Casing life prediction using Borda and support vector machine methods

Eight casing failure modes and 32 risk factors in oil and gas wells are given in this paper. According to the quantitative analysis of the influence degree and occurrence probability of risk factors, the Borda counts for failure modes are obtained with the Borda method. The risk indexes of failure modes are derived from the Borda matrix. Based on the support vector machine （SVM）, a casing life prediction model is established. In the prediction model, eight risk indexes are defined as input vectors and casing life is defined as the output vector. The ideal model parameters are determined with the training set from 19 wells with casing failure. The casing life prediction software is developed with the SVM model as a predictor. The residual life of 60 wells with casing failure is predicted with the software, and then compared with the actual casing life. The comparison results show that the casing life prediction software with the SVM model has high accuracy.

Vibration reliability analysis for aeroengine compressor blade based on support vector machine response surface method

To ameliorate reliability analysis efficiency for aeroengine components, such as compressor blade, support vector machine response surface method(SRSM) is proposed. SRSM integrates the advantages of support vector machine(SVM) and traditional response surface method(RSM), and utilizes experimental samples to construct a suitable response surface function(RSF) to replace the complicated and abstract finite element model. Moreover, the randomness of material parameters, structural dimension and operating condition are considered during extracting data so that the response surface function is more agreeable to the practical model. The results indicate that based on the same experimental data, SRSM has come closer than RSM reliability to approximating Monte Carlo method(MCM); while SRSM(17.296 s) needs far less running time than MCM(10958 s) and RSM(9840 s). Therefore,under the same simulation conditions, SRSM has the largest analysis efficiency, and can be considered a feasible and valid method to analyze structural reliability.

Krylov Iterative Methods for Support Vector Machines to Classify Galaxy Morphologies

Large catalogues of classified galaxy images have been useful in many studies of the universe in astronomy. There are too many objects to classify manually in the Sloan Digital Sky Survey, one of the premier data sources in astronomy. Therefore, efficient machine learning and classification algorithms are required to automate the classifying process. We propose to apply the Support Vector Machine (SVM) algorithm to classify galaxy morphologies and Krylov iterative methods to improve runtime of the classification. The accuracy of the classification is measured on various categories of galaxies from the survey. A three-class algorithm is presented that makes use of multiple SVMs. This algorithm is used to assign the categories of spiral, elliptical, and irregular galaxies. A selection of Krylov iterative solvers are compared based on their efficiency and accuracy of the resulting classification. The experimental results demonstrate that runtime can be significantly improved by utilizing Krylov iterative methods without impacting classification accuracy. The generalized minimal residual method (GMRES) is shown to be the most efficient solver to classify galaxy morphologies.

Probabilistic back analysis for geotechnical engineering based on Bayesian and support vector machine

Geomechanical parameters are complex and uncertain.In order to take this complexity and uncertainty into account,a probabilistic back-analysis method combining the Bayesian probability with the least squares support vector machine(LS-SVM) technique was proposed.The Bayesian probability was used to deal with the uncertainties in the geomechanical parameters,and an LS-SVM was utilized to establish the relationship between the displacement and the geomechanical parameters.The proposed approach was applied to the geomechanical parameter identification in a slope stability case study which was related to the permanent ship lock within the Three Gorges project in China.The results indicate that the proposed method presents the uncertainties in the geomechanical parameters reasonably well,and also improves the understanding that the monitored information is important in real projects.

Improvement of the prediction performance of a soft sensor model based on support vector regression for production of ultra-low sulfur diesel

A novel data-driven, soft sensor based on support vector regression （SVR） integrated with a data compression technique was developed to predict the product quality for the hydrodesulfurization （HDS） process. A wide range of experimental data was taken from a HDS setup to train and test the SVR model. Hyper-parameter tuning is one of the main challenges to improve predictive accuracy of the SVR model. Therefore, a hybrid approach using a combination of genetic algorithm （GA） and sequential quadratic programming （SQP） methods （GA-SQP） was developed. Performance of different optimization algorithms including GA-SQP, GA, pattern search （PS）, and grid search （GS） indicated that the best average absolute relative error （AARE）, squared correlation coefficient （R2）, and computation time （CT） （AARE = 0.0745, R2 = 0.997 and CT = 56 s） was accomplished by the hybrid algorithm. Moreover, to reduce the CT and improve the accuracy of the SVR model, the vector quantization （VQ） technique was used. The results also showed that the VQ technique can decrease the training time and improve prediction performance of the SVR model. The proposed method can provide a robust, soft sensor in a wide range of sulfur contents with good accuracy.

