基于思维进化优化极限学习机的滚动轴承故障的智能诊断

为了解决传统极限学习机随机产生的输入权值和阈值对故障诊断的准确率有较大影响的问题,提出了一种利用思维进化算法(mind evolutionary algorithm,MEA)来优化极限学习机(extreme learning machine,ELM)的智能诊断方法。MEA-ELM方法首先将ELM的权值w和阈值b编码成MEA算法个体,产生初始种群,然后通过趋同和异化操作完成种群间的竞争产生优胜种群,整个迭代过程中不断优化极限学习机的初始权值和阈值,最后获得最优个体,对最优个体解码获得隐含层的最优输入权值w和阈值b。将建立的MEA-ELM故障诊断模型应用于滚动轴承的故障诊断中,并分别与传统极限学习机故障诊断模型以及BP神经网络模型的实验结果进行对比,结果表明,经过MEA优化后的ELM不但保持了分类速度快的特点,而且有效提高了诊断的准确率,证明所提出的方法具有良好的可行性和有效性。     

基于LMD近似熵和PSO-ELM的齿轮箱故障诊断

针对齿轮箱使用中常见的故障检测与识别问题,考虑到齿轮箱振动响应信号非线性、非平稳的特性,提出基于局域均值分解(LMD)的近似熵和粒子群优化的极限学习机(PSO-ELM)结合的齿轮箱故障诊断方法。首先,使用LMD分解方法对齿轮箱各工况的振动信号进行分解,结合相关系数选取反映主要故障信息的前4个PF分量。利用近似熵进行定量描述,组成特征向量。最后用粒子群算法对ELM的输入权值与隐含层神经元阈值进行优化,建立PSO-ELM模型,并将近似熵特征值输入到ELM和PSO-ELM模型中,对齿轮箱不同工况进行故障识别与分类。结果表明,基于LMD近似熵和粒子群优化的ELM有更高的分类正确率,验证了该方法的可行性。     

基于小波包最优节点能量特征的BA-ELM齿轮故障诊断方法

针对表征齿轮故障特征信息难提取与极限学习机输入权值与隐含层节点阈值随机选取,致使齿轮故障分类模型泛化能力弱、精度差的问题,提出一种基于小波包最优节点能量特征的BA-ELM齿轮故障诊断方法。该方法首先将齿轮振动信号经过小波包分解,再利用分解所得各节点信号与原信号的相关系数选取出最优节点并计算其能量特征;其次,利用蝙蝠算法优化极限学习机的输入权值与隐含层节点阈值,建立BA-ELM的齿轮故障分类模型;最后,将所得小波包最优节点能量特征向量作为模型输入进行齿轮不同故障状态的分类识别。实验结果表明,与基于SVM和ELM的故障分类方法相比,基于小波包最优节点能量特征的BA-ELM齿轮故障诊断方法具有更高的分类精度,更强的泛化能力。     

基于ICEEMDAN及PFA-ELM的齿轮箱故障诊断研究

齿轮箱是工业设备中常用的传动部件。针对齿轮箱故障特征提取及诊断精度不足的问题，提出一种基于改进的自适应噪声完备集合经验模态分解(ICEEMDAN)及探路者算法(PFA)优化极限学习机(ELM)的故障诊断方法。首先，利用ICEEMDAN对信号进行分解，得到多个本征模态函数(IMF)。其次，基于斯皮尔曼相关系数，筛选出有效的IMF，并计算出每个有效IMF的模糊熵和排列熵作为故障特征向量。最后，利用PFA算法优化ELM中的权值和阈值，构建基于PFA-ELM的故障诊断模型。实验表明，PFA-ELM的故障诊断精度高达98.67%。该方法能够准确描述齿轮箱的工作状态，具有较高的实用价值。     

基于PSO优化的RBF网络液压泵故障诊断研究

提出了以小包分解和粒子群优化的径向基神经网络(RBFNN)为基础的液压泵故障诊断方法。通过小波包分解对振动信号做降噪处理并提取相应的故障信号的特征能量值,将此特征能量值作为神经网络的输入,再采用粒子群算法对神经网络的数据中心和宽度、输出权值和阈值进行优化,并将其分别与基于传统神经网络和基于遗传算法优化的故障诊断方法进行对比分析。对比结果表明,该方法具有很好的诊断效果。     

