Multi-objective Stability Control Algorithm of Heavy Tractor Semi-trailer Based on Differential Braking

Rollover and jack-knifing of tractor semi-trailer are serious threats for vehicle safety, and accordingly active safety technologies have been widely used to reduce or prevent the occurrence of such accidents. However, currently tractor semi-trailer stability control is generally only a single hazardous condition (rollover or jack-knifing) control, it is difficult to ensure the vehicle comprehensive stability of various dangerous conditions. The main objective of this study is to introduce a multi-objective stability control algorithm which can improve the vehicle stability of a tractor semi-trailer by using differential braking. A vehicle controller is designed to minimize the likelihood of rollover and jack-knifing. First a linear vehicle model of tractor semi-trailer is constructed. Then an optimal yaw control for tractor using differential braking is applied to minimize the yaw rate and lateral acceleration deviation of tractor, as well as the hitch articulation angle of tractor semi-trailer, so as to improve the vehicle stability. Second a braking scheme and variable structure control with sliding mode control are introduced in order to achieve the best braking effect. Last Fishhook maneuver is introduced to the active safety simulation and the active control system effect verification. The simulation results show that multi-objective stability control algorithm of semi-trailer could improve the vehicle stability significantly during the transient maneuvers. The proposed multi-objective stability control algorithm is effective to prevent the vehicle rollover and jackknifing.

Design andtwo-objective simultaneous optimization of torque controller for switched reluctance motor in electric vehicle

In order to reduce the torque ripple,increase the average torque and optimize the drive performance of the switched reluctance motor (SRM),the nonlinear dynamic model of SRM is established in the MATLAB /Simulink environment.The effects of the turn-on and turn-off angles are investigated by the simulation results of the dynamic model,and the function is made among the rotor speed,turn-on angle and turn-off angle.To optimize the torque dynamic performance,the two-objective simultaneous optimization function is proposed by two weight factors.And the optimized turn-on and turn-off angles as functions of rotor speed are developed by using the simultaneous optimization method.Then the optimized torque controller is designed based on the optimized turn-on and turn-off angles.The simulation results show that the optimized torque controller designed in this paper can effectively reduce the torque ripple and increase the average torque,and optimize the torque dynamic performance of the SRM.

The multi-objective optimal control with X-Q adaptive controller

This paper proposes a new type of nonlinear controllers and a large phase angle allowance design method based on the multi-objective optimal control system. With the proposed method, the performance of the system becomes better than that of the original system. Then, an example of the radar servo system is designed with a large phase angle allowance multi-objective optimal design method. Finally, the performance based on computer simulation demonstrates that the multi-objective optimal system is superior to linear optimal systems.

A Brief Tour on Exotic Control Objectives in Robotics

Formulation of control objectives is a key issue in automatic control systems design. Although at first sight the desired goal （control objective） of a control system seems to be a trivial and obvious matter, for effectiveness of some high level robotic tasks, unusual exotic control objectives may be required. This paper presents a review of some exotic control objectives useful in robotics, such as velocity field control objective and range control objective. The paper also proposes a novel confinement control objective. The usefulness of these exotic control objectives may appear in safe robot-human interaction and self-protection of robots against collisions.

Aircraft Landing Gear Control with Multi-Objective Optimization Using Generalized Cell Mapping

This paper presents a numerical algorithm tuning aircraft landing gear control system with three objectives,including reducing relative vibration, reducing hydraulic strut force and controlling energy consumption. Sliding mode control is applied to the vibration control of a simplified landing gear model with uncertainty. A two-stage generalized cell mapping algorithm is applied to search the Pareto set with gradient-free scheme. Drop test simulations over uneven runway show that the vibration and force interaction can be considerably reduced, and the Pareto optimum form a tight range in time domain.

