考虑收益管理的高铁平行车次动态差别定价

基于RP(Revealed Preference)和SP(Stated Preference)调查数据，利用潜在类别模型对高铁旅客进行细分，得到旅客对平行车次不同服务属性，如列车运行时间、发车时段和舒适度的偏好程度，并对其进行量化；引入收益管理，以多列车整体收益最大为目标，构建平行车次动态差别定价模型，并设计模拟退火算法进行求解；最后，通过京沪高铁进行实例验证.结果表明：与固定票价进行客票销售相比，所提方案能够适应高峰期和平峰期不同客流特点，提高铁路客票总收益，为高铁平行车次灵活定价提供参考.     

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。     

Strain prediction for critical positions of FPSO under different loading of stored oil using GAIFOA-BP neural network

FPSO (floating, production, storage and offloading) units are widely used in the offshore oil and gas industry. Generally, FPSOs have excellent oil storage capacity owing to their huge oil cargo holds. The volume and distribution of stored oil in the cargo holds influence the strain level of hull girder, especially at critical positions of FPSO. However, strain prediction using structural analysis tools is computationally expensive and time consuming. In this study, a prediction tool based on back-propagation (BP) neural network called GAIFOA-BP is proposed to predict the strain values of concerned positions of an FPSO model under different oil storage conditions. The GAIFOA-BP combines BP model and GAIFOA which is a combination of genetic algorithm (GA) and an improved fruit fly optimization algorithm (IFOA). Results from three benchmark tests show that the GAIFOA-BP model has a remarkable performance. Subsequently, a total of 81 sets of training data and 25 sets of testing data are obtained from experiment using fiber Bragg grating (FBG) sensors installed on the surface of an FPSO model. The numerical results show that the GAIFOA-BP is capable of predicting the strain values with higher accuracy as compared with other BP models. Finally, the reserved GAIFOA-BP model is utilized to predict the strain values under the inputs of a 10-day time series of volume and distribution of stored oil. The predicted strain results are further used to calculate the fatigue consumption of measurement points.     

VTS中雷达信息与AIS信息融合的探讨

文章对VTS中雷达信息与AIS信息的来源、种类与特点进行了比较,论证了两者信息融合的可行性与必要性,同时给出了信息的融合模型与方法,也提出信息融合需要进一步解决的问题.     

泥浆悬浮砂粒能力分层测定试验研究

为实现泥浆悬浮砂粒能力的量化分析,提出一种分层测定方法,选取12%、15%和18%3种质量分数的试验泥浆,通过自行设计的分层取样装置进行试验研究,获取不同泥浆质量分数、沉降时间和砂粒粒径条件下的10个深度分段的砂粒质量分布,分析各参数影响下的砂粒沉降变化规律。结果表明:1)该分层测定方法可较好地获取不同深度分段的砂粒质量,弥补现有测定方法只能获取底层砂粒沉降质量的不足;2)试验所采用的3种质量分数的泥浆对0.1 mm以上粒径的砂粒悬浮能力均较差。根据砂粒沉降曲线分布特征,提出一种用于判别泥浆悬浮砂粒能力的方法,即砂粒沉降曲线越平缓,各层质量差异性越小,底层质量无明显拐点,不同沉降时间曲线越紧密,则泥浆悬浮砂粒能力越强。     

Influence of AC system design on the realisation of tractive efforts by high adhesion locomotives

The main task for heavy haul railway operators is to reduce the cost of exported minerals and enhance the long-term viability of rail transport operations through increasing productivity by running longer and heavier trains. The common opinion is that this is achievable by means of implementation of high adhesion locomotives with advanced AC traction technologies. Modern AC high adhesion locomotives are very complex mechatronic systems and can be designed with two alternative traction topologies of either bogie or individual axle controls. This paper describes a modelling approach for these two types of AC traction systems with the application of an advanced co-simulation methodology, where an electrical system and a traction algorithm are modelled in Matlab/Simulink, and a mechanical system is modelled in a multibody software package. Although the paper concentrates on the analysis of the functioning for these two types of traction control systems, the choice of reference slip values also has an influence on the performance of both systems. All these design variations and issues have been simulated for various adhesion conditions at the wheel–rail interface and their influence on the high traction performance of a locomotive equipped with two three-axle bogies has been discussed.     

