最优法

The performance function and constraint equation in calculus of variations were constructed by analyzing input and output equations of the system containing parameters to be estimated. The traditional parameter estimation problem could be transformed to that of least squares estimation.

通过分析包含待估参数的系统输入输出方程，构造变分法中的性能范函和约束方程，将传统的参数估计问题化为带约束条件的最小二乘估计问题；利用拉格朗日乘子法，分析参数估计方程，得到参数的最优估计。

The primary work of this paper includes: 1 The general process and the fundamental theory of genetic algorithm is introduced systematically, which is also be applied to an example; 2 The penalty function method and the constraint tournament method are introduced in the paper, which are used to process the constraint limit. Via analyzing the basic principle of NSGA-II ,which is elaborated in the paper, the fast non- dominated sorting method, congestion distance and its comparison operator, the elite strategy and the main process of NSGA-II is researched particularly. 3 Via modeling the fire distribution problem, the model is computed by the algorithm of NSGA-II, which is combined with both the penalty function method and the restraint league tournament method The optimization of two goals are also realized in the paper. The results derived from the VC++6.0 indicate that, two algorithms both have the high convergence, simultaneously the Pareto optimal solution also maintain the variety of distribution.

本文所作的主要工作如下：系统地介绍了遗传算法的一般流程和基本理论，并应用于一个函数优化的实例；研究了用于处理约束限制的罚函数法和约束联赛法，论述了NSGA-II的基本原理，并对其提出的快速非支配排序法、拥挤度及其比较算子、精英策略及NSGA-II的主要流程作了详细的研究；建立了火力分配问题的模型，并将NSGA-II算法分别与罚函数法和约束联赛法相结合对该模型进行了计算，实现了对两个目标的最优化；用VC++6.0编程计算后所得的结果表明，两种算法均具有很好的收敛性，同时Pareto最优解也保持了好的多样性分布。

The method based upon semi-infinite slopes is intended to approximate the prescribed transfer function. In order to minimize the error function, the least square method is adopted. The method of correction with term by term is used to avoid the divergent difficulties in iterative design.

本文提出以折线法来构造网络的逼近函数，并利用最小二乘法和逐项修正法相结合的办法来达到最优逼近，然后依据网络综合的理论，用RC网络的综合步骤来计算出实际元件值。

As a result, it shows thatthe static or dynamic subsystem optimum alone is not equal to the system optimum. Three initial value problems met in the optimal design of flying vehicle are studied andconclusions are derived that: orthogonal test method can be adopted to decide the initial valueof static optimization problem, some mathematical techniques can be used to deal with thecostate variables of Maximum Principle and decide the initial value of the costate variable,the indirect method can be used to get the analytical solution under ideal case to guide thechoice of the initial control curve in the direct method. With some numerical examples oftrajectory optimization, it shows that all these methods are useful not only in accelerating theconvergence but also in converging to the global optimum.

针对飞行器优化设计中的三种初始值问题进行了研究，以远程弹道导弹弹道的工程优化为例说明，对于静态优化问题，采用正交试验法选取初始值，不仅可以大大加快收敛的速度，而且更有可能收敛到全局最优解；以气动力辅助变轨问题为例说明，用共态变量的一阶泰勒级数展开可以解决极大值原理中共态变量初值难于确定的问题；以二级弹道导弹的主动段弹道优化为例说明，利用间接法在理想情况下得到的解析解来指导直接法初始控制曲线的选择，将大大有利于提高直接法的收敛速度。

In this paper I introduce basic theory of Bayes' method and business risk. I give out the thought of essential solving steps, then combine with an instance, as a spinning mill which would produce two different manufactures, flower woolen cloth and gabardine. I adopt Bayes' expectation of loss method to analysis the two manufactures producing, then made a decision, figure out expectation value of the two schemes. Then select a plan which get best profit or least loss. I compute other indexes, for example, probabilities under different stations, tenderness analysis, risk degree of different plans, then compare those indexes, we make a decision.

在文中详细的介绍了贝叶斯方法的基础理论和企业风险的有关理论，给出了贝叶斯估计方法的基本解题思路和步骤，再结合具体实例，对某纺织厂公司生产两种产品，花呢和华达呢具体生产的决策问题采用贝叶斯期望损益分析法，计算出两种方案的期望值，选取收益最大或损失最小的决策方案为最优决策方案，在不同的自然状态下，再计算其他的指标，例如敏感度分析，风险度。

A fuzzy comprehensive clustering method has been established by combining the principle of maximal matrix element of the fuzzy clustering with the comprehensive judgment in fuzzy decision.

将模糊聚类最大矩阵元原理与模糊决策中的综合评判法相结合，建立了模糊综合聚类法，对地下土体污染程度进行最优评判，并且对污染因子进行分类，为治理土体污染提供了依据。

Model structure is determined according to the principle of minimizing residual sum of squares, model parameters are estimated by optimum instrumental variable method and prediction error method and validation of the model is performed by examining the whiteness of model residuals.

采用最小二乘法估计制动器ARX模型的参数，以损失函数最小为优化准则，判断了制动器模型的阶次。运用最优辅助变量法和预报误差法，对制动器ARMAX模型的参数进行了估计。

The improvement is 45% for the phase-lag of S2 after assimilating the altimetric data of the crossover points, while the correction for the diurnal constituents is not so good as for semidiurnal constituents.

利用基于最优插值法的混合法将交叉点的调和常数同化到动力模式中，同化后S_2分潮的迟角精度改进最大，可以改进45％，结果显示高度计资料的分析结果对模式结果的精度影响很大。

Vogel law and the initial solution than the beginning of the smallest element method Only solution is closer to the optimal solution.

而伏格尔法得到的初始解比最小元素法的初始解更接近最优解。

On the basis of ideas of 3D-structure arithmetic model and resolvents, a concrete quasiphysical and anthropopathic algorithm is formulated.

并设计了变步长梯度下降法来求局部最优格局和拟人跳坑策略来求全局最优格局。

On the other hand, the more important thing is because the urban housing is a kind of heterogeneity products.

另一方面，更重要的是由于城市住房是一种异质性产品。

Climate histogram is the fall that collects place measure calm value, cent serves as cross axle for a few equal interval, the area that the frequency that the value appears according to place is accumulated and becomes will be determined inside each interval, discharge the graph that rise with post, also be called histogram.

气候直方图是将所收集的降水量测定值，分为几个相等的区间作为横轴，并将各区间内所测定值依所出现的次数累积而成的面积，用柱子排起来的图形，也叫做柱状图。