A multi-objective optimal PID control for a nonlinear system with time delay

It is generally difficult to design feedback controls of nonlinear systems with time delay to meet time domain specifications such as rise time, overshoot, and tracking error. Furthermore, these time domain specifications tend to be conflicting to each other to make the control design even more challenging. This paper presents a cell mapping method for multi-objective optimal feedback control design in time domain for a nonlinear Duffing system with time delay. We first review the multi-objective optimization problem and its formulation for control design. We then introduce the cell mapping method and a hybrid algorithm for global optimal solutions. Numerical simulations of the PID control are presented to show the features of the multi-objective optimal design. @ 2013 The Chinese Society of Theoretical and Applied Mechanics. [doi：10.1063/2.1306306]

Tufting Carpet Machine Information Model Based on Object Linking and Embedding for Process Control Unified Architecture

In view of the lack of research on the information model of tufting carpet machine in China,an information modeling method based on Object Linking and Embedding for Process Control Unified Architecture(OPC UA)framework was proposed to solve the problem of“information island”caused by the differentiated data interface between heterogeneous equipment and system in tufting carpet machine workshop.This paper established an information model of tufting carpet machine based on analyzing the system architecture,workshop equipment composition and information flow of the workshop,combined with the OPC UA information modeling specification.Subsequently,the OPC UA protocol is used to instantiate and map the information model,and the OPC UA server is developed.Finally,the practicability of tufting carpet machine information model under the OPC UA framework and the feasibility of realizing the information interconnection of heterogeneous devices in the tufting carpet machine digital workshop are verified.On this basis,the cloud and remote access to the underlying device data are realized.The application of this information model and information integration scheme in actual production explores and practices the application of OPC UA technology in the digital workshop of tufting carpet machine.

Modelling and Multi-Objective Optimal Control of Batch Processes Using Recurrent Neuro-fuzzy Networks

In this paper, the modelling and multi-objective optimal control of batch processes, using a recurrent neuro-fuzzy network, are presented. The recurrent neuro-fuzzy network, forms a ＂global＂ nonlinear long-range prediction model through the fuzzy conjunction of a number of ＂local＂ linear dynamic models. Network output is fed back to network input through one or more time delay units, which ensure that predictions from the recurrent neuro-fuzzy network are long-range. In building a recurrent neural network model, process knowledge is used initially to partition the processes non-linear characteristics into several local operating regions, and to aid in the initialisation of corresponding network weights. Process operational data is then used to train the network. Membership functions of the local regimes are identified, and local models are discovered via network training. Based on a recurrent neuro-fuzzy network model, a multi-objective optimal control policy can be obtained. The proposed technique is applied to a fed-batch reactor.

Method of Designing Missile Controller Based on Multi-Objective Opti mization

A method of designing robust controller based on genetic algorithm is presented in order to overcome the drawback of manual modification and trial in designing the control system of missile. Specification functions which reflect the dynamic performance in time domain and robustness in frequency domain are presented, then dynamic/static performance, control cost and robust stability are incorporated into a multi-objective optimization problem. Genetic algorithm is used to solve the problem and achieve the optimal controller directly. Simulation results show that the controller provides a good stability and offers a good dynamic performance in a large flight envelope. The results also validate the effectiveness of the method.

Applying Object-oriented Simulation to the Development of FMS Control Software

The approach of control software development based on simulation is discussed. A library of object classes for a flexible manufacturing system(FMS) simulation has been developed using the technology of object-oriented programming. Using the library, the simulation software of a FMS which has the same manufacturing logic with the FMS control system can be easily constructed. A new approach in the development of FMS control software based on software reuse and an emulator of the blade FMS control system for testing control software have also been developed.

