Self-learning drift control of automated vehicles beyond handling limit after rear-end collision

Vehicles involved in traffic accidents generally experience divergent vehicle motion,which causes severe damage.This paper presents a self-learning drift-control method for the purpose of stabilizing a vehicle’s yaw motions after a high-speed rear-end collision.The struck vehicle generally experiences substantial drifting and/or spinning after the collision,which is beyond the handling limit and difficult to control.Drift control of the struck vehicle along the original lane was investigated.The rear-end collision was treated as a set of impact forces,and the three-dimensional non-linear dynamic responses of the vehicle were considered in the drift control.A multi-layer perception neural network was trained as a deterministic control policy using the actor-critic reinforcement learning framework.The control policy was iteratively updated,initiating from a random parameterized policy.The results show that the self-learning controller gained the ability to eliminate unstable vehicle motion after data-driven training of about 60,000 iterations.The controlled struck vehicle was also able to drift back to its original lane in a variety of rear-end collision scenarios,which could significantly reduce the risk of a second collision in traffic.

Causes and typical control model of wind-drift sandy lands in abandoned channel of the Yellow River

The historical formation and development of the abandoned channel of the Yellow River is reviewed and its causes of formation and present condition of prevention and control are analyzed in this paper. Based on this analysis, some ideas about control, critical problems and countermeasures in the next period are proposed with two typical control models as examples. We suggest that in preventing and controlling the wind-drift sandy lands in the region, the emphasis should be to develop, with a greatly expanded effort, a recycling economy. This should realize a combination of two ideas, i.e. integrate combating desertification with a structural adjustment of agricultural and an increase in the income of farmers.

Numerical Simulation of Turret Moored Ship Performance in Variable Ice Drift Based on Heading Control

The frequent change in ice drift direction poses a significant challenge for turret moored ship in ice. Variability in ice drift is mainly caused by the winds and currents. To solve this problem, a new method with numerical simulation based on heading control is applied to reduce the risk of operation of The Arctic Tandem Offloading Terminal(ATOT),which includes an offloading icebreaker(OIB) moored to a submerged turret and a shuttle tanker moored at the stern of the OIB in this paper. An icebreaking tanker, MT Uikku, was modeled in a simulation program. Then the level ice load on the tanker was calculated with different ice thicknesses and drift speeds, after which a heading controller assisted with mooring system is used to simulate the horizontal motion of the tanker under the ice action.

植保无人机精准喷施方法研究综述

作为一种新兴农业技术,植保无人机以其高效、精准、灵活等特点在农作物疾病和虫害防治中具有重要意义。综述了植保无人机精准喷施方法的关键技术,包括植保无人机发展现状、路径规划算法、喷施器研究和漂移控制。通过对相关文献的分析和整理,总结了植保无人机路径规划算法的特点和应用情况,重点介绍了经典路归算法、遗传算法以及蚁群优化等元启发算法的优点和不足,以及喷施器研究和漂移控制研究的进展和挑战。最后,提出了未来研究的方向和建议,包括改进算法性能、优化路径规划策略、提高喷施器的精度和稳定性、优化漂移控制算法等。旨在为相关研究者提供全面的研究概览,推动植保无人机精准喷施技术的进一步发展和应用。

桶混助剂和剂型创新在农药雾滴飘移控制中的应用及研究进展

近年来,随着植保无人机施药技术的迅速发展,农药雾滴飘移引起的药害问题更加凸显。除了降低农药利用率,雾滴飘移还对周围环境造成污染,同时也危害人类健康。雾滴特性、药械参数和施药环境是影响农药雾滴飘移的重要因素,其中雾滴特性直接受到桶混助剂和农药剂型的影响。基于农药助剂和制剂研发应用过程中的理论积累和实践经验,笔者通过分析影响农药雾滴飘移的原因,综述了农药桶混助剂在农药防飘移技术中的研究进展,分析了农药剂型创新在防飘移技术中的潜在用途,并对该领域的发展前景进行展望,以期为通过筛选优良助剂和创新农药剂型来减少农药飘移、提高农药有效利用率提供参考和指导。

Shift control method for the local time at descendi ngnode based on sun-synchronous orbit satellite

This article analyzes the shift factors of the descending node local time for sun-synchronous satellites and proposes a shift control method to keep the local time shift within an allowance range. It is found that the satellite orbit design and the orbit injection deviation are the causes for the initial shift velocity, whereas the atmospheric drag and the sun gravitational perturbation produce the shift acceleration. To deal with these shift factors, a shift control method is put forward, through such methods as orbit variation design, orbit altitude, and inclination keeping control. The simulation experiment and practical application have proved the effectiveness of this control method.

