拉曼光谱结合深度学习算法的塑料分类的研究

拉曼光谱法能识别塑料制品光谱特征峰,但操作流程繁琐且准确率有待提升,对此提出了基于一维卷积神经网络 (one-dimensional convolution neural network, 1-D CNN) 的塑料制品分类算法,首先建立以聚乙烯 (polyethylene, PE) 、聚丙烯 (polypropylene, PP) 、聚对苯二甲酸乙二醇酯 (polyethylene terephthalate, PET) 和聚苯乙烯 (polystyrene, PS) 为原材料的40种塑料包装样本数据集;然后设计1-D CNN、K近邻 (KNN) 、决策树 (DT) 和支持向量机 (SVM) 4种算法模型进行训练,并在光谱分类流程、模型准确率和鲁棒性等方面进行对比。实验结果表明,1-D CNN在不经过预处理条件下分类准确率达到98.62%,且在60 dB噪声下仍有96.42%的准确率,优于另外3种传统机器学习算法模型。该结果证实,拉曼光谱融合神经网络的多分类方法可提升塑料制品检测性能。     

基于机器视觉的手机电池表面缺陷检测

针对手机电池表面质量人工检测情况,开发了电池表面缺陷无损检测系统软件。首先电池表面经过倾斜矫正、感兴趣区域提取和字符灰度值修改等预处理操作,通过基于灰度密度分布和灰度差的自适应阈值亮度法对感兴趣区域进行子图像遍历,融合有重合区域的缺陷子图像并滤除没有明显缺陷的区域;然后采用支持向量机多种类分类法,提取二值图像像素分布规律作为训练特征,识别电池表面缺陷种类;最后设计了人机交互界面,确定最佳的可变参数,实验测试缺陷识别率达95%以上。     

Discharge prediction for rectangular sharp-crested weirs by machine learning techniques

The stage-discharge relationship of a weir is essential for posteriori calculations of flow discharges. Conventionally, it is determined by regression methods, which is time-consuming and may subject to limited prediction accuracy. To provide a better estimate, the machine learning models, artificial neural network (ANN), support vector machine (SVM) and extreme learning machine (ELM), are assessed for the prediction of discharges of rectangular sharp-crested weirs. A large number of experimental data sets are adopted to develop and calibrate these models. Different input scenarios and data management strategies are employed to optimize the models, for which performance is evaluated in the light of statistical criteria. The results show that all three models are capable of predicting the discharge coefficient with high accuracy, but the SVM exhibits somewhat better performance. Its maximum and mean relative error are respectively 5.44 and 0.99%, and 99% of the predicted data show an error below 5%. The coefficient of determination and root mean square error are 0.95 and 0.01, respectively. The model sensitivity is examined, indicative of the dominant roles of weir Reynolds number and contraction ratio in discharge estimation. The existing empirical formulas are assessed and compared against the machine learning models. It is found that the relationship proposed by Vatankhah exhibits the highest accuracy. However, it is still less accurate than the machine learning approaches. The study is intended to provide reference for discharge determination of overflow structures including spillways.     

基于支持向量机的钢淬透性预测研究

支持向量机是建立在统计学理论之上的强有力的机器学习技术。本文提出了基于支持向量机模型预测钢淬透性的方法，并分析了核函数的选择对支持向量机建模的影响。以江阴兴澄钢铁公司的实际数据进行实验，结果表明，支持向量机方法有着良好的泛化能力，优于人工神经网络建模方法。     

电机故障诊断支持向量机

基于数据的机器学习是现代智能技术中的重要方面。统计学习理论(Statistical learnmgtheory SLT)是研究小样本情况下机器学习规律的新理论。支持向量机(Support vector machine SVM)是在这一理论体系基础上发展起来的一种通用学习方法。SLT和SVM正成为继神经网络研究之后新的研究热点。通过对鼠笼式异步电动机转子断条故障进行实验模拟，对实验获取的采样电流信号经FFT分析，构造以低频到高频的频谱特性为分量的学习样本向量，通过支持向量机SVM对故障电流样本的训练，使SVM具有分类功能。最后，采用SVM对电动机各种转子断条故障进行诊断分类，取得较满意的结果，说明支持向量机SVM是进行故障诊断的一种新方法。     

基于支持向量机和模态频率的结构损伤诊断

支持向量机（support vector machine，SVM）是一种基于统计学习理论的机器学习算法，能够较好地解决小样本的学习问题。文中介绍支持向量机回归算法，并应用于结构损伤诊断领域；构造基于模态频率的损伤标识量，作为特征参数训练支持向量机实现对结构损伤的定位和程度标识；最后以梁的损伤识别为例进行验证。结果表明，支持向量机在结构损伤诊断领域中具有很好的应用前景。     

基于支持向量机的航空发动机故障诊断

支持向量机学习方法以结构风险最小化原则取代传统机器学习方法中的经验风险最小化原则,在有限样本的学习中显示出优异的性能。本文将这一新的统计学习方法应用到航空发动机故障诊断的研究中,并通过某型航空发动机故障诊断的实验结果表明了本文方法的有效性。     