Developing a Support Vector Machine Based QSPR Model to Predict Gas-to-Benzene Solvation Enthalpy of Organic Compounds

The purpose of this paper is to present a novel way to building quantitative structure-property relationship(QSPR) models for predicting the gas-to-benzene solvation enthalpy(ΔHSolv) of 158 organic compounds based on molecular descriptors calculated from the structure alone. Different kinds of descriptors were calculated for each compounds using dragon package. The variable selection technique of enhanced replacement method(ERM) was employed to select optimal subset of descriptors. Our investigation reveals that the dependence of physico-chemical properties on solvation enthalpy is a nonlinear observable fact and that ERM method is unable to model the solvation enthalpy accurately. The standard error value of prediction set for support vector machine(SVM) is 1.681 kJ ? mol^(-1) while it is 4.624 kJ ? mol^(-1) for ERM. The results established that the calculated ΔHSolvvalues by SVM were in good agreement with the experimental ones, and the performances of the SVM models were superior to those obtained by ERM one. This indicates that SVM can be used as an alternative modeling tool for QSPR studies.

Improved Scheme for Fast Approximation to Least Squares Support Vector Regression

The solution of normal least squares support vector regression(LSSVR)is lack of sparseness,which limits the real-time and hampers the wide applications to a certain degree.To overcome this obstacle,a scheme,named I2FSA-LSSVR,is proposed.Compared with the previously approximate algorithms,it not only adopts the partial reduction strategy but considers the influence between the previously selected support vectors and the willselected support vector during the process of computing the supporting weights.As a result,I2FSA-LSSVR reduces the number of support vectors and enhances the real-time.To confirm the feasibility and effectiveness of the proposed algorithm,experiments on benchmark data sets are conducted,whose results support the presented I2FSA-LSSVR.

A Novel Kernel for Least Squares Support Vector Machine

Extreme learning machine(ELM) has attracted much attention in recent years due to its fast convergence and good performance.Merging both ELM and support vector machine is an important trend,thus yielding an ELM kernel.ELM kernel based methods are able to solve the nonlinear problems by inducing an explicit mapping compared with the commonly-used kernels such as Gaussian kernel.In this paper,the ELM kernel is extended to the least squares support vector regression(LSSVR),so ELM-LSSVR was proposed.ELM-LSSVR can be used to reduce the training and test time simultaneously without extra techniques such as sequential minimal optimization and pruning mechanism.Moreover,the memory space for the training and test was relieved.To confirm the efficacy and feasibility of the proposed ELM-LSSVR,the experiments are reported to demonstrate that ELM-LSSVR takes the advantage of training and test time with comparable accuracy to other algorithms.

Solving large-scale multiclass learning problems via an efficient support vector classifier

Support vector machines （SVMs） are initially designed for binary classification. How to effectively extend them for multiclass classification is still an ongoing research topic. A multiclass classifier is constructed by combining SVM^light algorithm with directed acyclic graph SVM （DAGSVM） method, named DAGSVM^light A new method is proposed to select the working set which is identical to the working set selected by SVM^light approach. Experimental results indicate DAGSVM^light is competitive with DAGSMO. It is more suitable for practice use. It may be an especially useful tool for large-scale multiclass classification problems and lead to more widespread use of SVMs in the engineering community due to its good performance.

Data Selection Using Support Vector Regression

Geophysical data sets are growing at an ever-increasing rate,requiring computationally efficient data selection （thinning） methods to preserve essential information.Satellites,such as WindSat,provide large data sets for assessing the accuracy and computational efficiency of data selection techniques.A new data thinning technique,based on support vector regression （SVR）,is developed and tested.To manage large on-line satellite data streams,observations from WindSat are formed into subsets by Voronoi tessellation and then each is thinned by SVR （TSVR）.Three experiments are performed.The first confirms the viability of TSVR for a relatively small sample,comparing it to several commonly used data thinning methods （random selection,averaging and Barnes filtering）,producing a 10％ thinning rate （90％ data reduction）,low mean absolute errors （MAE） and large correlations with the original data.A second experiment,using a larger dataset,shows TSVR retrievals with MAE ＜ 1 m s-1 and correlations ≥ 0.98.TSVR was an order of magnitude faster than the commonly used thinning methods.A third experiment applies a two-stage pipeline to TSVR,to accommodate online data.The pipeline subsets reconstruct the wind field with the same accuracy as the second experiment,is an order of magnitude faster than the nonpipeline TSVR.Therefore,pipeline TSVR is two orders of magnitude faster than commonly used thinning methods that ingest the entire data set.This study demonstrates that TSVR pipeline thinning is an accurate and computationally efficient alternative to commonly used data selection techniques.