纯电动后驱汽车横纵向漂移动力学研究

对车辆轮胎漂移极限工况的分析可以大幅提高自动驾驶车辆的横纵向控制能力以及驾驶安全性。基于UniTire的大滑移的附着表达能力优化了整车漂移的控制算法,并依据整车稳定控制原理和预期制动回正时间参数等,实现漂移结束后车辆快速恢复稳态直线行驶的轮缸目标压力的计算,通过DYNA4与Simulink在CANoe工控机平台进行了快速原型验证。结果表明,优化后的控制算法能使车辆快速进入漂移的横纵向平衡状态以及漂移结束后快速恢复直线行驶,且能达到控制的实时性要求。

基于PI闭环反馈的EtherCAT分布式时钟漂移补偿优化

接入工业总线的设备的增加会导致高延迟等同步性问题。基于EtherCAT对分布式时钟同步算法进行研究与分析,针对其在漂移补偿过程中存在补偿精度低的问题,提出了一种基于闭环反馈控制思想的动态漂移补偿算法。算法先利用定点数改进本地时钟,再利用PI控制调节漂移补偿值。最后搭建了测试平台,包括基于SOEM实现的主站与基于STM32+FPGA架构实现的从站,优化前后的算法分别在FPGA中实现。测试结果表明:定点数改进的本地时钟分辨率可以达到2^(-20) ns, PI闭环反馈优化后的漂移补偿算法可以将同步误差降低到25 ns之内,明显提高从站之间的同步性能。

磁场对脱手检测功能的影响与优化方法分析

阐述一种通过监控学习获取可信EPS零漂的方法,并将可信EPS零漂引入到脱手检测控制逻辑中。该方法有效地消除扭矩传感器零漂对脱手报警的影响,提高自动驾驶辅助系统脱手报警的准确率。

海安市蚕桑生产防中毒保安全的几点做法

近年来,随着工业化进程加快,环境中不明化学因子增多,养蚕风险加剧。另一方面,农业种植大户普遍应用无人机飞防治虫,药剂漂移引致蚕桑生产中毒现象频频发生,蚕桑生产安全问题突出。海安市政府办公室通过广泛培训宣传,开展技术指导,加强督查和执法处罚,加大考核奖惩等措施,有效控制农业治虫对蚕桑生产影响。在桑园治虫方面,按要求选用农药,按标准配制药液,防止农药残留影响养蚕安全。

Robust Adaptive Control of Nonholonomic Systems with Nonlinear Parameterization

全球适应的州的反馈控制策略与强壮的非线性的飘移和未知非线性的参数在锁住的形式为 nonholonomic 系统的一个类被介绍。一种参数分离技术被介绍把非线性的 parameterization nonholonomic 系统转变成一个象线性一样 parameterized nonholonomic 系统。然后，反馈支配设计被使用设计一个全球适应稳定控制器，切换的策略被开发消除 uncontrollability 的现象。建议控制器能保证那得到状态全球性集成到起源的所有系统，当另外的信号仍然保持围住时。模拟例子表明有效性和建议控制器的柔韧的特征。

Magnetic Sensorless Control of Plasma Position and Shape in a Tokamak

Magnetic sensorless sensing and control experiments with the plasma horizontal position have been carried out in the superconducting tokamak HT-7. The sensing is made to focus on the ripple frequency component of the power supply with thyristor and directly from them without time integration. There is no drift problem with the integrator of wagnetic sensors. Two kinds of control experiments have been carried out： to keep the position constant and swing the position in a triangular waveform, And magnetic sensorless sensing of plasma shape is discussed.

Simulation and Control of Turbulence at Tokamaks with Artificial Intelligence Methods

The control of turbulence at tokamaks is very complex problem.The idea is to apply the fuzzy Markovian processes and fuzzy Brownian motions as good approximation of general robust drift kinetic equation. It is obtained by using the artificial neural networks for solving of appropriate advanced control problem. The proof of the appropriate theorem is shown.

Optimal weakening and damping using polynomial control for seismically excited nonlinear structures

This paper presents an approach for the optimal design of a new retrofit technique called weakening and damping that is valid for civil engineering inelastic structures. An alternative design methodology is developed with respect to the existing ones that is able to determine the locations and the magnitude of weakening and/or softening of structural elements and adding damping while insuring structural stability. An optimal polynomial controller that is a summation of polynomials in nonlinear states is used in Phase I of the method to reduce the peak response quantities of seismically excited nonlinear or hysteretic systems. The main advantage of the optimal polynomial controller is that it is able to automatically stabilize the structural system. The optimal design of a shear-type structure is used as an example to illustrate the feasibility of the proposed approach, which leads to a reduction of both peak inter-story drifts and peak total accelerations.

地下矿山进路式采矿爆破参数优化研究及控制措施

某地下矿山主矿体赋存于闪长岩与砂页岩接触带部位,岩石节理裂隙比较发育,因矿石中含造泥矿物和鳞片状矿物以及软弱夹层,导致矿体稳固性较差。为确保开采过程中的安全,设计采用进路式尾砂充填采矿法,分为两个回采步骤,即一步骤先采矿房,待矿房回采结束并充填后进行二步骤回采矿柱,采取“隔三采一”的方式。进路爆破质量受工程地质条件、原爆破孔网参数不合理等因素影响,导致生产爆破中出现炮孔利用率低、炸药单耗偏高、巷道成型差、超欠挖现象严重、大块多以及巷道支护工作量大等问题。为解决采矿进路爆破过程中的安全问题,从掏槽方式、炮孔布置、炮孔深度、装药结构及起爆顺序等方面进行爆破方案优化,试验结果表明:参数优化后爆破效果明显改善,炮孔平均利用率由82.1%提高至92.6%,提高了10.5%;炸药平均消耗量由2.93 kg/m^(3)降低至2.00 kg/m^(3),降低了31.74%;半壁孔痕率平均在76%以上,进路断面超欠挖量也控制在10 cm以下,断面轮廓成型较好,岩石块度均匀。研究成果可为类似爆破工程提供参考。

