Anomaly Detection of UAV State Data Based on Single-Class Triangular Global Alignment Kernel Extreme Learning Machine

Unmanned Aerial Vehicles(UAVs)are widely used and meet many demands in military and civilian fields.With the continuous enrichment and extensive expansion of application scenarios,the safety of UAVs is constantly being challenged.To address this challenge,we propose algorithms to detect anomalous data collected from drones to improve drone safety.We deployed a one-class kernel extreme learning machine(OCKELM)to detect anomalies in drone data.By default,OCKELM uses the radial basis(RBF)kernel function as the kernel function of themodel.To improve the performance ofOCKELM,we choose a TriangularGlobalAlignmentKernel(TGAK)instead of anRBF Kernel and introduce the Fast Independent Component Analysis(FastICA)algorithm to reconstruct UAV data.Based on the above improvements,we create a novel anomaly detection strategy FastICA-TGAK-OCELM.The method is finally validated on the UCI dataset and detected on the Aeronautical Laboratory Failures and Anomalies(ALFA)dataset.The experimental results show that compared with other methods,the accuracy of this method is improved by more than 30%,and point anomalies are effectively detected.

Power Transformer Fault Diagnosis Using Random Forest and Optimized Kernel Extreme Learning Machine

Power transformer is one of the most crucial devices in power grid.It is significant to determine incipient faults of power transformers fast and accurately.Input features play critical roles in fault diagnosis accuracy.In order to further improve the fault diagnosis performance of power trans-formers,a random forest feature selection method coupled with optimized kernel extreme learning machine is presented in this study.Firstly,the random forest feature selection approach is adopted to rank 42 related input features derived from gas concentration,gas ratio and energy-weighted dissolved gas analysis.Afterwards,a kernel extreme learning machine tuned by the Aquila optimization algorithm is implemented to adjust crucial parameters and select the optimal feature subsets.The diagnosis accuracy is used to assess the fault diagnosis capability of concerned feature subsets.Finally,the optimal feature subsets are applied to establish fault diagnosis model.According to the experimental results based on two public datasets and comparison with 5 conventional approaches,it can be seen that the average accuracy of the pro-posed method is up to 94.5%,which is superior to that of other conventional approaches.Fault diagnosis performances verify that the optimum feature subset obtained by the presented method can dramatically improve power transformers fault diagnosis accuracy.

Prediction of flyrock induced by mine blasting using a novel kernel-based extreme learning machine

Blasting is a common method of breaking rock in surface mines.Although the fragmentation with proper size is the main purpose,other undesirable effects such as flyrock are inevitable.This study is carried out to evaluate the capability of a novel kernel-based extreme learning machine algorithm,called kernel extreme learning machine(KELM),by which the flyrock distance(FRD) is predicted.Furthermore,the other three data-driven models including local weighted linear regression(LWLR),response surface methodology(RSM) and boosted regression tree(BRT) are also developed to validate the main model.A database gathered from three quarry sites in Malaysia is employed to construct the proposed models using 73 sets of spacing,burden,stemming length and powder factor data as inputs and FRD as target.Afterwards,the validity of the models is evaluated by comparing the corresponding values of some statistical metrics and validation tools.Finally,the results verify that the proposed KELM model on account of highest correlation coefficient(R) and lowest root mean square error(RMSE) is more computationally efficient,leading to better predictive capability compared to LWLR,RSM and BRT models for all data sets.

Dynamic model for predicting nitrogen oxide concentration at outlet of selective catalytic reduction denitrification system based on kernel extreme learning machine

To solve the increasing model complexity due to several input variables and large correlations under variable load conditions,a dynamic modeling method combining a kernel extreme learning machine(KELM)and principal component analysis(PCA)was proposed and applied to the prediction of nitrogen oxide(NO_(x))concentration at the outlet of a selective catalytic reduction(SCR)denitrification system.First,PCA is applied to the feature information extraction of input data,and the current and previous sequence values of the extracted information are used as the inputs of the KELM model to reflect the dynamic characteristics of the NO_(x)concentration at the SCR outlet.Then,the model takes the historical data of the NO_(x)concentration at the SCR outlet as the model input to improve its accuracy.Finally,an optimization algorithm is used to determine the optimal parameters of the model.Compared with the Gaussian process regression,long short-term memory,and convolutional neural network models,the prediction errors are reduced by approximately 78.4%,67.6%,and 59.3%,respectively.The results indicate that the proposed dynamic model structure is reliable and can accurately predict NO_(x)concentrations at the outlet of the SCR system.

