遗传投影寻踪回归在城市环境质量评价中的应用

引入投影降维的思想,将遗传投影寻踪与回归分析技术运用到城市环境质量评价中。将此技术与神经网络方法进行实例比较,投影寻踪回归方法不但可以合理地作出环境质量的综合评价,而且消除了神经网络方法中类别判断不够精确的影响。     

基于人工蜂群算法与BP神经网络的水质评价模型

针对BP网络水质评价模型的不足,引入人工蜂群(ABC)算法,将求解BP神经网络各层权值、阀值的过程转化为蜜蜂寻找最佳蜜源的过程,提出了一种新的结合人工蜂群算法的BP网络水质评价方法(ABC-BP)。并以2000—2006年渭河监测断面的10组实测数据作为测试样本对其水质进行了评价,实验结果表明该方法得到的水质评价结果准确,并具有很强的稳定性和鲁棒性。     

响应面法和神经网络优化Acinetobactersp．DNS32发酵基质

为了提高阿特拉津降解菌Acinetobactersp．DNS32的产量,分别采用响应曲面法和基于人工神经网络的遗传算法对阿特拉津降解菌DNS32发酵培养基中3个重要基质成分（玉米粉、豆饼粉、K：HPO。）进行优化研究。响应曲面法确定3种成分的含量为玉米粉39．494g／L,豆饼粉25．638g／L和K。HPO。3．265g／L时,预测发酵活菌最大生物量为7．079×10^8CFU／mL,实测量为7．194×10^8CFU／mL;人工神经网络结合遗传算法优化确定3种主要成分含量为玉米粉为39．650g／L,豆饼粉为25．500g／L,K2HPO4为2．624g／L时,预测最大值为7．199×10^8CFU／mL,实测量为7．244×10。CFU／mL;最终确定培养基配方：玉米粉为39．650g／L,豆饼粉为25．500g／L,K2HPO4为2．624g／L,CaCO3为3．000g／L,MgSO4·7H2O和NaCl均为0．200g／L;优化后阿特拉津降解菌DNS32发酵生物量比优化前提高了36．6％。结果表明,在阿特拉津降解菌DNS32发酵培养基组分优化方面,响应面法和基于人工神经网络的遗传算法都是可行的,基于人工神经网络的遗传算法具有更好的拟合度和预测准确度。     

模拟退火算法在大气环境质量综合评价中的应用

为了建立一种对多项指标都能普遍使用的大气环境质量综合评价模式,利用模拟退火算法对幂函数加和型指数评价中参数进行优化,并用优化后的综合评价指数公式对大气环境进行综合评价。该公式应用于大量实例的分析评价结果与其他多种评价方法评价结果比较表明:该公式不受污染物种类和数目多少的限制,计算简便,具有可行性、实用性和通用性。     

B—P网络逐步聚类法在环境测点优选中的应用

将Ｂ－Ｐ网络原理与逐步聚类分析思想相结合,用于环境测点聚类优选。该方法用于水清河几个监测断面的优选结果是符合客观实际的。     

基于L-M神经网络的道路交通噪声预测研究

神经网络具有很强的预测功能.根据石家庄公路交通噪声的实测数据,利用L-M优化算法的多层神经网络预测模型进行道路交通噪声的预测,经检验,计算值与实测值接近,预测精度令人满意.     

水环境质量综合评价的新模型

为检验已订的水环境质量评价标准的合理性,解决各单项水质指标的评估结果的不相容性问题,提高水质等级模型的分辨率,提出了一种新的水质评价模型-逻辑斯谛曲线(LOG)模型,它的水质等级是连续的实数值;根据LOG模型的参数值可以分析各水质指标值对水质等级的影响程度,从而检验原订水质等级标准的合理性;并给出了基于实码遗传算法的LOG建模的实施方案.实例研究说明,这套方案是实用的和通用的,在其它环境质量综合评价中也具有广泛的应用价值.     

核化危害源项反演技术现状及研究展望

源项反演对缓解和遏制核化危害源、精准预测核化危害时空传输和扩散情况、辅助作战行动和保障决策等具有十分重要的意义.本文从源项反演应用平台和源项反演关键算法(包括欧拉方法、拉格朗日方法、深度学习等)两个方面,对国内外核化危害源项反演技术的现状和二者间的差距进行了总结与分析.研究指出,利用深度学习提高反演精度和速率、从单污染...     

PARAMETER ESTIMATION OF THE NONLINEAR MUSKINGUM MODEL USING HARMONY SEARCH1

ABSTRACT: A newly developed heuristic algorithm, Harmony Search, is applied to the parameter estimation problem of the nonlinear Muskingum model. Harmony Search found better values of parameters in the nonlinear Muskingum model than five other methods including another heuristic method, genetic algorithm, in terms of SSQ (the sum of the square of the deviations between the observed and routed outflows), SAD (the sum of the absolute value of the deviations between the observed and routed outflows), DPO (deviations of peak of routed and actual flows), and DPOT (deviations of peak time of routed and actual outflow). Harmony Search also has the advantage that it does not require the process of assuming the initial values of design parameters. The sensitivity analysis of Harmony Memory Considering Rate showed that relatively large values of Harmony Memory Considering Rate makes the Harmony Search converge to a better solution.     

Energy consumption estimation model for dual-motor electric vehicles based on multiple linear regression

ABSTRACT

The drive range of electric vehicle (EV) is one of the major limitations that impedes its universalism. A great deal of research has been devoted to drive range improvement of EV, an accurate and efficiency energy consumption estimation plays a crucial role in these researches. However, the majority of EV’s energy consumption estimation models are based on single motor EV, these models are not suitable for dual-motor EVs, which are composed of more complex transmission mechanisms and multiple operating modes. Thus, an energy consumption estimation model for dual-motor EV is proposed to estimate battery power. This article focuses on studying the operating modes and system efficiency in each operating mode. The limitation of working area of each mode ensures the vehicle dynamic performance, then PSO algorithm is adopted to optimize the torque (speed) distribution between two motors to improve the system efficiency in the coupled driving mode. Finally, the energy consumption estimation model is established by multiple linear regression (MLR). The result shows that the proposed model has a high precision in energy consumption estimation of dual-motor EV.