基于深度强化学习的智能船舶航迹跟踪控制

[目的]智能船舶的航迹跟踪控制问题往往面临着控制环境复杂、控制器稳定性不高以及大量的算法计算等问题。为实现对航迹跟踪的精准控制,提出一种引入深度强化学习技术的航向控制器。[方法]首先,结合视线(LOS)算法制导,以船舶的操纵特性和控制要求为基础,将航迹跟踪问题建模成马尔可夫决策过程,设计其状态空间、动作空间、奖励函数;然后,使用深度确定性策略梯度(DDPG)算法作为控制器的实现,采用离线学习方法对控制器进行训练;最后,将训练完成的控制器与BP-PID控制器进行对比研究,分析控制效果。[结果]仿真结果表明,设计的深度强化学习控制器可以从训练学习过程中快速收敛达到控制要求,训练后的网络与BP-PID控制器相比跟踪迅速,具有偏航误差小、舵角变化频率小等优点。[结论]研究成果可为智能船舶航迹跟踪控制提供参考。     

频繁爆破下隧道内振动传播的数值研究

为揭示频繁爆破下隧道内振动传播衰减规律,文章以蒙华铁路段家坪隧道为工程背景,利用LS-DY NA建立了三维隧道模型,模拟分析了多次爆破下隧道内近区和中远区的振动传播规律。结果表明,质点垂向峰值振速随距离和爆破次数的增大而减小,少数振速有增大的现象;近区振动衰减较快,中远区振动衰减比近区缓慢;中远区a值比近区至少小12.5%,但整体上二者的a值随爆破作用次数的增加呈缓慢上升趋势;系数K随爆破作用次数的增加而降低,近区K值降低速率普遍大于中远区,且近区K值比中远区至少大29.1%;频繁爆破下,中远区比近区较符合萨道夫斯基经验公式。     

装配式综合管廊在地铁车辆基地中的发展及应用探讨

装配式综合管廊在地铁车辆基地中的应用尚处于探索阶段,为了将装配式综合管廊与地铁车辆基地有效结合,提出一种适合于地铁车辆基地的装配式综合管廊解决方案。系统研究车辆基地发展装配式管廊的可行性,从目前车辆基地综合管廊建设和运营现状出发,提出了单仓和双仓两种管廊断面模式。通过应用BIM技术对管线进行碰撞检查和节点深化设计,并在管廊设计中考虑相关附属配套设施。工程实践证明,装配式综合管廊比现浇管廊土建成本减少4%,工期缩短45%,从安全、环保、质量、工期、场地、运维等多方面具有明显优势,应大力推广。下阶段应从标准化设计、施工方面对装配式管廊进行系统研究并争取尽快应用到实际项目中。     

Time-domain coupled dynamic simulation for SFT-mooring-train interaction in waves and earthquakes

In this study, Submerged Floating Tunnel (SFT)-mooring-train coupled dynamics is solved in the time domain to investigate their dynamic and hydro-elastic interactions under wave and earthquake excitations. The SFT is modeled by the rod-FE (finite element) theory, and it is connected to mooring lines through dummy-connection-mass and linear and rotational springs. A 3D rigid-multi-body dynamic model is developed for train dynamics that consists of seven rigid bodies. The tunnel-train interaction is taken into consideration based on the wheel-rail correspondence assumption and the simplified Kalker linear creep theory. The developed computer simulation program is validated through comparisons with commercial programs and published results when possible. In the case of earthquake-induced dynamics of the coupled system, the effects of soil conditions, tunnel length, mooring interval, seismic-wave propagation, and seaquake are investigated. The magnitudes of the SFT downward motions induced by the moving train are small compared with the motions induced by earthquakes. The earthquake causes transient SFT responses especially at their lowest wet natural frequencies while high-frequency motions are induced by seaquake effect. Structural damping and seismic propagation play an important role in dynamic responses. The interaction of the tunnel and moving train is also evaluated for various train speeds in terms of the derailment and offload factors and riding-comfort criterion. For the given SFT and train designs, the offload factor and riding-comfort criterion can slightly exceed their limits at certain earthquake conditions with the speed as high as 70 m/s, which can be adjusted by reducing train speed.     