双屈服点屈曲约束支撑-钢框架结构抗震性能研究

针对传统钢框架-屈曲约束支撑结构的薄弱层控制难题,本研究提出了一种面向结构最大层间变形控制和薄弱层控制双重需求的并联式双屈服点屈曲约束支撑。相比于已有双屈服点屈曲约束支撑,具有刚度和耗能能力利用率高的优点。基于某钢框架-支撑原型结构,设计了2个传统屈曲约束支撑案例和3个新型双屈服点屈曲约束支撑案例,通过对比各案例的关键地震响应,明确了新型支撑的结构最大变形控制效果和薄弱层控制效果。结果表明:罕遇地震作用下,相比于屈曲约束支撑,新型支撑的最大层间位移角峰值可降低6.2%~21.6%;表征薄弱层损伤集中程度的层间位移角集中系数分别由1.54和1.51最低降至1.29,绝大部分楼层具有了相近的位移角,且小于屈曲约束支撑结构,表明新型支撑引导了薄弱层的迁移,显著减轻了结构变形损伤集中问题。本研究的相关成果可为钢框架-支撑结构的地震响应控制提供参考。

高机动水下航行体运动控制技术研究

针对航行体水下高机动运动控制问题,建立基于水下航行体动力学方程的六自由度数学仿真模型,分析控制力和推进力对航行体水下机动过程的影响,提出小攻角机动和大攻角漂移机动两种弹道模式。仿真结果表明,实现小攻角机动控制力需求大,航行体运动速度高;漂移机动模式能够大幅降低控制力需求,弹道参数及稳定性受航行体运动速度影响显著,尽可能晚地施加推进力有利于姿态稳定控制,但航行体运动速度衰减较大。通过开展航行体水下机动实航试验,验证和确认了漂移机动模式的工程可实现性。

鄱阳湖水利枢纽船舶失控漂移建模方法

为精准设计和布设鄱阳湖水利枢纽防撞设施、配布相关导助航设施和安全警示标等。基于船舶失控漂移运动方程和蒙特卡洛算法,针对鄱阳湖水利枢纽设施的分布特征,提出鄱阳湖水利枢纽船舶失控漂移建模方法,对船舶失控后在水利枢纽内的运动轨迹空间分布进行数值计算,判断船舶失控后是否会碰撞水利枢纽,并精确计算出不同工况下船舶失控后对水利枢纽的碰撞概率。通过Python建模,计算出在鄱阳湖水利枢纽上、下游船闸引航道口门各向外约1km的通航水域范围内,碰撞枢纽工程的平均频率为7~13次/千年。本方法具有较强的针对性,对鄱阳湖水利枢纽的安全防护具有指导意义。

基于ZYNQ的磁悬浮天平测量系统设计与实现

针对磁悬浮天平系统存在设计结构复杂,造价昂贵的局限性同时测量数据漂移,长期测量的精度波动以及依赖于PC端来处理数据的问题,提出了基于ZYNQ的磁悬浮天平测量系统设计,设计运动控制器保证天平高精度定位的稳定性以减小天平托盘位置变化对驱动电流测量的影响,同时设计的小型ZYNQ系统完成AD、DA接口传输数据并在soc中完成数据的处理,回避了传统测量系统依赖PC端处理数据且受到PC端供电电源波动噪声而对测量精度产生的影响等缺点,以及通过修正算法抑制长时间测量所可能产生的数据漂移。实验结果表明:基于ZYNQ的磁浮天平测量系统优化了设计结构且造价低的同时保证了磁悬浮天平测量精度,有效抑制长时间测量带来的噪声和漂移。

Deep reinforcement learning-based drift parking control of automated vehicles

Drift parking usually requires precise control of a vehicle by a professional driver,which can reflect the performance of the vehicle under critical conditions.The obstacles to implementing this action include the high coupling between the longitudinal and lateral states,the high precision required for the vehicle initial state when the drift is triggered,and the difficulty in determining the reference state variables in the drift process.A two-segment drift parking control system is proposed in this paper.In the approaching control segment,the vehicle achieves the drift-triggered vehicle speed and pose,which relies on a pathtracking algorithm based on linear time-varying model predictive control.In the drifting control segment,the deep reinforcement learning algorithm twin-delayed deep deterministic policy gradient is creatively introduced to the controller design.It solves the precise vehicle motion control problem under the condition of the rear wheels having locked brakes.Through various simulations,the superiority and robustness to different initial conditions and abrupt changes in the parking space are verified.The effectiveness of the proposed control system is verified by a ground test.