Deep kernel extreme learning machine classifier based on the improved sparrow search algorithm

In the classification problem,deep kernel extreme learning machine(DKELM)has the characteristics of efficient processing and superior performance,but its parameters optimization is difficult.To improve the classification accuracy of DKELM,a DKELM algorithm optimized by the improved sparrow search algorithm(ISSA),named as ISSA-DKELM,is proposed in this paper.Aiming at the parameter selection problem of DKELM,the DKELM classifier is constructed by using the optimal parameters obtained by ISSA optimization.In order to make up for the shortcomings of the basic sparrow search algorithm(SSA),the chaotic transformation is first applied to initialize the sparrow position.Then,the position of the discoverer sparrow population is dynamically adjusted.A learning operator in the teaching-learning-based algorithm is fused to improve the position update operation of the joiners.Finally,the Gaussian mutation strategy is added in the later iteration of the algorithm to make the sparrow jump out of local optimum.The experimental results show that the proposed DKELM classifier is feasible and effective,and compared with other classification algorithms,the proposed DKELM algorithm aciheves better test accuracy.

Constrained voting extreme learning machine and its application

Extreme learning machine(ELM)has been proved to be an effective pattern classification and regression learning mechanism by researchers.However,its good performance is based on a large number of hidden layer nodes.With the increase of the nodes in the hidden layers,the computation cost is greatly increased.In this paper,we propose a novel algorithm,named constrained voting extreme learning machine(CV-ELM).Compared with the traditional ELM,the CV-ELM determines the input weight and bias based on the differences of between-class samples.At the same time,to improve the accuracy of the proposed method,the voting selection is introduced.The proposed method is evaluated on public benchmark datasets.The experimental results show that the proposed algorithm is superior to the original ELM algorithm.Further,we apply the CV-ELM to the classification of superheat degree(SD)state in the aluminum electrolysis industry,and the recognition accuracy rate reaches87.4%,and the experimental results demonstrate that the proposed method is more robust than the existing state-of-the-art identification methods.

Research on the IL-Bagging-DHKELM Short-Term Wind Power Prediction Algorithm Based on Error AP Clustering Analysis

With the continuous advancement of China’s“peak carbon dioxide emissions and Carbon Neutrality”process,the proportion of wind power is increasing.In the current research,aiming at the problem that the forecasting model is outdated due to the continuous updating of wind power data,a short-term wind power forecasting algorithm based on Incremental Learning-Bagging Deep Hybrid Kernel Extreme Learning Machine(IL-Bagging-DHKELM)error affinity propagation cluster analysis is proposed.The algorithm effectively combines deep hybrid kernel extreme learning machine(DHKELM)with incremental learning(IL).Firstly,an initial wind power prediction model is trained using the Bagging-DHKELM model.Secondly,Euclidean morphological distance affinity propagation AP clustering algorithm is used to cluster and analyze the prediction error of wind power obtained from the initial training model.Finally,the correlation between wind power prediction errors and Numerical Weather Prediction(NWP)data is introduced as incremental updates to the initial wind power prediction model.During the incremental learning process,multiple error performance indicators are used to measure the overall model performance,thereby enabling incremental updates of wind power models.Practical examples show the method proposed in this article reduces the root mean square error of the initial model by 1.9 percentage points,indicating that this method can be better adapted to the current scenario of the continuous increase in wind power penetration rate.The accuracy and precision of wind power generation prediction are effectively improved through the method.