基于SVM的传感器非线性特性校正新方法

介绍了一种基于支持向量机的解决传感器系统非线性特性问题的新方法。支持向量机是Vapnik教授提出的基于统计学习理论的新一代机器学习技术，它有效地解决了小样本学习问题，因此该方法对样本数量没有特殊的要求。实验证明该方法有效，同时研究表明该方法也能用于其他系统的非线性校正。     

PENETRATION QUALITY EVALUATION IN ROBOTIZED ARC WELDING BASED ON SUPP0RT VECTOR MACHINE

A quality monitoring method by means of support vector machines (SVM) for robotized gasmetal arc welding (GMAW) is introduced. Through the feature extraction of the welding process signal,a SVM classifier is constructed to establish the relationship between the feature of process parametersand the quality of weld penertration. Under the samples obtained from auto parts welding productionline, the learning machine with a radial basis function kernel shows good performance. And thismethod can be feasible to identify defect online in welding production.     

基于GMKL-SVM的模拟电路故障诊断方法

提出了一种新颖的基于广义多核支持向量机(GMKL-SVM)的模拟电路故障诊断方法。首先,应用Haar小波分析提取被测电路时域响应信号的小波系数作为特征参量,并生成样本数据;然后,基于样本数据,应用量子粒子群算法对GMKL-SVM的参数进行优化,并以此建立基于GMKL-SVM的故障诊断模型,用于区分模拟电路的各个故障。实例电路的单故障和双故障诊断实验结果表明,所提出的GMKL-SVM方法能较好地实现模拟电路故障诊断,与传统的GMKL-SVM方法相比,表现出了更好的性能,获得了更高的故障诊断正确率。     

A novel sense-through-foliage target recognition system based on sparse representation and improved particle swarm optimization-based support vector machine

A new recognition system of improved particle swarm optimization-based support vector machine (SVM) combined with sparse representation-based feature extraction is proposed for recognize targets obscured by foliage. Real data sets of four kinds of samples are acquired using a bistatic ultra-wideband (UWB) radar system. Sparse representation (SR) theory is applied to analyzing the components of received target echo signals and sparse coefficients are used to describe target features, the dimension of the sparse coefficients is reduced using principal component analysis (PCA). Support vector machine is a powerful tool for solving the recognition problem with small sampling, nonlinearity and high dimension. Improved particle swarm optimization (IPSO) is developed in this study to determine the optimal parameters for SVM with the highest accuracy and generalization ability. The experiment results indicate that the method of feature extraction using SR can effectively represent the original data better. The recognition result of the proposed method is also compared with SVM, k-nearest neighbor (KNN) and BP neural network (BPNN). The effectiveness of the proposed approach is verified by experiments taken in the forest environment. Our findings show that the proposed method combined with bistatic UWB radar technology provides a good access to achieve the aim of automatic sense through foliage target recognition.     

钢筋混凝土框架近断层速度脉冲地震响应分析

针对滚动轴承的故障诊断问题，提出了一种基于栈式稀疏自编码网络(stacked sparse auto encoder，简称SSAE)、改进灰狼智能优化算法(improved grey wolf optimization，简称IGWO)以及支持向量机(support vector machine，简称SVM)的混合智能故障诊断模型。首先，利用栈式自编码网络强大的特征自提取能力，实现故障信号深层频谱特征的自适应学习，通过引入稀疏项约束提高特征学习的泛化性能；其次，利用改进的灰狼算法实现支持向量机的参数优化；最后，基于优化后的SVM完成对故障特征向量的分类识别。所提混合智能故障诊断模型充分结合了深度神经网络强大的特征自学习能力和支持向量机优秀的小样本分类性能，避免了手工特征提取的弊端，可对不同故障类型的振动信号实现更精准的识别。多组对比实验表明，相比传统方法，笔者所提出的模型具有更优秀的故障识别能力，诊断准确率可达98%以上。     

基于ELM和近似熵的脑电信号检测方法

脑电癫痫波的自动检测与分类对癫痫病情的诊断具有重要意义。提出了一种基于极端学习机(extreme learning ma-chine,ELM)和近似熵的脑电信号检测方法。首先,计算脑电信号的近似熵作为非线性特征,并与利用小波变换技术提取的线性特征波动指数相结合,组成特征向量,然后将特征向量送入单隐层前馈神经网络,采用ELM学习算法训练网络。实验表明,与BP(backpropagation)和SVM(support vector machine)算法相比,ELM在训练时间和识别精度两方面性能最佳,对用于实验的脑电数据检测识别率达到98%以上。     

SOFT SENSING MODEL BASED ON SUPPORT VECTOR MACHINE AND ITS APPLICATION

Soft sensor is widely used in industrial process control. It plays an important role to improve the quality of product and assure safety in production. The core of soft sensor is to construct soft sensing model. A new soft sensing modeling method based on support vector machine (SVM) is proposed. SVM is a new machine learning method based on statistical learning theory and is powerful for the problem characterized by small sample, nonlinearity, high dimension and local minima. The proposed methods are applied to the estimation of frozen point of light diesel oil in distillation column. The estimated outputs of soft sensing model based on SVM match the real values of frozen point and follow varying trend of frozen point very well. Experiment results show that SVM provides a new effective method for soft sensing modeling and has promising application in industrial process applications.     