基于SAPSO-ELM的纳米铁粉分解炉温度预测

为实现纳米铁粉分解炉温度的精准预测,提出了一种基于自适应粒子群优化算法(SAPSO)和极限学习机(ELM)的分解炉温度预测模型。采用现场数据,选取相关因素,利用ELM建立了对应的模型,并针对ELM输入权值矩阵和隐含层阈值选取的随机性,采用SAPSO对其进行动态寻优。通过仿真分析,分解炉温度预测误差达到0.039 2%,验证了模型的准确性。设置不同SAPSO参数进行试验,验证了模型的稳定性。设置不同神经元数目,与普通ELM的对比试验表明,SAPSO-ELM温度预测模型具有更好的泛化性。     

分层极限学习机在滚动轴承故障诊断中的应用

针对滚动轴承信号的非线性、非平稳特性,致使轴承状态难识别的问题,提出分层极限学习机(HELM)故障诊断模型。首先采用集合经验模式分解(EEMD)将轴承信号分解为若干个本征模式分量(IMFs),并提取其能量熵值构建特征向量;其次利用自动编码器(AE)对极限学习机的隐含层进行分层,且使隐含层节点的输入权值和阈值满足正交条件;最后将构建的特征向量作为H-ELM算法的输入,通过训练建立H-ELM滚动轴承故障分类模型。实验结果表明:H-ELM滚动轴承故障分类模型比SVM、ELM故障分类模型具有更高的精度、更强的稳定性。     

基于互信息和IGSA优化ELM的重整芳烃收率软测量

芳烃收率是催化重整生产过程中一个重要的产品质量指标。针对芳烃收率难以在线测量的问题,提出一种基于互信息(MI)和改进引力搜索算法(IGSA)优化极限学习机(ELM)的芳烃收率软测量建模方法。首先利用MI技术对输入变量进行特征提取及降维处理,确定软测量模型的辅助变量;其次通过引入序列二次规划法(SQP)和混沌变异策略,构建一种具有良好全局寻优性能的改进引力搜索算法,并利用该算法优化极限学习机的隐层阈值及输入权值参数,优化目标同时兼顾模型输出均方根误差和输出矩阵条件数的最小化,建立起基于IGSA优化ELM的芳烃收率软测量模型;最后应用该模型对某炼化企业催化重整装置的芳烃收率进行预报研究,结果表明,该软测量模型具有较高的预测精度和可靠性能。     

H-K-ELM在滚动轴承故障诊断中的应用

针对滚动轴承振动信号的不规则性和复杂性,导致轴承状态难以有效识别的问题,提出基于分层核极限学习机(Hierarchical Kernel Extreme Learning Machine,H-K-ELM)的滚动轴承故障诊断方法。首先,将测得信号经集合经验模态分解(Ensemble Empirical Mode Decomposition,EEMD)处理后得到一系列IMF本征模态分量,并提取各分量的排列熵PE值组成高维特征向量集;其次,利用高斯核函数的内积来表达ELM算法的隐含层输出函数,然后使用自动编码器对其分层,从而隐含层节点数自适应确定和隐含层阈值与输入权值满足正交条件;最后,将所得高维特征向量集作为H-KELM算法的输入,通过训练建立核函数极限学习机滚动轴承故障分类模型,进行滚动轴承不同故障状态的分类辨识。实验结果表明:H-K-ELM滚动轴承故障分类模型比ELM、K-ELM故障分类模型具有更高的精度、更强的稳定性。     

GA-BP算法在船舶主机故障诊断中的应用

针对船舶主机故障具有诊断对象多、多因素耦合造成诊断准确率低等问题,提出了用遗传算法优化BP神经网络的故障诊断方法,利用GA算法对BP神经网络的初始权值、阈值在较大范围内搜索寻值,同时采用反向传播算法在较小范围内进行微调,优化网络结构和参数,加快目标最优值的求解,最后结合一般BP神经网络方法进行分析比较。实验结果表明,优化初始权值和阈值后的测试样本的误差由0.996 43减少到0.097 333,训练样本的误差由1.464 1减少到0.080 657;经GA优化后的BP神经网络模型对主机故障类型的诊断的准确率为100%,实现对船舶故障诊断的高效判别。     

