共查询到19条相似文献,搜索用时 140 毫秒
1.
针对传统油液光谱数据预测模型精度有限的不足,提出了一种基于最小二乘支持向量回归(LSSVR)与AR模型相结合的非平稳时间序列建模方法(LSSVR-AR),并应用于某型履带车辆发动机油液光谱数据及故障的预测。首先对非平稳时间序列进行最小二乘支持向量回归,得到非平稳时间序列的趋势项及剔除趋势项后的随机项;然后对随机项建立AR模型并与趋势项的LSSVR模型组合,得到非平稳时间序列模型;最后用所建模型对油液光谱数据及发动机故障进行预测。用所提建模方法对Fe、Cu、Pb、Si光谱数据预测的平均绝对百分比误差分别为1.987%、2.889%、2.343%、6.860%,明显低于其他模型。实例证明,所提模型能对发动机故障进行准确预测。 相似文献
2.
3.
为解决故障劣化渐变过程的长时间序列对齿轮箱状态监测模型的影响问题,提升其决策精度,提出一种基于数据采集与监控(SCADA)数据的组合建模方法。首先,采用主成分分析法(PCA)选取与齿轮箱温度密切相关的输入观测向量,并应用长短期记忆(LSTM)神经网络分别对齿轮箱正常工况和异常工况独立建立温度模型;其次,结合模型输出结果与SCADA数据提取残差分布特征向量,建立随机森林残差分布模型对机组齿轮箱运行状态进行监测;最后,对某大型风电场机组进行模型建立和仿真研究。结果表明,基于LSTM神经网络结合随机森林算法对风电机组齿轮箱状态监测有较强的实用性和较高的准确率,为后续开展齿轮箱健康度评价提供了新的方法和思路。 相似文献
4.
5.
6.
鉴于传统的单一径流预报模型很难描述径流未来变化规律,将自适应变分模态分解(AVMD)与基于组合物理核函数的高斯过程回归(GPR-CK)相结合,构建了AVMD-GPR-CK预报模型,该模型采用AVMD将实测径流分解为多个子序列,对子序列依据其自身特点分别建模,子序列预报结果叠加重构即为最终预报结果。模型应用于金沙江流域向家坝站未来1~12个月的径流预报的结果表明,所有预见期AVMD-GPR-CK模型的确定性系数均大于0.94,平均绝对百分比误差(MMAPE)在±17%以内,预见期在10个月以内时,MMAPE在±10%以内;预报精度明显优于常见的BP、GRNN、RBF、RELM模型。 相似文献
7.
针对现代电力系统月负荷数据的趋势增长性和波动性的非线性特征,提出了一种基于小波变换的混合支持向量机负荷预测模型。通过小波变换将负荷序列分解为不同尺度的子序列,考虑负荷的季节波动性,将温度因素作为输入变量,构建混合核函数LWPSO-LSSVM。将负荷子序列分别放入膜系统的基本膜中进行并行预测,然后对子序列预测数据进行重构得到预测结果。利用四川省某地区电网负荷数据进行应用研究,结果表明所提出的模型较传统核函数支持向量机预测精度和效率有明显提高。 相似文献
8.
降水通常是一个地区水资源的主要补给来源,其准确预测对于水资源量的预测等十分重要。为提高降水量的预测精度,以吉林省西部某气象站为例,采用奇异谱分析对月降水量数据进行预处理,提取出多个独立的子序列,再利用支持向量回归机对不同子序列单独建立预测模型,对不同子序列预测模型的输出值求和即可得到该耦合模型的预测值,并利用该耦合模型(SSA-SVR)与小波分析-支持向量回归机耦合模型(WA-SVR)以及在原始降水量数据基础上建立的支持回归机预测模型(SVR)对其月降水量进行步长为1个月、3个月以及6个月的预测。结果表明,三种模型中,SSA-SVR模型的预测值与实测值最为接近,预测精度更高。 相似文献
9.
基于改进Kriging代理模型的自适应序列优化算法在离心压缩机蜗壳设计中的应用 总被引:1,自引:0,他引:1
《动力工程学报》2015,(7):562-567
提出了一种基于改进Kriging代理模型的自适应序列优化算法,并利用Matlab软件开发相应的优化平台.采用该优化平台,针对某特定流量工况,以质量流量平均总压损失系数为目标变量对离心压缩机蜗壳系统模型进行气动优化设计,并对优化前后蜗壳模型进行对比计算,来验证优化结果在实际蜗壳系统中的适用性.结果表明:优化后蜗壳的总压损失系数小、静压恢复系数大,性能得到改善. 相似文献
10.
11.
