토목학회 2020 KSCE JOURNAL OF CIVIL ENGINEERING Vol.24 No.10

At present, there are many studies on the dynamic response of overlapped tunnels, but most of them are through numerical simulation. Very few has been conducted by the experimental model research and frequency domain analysis. Combined with the model test and the numerical simulation, the dynamic response of the tunnel lining structure under the action of different train speeds and different tunnel clear distances are investigated, which can remedy the deficiencies in the relevant fields and verify the accuracy of numerical simulation results. The results show that as the train speed increases, the amplitude of the energy spectra of the vibration loads decrease significantly. The tunnel response at the sidewalls is smaller than that at the tunnel crown and at the invert in the lower tunnel. As the net distance increases, the amplitudes of the acceleration frequency spectrum and the energy spectra of the lower tunnel decrease, but with a diminishing rate. The dynamic coefficients of circumferential of the upper tunnel under a train load are larger than those in the longitudinal direction in the invert.

Dynamic Characteristics of Intersection Structure Consisting of Twin Shield Tunnels and a Transverse Passage

Qixiang Yan,Junchen Zhang,Wenyu Chen,Longxiang Ma,Cong Wu,Wen Zhang 대한토목학회 2019 KSCE JOURNAL OF CIVIL ENGINEERING Vol.23 No.11

The intersection structure, composed of twin shield tunnels and a transverse passage, is ubiquitous in the metros around the world. However, the dynamic characteristics of this kind of intersection structure have not been studied a lot yet. By carrying out the corresponding model tests and numerical simulations, the dynamic characteristics of this kind of intersection structure are studied in this paper, which is very helpful for the determination of the ground vibration from this kind of underground structure. The results show that the vibration of the transverse passage is more severe than the main tunnel, manifested that the frequency response function (FRF) of the transverse passage has greater magnitudes than that of the main tunnel at the locations with the same distance from the vibration source. The peak frequencies of the acceleration responses at different locations of the intersection structure under the moving train load are all located in the frequency band 44.9 − 56.1 Hz where the corresponding 1/3 octave band spectra of FRF have the largest values in the considered frequency band 31.5 − 250 Hz, indicating that the natural frequencies of the intersection structure in the frequency band 44.9~56.1 Hz have significant influences on its acceleration responses below 250 Hz induced by the moving train.

Study of Material Removal Behavior during Laser-assisted Ultrasonic Dressing of Diamond Wheel

Zhibo Yang,Shiyu Zhang,Junchen Hu,Zhen Zhang,Kaiqiang Li,Bo Zhao 한국정밀공학회 2020 International Journal of Precision Engineering and Vol.7 No.1

Laser-assisted ultrasonic dressing (LUD) of the removal behavior of diamond wheel material is investigated by simulation and experimental method. The finite element model of diamond wheel is constructed for simulation during LUD. The effect of parameters of LUD process on the dressing force is discussed according to the simulation results. LUD experiments of diamond wheels are carried out after obtaining optimization of parameter. The dressing force obtained from simulation and experiments are compared. It is found that the variation tendency of simulated dressing force is in agreement with the experimental result. This indicates that the simulation results can be effectively used for the selection of process’ parameters.

Spindle Spinel CoFeCoO4 Microparticles/rGO as an Oxygen Reduction and Oxygen Evolution Catalyst

Bowen Wang,Nian Tao,Junchen Liu,Hao Wang,Yinxiao Du,Hujiang Yang,Yonggang Wang,Kai Huang,Ru Zhang,Ming Lei 성균관대학교(자연과학캠퍼스) 성균나노과학기술원 2019 NANO Vol.14 No.4

The representative spinel-type materials AB2O4 (both A and B are transition metals) electrocatalysts for oxygen reduction reaction (ORR) and oxygen evolution reaction (OER) have been investigated and significant improvements have been achieved in the activity and durability for ORR and OER in the alkaline solution. But CoFeCoO4 was not explored widely like ZnCo2O4 (or NiCo2O4) as the ORR electrocatalyst for its relatively complicated atomic site occupation. CoFeCoO4 has a typical cubic spinel structure with Co2+ in the tetrahedron and Co3+ and Fe3+ in the octahedron. A mixture of Co3+ and Fe3+ in the B site makes the oxide have a wider overlap between transition metal 3d orbit and O 2p orbit, which can lead to an effective charge transfer in the rate-determining steps of ORR process and then enhance the ORR activity. The high electronic conductivity and specific surface area of rGO can accelerate charger transfer and provide more catalytic sites, which would contribute to a faster ORR process. In this work, the porous spindle CoFeCoO4 microparticles which were synthesized by hydrothermal technology, were assembled on the rGO surface to obtain the CoFeCoO4/rGO composite, which exhibited enhanced ORR activity and catalytic stability comparable to that of Pt/C. On the other hand, the OER catalytic activity of the prepared samples was also studied to explore the potential of CoFeCoO4/rGO as a bifunctional oxygen catalyst.

Analysis of Characteristics of Swirling Spray of the Ammonium Dinitramide (ADN)-Based Green Monopropellant

Jun Chen,Guoxiu Li,Tao Zhang 한국항공우주학회 2018 International Journal of Aeronautical and Space Sc Vol.19 No.4

Ammonium dinitramide (ADN) based green propellant is a promising alternative propellant for future space propulsion. Atomization of thruster plays an important role in the entire operation process. This paper describes the effect of swirl injection regarding tangential hole geometric parameter on the atomization characteristics of ADN-based green monopropellant. The experimental apparatus was prepared using a high-speed camera equipped with a macro lens and a Malvern laser particle size analyzer, and an injection device was designed. Characteristics features including particle-size distribution, spray cone, and breakup length of tangential hole number were recorded, and the effect of key parameters on spray processes was evaluated. The results show that the designed swirl injector completely achieved the atomization characteristics. With the increase in tangential hole number, the flow resistance increased, thus significantly affecting the atomization performance. The corresponding average particle size decreased. Moreover, a very large or small tangential hole number clearly affected the breakup length, spray cone angle, and average particle size. The optimum tangential hole diameter was 0.9 mm. The results are beneficial for the improvement of design structure of swirl nozzle based on ADN-based green monopropellant.

Sampling-based Event-triggered and Self-triggered Control for Linear Systems

Jun Chen,Yuan Fan,Chengxiao Zhang,Cheng Song 제어·로봇·시스템학회 2020 International Journal of Control, Automation, and Vol.18 No.3

This work considers the event-triggered and self-triggered control for linear systems with periodic sampling schemes. An event-triggered control using sampled states is proposed. The asymptotic stability of the closedloop system is guaranteed by a condition in terms of a linear matrix inequality. Moreover, a self-triggered control with sampling is presented and the next control task release time is predicted based on the current sampled data. It is noted that by introducing the periodic sampling scheme, Zeno behaviors can be naturally avoided in both of the algorithms. Finally, simulation results are provided to illustrate the theoretical effectiveness.