基于IQPSO优化ELM的熟料质量指标软测量研究

水泥熟料游离氧化钙(f Ca O)含量是水泥生产过程的重要质量指标。针对难以建立其精确的数学模型和难以实时在线测量的问题,首先采用序列二次规划方法增强量子粒子群算法的局部搜索能力,提出了一种局部区域可调的改进量子粒子群优化(IQPSO)算法,并采用提出的IQPSO算法优化超限学习机(ELM)的输入层权值和隐层阈值参数,在优化过程中同时兼顾均方根误差和隐层输出矩阵条件数最小的原则,建立了基于IQPSO优化ELM的水泥熟料f Ca O软测量模型,仿真验证结果表明,IQPSO算法具有较高的搜索精度以及较快的收敛速度,建立的软测量模型精度高、泛化能力强。最后基于该模型,通过软件编程的方法给出了水泥熟料质量指标软测量仪表,实现了f Ca O含量的在线软测量。     

基于ASOS-ELM的湿式球磨机负荷软测量方法

针对湿式球磨机在磨矿过程中内部负荷靠专家经验难以准确预测的问题,提出一种基于改进的共生生物搜索(ameliorated symbiotic organisms search,简称ASOS)-极限学习机(extreme learning machine,简称ELM)的磨机负荷软测量方法。首先,利用ELM算法建立磨机负荷软测量模型,运用ASOS算法优化软测量模型的隐含层参数;其次,以筒体振动与振声信号的特征信息构建磨机负荷特征向量,并将其作为软测量模型的输入,将磨机负荷参数作为输出;最后,通过磨矿负荷检测实验和对比分析表明,磨机负荷软测量模型的负荷参数预测准确率较高,泛化能力较强,为磨机磨矿效率的提高及控制优化提供了有益的指导。     

Artificial neural network based on genetic learning for machining of polyetheretherketone composite materials

In this paper an artificial neural network (ANN) aiming for the efficient modelling of a set of machining conditions for orthogonal cutting of polyetheretherketone (PEEK) composite materials is presented. The supervised learning of the ANN is based on a genetic algorithm (GA) supported by an elitist strategy. Input, hidden and output layers model the topology of the ANN. The weights of the synapses and the biases for hidden and output nodes are used as design variables in the ANN learning process. Considering a set of experimental data, the mean relative error between experimental and numerical results is used to monitor the learning process obtaining the completeness of the machining process modelling. Also a regularization term associated to biases in hidden and output neurons are included in the GA fitness function for learning. Using a different set of experimental results, the optimal ANN obtained after learning is tested. The optimal number of nodes on the hidden layer is searched and the positive influence of the regularization term is demonstrated. This approach of ANN learning based on GA presents low mean relative errors in learning and testing phases.     

An extreme learning machine combined with Landweber iteration algorithm for the inverse problem of electrical capacitance tomography

The image reconstruction of the electrical capacitance tomography (ECT) is an ill-posed and sparse problem. In order to increase the accuracy and speed of the image reconstruction, this paper proposes a new reconstruction algorithm which is based on the extreme learning machine (ELM) with the Landweber iteration method. Firstly, a nonlinear mapping model is established between the pixel gray-scale values and the interelectrode capacitances by using the ELM which has a good learning ability and high speed. Secondly, the Landweber iteration method, which has a good performance in convergence and stability, is applied to calculate the output weight matrix of ELM. Finally, a convergence and stable mapping model of ELM with the Landweber iteration algorithm (L-ELM) for ECT image reconstruction is trained on Matlab platform. Both simulation and measurement tests are carried out to evaluate and analyze the proposed method. Experimental results indicate that the proposed algorithm has good generalization ability and high image reconstruction quality which are better than those of conventional ELM algorithm.     