Determination of influential parameters for prediction of total sediment loads in mountain rivers using kernel-based approaches

It is important to have a reasonable estimation of sediment transport rate with respect to its significant role in the planning and management of water resources projects. The complicate nature of sediment transport in gravel-bed rivers causes inaccuracies of empirical formulas in the prediction of this phenomenon. Artificial intelligences as alternative approaches can provide solutions to such complex problems. The present study aimed at investigating the capability of kernel-based approaches in predicting total sediment loads and identification of influential parameters of total sediment transport. For this purpose, Gaussian process regression(GPR), Support vector machine(SVM) and kernel extreme learning machine(KELM) are applied to enhance the prediction level of total sediment loads in 19 mountain gravel-bed streams and rivers located in the United States. Several parameters based on two scenarios are investigated and consecutive predicted results are compared with some well-known formulas. Scenario 1 considers only hydraulic characteristics and on the other side, the second scenario was formed using hydraulic and sediment properties. The obtained results reveal that using the parameters of hydraulic conditions asinputs gives a good estimation of total sediment loads. Furthermore, it was revealed that KELM method with input parameters of Froude number(Fr), ratio of average velocity(V) to shear velocity(U*) and shields number(θ) yields a correlation coefficient(R) of 0.951, a Nash-Sutcliffe efficiency(NSE) of 0.903 and root mean squared error(RMSE) of 0.021 and indicates superior results compared with other methods. Performing sensitivity analysis showed that the ratio of average velocity to shear flow velocity and the Froude number are the most effective parameters in predicting total sediment loads of gravel-bed rivers.

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.

Incorporating Prior Knowledge into Kernel Based Regression

在一些，样品基于回归任务，观察样品是相当很少足够增进知识。作为结果，在样品和模型复杂性的数字之间的冲突出现，并且回归方法将面对窘境是否选择一个复杂模型。合并优先的知识是这窘境的一个潜在的解决方案。在这份报纸，一种优先的知识被调查，把它合并到核的一个新奇方法基于回归计划被建议。建议优先的 knowledge based 核回归(PKBKR ) 方法包括二 subproblems：在函数空间代表优先的知识，并且联合这个代表和训练样品获得回归函数。为代表的步的一个贪婪算法和为加入步的加权的损失功能被建议。最后，实验被执行验证建议 PKBKR 方法，结果在那里证明建议方法能与适当模型复杂性完成相对高的回归性能，特别当样品的数字是小的或观察噪音大时。

基于KPCA-PSO-ELM算法的地表水化学需氧量紫外-可见吸收光谱检测研究

化学需氧量(COD)是水质检测重要指标之一,反映水体有机物含量。传统的COD化学检测方法存在操作繁琐,等待时间长,二次污染等缺点。紫外-可见吸收光谱法是目前水体化学需氧量检测中应用最为广泛的方法之一,具有检测快速、无污染等特点。为了满足地表水化学需氧量快速、实时、在线监测等要求,采用紫外-可见吸收光谱进行测量,提出了内核主成分分析(KPCA)结合粒子群优化极限学习机(PSO-ELM)预测模型,满足当前对地表水化学需氧量快速、实时监测的要求。对光谱进行Savitzky-Golay(SG)滤波以降低随机噪声的影响;用积分光谱代替原光谱,以降低信号波动带来的影响;再将得到的光谱信息归一化,消除不同光谱数据量纲的影响。将预处理后的数据利用KPCA算法将全光谱数据压缩为5个特征,有效解决光谱信息冗余的问题;采用PSO算法对ELM的权重和偏置进行优化极大提高了模型的精度。对217个河流、长江及支流、湖库等地表水样本按照7∶3随机划分成训练集和测试集,并进行建模测试,其中训练集拟合优度(R2)为0.930 2、均方根误差(RMSE)为0.363 0 mg·L^(-1)、测试集拟合优度R2为0.931 9、均方根误差(RMSE)为0.400 7 mg·L^(-1)。为了验证提出的基于KPCA全光谱数据压缩方法对预测模型的提升效果,分别对比了主成分分析(PCA)、连续投影算法(SPA)、套索回归(LASSO)等特征处理算法。PCA-PSO-ELM模型的RMSE为0.715 1 mg·L^(-1)、 SPA-PSO-ELM模型的RMSE为0.473 7 mg·L^(-1)、 LASSO-PSO-ELM模型的RMSE为0.412 6 mg·L^(-1), KPCA-PSO-ELM模型较上述三种模型,RMSE分别降低了78.46%、 18.22%、 2.97%,结果表明KPCA是一种高效的光谱降维算法,能够有效消除光谱冗余信息,提升模型预测精度。基于KPCA-PSO-ELM预测模型结合紫外-可见吸收光谱可以实现对地表水COD快速、实时检测,为在线COD检测场景提供方法支撑。