机器学习驱动锅炉燃烧优化技术的现状与展望

伴随可再生能源发电装机容量快速增加,深度调峰过程中负荷多变、燃烧失稳等不稳定工况对火电机组的燃烧优化控制提出了更高要求,快速发展的人工智能技术与深度学习算法为锅炉参数预测建模及优化提供了重要手段。在机器学习算法方面,总结了特征筛选与建模算法的研究现状,提出了传统统计学方法与线性降维方法的科学解释性较差且不能很好地辨识高维数据,结合深度学习算法的特征筛选方法在处理复杂的火电机组数据时优势更明显;对比了多种神经网络在NO_(x)排放浓度建模中的优缺点,其中长短期记忆神经网络与卷积神经网络在处理时序数据时效果更好、集成模型通过组合不同学习器的优势可提高整个模型的泛化能力和鲁棒性。在预测模型的应用方面,通过对SCR脱硝系统建立预测模型可以方便运行人员模拟并修正可调参数,同时作为软测量手段监测燃烧系统运行状态;引入NO_(x)排放浓度预测模型的前馈控制和模型预测控制等先进控制手段可有效改善火电机组传统PID控制效果较差的问题;在多目标优化中NO_(x)脱除效率通常与锅炉效率或脱硝成本共同作为优化目标,以期实现经济效益与社会效益的和谐统一。

约束非线性系统理想点多目标安全预测控制

考虑具有状态和控制约束的仿射非线性系统多目标安全控制问题,本文提出一种保证安全和稳定的多目标安全模型预测控制(MOSMPC)策略.首先通过理想点逼近方法解决多个控制目标的冲突问题.其次,利用控制李雅普诺夫障碍函数(CLBF)参数化局部控制律,并确定系统不安全域.在此基础上,构造非线性系统的参数化双模控制器,减少在线求解模型预测控制(MPC)优化问题的计算量.进一步,应用双模控制原理和CLBF约束,建立MOSMPC策略的递推可行性和闭环系统的渐近稳定性,并保证闭环系统状态避开不安全域.最后,以加热系统的多目标控制为例,验证了本文策略的有效性.

面向对象技术的智能插秧机控制系统设计研究

以插秧机智能控制系统为研究对象,基于面向控制对象技术设计一种无人驾驶插秧机智能控制系统,并在水泥路面和水田两种不同环境中对插秧机进行性能试验测试。试验结果表明:在水泥路面上插秧机行进过程最大横向偏差小于50mm,最大航向偏差小于2°;在水田内插秧机行进过程最大横向偏差小于60mm,最大航向偏差小于3°,表明智能控制系统在使用过程中具有较高的可靠性和稳定性。

基于ASP-SAC算法的列车自动驾驶速度控制

随着经济建设的绿色转型以及人工智能的快速发展,城市轨道交通已成为居民日常出行的重要方式,在保障安全性、高效性和准点性的前提下,列车运行的节能性和舒适性需求也越来越被关注。合理的运行策略能够有效实现多种目标需求下的列车自动驾驶速度控制,强化学习作为一种智能决策方法,能够有效解决这一控制问题。首先,通过综合分析技术、安全性和乘客体验等方面的因素,基于专家经验动作划分和状态信息熵将软演员-评论家(SAC)改进为动作状态经验优先软演员-评论家(ASP-SAC)方法,用于研究列车自动驾驶速度控制问题。其次,将问题马尔可夫形式化,搭建了列车运行环境,确定了状态空间、动作空间以及基于目标控制的奖励函数。最后,以北京地铁亦庄线的一段区间数据为例进行试验,对ASP-SAC方法进行验证并与其他一些算法在相同环境下进行性能优劣比较。研究结果表明:该方法对于多目标控制需求下的列车自动驾驶速度控制问题具有可行性,与未改进前相比算法效率提高22.73%,与PPO算法相比提高29.17%,改进效果良好。同时,列车运行时在安全性、舒适性无误的情况下,准时性、精确性和节能性都强于SAC、DQN、PPO以及PID算法,其中能耗分别减少3.64%、5.62%、4.38%、7.35%,控制效果良好。此外,该方法亦具备鲁棒性,在列车自动驾驶速度控制方面具有一定的优越性和可参考性。

基于集合经验模态分解和多目标遗传算法的火-多储系统调频功率双层优化

针对分布于区域电网不同网络节点的多座储能电站参与电网调频功率调度问题,该文提出一种基于集合经验模态分解(EEMD)和多目标遗传算法(MOGA)的火-多储系统调频功率双层优化策略。该策略包含火-储调频功率优化层和多储能电站调频功率优化层:上层计及火-储调配资源各自优势及剩余调频能力,构建火-储调频功率优化分配模型,完成火-储调频功率的分配;下层引入关于调频成本和荷电状态(SOC)的自适应权重系数,以调频成本最低和SOC均衡为优化目标,完成调频功率在多储能电站之间的分配。仿真结果表明,所提策略可以提升区域电网调频效果并降低调频成本,均衡控制多个储能电站的调频成本和SOC,可以防止经济性较好的储能电站长期处于SOC越限边缘状态,提升储能电站参与调频的积极性和可持续性。