自适应集成极限学习机在故障诊断中的应用

为了改善在线贯序极限学习机的分类效果,进一步提高算法在小样本数据下的稳定性和泛化性,设计自适应网络集成机制,提出极限学习机改进算法。该算法借鉴learn++集成思想,通过计算增量学习时的分类准确率和隐层网络输出权值范数,在线调整集成输出中子网络的投票权值以及网络输入权值和节点偏置。UCI数据集及轴承故障的实验分析表明,与改进前相比,该算法分类准确率提高约1个百分点的同时,6个数据集100次实验的标准差分别降低了0.1～1.2个百分点。最后将该算法与小波包相结合应用于发动机的故障诊断中,取得了91.16％的分类准确率。     

采用鱼群算法进化极限学习机的假肢步态识别

为提高下肢假肢步态识别的准确性,提出一种基于鱼群(fish swarm,简称FA)算法优化极限学习机(extreme learning machine,简称ELM)的模式识别方法。首先,提取张量投影特征,分析了特征值选取的合理性;其次,采用主成分分析法降维;最后,利用鱼群算法进化极限学习机分类识别平地行走、上楼、下楼、上坡及下坡5种步态,识别准确率达到97.45%。通过实验比较了该算法与极限学习机等分类器在假肢步态分类上的识别准确率与识别时间,结果表明,FA-ELM方法识别准确率优于其他方法。     

A robust hybrid model integrating enhanced inputs based extreme learning machine with PLSR (PLSR-EIELM) and its application to intelligent measurement

In this paper, a robust hybrid model integrating an enhanced inputs based extreme learning machine with the partial least square regression (PLSR-EIELM) was proposed. The proposed PLSR-EIELM model can overcome two main flaws in the extreme learning machine (ELM), i.e. the intractable problem in determining the optimal number of the hidden layer neurons and the over-fitting phenomenon. First, a traditional extreme learning machine (ELM) is selected. Second, a method of randomly assigning is applied to the weights between the input layer and the hidden layer, and then the nonlinear transformation for independent variables can be obtained from the output of the hidden layer neurons. Especially, the original input variables are regarded as enhanced inputs; then the enhanced inputs and the nonlinear transformed variables are tied together as the whole independent variables. In this way, the PLSR can be carried out to identify the PLS components not only from the nonlinear transformed variables but also from the original input variables, which can remove the correlation among the whole independent variables and the expected outputs. Finally, the optimal relationship model of the whole independent variables with the expected outputs can be achieved by using PLSR. Thus, the PLSR-EIELM model is developed. Then the PLSR-EIELM model served as an intelligent measurement tool for the key variables of the Purified Terephthalic Acid (PTA) process and the High Density Polyethylene (HDPE) process. The experimental results show that the predictive accuracy of PLSR-EIELM is stable, which indicate that PLSR-EIELM has good robust character. Moreover, compared with ELM, PLSR, hierarchical ELM (HELM), and PLSR-ELM, PLSR-EIELM can achieve much smaller predicted relative errors in these two applications.     

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。     

Adaptive control of nonlinear system using online error minimum neural networks

In this paper, a new learning algorithm named OEM-ELM (Online Error Minimized-ELM) is proposed based on ELM (Extreme Learning Machine) neural network algorithm and the spreading of its main structure. The core idea of this OEM-ELM algorithm is: online learning, evaluation of network performance, and increasing of the number of hidden nodes. It combines the advantages of OS-ELM and EM-ELM, which can improve the capability of identification and avoid the redundancy of networks. The adaptive control based on the proposed algorithm OEM-ELM is set up which has stronger adaptive capability to the change of environment. The adaptive control of chemical process Continuous Stirred Tank Reactor (CSTR) is also given for application. The simulation results show that the proposed algorithm with respect to the traditional ELM algorithm can avoid network redundancy and improve the control performance greatly.     

基于SSA-ELM的双层十字梁结构光纤布拉格光栅传感器三维力解耦

针对三维力传感器维间耦合干扰严重的问题,以双层十字梁结构光纤布拉格光栅三维力传感器为研究对象,提出了基于麻雀搜索算法优化极限学习机(Sparrow Search Algorithm–Extreme Learning Machine,SSA-ELM)的解耦算法.首先,研究了光纤布拉格光栅的传感及测力原理,揭示该三维力传感...