中深孔爆破一次成井技术研究与应用

目前中深孔爆破一次成井普遍存在断面小、深度低的特点。一般深度都控制在12 m以内，20 m左右一次爆破成型的盲、天溜井案例较少，且多为失败案例。但随着科技进步，设备更新，开采分段逐渐严格，天溜井施工工艺要求也逐渐增大。为保证中深孔爆破的安全与高效，试验、研究中深孔爆破一次成井技术，从爆破设计、参数、设备选型等方面，实施了一种高效的中深孔爆破一次成井实例，对一次成井施工技术的研究具有重要意义。     

Combined freeze-sealing and New Tubular Roof construction methods for seaside urban tunnel in soft ground

Construction of seaside urban tunnels is significantly difficult due to the densely adjacent buildings and underground facilities in conjunction with unfavourable geological conditions. For this, this paper investigates the construction methods used for Gongbei Tunnel, which is a typical seaside tunnel connecting Hong Kong-Zhuhai-Macau Bridge in China. The construction methods and stability of the undercutting section will be focused. In the tunnel section of interest, dozens of thick steel tubes are jacked into the soft soil, and freeze-sealing method is applied to form a thick water-proofing wall. In this study, the combined freezing and New Tubular Roof (NTR) method are simulated by thermo-mechanical coupling analysis. The temperature field obtained in the freezing process indicates that the thickness of frozen wall grows approx. 2.0 m after 50 days of freezing. Besides, the stability of the surrounding ground and supporting structures in the bench-cutting stage are also investigated. Then the thawing process is simulated and associated suggestions for post-grouting to prevent excessive thawing settlement are proposed. The numerical results show that the tunnel is stable and the influence of tunnel excavation on adjacent buildings is within the permissible range. It also shows that the designed construction methods can be used to adequately meet safety and stability standards when adopting the proposed construction and supporting system.     

基于并行跟踪检测框架与深度学习的目标跟踪算法

在空地协同背景下，地面目标的移动导致其在无人机视角下外观会发生较大变化，传统算法很难满足此类场景的应用要求。针对这一问题，提出基于并行跟踪和检测（PTAD）框架与深度学习的目标检测与跟踪算法。首先，将基于卷积神经网络（CNN）的目标检测算法SSD作为PTAD的检测子处理关键帧获取目标信息并提供给跟踪子；其次，检测子与跟踪子并行处理图像帧并计算检测与跟踪结果框的重叠度及跟踪结果的置信度；最后，根据跟踪子与检测子的跟踪或检测状态来判断是否对跟踪子或检测子进行更新，并对图像帧中的目标进行实时跟踪。在无人机视角下的视频序列上开展实验研究和对比分析，结果表明所提算法的性能高于PTAD框架下最优算法，而且实时性提高了13%，验证了此算法的有效性。     

Experimental study on the effect of lateral concentrated smoke extraction on smoke stratification in the longitudinal ventilated tunnel

Smoke is the main cause of death in tunnel fires. It is one of the important measures to maintain smoke stratification in the early stage of tunnel fire. This article focused on experimentally studying the combined effect of lateral concentrated smoke extraction and longitudinal ventilation on the smoke stratification, which never be revealed before. The velocity of the smoke layer and air layer, vertical temperature distribution, and the flow patterns of the smoke were measured. It was found that the longitudinal ventilation and lateral concentrated smoke extraction would affect the flow of the smoke and change the shear velocity between the smoke layer and air layer, then, the patterns of the smoke layer will be affected. And the flow patterns with Froude (Fr) number can be classified into three categories: (a)Fr < 0.6 , with stable smoke stratification; (b) 0.6 < Fr < 0.85 , with a stable smoke stratification but the blurring interface; and (c) Fr > 0.85 , the smoke layer is completely unstable. The result can provide a reference for ventilation design of immersed tube tunnels.     

Research on image segmentation of Miao costume patterns based on the RSKP-UNet model北大核心CSCD