Dynamic Spatial Discrimination Maps of Discriminative Activation between Different Tasks Based on Support Vector Machines

As a set of supervised pattern recognition methods, support vector machines (SVMs) have been successfully applied to functional magnetic resonance imaging (fMRI) field, but few studies have focused on visualizing discriminative regions of whole brain between different cognitive tasks dynamically. This paper presents a SVM-based method for visualizing dynamically discriminative activation of whole-brain voxels between two kinds of tasks without any contrast. Our method provides a series of dynamic spatial discrimination maps (DSDMs), representing the temporal evolution of discriminative brain activation during a duty cycle and describing how the discriminating information changes over the duty cycle. The proposed method was applied to investigate discriminative brain functional activations of whole brain voxels dynamically based on a hand-motor task experiment. A set of DSDMs between left hand movement and right hand movement were reached. Our results demonstrated not only where but also when the discriminative activations of whole brain voxels occurred between left hand movement and right hand movement during one duty cycle.

Improved Support Vector Machine Approach Based on Determining Thresholds Automatically

To improve the training speed of support vector machine （SVM）, a method called improved center distance ratio method （ICDRM） with determining thresholds automatically is presented here without reduce the identification rate. In this method border vectors are chosen from the given samples by comparing sample vectors with center distance ratio in advance. The number of training samples is reduced greatly and the training speed is improved. This method is used to the identification for license plate characters. Experimental resuhs show that the improved SVM method-ICDRM does well at identification rate and training speed.

基于机器学习与DBN网络的网络入侵检测方法研究

随着计算机网络的发展,网络入侵的情况也越来越严重。传统网络入侵检测方法存在检测效率低、误判率高的情况,为了解决这些问题,提出了一种基于支持向量机的深度置信网络(SVM-DBN)的入侵检测方法。通过对支持向量机(SVM)进行优化,将支持向量机与深度信念网络(DBN)融合,利用SVM、DBN与SVM-DBN在网络入侵数据集中进行对比。结果表明,SVM-DBN算法的误差率最低,比DBN和SVM的误差率平均值分别低了8.95%,12.70%,且SVM-DBN算法在训练次数为140次时最大绝对百分比误差为4.8%,均优于对比方法。这说明SVM-DBN网络能够有效地提高网络入侵检测的精度和效率。

基于空间投影和聚类划分的SVR加速算法

数据不仅能产生价值,还对统计学的科学发展提供了动力。随着科技的飞速发展,海量数据得以涌现,但大规模的数据会导致很多传统处理方法很难满足各领域对数据分析的需求。面对海量数据时代学习算法的低效性,分治法通常被认为是解决这一问题最直接、最广泛使用的策略。SVR是一种强大的回归算法,在模式识别和数据挖掘等领域有广泛应用。然而在处理大规模数据时,SVR训练效率低。为此,该文利用分治思想提出一种基于空间投影和聚类划分的SVR加速算法(PKM-SVR)。利用投影向量将数据投影到二维空间;利用聚类方法将数据空间划分为k个互不相交的区域;在每个区域上训练SVR模型;利用每个区域的SVR模型预测落入同一区域的待识别样本。在标准数据集上与传统的数据划分方法进行对比实验,实验结果表明该算法训练速度较快,并表现出更好的预测性能。

基于广域信息处理的配电网故障隔离技术研究

针对分布式电源并入配电网后,传统算法进行故障检测时存在定位准确度偏低、反应速度较慢的问题,文中基于广域信息处理技术提出了一种配电网故障隔离方法。该方法采用模态分解算法将故障复杂信号分解为多种类基础小信号,使用支持向量机对这些小信号进行数据分类。但由于传统支持向量机的收敛速度较慢,因此通过引入粒子群算法对其参数加以优化,从而提升模型的运算速度。实验结果表明,在加入分布式电源的电网中,所提算法的故障定位准确率为96.7%,平均运行时间则为43.9 s,且这两项参数在对比算法中均为最优。由此证明,该算法可应用于实际工程中,为配电网故障隔离提供技术支撑。