基于IAOA-KELM的储气库注采管柱内腐蚀速率预测

针对储气库注采管柱的内腐蚀速率预测问题,建立了基于阿基米德优化算法(Archimedes Optimization Algorithm,AOA)与核极限学习机(Kernel Extreme Learning Machine,KELM)相结合的模型提高腐蚀速率预测精度。通过引入佳点集、改进密度降低因子、采用黄金正弦算法缩小搜索空间,提高局部开发能力,利用改进阿基米德优化算法(Improved Archimedes Optimization Algorithm,IAOA)优化KELM正则化系数(C)和核函数参数(γ),进而建立IAOA-KELM储气库注采管柱内腐蚀速率预测模型;使用MATLAB软件运用该模型对某注采管柱内腐蚀数据集进行学习与预测,将IAOA-KELM模型与KELM、粒子群优化算法(Particle Swarm Optimization,PSO)-KELM、AOA-KELM结果进行预测误差对比。结果表明,IAOA-KELM模型的预测值与实际值较为拟合,其E RMSE为0.65%,E MAE为0.39%,R 2为99.83%,均优于其他模型。研究表明,IAOA-KELM模型能够更为准确地预测储气库注采管柱内腐蚀速率,为储气库注采管柱的运维及储气库的健康管理提供参考。

基于多帧聚类的紧凑型HFSWR虚假点迹识别方法

紧凑型高频地波雷达发射功率低,目标检测时信噪比低、虚警率高,会产生大量虚假点迹,影响后续目标跟踪性能。为了滤除虚假点迹,利用目标的运动特性,提出了一种多帧聚类与极限学习机分类两级级联的虚假点迹识别方法。首先,利用基于最优邻域尺寸的多帧聚类方法,将连续多帧中与待识别点迹属于同一潜在目标的点迹聚类成簇。然后,计算簇内待识别点迹与其相邻帧内点迹的距离-多普勒速度的差分值,以其为特征利用极限学习机辨识虚假点迹。实验结果表明,所提方法能够准确将属于同一目标的点迹聚类,虚假点迹识别率达到95%。

基于Adaboost-INGO-HKELM的变压器故障辨识

针对目前变压器故障诊断准确率低的问题,提出一种多策略集成模型。首先通过等度量映射(isometric mapping, Isomap)对高维非线性不可分的变压器故障数据进行降维处理。其次,利用混合核极限学习机(hybrid kernel based extreme learning machine, HKELM)进行训练学习,考虑到HKELM模型易受参数影响,所以利用北方苍鹰优化算法(northern goshawk optimization, NGO)对其参数进行寻优。但由于NGO收敛速度较慢,易陷入局部最优,引入切比雪夫混沌映射、择优学习、自适应t分布联合策略对其进行改进。同时为了提高模型整体的准确率,通过结合Adaboost集成算法,构建Adaboost-INGO-HKELM变压器故障辨识模型。最后,将提出的Adaboost-INGO-HKELM模型与未进行降维处理的INGO-HKELM模型、Isomap-INGO-KELM模型、Adaboost-Isomap-GWO-SVM等7种模型的测试准确率进行对比。提出的Adaboost-INGO-HKELM模型的准确率可达96%,均高于其他模型,验证了该模型对变压器故障辨识具有很好的效果。

基于BA-MKELM的微电网故障识别与定位

提出一种基于贝叶斯算法优化多核极限学习机的微电网故障识别和定位方法。针对极限学习机输入参数和隐含层节点数随机选取导致回归能力不足的问题,引入核函数,将多项式与高斯径向基核函数加权组合构成多核极限学习机建立故障识别与定位模型,并采用贝叶斯算法对多核极限学习机相关参数进行优化,进一步提高模型的逼近能力。为了验证所提模型的故障识别与定位性能,选用极限学习机和多核极限学习机分别建立故障诊断模型进行比较分析。实验结果表明,所提方法能够高性能地识别和定位微电网中任何类型的故障,识别和定位精度更高。