基于模糊综合评价法的城市综合管廊结构健康评价方法研究

为解决城市综合管廊结构健康状况评估结果无法量化和指导运维的问题，通过分析模糊综合评价理论在交通隧道结构健康评价方法研究中的应用，依照类比思想，利用该理论建立城市综合管廊结构健康状况评价体系。首先，依据有关养护规定和调研结果，基于不同需求分别建立管廊结构的本体完好状况和本体结构状况评价指标体系； 其次，以交通隧道和综合管廊养护经验为基础，划分各指标的分级判定标准； 然后，采用层次分析法，计算评价指标的权重分配； 最后，采用柯西分布型隶属函数和矩阵型隶属函数确定各指标的隶属度，建立一级和二级模糊综合评价模型，赋予评价向量中各评语相应分值，将评价向量单值化，判定管廊结构健康状况。采用所提出的评价方法应用于实际工程，所得评价结果与经验评判得到的结果相同。     

提高TSP探测精度的途径

TSP作为目前最先进的隧道地质超前预报探测仪器，得到了广泛的应用。但是由于在现实中存在各种问题，从而导致该仪器的预测精度受到了极大限制，主要阐述如何提高其预测精度，更好地为隧道的建设服务。     

流线型钢箱梁涡激振动机理与气动控制措施

以某主跨390 m的独塔流线型钢箱梁斜拉桥为工程依托，采用风洞试验与计算流体动力学（Computational Fluid Dynamics，CFD）相结合的方法对流线型钢箱梁涡激振动机理与气动控制措施进行研究。首先，采用几何缩尺比为1∶30的主梁节段模型进行主梁涡振性能与气动控制措施优化研究；其次，采用CFD方法对主梁涡振响应进行流固耦合计算，将Newmark-β算法嵌入ANSYS Fluent用户自定义函数（User Defined Functions，UDFs）实现主梁结构振动响应求解，同时结合动网格技术实现主梁断面流固耦合分析；并根据判断条件来检索箱梁壁面上的网格单元，以获得主梁断面振动过程中的表面压力，然后结合主梁结构振动响应、表面压力以及流场特征等对主梁涡激振动机理进行分析。结果表明：该桥主梁原设计方案存在涡激共振现象，将梁底检修车轨道内移120 cm可有效抑制主梁涡振响应；主梁涡激振动响应的数值模拟结果与风洞试验结果吻合较好；检修车轨道内移120 cm后主要改变了箱梁下表面平均压力系数分布特性，且箱梁表面各测点脉动压力卓越频率不一致，有效减小了主梁涡激振动响应；流线型箱梁靠近迎风侧的“被动区域”对结构涡振响应贡献较小，背风侧“驱动区域”发生周期性旋涡脱落是影响流线型箱梁涡振的主要因素。     

高速公路山岭隧道设计阶段安全风险评估

通过定性分析与定量分析相结合的方法,利用专家分析法和层次分析法研究各风险控制因素与权值.从技术角度考虑设计方案中各种不确定因素对后续施工及运营造成的不利影响,并得出相关结论,对于指导实际工作有一定的意义.     

Key technologies of ship remote control system in inland waterways under ship-shore cooperation conditions北大核心CSCD

［Objective ］ To meet the requirements of remotely controlling ship in curved, narrow and crowded inland waterways, this paper proposes an approach that consists of CNN-based algorithms and knowledge based models under ship-shore cooperation conditions. ［Method］On the basis of analyzing the characteristics of ship-shore cooperation, the proposed approach realizes autonomous perception of the environment with visual simulation at the core and navigation decision-making control based on deep reinforcement learning, and finally constructs an artificial intelligence system composed of image deep learning processing, navigation situation cognition, route steady-state control and other functions. Remote control and short-time autonomous navigation of operating ships are realized under inland waterway conditions, and remote control of container ships and ferries is carried out. ［Results］The proposed approach is capable of replacing manual work by remote orders or independent decision-making, as well as realizing independent obstacle avoidance, with a consistent deviation of less than 20 meters. ［Conclusions］The developed prototype system carries out the remote control operation demonstration of the above ship types in such waterways as the Changhu Canal Shenzhou line and the Yangtze River, proving that a complete set of algorithms with a CNN and reinforcement learning at the core can independently extract key navigation information, construct obstacle avoidance and control awareness, and lay the foundation for inland river intelligent navigation systems. © 2022 Journal of Clinical Hepatology. All rights reserved.     

新建隧道下穿多座隧道施工技术

以渝黔引入贵阳枢纽铁路龙宝冲隧道下穿6座已建及在建隧道工程为例,结合现场,详细分析、介绍了下穿隧道施工方案、原则、施工方法;提出了新建铁路隧道近距离下穿隧道交叉点附近施工爆破控制、防护方案,以及新建、既有隧道的监控量测、超前地质预报、安全性评估与评价等施工技术;解决了下穿隧道施工中既保证新建隧道施工安全,又保证既有隧道不受影响的问题。