本文關(guān)鍵詞：基于高斯過(guò)程的風(fēng)電機(jī)組部件建模與監(jiān)測(cè)研究　出處：《華北電力大學(xué)》2015年碩士論文　論文類(lèi)型：學(xué)位論文

  更多相關(guān)文章： 風(fēng)力發(fā)電 高斯過(guò)程 高斯優(yōu)化改進(jìn) 齒輪箱溫度 塔架振動(dòng)

【摘要】：風(fēng)力發(fā)電是新能源發(fā)電的新興力量。經(jīng)過(guò)近幾年的迅猛發(fā)展,我國(guó)風(fēng)電產(chǎn)業(yè)正處在由粗放型發(fā)展向精密型發(fā)展的階段。在發(fā)展速度放緩的過(guò)程中,解決發(fā)展初期遺留下來(lái)的技術(shù)問(wèn)題成為風(fēng)電制造企業(yè)關(guān)注的焦點(diǎn)。其中,風(fēng)電機(jī)組的狀態(tài)監(jiān)測(cè)是亟需解決的關(guān)鍵點(diǎn)之一。本文采用高斯過(guò)程(Gaussian process,GP)進(jìn)行建模分析,由于高斯過(guò)程建模既能提取運(yùn)行數(shù)據(jù)的隨機(jī)分布規(guī)律,又能有效的分離測(cè)量噪聲,適合風(fēng)電機(jī)組大數(shù)據(jù)樣本的建模工作。同時(shí)風(fēng)電機(jī)組部件監(jiān)測(cè)是通過(guò)建模和分析殘差方式實(shí)現(xiàn)的,因此提高建模精度對(duì)監(jiān)測(cè)分析的意義重大。論文的主要研究?jī)?nèi)容如下：1、由于風(fēng)電機(jī)組建模數(shù)據(jù)集較大,協(xié)方差矩陣維數(shù)較高,直接求解高斯過(guò)程協(xié)方差矩陣逆存在一定的困難。為此采用Cholesky分解法避免矩陣求逆可能存在的矩陣病態(tài),同時(shí)采用緩存矩陣解決矩陣求逆重復(fù)計(jì)算的問(wèn)題,從而保證高斯過(guò)程建模的快速性和準(zhǔn)確性。2、風(fēng)電機(jī)組具有強(qiáng)隨機(jī)性和間歇性工作的特點(diǎn),對(duì)象工況復(fù)雜多變,高斯過(guò)程優(yōu)化最優(yōu)解可能不是全局最優(yōu)解,為此提出信賴(lài)域高斯過(guò)程回歸方法進(jìn)行監(jiān)測(cè)研究。同時(shí)信賴(lài)域的優(yōu)化算法中包括二階導(dǎo)數(shù)信息,為避免運(yùn)算量較大造成計(jì)算量過(guò)大的問(wèn)題,簡(jiǎn)化海森矩陣的計(jì)算,提高建模效率,加速二階優(yōu)化過(guò)程。3、將以上高斯過(guò)程改進(jìn)方法應(yīng)用于兩個(gè)監(jiān)測(cè)對(duì)象,即齒輪箱溫度和塔架振動(dòng)。通過(guò)研究監(jiān)測(cè)對(duì)象的運(yùn)行特征,提取與監(jiān)測(cè)對(duì)象相關(guān)的變量集,構(gòu)建相應(yīng)的高斯模型。將殘差結(jié)果與其他建模方法進(jìn)行對(duì)比,驗(yàn)證了高斯過(guò)程建模的高效穩(wěn)健。同時(shí)通過(guò)塔架振動(dòng)的狀態(tài)監(jiān)測(cè)分析,監(jiān)測(cè)出塔架故障所在,表明高斯過(guò)程建模分析能夠?qū)崟r(shí)監(jiān)測(cè)塔架故障。
[Abstract]:Wind power is a new force of new energy power generation. With the rapid development in recent years, China's wind power industry is in from extensive development to precision development stage. In the process of slowing down the speed of development, to solve the technical problems of the legacy of the early development of the wind power manufacturing enterprises has become the focus of attention. Among them, the wind turbine state monitoring is one of the key points that need to be solved. This paper uses the Gauss process (Gaussian process, GP) are modeled and analyzed by Gauss process modeling can extract the random distribution of data, and can separate the effective measurement noise, modeling of wind turbine for large data samples. At the same time, wind power the monitoring unit components is achieved through the modeling and analysis of residual method, thus to improve the modeling accuracy of monitoring and analysis of great significance. The main contents of this thesis are as follows: 1, the wind turbine modeling The data set is large, the dimension of the covariance matrix is higher, there are some difficulties in solving inverse Gauss process covariance matrix. Using Cholesky decomposition method to avoid inverse matrix ill conditioned matrix may exist, and the use of cache matrix to solve the inverse matrix problem of repetitive calculation, so as to ensure the accuracy and speed of.2 Gauss process modeling, characteristics of wind power the unit has strong randomness and intermittent work, object condition is complicated, the optimal solution may not be the optimal solution of Gauss process, the trust region Gauss process regression monitoring research. At the same time trust includes two derivative information optimization domain, to avoid a large amount of computation caused by the large amount of calculation. Simplified calculation of Hessian matrix, improve the modeling efficiency, accelerate the optimization process of order two.3, the Gauss process improvement method is applied to the two monitoring The object that the gear box temperature and vibration of the tower. By running the characteristics of monitoring objects, monitoring object extraction and related variables, construct the Gauss model. The residual results and other modeling methods are compared and verified in an efficient and robust modeling of the Gauss process. At the same time through monitoring the tower vibration analysis, monitoring tower the fault that Gauss, the process modeling and real-time monitoring of tower failure.

【學(xué)位授予單位】：華北電力大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2015
【分類(lèi)號(hào)】：TM315

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 熊志化,黃國(guó)宏,邵惠鶴;基于高斯過(guò)程和支持向量機(jī)的軟測(cè)量建模比較及應(yīng)用研究[J];信息與控制;2004年06期

，

本文編號(hào)：1399227