基于ikPCA-FABAS-KELM的短期风电功率预测

为了增强在短期风电功率预测领域中传统数据驱动机器学习模型的精度,提出基于ikPCA-FABAS-KELM的短期风电功率预测模型.首先,对主成分分析进行改进,提出可逆核主成分分析(ikPCA),在保证数据特征的同时,降低输入数据的复杂度,以提升模型运行速度;其次,引入萤火虫个体吸引策略对天牛须算法(BAS)进行改进,提出FABAS算法;最后,利用FABAS算法对核极限学习机(KELM)的正则化参数C和核参数γ进行寻优,降低人为因素对模型盲目训练的影响,提高模型预测精度.仿真结果显示,提出的预测模型有效提高了传统模型的预测精度.

基于小波核极限学习机的烟叶烘烤过程的智能识别

烟叶烘烤设备操作复杂、技术含量高、熟练掌握烟叶烘烤技术人员不足等问题,影响了烟叶的烘烤质量。针对上述问题,本文提出了基于小波核极限学习机的烟叶烘烤过程的智能识别方法。实验中对三段式烘烤过程中的叶片变软、主脉变软、勾尖卷边、小打筒、大打筒和干筋6个烘烤阶段分别提取了颜色、纹理和温湿度特征,组建了9维特征向量进入小波核极限学习机,通过增量型算法自适应地选择神经元个数,快速准确地识别了6个阶段,得到了98.33%的识别率。实验结果表明本文提出的基于小波核极限学习机的烟叶烘烤过程的智能识别方法具有一定的可行性,为研发烟叶烘烤智能调控系统奠定了理论基础。

基于GMPE和GWO-MKELM算法的往复压缩机轴承故障诊断

针对往复压缩机内部结构复杂,轴承间隙故障特征提取困难和识别准确率不高等问题,提出了多尺度排列熵和多核极限学习机混合算法的智能诊断新方法。首先,针对多尺度排列熵在多尺度过程中,利用均值粗粒化的方式在一定程度上“中和”了原始信号的动力学突变行为,降低了熵值分析的准确性,提出了一种广义多尺度排列熵算法;然后,为解决核极限学习机处理复杂数据样本分类存在的局限性,将高斯核函数、多项式核函数和感知器核函数进行线性叠加,构建混合核函数,提出了多核极限学习机模型。仿真实验结果表明,该故障诊断方法识别准确率高达98%,高效地实现了轴承不同种类故障的智能诊断。

不均衡小样本下多特征优化选择的生命体触电故障识别方法

针对现有的剩余电流保护装置无法有效识别触电事故的问题,该文提出了一种不均衡小样本下多特征优化选择的生命体触电故障识别方法。首先通过变分自编码器(VAE)对实验收集到的生命体触电小样本数据进行增殖以实现正负样本均衡;然后在时域上提取能够反映波形动态变化特性的23个特征量,并利用高斯核Fisher判别分析(GKFDA)与最大信息系数(MIC)法从中选择最优表达特征组;最后,提出基于遗忘因子的在线顺序极限学习机(FOS-ELM)算法实现生命体触电行为的鉴别。实验结果表明,所提方法利用不均衡小样本触电数据集就可以训练出一个优秀的分类模型,诊断准确率可达98.75%,诊断时间仅为1.33 ms。其优良的性能结合在线增量式学习分类器设计,使得模型具备新知识学习能力,具有极好的工程应用前景。

基于ARO-MKELM的微电网攻击检测

智能电网的复杂性和开放性使其在信息交换时更易受到网络攻击的威胁。目前大多数检测方法只关注检测攻击的存在性,不能确定受到攻击的分布式电源的具体位置,导致无法快速将被攻击的分布式电源隔离,继而造成严重的损失。提出一种基于人工兔群优化算法优化多核极限学习机的交流微电网虚假数据注入攻击检测方法。在传统极限学习机中引入组合核函数以提升检测模型的学习能力和泛化能力,并采用具有强全局搜索能力的人工兔群优化算法优化多核极限学习机的核函数参数及正则化系数,进一步提升检测模型的检测精度。利用非训练样本内幅值为55和95的阶跃攻击信号进行仿真验证,检测准确率范围分别达到了(93.44~94.64)%和(98.11~99.23)%,与其他检测模型进行对比分析,验证了所提方法的优越性。