基于响应面和遗传算法的柴油机瞬态过程喷油参数优化

基于台架试验数据,利用响应面法建立了某工程机械用柴油机瞬态过程喷油参数与性能的近似高精度模型,基于此模型采用遗传算法对瞬态过程喷油参数分别进行离线优化研究。结果表明:采用单目标优化确定的燃油消耗率(BSFC)、NO_x比排放量和颗粒质量(PM)比排放量的优化极限分别可达180.23g/(kW·h),8.92g/(kW·h)和0.011 8g/(kW·h),相对原机可降低多达4.5%,34.0%和37.3%。双目标优化的Pareto解集表明,相比于同时优化BSFC和NO_x比排放量,BSFC和PM比排放量更容易同时得到优化。采用权重因子适应度函数的三目标优化结果对应的BSFC,NO_x比排放量及PM比排放量分别为184.70g/(kW·h),12.62g/(kW·h)和0.012 2g/(kW·h),较原机分别降低2.1%,6.6%和35.3%。改进优化模型后,性能优化Pareto解集对应的BSFC和PM比排放量水平都非常接近其优化极限,但NO_x比排放量相对其优化极限仍然较高。     

基于小波和粒子群算法的HEV行驶状况辨识方法研究

针对混合动力汽车(HEV)行驶状况(道路坡度和整车载荷)变化难以有效识别,导致驱动系统控制策略不能有效满足驾驶员意图问题,以混联式HEV为研究对象,提出了基于小波滤波和粒子群算法的HEV行驶状况辨识方法。首先建立了汽车行驶状况辨识模型,采用最小二乘法确立了优化目标函数,其次研究了基于小波滤波和粒子群算法的HEV行驶状况辨识原理,最后进行了行驶状况粒子群智能算法辨识试验。在采集实车数据的基础上,对实车数据进行小波滤波,并运用行驶状况辨识方法对道路坡度和整车载荷进行了辨识,并对辨识结果进行小波滤波,结果表明,试验工况下整车载荷辨识的相对误差绝对平均值为2.71%,道路坡度辨识的相对误差绝对平均值为3.85%,验证了所提出方法的有效性。     

稀燃条件下甲醇汽油混合燃料颗粒物排放特性

在1台GDI增压汽油机上,进行了稀燃发动机燃用M0,M10和M20(其中M0为汽油,M10为甲醇体积分数10%、汽油体积分数90%的混合燃料,以此类推)甲醇汽油混合燃料的试验,研究了在稀燃条件下甲醇汽油混合燃料对GDI发动机颗粒粒径分布特性、数量浓度特性和质量浓度特性的影响。试验结果表明:在稀燃条件下,随着甲醇比例的增加颗粒数量浓度峰值逐渐增大,颗粒数量浓度随粒径分布呈现出双峰分布;颗粒中的核态颗粒和积聚态颗粒的总数量都随甲醇比例的增加而增加,其中M20的积聚态和核态颗粒数量浓度最大;颗粒粒径峰值都随着甲醇比例的增加逐渐增大,并且核态颗粒粒径峰值主要集中在20.54~31.62nm,积聚态颗粒粒径峰值主要集中在56.23~100nm;颗粒质量浓度随甲醇比例的增加而增大,粒径分布在316~700nm的积聚态颗粒明显增多,积聚态颗粒质量浓度随粒径分布的范围明显增加,质量浓度也相应增加,而粒径分布在56.23~316nm范围内的颗粒质量浓度却在降低。     

公交通行能力约束的智能调度优化模型

公交通行能力是解决城市交通拥堵问题、促进城市公共交通系统高效运行的要素之一。介绍了公交通行能力的计算要素,并针对目前我国城市由于盲目调度造成的公交系统运营效率、服务水平下降的问题,提出将公交通行能力作为约束条件对公交调度进行优化。鉴于公交企业制订调度方案时需兼顾公交服务水平和企业效益,将智能调度的目标确定为候车时间满意度、候车空间满意度、车内舒适满意度和企业满意度加权平均值最大,并给出了相应的计算方法。最后讨论了利用遗传算法对模型进行求解的过程。