基于SVM构造的FLANN数据融合方法在CPS修正中的应用

在对常规函数链接型神经网络（FLANN）构造方法的认识基础上，讨论了一种基于支持向量机（SVM）技术的FLANN构造新方法，并利用该方法对实际的电容压力传感器（CPS）系统进行非线性修正及温度补偿。先将SVM的拓扑结构与常规FLANN结构进行比较，确定两者的等价性。因此，可通过SVM求解二次规划问题来实现FLANN结构的唯一优化。用常规FLANN方法在同样条件下进行对比实验，实验结果表明用该方法构造的FLANN具有结果唯一、结构简单、全局优化等特点，特别是在实验数据较少的小样本条件下仍然具有更高的鲁棒性和修正精度。     

Support vector machine based optimization of multi-fault classification of gears with evolutionary algorithms from time–frequency vibration data

A multi-fault classification of gears has been attempted by support vector machine (SVM) learning techniques with the help of time–frequency (wavelet) vibration data. A suitable exploitation of SVM is based on the selection of SVM parameters. The main focus of the present paper is to study the performance of the multiclass capability of SVM techniques. Different optimization methods (i.e., the grid-search method (GSM), the genetic algorithm (GA) and the artificial bee colony algorithm (ABCA)) have been performed for optimizing SVM parameters. Four fault conditions of gears have been considered. The continuous wavelet transform (CWT) and wavelet packet transform (WPT) are estimated from time domain signals, and a set of statistical features are extracted from the wavelet transform. The prediction of fault classification has been attempted at the same angular speed as the measured data as well as innovatively at the intermediate and extrapolated angular speed conditions, since it is not feasible to have measurement of vibration data at continuous speeds of interest. The classification ability is noted and compared with predictions when purely time domain data is used, and it shows an excellent prediction performance.     

Support vector machine in machine condition monitoring and fault diagnosis

Recently, the issue of machine condition monitoring and fault diagnosis as a part of maintenance system became global due to the potential advantages to be gained from reduced maintenance costs, improved productivity and increased machine availability. This paper presents a survey of machine condition monitoring and fault diagnosis using support vector machine (SVM). It attempts to summarize and review the recent research and developments of SVM in machine condition monitoring and diagnosis. Numerous methods have been developed based on intelligent systems such as artificial neural network, fuzzy expert system, condition-based reasoning, random forest, etc. However, the use of SVM for machine condition monitoring and fault diagnosis is still rare. SVM has excellent performance in generalization so it can produce high accuracy in classification for machine condition monitoring and diagnosis. Until 2006, the use of SVM in machine condition monitoring and fault diagnosis is tending to develop towards expertise orientation and problem-oriented domain. Finally, the ability to continually change and obtain a novel idea for machine condition monitoring and fault diagnosis using SVM will be future works.     

势函数聚类的优化下采样SVM分类方法

为了改善大样本集下支持向量机(SVM)的训练效率和泛化性能,提出一种新算法。该算法运用采样优化和学习器优化相结合的策略,通过构建势函数对原始样本空间进行密度度量,建立了不同参数的高斯核,以实现对样本空间不同区域的逐次覆盖,并以增量学习的方式生成下采样集。然后,在所获取的下采样集上进行SVM初始训练,通过寻找原始训练集中的边界样本,进行SVM二次优化。最后,将新算法应用于人工数据集及基准数据集,结果表明,该算法在有效改善训练效率的同时,保证了分类器的泛化性能。     

基于混合核函数支持向量机的齿轮诊断方法研究

支持向量机是一种基于统计学习理论的新型机器学习方法,它具有在训练样本很少的情况下达到很好的分类效果的优点.把支持向量机技术应用于齿轮故障诊断,通过预先使用局部、全局核函数支持向量机的分类结果适当选取各自在混合函数中的权重,来作为混合核函数进行支持向量机分类.实验和数据分析证明,使用混合核的支持向量机比单独使用全局或局部...     

基于支持向量机的矿井提升机制动系统的故障诊断

故障样本缺乏是制约智能故障诊断发展的重要原因,支持向量机是近年来提出的一种基于小样本的统计学习方法.将支持向量机分类算法应用到提升机制动系统的多类故障分类,并与BP神经网络进行对比研究,实验表明,支持向量机算法比BP神经网络具有更好的分类性能,且 "一对多"支持向量机的分类效果是最好的,更适合于提升机制动系统的故障诊断.