移动机器人动态避障算法

把滚动规划和径向基函数神经网络（RBFNN）预测相结合，提出一种动态不确定环境下移动机器人局部路径规划过程中，针对动态障碍物的新的混合避障算法．利用摄像镜头采集动态障碍物的移动轨迹，提取形心序列，利用RBFNN建立预测模型．在移动机器人实时规划时，根据当前位置在超声波传感器的扫描范围内建立滚动窗口．当检测到动态障碍物进入滚动窗口以后，才开始进行预测计算．根据动态障碍物相邻时刻的三个时间序列值，来预测障碍物下一时刻的运动轨迹，从而把动态障碍物的避障问题转化为瞬时静态障碍物的避障问题，实现实时规划．这种算法能够提高动态避障的安全性和规划的实时性．仿真结果证明了算法是可行、高效的．     

基于混沌吸引子的快衰落信道预测算法

提出了一种新的快衰落信道非线性预测算法，该算法基于多径快衰落信道具有混沌行为。利用坐标延迟理论。重建快衰落信道系数的相空间，再根据混沌吸引子的稳定性和分形性，在相空间中进行预测，实现了快衰落信道的非线性预测．该算法对原始数据可进行更平滑的处理，在噪声环境下预测的时间范围更长．对时间跨度为63．829ms的衰落系数进行了预测，仿真结果表明，在信噪比为12dB时，预测结果优于AR算法．     

基于改进BP算法的商品销售量的预测

提出了一种改进的BP算法，该方法通过结合Cauchy训练来改进传统BP算法，避免传统BP算法容易陷入局部极小点，提高Cauchy训练的训练速度和解决不收敛的问题，并运用该方法于商品销售量的预测，实例表明该方法使网络具有较快的收敛速度和较高的准确度．     

基于交互式多模型算法的无人车车辆跟踪预测技术

针对无人车车辆路口通行中动态目标的跟踪预测,分析比较基于SICK与Velodyne两种激光雷达数据的车辆提取方法,参照Velodyne的提取方法,提出合适的激光雷达布局对路口环境中的动态障碍物(主要是车辆、行人)信息进行了提取.选取交互式多模型(IMM)算法对动态目标运动趋势进行预测,并对IMM算法进行优化,提出将局部路径规划的三次曲率多项式算法抽象为路径规划模型,作为IMM算法的滤波模型以替代常规的车辆运动模型作为滤波模型.验证实验结果表明基于路径规划模型的IMM算法在无人车车辆运动趋势的预测上具有更好的超前性与更高的预测精度.     

一种基于神经网络预测模型的DMC算法及其仿真

研究了一种基于神经网络预测模型的动态矩阵控制(DMC)算法,首先利用多层前馈神经网络辨识对象模型,同时预测对象的未来输出,然后用DMC算法进行滚动优化和反馈校正。通过对一类化工反应器非线性系统的仿真,结果表明该算法在非线性对象的任意工作点都可以通过神经网络辨识获得工作点附近的近似线性模型,具有较好的实时性。     

预测算法在头部跟踪系统中的应用

介绍了头部跟踪技术的研究动态,阐述了对头部跟踪规律的探索以及在预测算法的设计上所做的工作.针对遥操作控制系统,建立了具有时间延迟的系统模型.在消除时间上的延迟所造成的误差以及对这些数据流进行合理的预测等方面,采用了多种解决方案,以达到实时跟踪的目的.详细描述了外插法和自回归法两种预测算法在姿态跟踪中的应用,并对这两种算法用Matlab进行了软件实现.通过对两种预测算法下头部跟踪曲线的分析,选择了适合的方法应用在该遥操作系统中,并取得了比较满意的效果.     

