共查询到19条相似文献,搜索用时 109 毫秒
1.
为了解决标准Kalman滤波法不能很好处理大坝变形观测粗差与状态方程异常的问题,提出了采用基于M估计的抗差Kalman滤波算法,在最小二乘准则的基础上,通过调整观测值对状态估计的比例权重,可得到模型参数的稳健估计,给出了其滤波准则及递推公式,并根据预测残差调节增益矩阵的大小,尽可能地削弱监测噪声和动态噪声里粗差的影响,让系统处于比较稳定的状态。实例应用结果表明,该算法不仅可提高滤波精度,且能很好地控制观测异常和动态扰动异常对监测的影响。 相似文献
2.
随着大坝监测自动化的普及,在大坝安全分析评估中寻求可靠的粗差判别方法显得越来越重要,而基于回归统计的粗差判别准则中,由于粗差数据也会先参与回归建模,由此导致回归模型本身可能失真,从而易引发后续的误判和漏判粗差。对此,提出了一种针对混凝土重力坝变形监测的粗差判别方法。首先,计算样本中每个测值的离差和;其次,基于离差和剔除部分疑似粗差的测值,从而建立回归模型;最后,根据回归模型计算每个测值的拟合残差,并基于肖维勒准则最终确定粗差。实例仿真表明,该算法不受原始数据粗差的影响,具有更高的精度和鲁棒性。 相似文献
3.
4.
针对额定风速以上风电机组变桨距控制问题,提出了一种基于改进最小方差法的风电机组变桨距控制策略。该方法将延长预测步长思想,时变砺设计和柔化控制作用相结合,能够在突变过程初期,限制控制幅度,在控制后期能够加快收敛速度。同时与递推最小二乘辨识方法结合,用于额定风速以上风电机组变桨距控制系统。通过算例仿真表明,与传统的最小方差控制和PI控制方法相比,该方法能够使得系统响应迅速,在额定风速以上快速改变桨距角,保证了风电机组恒功率输出运行。 相似文献
5.
基于模糊隶属度的电力系统抗差估计 总被引:1,自引:0,他引:1
提出了一种电力系统模糊自适应抗差估计(fuzzy adaptive robust estimation,FARE)方法。计及了量测权重的不确定性,以连续的模糊隶属度评价测点的优劣,很好地解决了测点非优即劣的问题,以最小化测点劣质性的加权模糊隶属度之和为优化目标,采用原对偶内点法(Primal-Dual Interior Point Method,PDIPM)求解,并且实现了对量测粗差的自适应。多个IEEE标准算例以及波兰系统的仿真测试结果表明,该方法具有良好的抗差性能 相似文献
6.
遥测降雨的抗差修正研究 总被引:3,自引:0,他引:3
分析了遥测降雨观测资料的分布特征,引入抗差估计理论修正遥测降雨资料中出现的异常值,提高实时洪水预报精度。根据实际应用中出现的问题进行了改进。对闽江七里街流域1988~1998年45场洪水的暴雨资料,用生成的误差系列比较了各种方法的修正效果和探测效率。改进后的三步抗差修正的优越性获得了较好的修正效果.均超过60%。 相似文献
7.
一、硬度差控制 活塞环材质为适应摩擦付的耐磨性,要求有一定的硬度和同片环最小的硬度差,以使环周磨损均匀,保持气密性。然活塞环在铸造中受截面积、共晶度和冷却速度影响,致使同片环在不同部位硬度不同。成品要求硬度差≤3HRB,这给铸造带来困难。为控制硬度差,各生产厂在铸造检测控制方法上有所不同,区别在:逐包抽样和隔包抽样及抽查;硬度要求98~10~8HRB和≥99~108HRB;硬度差≤6HRB不作考核之分。时效后按GB1149-81标准验收:硬度98~108HRB;硬度差≤3HRB。则铸造检测作何控制?为此,笔者通过一定数量铸态环检测调查,有以下方面的启示: 1、按规范检测,规律是:硬度值低点在开口5~7mm处(成品尺寸),高点在90°处,硬度差为该二处差值。 相似文献
8.
详细讨论被预测参数相关变量的选择原则,偏最小二乘法中选择主成分个数的交叉有效性原则,并采用偏最小二乘法建立火电厂实时数据预测模型的回归方程。以某火电厂300 MW机组的PI实时数据库中的数据作为样本数据,建立实时数据预测模型对传感器测点测量数据进行故障检测及诊断,解决了普通多元回归模型对多重具有相关性的数据适应性差的问题,具有速度快、预测精度高的优点。 相似文献
9.
针对马斯京根模型参数抗差估计方法存在将真实值作为异常值的风险,利用蒙特卡洛方法分析了不同频率、不同量级的异常值影响下马斯京根模型参数抗差估计方法风险与效果间的关系。结果表明,马斯京根模型参数抗差估计方法的风险随异常值量级和频率的减小而增大,同时还与估计方法选取的抗差权函数有关。 相似文献
10.
针对偏最小二乘回归法含有全部自变量引起的预测误差问题,对偏最小二乘回归法进行了改进,采用主元选择的GA-PLSR法,即引入逐步回归方法中挑选和剔除因子的思想来选择与因变量相关性较强的自变量主元,然后利用偏最小二乘回归法进行建模,再采用遗传算法对其回归系数建立目标函数进行优化,确立最后的拟合模型用于因变量的预测,并通过实例应用,将选择主元的偏最小二乘回归模型、常规的偏最小二乘回归模型及基于主元选择的GA-PLSR模型的预测结果进行比较。结果表明,基于主元选择的GA-PLSR模型的拟合效果较好,且预测精度更高。 相似文献
11.