基于BA-SVR混合模型的果蔬生鲜物流需求预测模型研究

本文通过构建BA-SVR混合模型对果蔬生鲜物流需求进行预测研究。首先通过互联网大数据搜索技术构建果蔬生鲜需求指数相关网络关键词词库,进而采用皮尔森(Pearson)相关分析和逐步回归选择预测因子。其次,结合果蔬自身特点以及物流市场变动因素,提出了果蔬生鲜物流指数(Fruit&Vegetable Logistic Index, FVLI)概念,分析了FVLI变动的影响变量,使其成为反映物流市场信息变动的重要指标。再次,利用蝙蝠算法(Bat Algorithm, BA)自动更新迭代参数的优势,将其引入到支持向量回归(Support Vector Regression, SVR)模型中,用于优化SVR模型中自由参数值,进而构建BA-SVR混合模型对北京市果蔬生鲜需求变化趋势进行模拟仿真及实证预测。最后根据构建的性能预测指标,通过确立的基准模型与其进行对比,评估BA-SVR混合模型性能的优劣,从而提出一种可以用于果蔬生鲜物流信息短期预测的改进方法。

基于贪婪算法的云计算数据块节能存储仿真

针对云数据储存能量消耗大的问题,提出基于贪婪算法的云计算数据块节能存储方法。建立具有用户访问层、核心服务层和服务管理层的云计算架构,了解数据块产生过程和储存环境;将物理机利用率、能源消耗量和主机储存能力作为节能储存的约束条件,将待储存的数据块封装为虚拟机,利用贪婪算法描述虚拟机部署问题,构建贪婪算法下虚拟机分配环境;计算单个物理机和整个数据中心的数据块储存能力和资源请求能力,综合考虑虚拟机分配的相关向量,运算数据储存时的能量消耗;以总体能量最小为目标函数,将虚拟机分为主模块与备用模块,通过设置虚拟机状态转换规则来减少储存开销,实现节能储存。实验结果表明,上述方法在数据储存过程中能够有效减少服务器开启数量,节省储存功率,达到节能目的。

基于纸张纤维特征的纸页抗张强度智能模拟及预测研究

对纸页抗张强度进行智能模拟,有助于更好地对某种纸页的性能进行分析甚至预测。基于此,针对现有纸页抗张强度模拟方法的缺陷进行总结,认为现有典型Page分析模型存在客观性分析不足等问题,结合偏最小二乘法、支持向量机等构建了一种基于造纸纤维特性的纸页抗张强度智能模拟模型,借助该模型对某种典型纸页的性能进行模拟分析。测试结果表明:该模型能够高效、准确地对纸页抗张强度进行预测,与传统模型相比具有更强的实用性。

基于特征判定系数的电力变压器振动信号故障诊断

变压器带电故障诊断对于保证电力变压器安全平稳运行具有重要的意义。针对变压器工作环境复杂且单一参数表征变压器故障类型不全面的问题,文中提出一种基于自适应噪声完备集合经验模态分解(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)和特征熵权法(entropy weight method,EWM)进行故障诊断的方法。通过相关系数与峭度加权(correlation coefficient and weighted kurtosis,CCWK)原则筛选CEEMDAN分量并重构信号,在实现剔除冗余分量的同时,提升变压器振动信号特征的表征能力;利用EWM构建特征判定系数实现单一数据诊断变压器故障类型;通过主成分分析法减小混合域特征尺度,采用鸡群优化算法优化支持向量机(support vector machine,SVM)模型进行故障诊断。对某变电站110 kV三相油浸式变压器进行分析,结果表明与概率神经网络和SVM等变压器故障诊断方法相比,文中方法能在提前定性故障类型的同时,进一步提高变压器故障诊断的准确率与效率。

基于SARIMA和SVR组合模型的转向架系统寿命评估

随着地铁运营时间和里程的增加,地铁车辆逐渐接近其理论寿命,为确保车辆运行安全性,需对其重要子系统进行健康状态及剩余寿命评估。文中选取车辆转向架系统作为研究对象,提出了一种基于协方差优选法的季节性回归移动平均(SARIMA)和支持向量回归(SVR)的组合模型对转向架寿命进行评估。首先,将车辆转向架系统历史故障率转化为健康指数,然后基于协方差优选法将SARIMA和SVR进行赋权组合,根据转向架系统历史健康指数进行预测,最后建立历史和预测的健康指数与运行时间的数学模型,分析得到转向架系统的剩余寿命。以某地铁车辆转向架系统为例进行算例分析及验证,结果表明组合模型可更准确地预测其健康状态,为有关维修部门开展维修维护策略提供理论依据,估计得出其剩余寿命,为车辆寿命后期退役及延寿决策提供理论数据分析支撑。