The Miao nationality is the sixth largest ethnic group in China which has a history of thousands of years. It has created a unique material culture and spiritual culture in its development process and the Miao costume is a highly condensed collection of the material and spiritual culture of the Miao nationality. As one of the unique symbols of Miao culture the Miao costume has profound cultural heritage and cultural connotations. The patterns of the Miao costume are particularly eye-catching as they not only symbolize the wisdom of the Miao people in thousands of years of production and life but also symbolize the pursuit of the good spirit of the Miao people. However under the impact of modern pop culture and foreign culture these cultural symbols are gradually disappearing. In order to protect and inherit them the Miao costume pattern segmentation has become the most important work. However the Miao costume pattern segmentation is quite difficult. At present there are few studies on the extraction classification identification and preservation of the features of Miao costume pattern segmentation. With the excellent segmentation performance of the U-Net model and the advantages of easy deployment the paper improves the basic structure of the U-Net model and proposes a Miao costume pattern segmentation algorithm based on the RSKP-UNet Residual Selective-Kernel Parallel U-Net model. The algorithm adds Residual modules in the encoder part of the U-Net model to improve the feature extraction capability of the model and embeds the SKNet modules and ParNet modules in the decoder part to enhance the feature expression capability of the model. The paper uses evaluation metrics to measure the segmentation performance of the model and compares it with four segmentation models based on deep learning. The paper not only combines the current research focus-deep learning and attention mechanism but also introduces the Lovász-hinge loss function to effectively solve the problem of class imbalance in the Miao costume patterns. The RSKP-UNet model is better than other models in various segmentation indicators. Compared with the benchmark model U-Net the Dice coefficient IoU precision recall and accuracy are improved by 6. 98% 11. 07% 2. 89% 6. 75% and 3. 92% . The segmentation algorithm proposed in this paper realizes the extraction of the element content of the Miao costume patterns through image segmentation of Miao costume patterns which can be used to build the Miao costume pattern database in this way thus helping designers relevant researchers and organizations to provide research foundation and completing the protection and inheritance of the Miao costume culture. The paper also provides some reference for the segmentation research of other minority costume patterns. © 2022 Authors. All rights reserved.     

地下输水隧洞围岩稳定监测系统设计研究

在地下隧洞施工输水整个环节中,施工环境复杂多变。由于地质岩体结构应力、地下水以及岩体力学构造等各方面的不确定、不稳定因素的影响极大,如果仅依靠传统经验来进行管理,已经不符合现代化管理的最基本要求,也无法达到标准化管理。文章首先阐述了地下输水隧洞围岩稳定监测系统设计的目的,然后对设计输水隧洞围岩稳定监测系统进行了分析,以便及时正确掌控地下输水的隧洞围岩发展状态,保证隧洞施工的顺利完成。     

Influences of flow rate and baffle spacing on hydraulic characteristics of a novel baffle dropshaft

Due to limited flow capacity and the instability of the asymmetric structure of traditional baffle dropshafts, a novel baffle dropshaft with a symmetric structure, adopting the construction shield well directly, is proposed for large-range flow discharge in deep tunnel drainage systems. In this study, a two-phase flow field of the novel baffle dropshaft with three different baffle spacings was simulated at seven different flow rates with a three-dimensional (3D) numerical model verified with experiments, to study hydraulic characteristics of this novel baffle dropshaft. The results show that the novel baffle dropshaft has a remarkable energy dissipation effect. Baffle spacing of the novel baffle dropshaft has a greater effect on flow patterns and baffle pressure distributions than the comprehensive energy dissipation rate. Flow rate is a critical issue for the selection of baffle spacing in the design. Some guidance on baffle spacing selection and structure optimization for the application of this novel baffle dropshaft in deep tunnel drainage systems is proposed.     

基于改进Faster R-CNN及YOLO的大角度车牌识别算法

随着大数据时代的到来,智慧城市等一系列概念的提出,人工智能开始在城市各个角落得到广泛应用。其中,车牌识别作为城市道路交通重要的一环,也取得了重大突破。基于深度学习的车牌识别一经提出,各类算法应用于车牌检测及识别上,对比于传统的车牌识别,大大提高了识别的速率和准确率。然而,在非限制条件下,如大角度车牌识别准确率仍有提升的空间。提出了一种改进的FasterR-CNN与YOLO的深度学习车牌识别算法,将对大角度下的车牌识别准确率达到了99.7%。由于是轻量型的框架,为后续的移动设备部署工作提供了便利。     

Multi-View Multi-Modal Head-Gaze Estimation for Advanced Indoor User Interaction

Gaze estimation is one of the most promising technologies for supporting indoor monitoring and interaction systems. However, previous gaze estimation techniques generally work only in a controlled laboratory environment because they require a number of high-resolution eye images. This makes them unsuitable for welfare and healthcare facilities with the following challenging characteristics: 1) users’ continuous movements, 2) various lighting conditions, and 3) a limited amount of available data. To address these issues, we introduce a multi-view multi-modal head-gaze estimation system that translates the user’s head orientation into the gaze direction. The proposed system captures the user using multiple cameras with depth and infrared modalities to train more robust gaze estimators under the aforementioned conditions. To this end, we implemented a deep learning pipeline that can handle different types and combinations of data. The proposed system was evaluated using the data collected from 10 volunteer participants to analyze how the use of single/multiple cameras and modalities affect the performance of head-gaze estimators. Through various experiments, we found that 1) an infrared-modality provides more useful features than a depth-modality, 2) multi-view multi-modal approaches provide better accuracy than single-view single-modal approaches, and 3) the proposed estimators achieve a high inference efficiency that can be used in real-time applications.