通州市道路交通事故预测

利用江苏省通州市交警大队提供的交通事故数据资料,运用灰色系统预测模型法和多元线性回归预测法对其进行分析研究和预测,预测结果对加强苏省通州市的安全管理、改善其道路交通安全状况有一定的理论意义和实用价值.     

乘用车平顺性预测与分析软件的开发

乘用车以人为运输对象，平顺性指标非常重要，平顺性预测及分析也有着自己的特点，提出并以综合振动舒适度作为评价及优化指标，季相应的计算机软件，为该类车型的平顺性评价及概念车设计提供了有力工具。     

New methodology for fast prediction of wheel wear evolution

In railway applications wear prediction in the wheel–rail interface is a fundamental matter in order to study problems such as wheel lifespan and the evolution of vehicle dynamic characteristic with time. However, one of the principal drawbacks of the existing methodologies for calculating the wear evolution is the computational cost. This paper proposes a new wear prediction methodology with a reduced computational cost. This methodology is based on two main steps: the first one is the substitution of the calculations over the whole network by the calculation of the contact conditions in certain characteristic point from whose result the wheel wear evolution can be inferred. The second one is the substitution of the dynamic calculation (time integration calculations) by the quasi-static calculation (the solution of the quasi-static situation of a vehicle at a certain point which is the same that neglecting the acceleration terms in the dynamic equations). These simplifications allow a significant reduction of computational cost to be obtained while maintaining an acceptable level of accuracy (error order of 5–10%). Several case studies are analysed along the paper with the objective of assessing the proposed methodology. The results obtained in the case studies allow concluding that the proposed methodology is valid for an arbitrary vehicle running through an arbitrary track layout.     

地铁列车运行引起环境振动响应的人工单点列脉冲激励预测方法

为了在频域内精确预测地铁列车运行引起的环境振动响应,研究提出基于实测振动传递特性的人工单点列脉冲激励预测方法。应用人工单点列脉冲激励获得传播系统的振动传递特性,采用振动传递转换公式将其转化为地铁列车运行时的振动传递特性;结合已建立的实测振源数据库,预测地铁列车运行引起的环境振动响应。以地铁15号线望京站—望京东站区间的地表振动预测为例,采用该方法、数值模拟方法和链式衰减预测法分别预测该区间地表预测点处的振动响应,并与实测结果进行对比。结果表明:采用该方法可以得到受振目标测点的频谱、1/3倍频程谱、Z振级等指标,并可实现多点同步、精确的振动响应预测;与其他2种预测方法相比,该方法具有预测精确度高、预测频带宽、受振目标针对性强等特点,适用于地铁隧道修建前后对重点受振目标的频域内精确预测。     

天然气高瓦斯山岭隧道地质灾害的特点与预报

研究目的:开挖油气田区的高瓦斯隧道,有着极高的危害性。由于隧道底部围岩为油气层,成为隧道施工瓦斯的补给源。而且,不同于煤层瓦斯的是,油气田区瓦斯无处不在。只要有断层、节理带存在,通常会有瓦斯溢出。所以,在油气田区,必须密切关注节理、断层的位置。查明其位置、性质、产状、规模,判断其是否成为导气构造,以便及时采取措施,保证施工安全。研究结论:(1)对于油气田区隧道,只有在区域地质分析的基础上,充分认识瓦斯赋存的特点,才能认清瓦斯溢出(突出)的本质,掌握灾害发生的机理,从而制定出具有针对性的预报方案;(2)精确的地质分析可为TSP隧道物理探测奠定坚实的基础,有效地消除解译结果的多解性;(3)严格现场操作,规范探测与钻探施工是实现准确预报的必要条件;(4)地质与物探相结合、宏观与微观相佐证,步步为营,是成功探测的基础。     

河道型水库总磷预测模型的建立及应用

根据河道型水库特有的水文、水力条件，按各水期的不同情况分别将直角坐标系下的二维河流污染物扩散模型和极坐标下的AB卡拉乌舍夫扩散模型结合起来，建立了河道型水库的总磷预测模型，并将其应用于水深不超过5m的狭长型河道水库．以绵阳市三江水库为例，用此模型模拟并预测库区水体中总磷的浓度变化，计算结果与观测值的相对误差小于10％。     

Floating Car Data Based Nonparametric Regression Model for Short-Term Travel Speed Prediction

A K-nearest neighbor (K-NN) based nonparametric regression model was proposed to predict travel speed for Beijing expressway. By using the historical traffic data collected from the detectors in Beijing expressways, a specically designed database was developed via the processes including data filtering, wavelet analysis and clustering. The relativity based weighted Euclidean distance was used as the distance metric to identify the K groups of nearest data series. Then, a K-NN nonparametric regression model was built to predict the average travel speeds up to 6 min into the future. Several randomly selected travel speed data series, collected from the floating car data (FCD) system, were used to validate the model. The results indicate that using the FCD, the model can predict average travel speeds with an accuracy of above 90%, and hence is feasible and effective.     

二次指数平滑法中确定初始值的简便方法

在利用二次指数平滑法建立趋势预测模型时，必须合理确定初始平滑值．确定初始平滑值比较复杂繁琐，用初期指标值替代初始平滑值是一种简便的处理方法．通过推导，论证了这一方法的可行性，并给出了适用条件．     

基于灰色理论的公路沉降预测研究

以工程实测数据为基础,根据灰色理论中的数列预测理论,针对公路建设中路基沉降监测,建立灰色预测模型.根据预测结果与沉降实际测量数据的对比,分析了模型预测结果的合理性.同时讨论了所用灰色预测模型的特点及其在沉降监测中的应用.     

Bus running time prediction using a statistical pattern recognition technique

Abstract

Given that real-time bus arrival information is viewed positively by passengers of public transit, it is useful to enhance the methodological basis for improving predictions. Specifically, data captured and communicated by intelligent systems are to be supplemented by reliable predictive travel time. This paper reports a model for real-time prediction of urban bus running time that is based on statistical pattern recognition technique, namely locally weighted scatter smoothing. Given a pattern that characterizes the conditions for which bus running time is being predicted, the trained model automatically searches through the historical patterns which are the most similar to the current pattern and on that basis, the prediction is made. For training and testing of the methodology, data retrieved from the automatic vehicle location and automatic passenger counter systems of OC Transpo (Ottawa, Canada) were used. A comparison with other methodologies shows enhanced predictive capability.