Time series of 20 years of daily solar irradiance data from four italian stations are analyzed on a statistical basis. It is shown that the irradiation sequences are not stationary, both in the mean and in the variance. They can be determined by three components: (a) a mean, well described by a Fourier series with only one coefficient; (b) a variance about the mean, well fitted by a Fourier expansion with two coefficients; (c) a stochastic component. The stochastic component follows a first order Markov model. Since it has a non-normal distribution, a normalizing transform has been introduced which does not affect its statistical properties. 相似文献
12.
小波分析方法在水文径流模拟中的应用 总被引:2,自引:3,他引:2
利用小波分析识别年径流周期得到年径流周期成分,再对剔除周期成分的剩余序列进行小波消噪,消噪后的序列作为平稳随机成分建立自回归模型,并把噪声序列作为独立随机成分进行模拟,最后把周期成分、相依随机成分和独立随机成分组合建立随机模拟模型。实例研究表明,基于小波分析的水文随机模型比传统随机模型的模拟效果好,统计参数更接近实测序列的统计参数。 相似文献
13.
A neural networks approach for wind speed prediction 总被引:5,自引:0,他引:5
14.
15.
The large eddy simulation (LES) is applied to an unconfined swirling flow of an air surrounding a bluff-body having a central jet of air, and the complicated flowfield that involves the recirculation and vortex breakdown is investigated. The Smagorinsky model is used as the sub-grid scale model. The results of the present numerical simulation are compared with the experimental data of the mean and stochastic root mean square (RMS) variations of two velocity components. Although the inflow conditions are specified in a simple manner, the obtained numerical results are in reasonable agreement with the experiments, except for a part of RMS variation values near downstream of the bluff body. The present numerical calculations can successfully reproduce the two characteristics of the flow, i.e., an upstream recirculation zone established just downstream of the burner plane and the additional recirculation zone established at the more downstream location. 相似文献
16.
This paper presents a new stochastic framework for provision of reserve requirements (spinning and non-spinning reserves) as well as energy in day-ahead simultaneous auctions by pool-based aggregated market scheme. The uncertainty of generating units in the form of system contingencies are considered in the market clearing procedure by the stochastic model. The solution methodology consists of two stages, which firstly, employs Monte–Carlo Simulation (MCS) for random scenario generation. Then, the stochastic market clearing procedure is implemented as a series of deterministic optimization problems (scenarios) including non-contingent scenario and different post-contingency states. The objective function of each of these deterministic optimization problems consists of offered cost function (including both energy and reserves offer costs), Lost Opportunity Cost (LOC) and Expected Interruption Cost (EIC). Each optimization problem is solved considering AC power flow and security constraints of the power system. The model is applied to the IEEE 24-bus Reliability Test System (IEEE 24-bus RTS) and simulation studies are carried out to examine the effectiveness of the proposed method. 相似文献
17.
F. Behzad Z. Mansoori M. Saffar-Avval H. Basirat Tabrizi G. Ahmadi 《International Journal of Heat and Mass Transfer》2010,53(5-6):1175-1182
New thermal stochastic particle collision model in gas–solid flow in a riser is developed. The simulation is based on four-way coupling of phases considering inter-particle collision and heat transfer. It is shown that the limitation of excessive computational time in Eulerian–Lagrangian simulation of gas–solid flows for the high loading ratios is eliminated by using the stochastic particle collision model. The simulation results demonstrate that the predictions of the developed thermal stochastic particle collision modem are in good agreement with those obtained by the direct particle collision model and the available experimental data. The new stochastic modeling is used and nearly dense gas–solid flow is simulated for high loading ratios up to eight and the results are presented and discussed. 相似文献
18.
可控串联补偿器(TCSC)可以灵活地调节线路潮流,提高系统运行的稳定性,传统分析方法在评估TCSC提高系统静态电压稳定性作用时存在缺陷,无法考虑不确定性因素的影响。因此,建立计及TCSC接入的系统负荷裕度概率模型,考虑运行参数的随机波动,通过半不变量法和Gram-Charlier级数计算负荷裕度概率特征,进而得到电压失稳概率值。分别在常态与故障下对比TCSC安装前后的IEEE39节点系统失稳概率,结果表明,TCSC能有效地提高系统的静态电压稳定性,验证了本文方法的可行性与准确性。 相似文献
19.
把随机微分方程理论引入到汇流计算中,以线性水库汇流系统为例,建立了一个计算汇流过程的随机微分方程模型。该模型将输入过程和模型参数均视为随机变量,采用建立矩方程的方法求解相应的随机微分方程,得到一个简单的计算汇流系统出流过程的统计矩公式。研究表明,随机微分方程理论应用到汇流系统是一种值得深入研究的方法。 相似文献