计及IGBT结温约束的光伏高渗透配电网无功电压优化控制策略

光伏电源参与配电网无功电压调节是提升光伏高渗透配电网运行经济性和可靠性的有效手段,但光伏电源提供无功支撑会使得光伏电源IGBT最大结温升高、结温波动加剧,进而影响光伏电源和配电网的安全稳定运行。为此,该文提出一种计及IGBT结温约束的光伏高渗透配电网无功电压优化控制策略。首先,利用CatBoost算法计算IGBT结温,提高了IGBT结温计算效率,避免了传统结温算法对IGBT热模型参数的依赖;然后,建立考虑IGBT结温约束的有源配电网多目标无功优化模型,利用二分法求解IGBT结温约束下的光伏电源最大输出功率,实现了IGBT结温约束向二阶锥约束的转换;最后,利用IEEE33节点典型配电系统验证了所提策略在光伏高渗透配电网无功电压优化、光伏电源运行可靠性提升方面的有效性,并提出了综合考虑配电网网损、光伏电源可靠性的光伏电源IGBT结温限值整定原则。

考虑模糊多目标优化的风电场无功电压分区控制

为提升双馈风电场的无功功率补偿和电压稳定能力,提出了一种考虑模糊多目标优化的风电场无功电压分区控制方法。基于有功功率数据对风电场进行分区降维,并计算获得了各分区的无功优化限值;定义了分区无功裕度指标用以描述风电场电压运行的安全裕度,综合考虑运行安全性和稳定性,建立了风电场无功电压的模糊多目标优化模型;提出了一种可大范围全局快速寻优的自适应遗传禁忌算法,通过重新定义交叉与变异概率提升了寻优的全局时效性,通过引入禁忌算法改善了寻优准确性。最后,以某双馈风电场为例进行了仿真验证。结果表明:所提方法能够为风电场预留充足的无功裕度,显著降低系统内部的电压波动。

融合分类校正与样本扩增的小样本目标检测

现有小样本目标检测方法在扩增样本时往往存在数据分布偏移问题,同时分类任务性能容易受定位任务影响。针对上述问题,提出一种新的小样本目标检测算法。该算法在Faster R-CNN框架基础上引入分类校正模块(CCB)、样本扩增模块(SAB)和梯度限制层(GCL)改善性能。CCB使用离线的强分类网络对检测器最终结果进行校正;SAB在特征域利用基类样本信息修正新类样本分布,从而在修正的分布中进行采样完成新类样本扩增;在梯度反向传播中通过GCL限制主干网络接收的基类和新类信息。在PASCAL VOC和COCO数据集上的实验结果表明,相较于目前已知的最新算法结果,提出的小样本目标检测算法在样本数量很小的情况下提升了检测效果,在公共数据集PASCAL VOC上最高提升可以达到5.1%,更难的数据集COCO上最高提升可达到1.9%,同时拥有很好的鲁棒性和泛化能力。

基于山体风貌保护视角的青岛中心城区城市高度控制研究

近年来青岛快速扩张的城市建设对中心城区原有的山水格局产生了一定的影响,尤其是城市与山体之间和谐的空间关系面临严峻挑战。结合《青岛市城市风貌保护规划》项目,多维度分析青岛中心城区山体周边风貌保护的现状特征及问题,从山体保护对象确定、山体保护分级以及山体周边建筑相关高度控制等方面入手构建青岛山体周边高度控制体系。并在此基础上结合外部认知要素与内生需求要素,提出青岛中心城区城市高度形态控制方案,整体保护青岛城市风貌,回归青岛“城”与“景”的融洽关系,并为其他城市的高度控制工作提供参考。