超限學習機的優(yōu)化改進及應用研究
發(fā)布時間：2018-11-18 20:44
【摘要】：隨著互聯(lián)網(wǎng)+時代的來臨,不論在互聯(lián)網(wǎng)行業(yè)、快消品行業(yè)、金融行業(yè),還是傳統(tǒng)的化工行業(yè)、制造行業(yè),其數(shù)據(jù)量都正在以爆炸式的速度增長。大數(shù)據(jù)的流通、存儲、分析、可視化等任務對于各企業(yè)都是重大的挑戰(zhàn)。機器學習技術(shù)作為一種對數(shù)據(jù)中隱含模式及規(guī)律進行分析和挖掘的重要手段,也日益凸顯出它的威力和重要性。直至今日,機器學習的研究和應用已被廣泛地應用于圖像識別,語音分析,自然語言處理及各類商用數(shù)據(jù)以及工業(yè)數(shù)據(jù)的挖掘中。在機器學習的研究中,分類和回歸是兩大基礎(chǔ)。在機器學習的研究進程中,出現(xiàn)了如廣義線性模型(GLM)、人工神經(jīng)網(wǎng)絡(ANN)、支持向量機(SVM)、超限學習機(ELM)等通用算法。如何在提高分類器的準確率或者回歸器的擬合精度的同時提高算法的泛化能力,已經(jīng)成為現(xiàn)在機器學習技術(shù)發(fā)展的重要課題。在此背景下,本文主要研究并完成了以下工作:(1)針對ELM算法中由于輸入層-隱層的權(quán)重隨機初始化操作而會導致的隱層輸出矩陣H不滿秩從而導致部分隱層節(jié)點不起作用的問題,本文提出了相關(guān)性映射超限學習機。利用輸入特征與預測標簽之間的相關(guān)性系數(shù),將特征與標簽之間的線性相關(guān)信息經(jīng)過非線性函數(shù)映射后,用于確定輸入層-隱層的權(quán)重矩陣。數(shù)據(jù)集測試結(jié)果表明該算法不僅可以提高超限學習機在分類及回歸任務中的預測準確率和精度,同時可以更加高效地利用隱層節(jié)點,提高模型的泛化能力。(2)針對由于ELM網(wǎng)絡中隱層激活函數(shù)單一化而導致其難以學習復雜數(shù)據(jù),同時易產(chǎn)生冗余隱層節(jié)點的問題,本文提出了基于粒子群算法的混合域超限學習機算法。該算法將隱層激活函數(shù)的組合(包含7種候選的激活函數(shù))定義為一個粒子,隨機產(chǎn)生大量粒子成為初始群體,按照一定進化規(guī)則迭代尋找隱層節(jié)點對應最優(yōu)個體,即最優(yōu)的激活函數(shù)組合。數(shù)據(jù)集測試結(jié)果表明該算法有效地提高了隱層節(jié)點的利用率和模型最終的泛化能力。(3)針對石油化工生產(chǎn)過程中設備管道流動腐蝕的沖刷腐蝕現(xiàn)象,結(jié)合實際問題,開展了如下研究工作:1.利用實驗設備,按照固定變量法,獲得10號碳鋼在不同實驗條件下的沖蝕速率。2.利用CFD計算流體力學仿真軟件,對90度彎管在不同條件下的沖蝕速率(包括平均速率和最大速率)進行仿真測試。對以上2種沖刷腐蝕現(xiàn)象,基于收集的歷史數(shù)據(jù),利用多種機器學習模型進行建模測試,發(fā)現(xiàn)本文提出的2種超限學習機改進算法均能更好地對沖蝕數(shù)據(jù)進行擬合和預測,從而為石油化工行業(yè)中腐蝕建模預測問題提供了一種可行的方法。本文從理論分析到實際應用都取得了一定的進展,為超限學習機在復雜工業(yè)問題中的應用提供了一些新的思路,具有一定的理論意義和實踐作用。
[Abstract]:With the advent of the Internet era, whether in the Internet industry, consumer goods industry, financial industry, or the traditional chemical industry, manufacturing industry, the amount of data is increasing at an explosive rate. Big data's circulation, storage, analysis, visualization and other tasks are major challenges for enterprises. Machine learning technology, as an important means of analyzing and mining hidden patterns and rules in data, also highlights its power and importance day by day. Up to now, the research and application of machine learning have been widely used in image recognition, speech analysis, natural language processing, various kinds of commercial data and industrial data mining. In the research of machine learning, classification and regression are the two major bases. In the research process of machine learning, general algorithms such as generalized linear model (GLM), artificial neural network, (ANN), support vector machine, (SVM), overlimit learning machine (ELM) have emerged. How to improve the accuracy of classifier or the fitting accuracy of regression and improve the generalization ability of the algorithm has become an important topic in the development of machine learning technology. In this context, The main work of this paper is as follows: (1) aiming at the problem that the output matrix H of hidden layer does not work due to the random initialization of the weights of the input layer and the hidden layer in the ELM algorithm, some hidden layer nodes do not work. In this paper, a correlation mapping learning machine is proposed. Using the correlation coefficient between input feature and prediction label, the linear correlation information between feature and label is mapped by nonlinear function to determine the weight matrix of input layer and hidden layer. The data set test results show that the algorithm can not only improve the prediction accuracy and accuracy of the out-of-limit learning machine in classification and regression tasks, but also make more efficient use of hidden layer nodes. To improve the generalization ability of the model. (2) because of the homogeneity of hidden layer activation function in ELM network, it is difficult to learn complex data, and it is easy to generate redundant hidden layer nodes. In this paper, a hybrid domain learning machine algorithm based on particle swarm optimization (PSO) is proposed. In this algorithm, the combination of hidden layer activation functions (including seven candidate activation functions) is defined as a particle, and a large number of particles are randomly generated into an initial population, and the hidden layer nodes are iterated to find the optimal individuals according to certain evolutionary rules. The optimal combination of activation functions. The data set test results show that the algorithm can effectively improve the utilization ratio of hidden layer nodes and the ultimate generalization ability of the model. (3) in view of the erosion corrosion phenomenon of pipeline flow in petrochemical production process, combined with practical problems, The following research work has been carried out: 1. According to the fixed variable method, the erosion rate of 10 # carbon steel under different experimental conditions was obtained by using the experimental equipment. 2. 2. The erosion rate (including average rate and maximum rate) of 90 degree bend pipe under different conditions was simulated by CFD computational fluid dynamics simulation software. On the basis of the historical data collected and the various machine learning models used to model and test the above two kinds of scour corrosion phenomena, it is found that the two improved algorithms proposed in this paper can better fit and predict the erosion data. It provides a feasible method for corrosion modeling and prediction in petrochemical industry. In this paper, some progress has been made from theoretical analysis to practical application, which provides some new ideas for the application of over-limit learning machine in complex industrial problems, and has certain theoretical and practical significance.