基于灰色理论的拍卖预测算法研究

基于网上拍卖结果难以预测,提出一种基于灰色理论的拍卖预测算法,利用连续的灰色微分方程GM（1,1）模型,对拍卖结果进行预测．基于固定历史数据和移动历史数据分别与简单指数函数预测算法和时间序列预测算法使用平均残差（ARE）进行比较,结果显示该方法不但所使用的数据较少也具有较高的准确性．表明该方法可以有效地预测拍卖结果．     

实时数据下城市高架路短期交通流预测模型

灰狼算法具有容易困于局部最优且收敛精度有缺陷，笔者改进非线性收敛因子，同时利用差分进化策略，得到新的灰狼优化算法。借助基准测试函数进行验证，改进后算法的全局搜索能力和收敛速度强于标准灰狼算法。进一步把改进后的算法应用在城市高架路短期交通流预测，具有较好的可行性，经过比较可知，预测的精度有明显的提升，优化了实时数据下高架路短期交通流预测的计算路径。     

基于混沌小波网络的交通流预测算法研究

实时准确的交通流量预测是实现智能交通诱导及控制的前提与关键。也是智能化交通管理的客观需要．结合交通流预测的特点，提出了一种基于小波网络的路段交通流预测方法，把混沌优化算法引入小波网络的拓扑构造，结合提出的相似时段的预测思想，给出了一种基于混沌优化算法的小波网络交通流量预测模型．实验结果表明，引入相似时段的预测思想可以有效提高交通流的预测精度，基于混沌优化算法的小波网络在交通流预测的精度和收敛速度方面明显优于常规BP网络．     

用于多媒体的最早截止时间优先算法改进

对经典实时调度算法之一的最早截止时间优先算法进行研究,提出一种基于动态死线时间的改进方法,避免了瞬时过载导致的系统不可预测的行为．实验表明,本方法保证了连续多媒体应用的服务质量,达到较高的资源利用率,使该算法更加适合多媒体应用环境．     

Modeling and Simulation of Time Series Prediction Based on Dynamic Neural Network

Molding and simulation of time series prediction based on dynamic neural network(NN) are studied.Prediction model for non-linear and time-varying system is proposed based on dynamic Jordan NN. Aiming at the intrinsic defects of back-propagation (BP) algorithm that cannot update network weights incrementally, a hybrid algorithm combining the temporal difference (TD) method with BP algorithm to train Jordan NN is put forward.The proposed method is applied to predict the ash content of clean coal in jigging production real-time and multistep. A practical example is also given and its application results indicate that the method has better performance than others and also offers a beneficial reference to the prediction of nonlinear time series.     

Modeling and Simulation of Time Series Prediction Based on Dynic Neural Network

Molding and simulation of time series prediction based on dynic neural network(NN) are studied. Prediction model for non-linear and time-varying system is proposed based on dynic Jordan NN. Aiming at the intrinsic defects of back-propagation (BP) algorithm that cannot update network weights incrementally, a hybrid algorithm combining the temporal difference (TD) method with BP algorithm to train Jordan NN is put forward. The proposed method is applied to predict the ash content of clean coal in jigging production real-time and multi-step. A practical exple is also given and its application results indicate that the method has better performance than others and also offers a beneficial reference to the prediction of nonlinear time series.     

Coal flotation using wash oil as a new type of collector

The use of wash oil as a coal collector is proposed to overcome the disadvantages of regular collectors in coal slime flotation. These disadvantages include high price, limited sources and high consumption. The effect of additives on flotation was studied and an innovative "one rough separation-one cleaning separation" flotation technology was developed. The experimental results show that the clean coal ash content decreases by about 1.36% and the clean coal yield declines by around 10% with the application of the depressant. There is an increase of 3.76% in the yield of clean coal and a decrease of 0.40% in the ash content caused by utilizing a dispersant. An ultimate product having an ash content of 10.78% and yield of 70.12% can be attained using a combination of dispersant and depressant. The use of this new technology decreases the ash content by 1.21%, decreases the yield by 2.80% and an increases the coal flotation perfect index by 2.03%. Compared to common flotation, the utilization of the new technology reduces ash by 0.17%, increases yield by 5.3% and increases perfect index by 4.18%.     