Recently, the metallic bipolar plate (BPP) has received considerable attention because of its advantageous electrical and mechanical properties. In this study, a methodology based on FEA model and Monte Carlo simulation is developed to investigate the effect of dimensional error of the metallic BPP on the pressure distribution of gas diffusion layer (GDL). At first, a parameterized FEA model of metallic BPP/GDL assembly is established, and heights of the channel and rib are considered to be randomly varying parameters of normal distribution due to the dimensional error. Then, GDL pressure distributions with different dimensional errors are obtained respectively based on the Monte Carlo simulation, and the desirability function method is employed to evaluate them. At last, a regression equation between the GDL pressure distribution and the dimensional error is modeled. With the regression equation, the allowed maximum dimensional error for the metallic BPP is calculated. The methodology in this study can be applied to guide the design and manufacturing of the metallic BPP. 相似文献
12.
本文分析了费用函数误差及最优分配执行误差对最优分配效益的影响,证明了一个定理,给出了计算这些误差减少最优效益(增加费用)的方法。 相似文献
13.
A number of Asian cities decided to establish gaming and resort facilities in order to capitalize on the growing number of gamblers and their family members in Asia. In doing so, they expect to sustain economic growth but, on the other hand, will consume a considerable amount of energy. Nevertheless, the causal relationship between economic growth and electricity consumption in this type of service-oriented territories has never been investigated. Using the historical data obtained from the Government of Macao SAR, we found that electricity consumption and economic growth in terms of gross domestic product are co-integrated for the period of 1999 Quarter 1-2008 Quarter 4. Moreover, vector error correction (VEC) models indicated a lack of short-run relationships but showed that there was a long-run equilibrium relationship between electricity consumption and gross domestic product. The accuracy of VEC models was assessed by using the mean squared error and the mean absolute error. The error analysis shows that VEC models reproduced time series of gross domestic product and electricity consumption in difference form accurately. 相似文献
14.
15.
Hao Li Shuangjun Yang Weiqi Zhao Zhihan Xu Shiyu Zhao Xifeng Liu 《Energy Sources, Part A: Recovery, Utilization, and Environmental Effects》2016,38(11):1569-1573
This article aims at using Artificial Neural Networks (ANNs) and linear prediction to predict the physicochemical properties of woody biomass, including gross calorific value, carbon content, and oxygen content. By analyzing 43 data groups, it was found that Multilayer Feedforward Neural Network (MLFN) with 11 nodes is the best model for predicting the gross calorific value, with a root mean square (RMS) error of 0.85; General Regression Neural Network (GRNN) is the best model for predicting the carbon content, with an RMS error of 1.66; and linear prediction is the best model for predicting the oxygen content, with an RMS error of 2.11. 相似文献
16.
17.
18.
以往太阳辐射预测计算的研究多采用柯伯方程等误差较大的公式,往往忽略了太阳方位参数计算误差对辐射预测计算模型的影响。忽略其他因素影响,仅计算不同太阳方位参数误差所对应的太阳辐照度,计算结果与天文年历标准值的计算结果进行对比,发现太阳方位参数的误差不仅对太阳辐照度计算造成7%以上的误差(时角大于70°时),而且在日出和日落之间临界点时也会产生极大的数值计算误差。针对以上问题,本文提出了引入儒略日为时间变量和采用大数据量最小二乘法拟合改进的数值模拟法,在保持计算公式简易的同时,显著降低了临界点的计算误差,而且辐射计算结果的相对误差小于0.2%。 相似文献
19.
Surendra P. Verma Jorge Andaverde E. Santoyo 《Energy Conversion and Management》2006,47(20):3659-3671
We used the error propagation theory to calculate uncertainties in static formation temperature estimates in geothermal and petroleum wells from three widely used methods (line-source or Horner method; spherical and radial heat flow method; and cylindrical heat source method). Although these methods commonly use an ordinary least-squares linear regression model considered in this study, we also evaluated two variants of a weighted least-squares linear regression model for the actual relationship between the bottom-hole temperature and the corresponding time functions. Equations based on the error propagation theory were derived for estimating uncertainties in the time function of each analytical method. These uncertainties in conjunction with those on bottom-hole temperatures were used to estimate individual weighting factors required for applying the two variants of the weighted least-squares regression model. Standard deviations and 95% confidence limits of intercept were calculated for both types of linear regressions. Applications showed that static formation temperatures computed with the spherical and radial heat flow method were generally greater (at the 95% confidence level) than those from the other two methods under study. When typical measurement errors of 0.25 h in time and 5 °C in bottom-hole temperature were assumed for the weighted least-squares model, the uncertainties in the estimated static formation temperatures were greater than those for the ordinary least-squares model. However, if these errors were smaller (about 1% in time and 0.5% in temperature measurements), the weighted least-squares linear regression model would generally provide smaller uncertainties for the estimated temperatures than the ordinary least-squares linear regression model. Therefore, the weighted model would be statistically correct and more appropriate for such applications. We also suggest that at least 30 precise and accurate BHT and time measurements along with the respective errors should be obtained for a reliable application of the proposed regression procedure. 相似文献