【學位授予單位】：浙江理工大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP181
本文編號：2341166
[Abstract]:With the advent of the Internet era, whether in the Internet industry, consumer goods industry, financial industry, or the traditional chemical industry, manufacturing industry, the amount of data is increasing at an explosive rate. Big data's circulation, storage, analysis, visualization and other tasks are major challenges for enterprises. Machine learning technology, as an important means of analyzing and mining hidden patterns and rules in data, also highlights its power and importance day by day. Up to now, the research and application of machine learning have been widely used in image recognition, speech analysis, natural language processing, various kinds of commercial data and industrial data mining. In the research of machine learning, classification and regression are the two major bases. In the research process of machine learning, general algorithms such as generalized linear model (GLM), artificial neural network, (ANN), support vector machine, (SVM), overlimit learning machine (ELM) have emerged. How to improve the accuracy of classifier or the fitting accuracy of regression and improve the generalization ability of the algorithm has become an important topic in the development of machine learning technology. In this context, The main work of this paper is as follows: (1) aiming at the problem that the output matrix H of hidden layer does not work due to the random initialization of the weights of the input layer and the hidden layer in the ELM algorithm, some hidden layer nodes do not work. In this paper, a correlation mapping learning machine is proposed. Using the correlation coefficient between input feature and prediction label, the linear correlation information between feature and label is mapped by nonlinear function to determine the weight matrix of input layer and hidden layer. The data set test results show that the algorithm can not only improve the prediction accuracy and accuracy of the out-of-limit learning machine in classification and regression tasks, but also make more efficient use of hidden layer nodes. To improve the generalization ability of the model. (2) because of the homogeneity of hidden layer activation function in ELM network, it is difficult to learn complex data, and it is easy to generate redundant hidden layer nodes. In this paper, a hybrid domain learning machine algorithm based on particle swarm optimization (PSO) is proposed. In this algorithm, the combination of hidden layer activation functions (including seven candidate activation functions) is defined as a particle, and a large number of particles are randomly generated into an initial population, and the hidden layer nodes are iterated to find the optimal individuals according to certain evolutionary rules. The optimal combination of activation functions. The data set test results show that the algorithm can effectively improve the utilization ratio of hidden layer nodes and the ultimate generalization ability of the model. (3) in view of the erosion corrosion phenomenon of pipeline flow in petrochemical production process, combined with practical problems, The following research work has been carried out: 1. According to the fixed variable method, the erosion rate of 10 # carbon steel under different experimental conditions was obtained by using the experimental equipment. 2. 2. The erosion rate (including average rate and maximum rate) of 90 degree bend pipe under different conditions was simulated by CFD computational fluid dynamics simulation software. On the basis of the historical data collected and the various machine learning models used to model and test the above two kinds of scour corrosion phenomena, it is found that the two improved algorithms proposed in this paper can better fit and predict the erosion data. It provides a feasible method for corrosion modeling and prediction in petrochemical industry. In this paper, some progress has been made from theoretical analysis to practical application, which provides some new ideas for the application of over-limit learning machine in complex industrial problems, and has certain theoretical and practical significance.
【學位授予單位】：浙江理工大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP181
【相似文獻】
相關(guān)期刊論文 前4條
1 余以道,秦國軍,溫熙森;演化神經(jīng)網(wǎng)絡診斷模型隱層節(jié)點自生成算法的探討及應用[J];湘潭礦業(yè)學院學報;2000年01期
2 田大鋼;;關(guān)于多層前饋神經(jīng)網(wǎng)絡學習能力的一個注記[J];數(shù)學的實踐與認識;2009年23期
3 申豐山;王黎明;張軍英;;基于SVM技術(shù)的精簡極速學習機[J];華中科技大學學報(自然科學版);2014年06期
4 ;[J];;年期
相關(guān)碩士學位論文 前1條
1 吳學華;超限學習機的優(yōu)化改進及應用研究[D];浙江理工大學;2017年
，本文編號：2341166
本文鏈接：http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2341166.html
最近更新
教材專著