Triboelectrostatic Separation-anEfficient Method of Producing Low Ash Clean Coal

1　 IntroductionActive carbon has been used in fields ofmedicine,food,environmental protection,mili-tary,and so on,because it has a developed innerspace and a tremendous specific surface area.Thepresent active carbon produced from coal is in itslow- grade because of the high ash contentof feed-stock coal.To deeply remove ash and producelow- ash ( <3% or <2 % ) clean coal is the keystep to produce high- grade coal- base active car-bon.At present,the wet processing is the mainmethod of fine coal…     

细粒煤浮选数学模型的研究

通过大量试验,研究了浮选泡沫产品中细粒煤含量与水量关系,探讨了浮选过程中水流的机械夹带对细粒煤浮选的影响,考察了水浮选速率常数Ｋｗ 与操作变量之间的关系,得出了水浮选速率常数与操作变量之间的经验公式,确定了水量回收模型,从而最终建立了细粒煤产率与回收水量之间关系的动力学模型．通过引入降灰系数,导出了任一浮选时刻对应的细粒浮选精煤灰分的计算公式．     

Performance analysis of jig for coal cleaning using 3D response surface methodology

Beneficiation of coal of -4.76 mm + 3 mm size fraction was investigated in a laboratory model Denver jig.Process variables were studied to analyze their effect on the performance of jig in terms of yield and ash content of clean coal. Three-factor three-level Box-Behnken design of experiments with response surface methodology(RSM) was employed to understand the performance behavior of jig. From the study, the bed height was found to be the most significant parameter affecting the yield and ash content of clean coal. It was possible to reduce the ash content from 24.32% in feed to an ash content of 16.55% in clean coal at 2 L/min water flow rate and 10 min jigging time. Influence of operating variables of the jig on responses was presented and discussed in 3D surface plots. The developed model was found to be significant within the range of parameters under investigation with correlation of co-efficient values as 0.99(yield) and 0.98(ash).     

Research on Mathematical Model of Fine Coal Flotation

通过大量试验,研究了浮选泡沫产品中细粒煤含量与水量关系,探讨了浮选过程中水流的机械夹带对细粒煤浮选的影响,考察了水浮选速率常数K     

Predicting Model forComplex Production Process Based on Dynamic Neural Network

Based on the comparison of several methods of time series predicting, this paper points out that it is necessary to use dynamic neural network in modeling of complex production process. Because self-feedback and mutual-feedback are adopted among nodes at the same layer in Elman network, it has stronger ability of dynamic aping given, dynamic back-propagation (BP) algorithm of training weights of Elman neural network is deduced. At last, the network is used to predict ash content of black amber in jigging production process. The results show that this neural network is powerful in predicting and suitable for modeling, predicting, and controling of complex production process.     

超声波处理对煤泥特性的影响研究

为了提高煤泥浮选的效率和选择性，提出了在浮选前对煤泥进行超声波预处理的方法．利用扫描电镜、激光粒度仪和图像识别软件等研究了超声处理对煤泥特性的影响．比较了超声波处理前后相同粒级煤泥的产率、硫分、灰分和圆形系数，分析了超声波处理前后煤泥颗粒的表面状态，并用真空浮选试验进行了验证．浮选速度试验结果表明，超声处理后精煤的硫分、灰分较超声波处理前分别降低了33．84％和32．09％，前2min的精煤产率平均提高了约10％．试验证明超声处理改变了煤泥颗粒的大小、形状以及煤粒表面的状态，促使煤粒与黄铁矿、矸石解离，因此超声波预处理是煤泥浮选脱硫降灰的一种有效方法．     

Application of response surface methodology(RSM) for optimization of leaching parameters for ash reduction from low-grade coal

Coal is the world's most abundant energy source because of its abundance and relatively low cost. Due to the scarcity in the supply of high-grade coal, it is necessary to use low-grade coal for fulfilling energy demands of modern civilization. However, due to its high ash and moisture content, low-grade coal exerts the substantial impact on their consumption like pyrolysis, liquefaction, gasification and combustion process. The present research aimed to develop the efficient technique for the production of clean coal by optimizing the operating parameters with the help of response surface methodology. The effect of three independent variables such as hydrofluoric acid(HF) concentration(10–20% by volume), temperature(60–100 °C), and time(90–180 min), for ash reduction from the low-grade coal was investigated. A quadratic model was proposed to correlate the independent variables for maximum ash reduction at the optimum process condition by using central composite design(CCD) method. The study reveals that HF concentration was the most effective parameter for ash reduction in comparison with time and temperature. It may be due to the higher F-statistics value for HF concentration, which effects to large extent of ash reduction. The characterization of coal was evaluated by Fourier transform infrared spectroscopy(FTIR) analysis and Field-emission scanning electron microscopy with energy-dispersive X-ray(FESEMEDX) analysis for confirmation of the ash reduction.