基于KNN-SVM的混合气体检测方法研究

当今混合气体检测的研究中,针对多组分气体数据进行分类预测的数学算法百花齐放,如何快速且准确的检测出气体的成分和浓度逐渐成为当今研究的热门。然而在一些研究中,气体数据特征难以捕捉和判断,泛化能力不足,对气体数据进行分类预测的精度和效率表现较差。为此,针对一些数据偏差和泛化误差无界的问题,提出了一种K最近邻-支持向量机(KNN-SVM)算法,对一些难以作出分类的模糊气体数据进行二次分类,采用KNN和SVM两种算法共同抉择,更加全面的捕捉数据特征,根据实验确定各自算法的权重比从而提高判别气体类别的准确率,两种算法的集成也能提高算法的效率,对于不同种类的气体也能有良好的适应性的稳定性。该实验气体组分由12 mg·L^(-1)的C_(2)H_(2)、NO_(2)、SF_(6),10 mg·L^(-1)的NO_(2)、SF_(6)和5 mg·L^(-1)的C_(2)H_(2)(背景气体皆为N_(2))以及两瓶纯N_(2)的气瓶组成;通过互相混合和与N_(2)配比制备出实验设定的气体浓度。实验过程通过单一气体的检测可分别对三种气体获得60组训练集,并通过这60组数据可进行线性拟合得到每种气体的拟合线,得到气体浓度与气体吸收峰值的关系,通过实验检测得到的三种气体拟合线,其中C_(2)H_(2)拟合线的调整后R^(2)为0.991,NO_(2)拟合线的调整后R^(2)为0.981,SF_(6)拟合线的调整后R^(2)为0.987,可得气体检测的准确性。再通过互相混合进行检测可分别获得40组训练集,采用KNN-SVM算法对混合气体进行分类和预测,后通过拟合线即可反演出混合气体中每种气体的浓度。将该算法与传统SVM算法进行各种分类指标对比均可显示出该算法的有效性和优越性。实验结果表明,KNN-SVM算法在气体分类预测方面表现出卓越的性能,准确率高达99.167%,AUC(area under curve)值达99.375%。这一算法不仅提高了气体检测的准确性,还增强了泛化能力可适应多样化的气体组分,为实时气体检测系统提供了有力支持。

基于SARIMA-SVM模型的季节性PM_(2.5)浓度预测

空气污染是城市环境治理的主要问题之一,而PM_(2.5)是影响空气质量的重要因素。针对传统时间序列预测模型对PM_(2.5)浓度预测缺少季节性因素分析,预测精度不够高的问题,提出一种基于机器学习的季节性差分自回归滑动平均-支持向量机(SARIMA-SVM)融合模型。该融合模型为串联型融合模型,将数据拆分为线性部分与非线性部分。SARIMA模型在差分自回归滑动平均(ARIMA)模型的基础上增加了季节性因素提取参数,能有效分析PM_(2.5)浓度数据的季节性规律变化趋势,较好地预测数据未来的线性变化趋势。结合SVM模型对预测数据的残差序列进行优化,利用滑动步长预测法确定残差序列的最优预测步长,通过网格搜索确定最优模型参数,实现对PM_(2.5)浓度数据的长期预测,同时提高整体预测精度。通过对武汉市近5年的PM_(2.5)浓度监测数据进行分析,结果表明该融合模型的预测准确率相较于单一模型有很大提升,在相同的实验环境下比单一的ARIMA、Auto ARIMA、SARIMA模型分别提升了99%、99%、98%,稳定性也更好,为PM_(2.5)浓度预测研究提供了新的思路。

Enhancing XRF sensor-based sorting of porphyritic copper ore using particle swarm optimization-support vector machine(PSO-SVM)algorithm

X-ray fluorescence(XRF)sensor-based ore sorting enables efficient beneficiation of heterogeneous ores,while intraparticle heterogeneity can cause significant grade detection errors,leading to misclassifications and hindering widespread technology adoption.Accurate classification models are crucial to determine if actual grade exceeds the sorting threshold using localized XRF signals.Previous studies mainly used linear regression(LR)algorithms including simple linear regression(SLR),multivariable linear regression(MLR),and multivariable linear regression with interaction(MLRI)but often fell short attaining satisfactory results.This study employed the particle swarm optimization support vector machine(PSO-SVM)algorithm for sorting porphyritic copper ore pebble.Lab-scale results showed PSO-SVM out-performed LR and raw data(RD)models and the significant interaction effects among input features was observed.Despite poor input data quality,PSO-SVM demonstrated exceptional capabilities.Lab-scale sorting achieved 93.0%accuracy,0.24%grade increase,84.94%recovery rate,57.02%discard rate,and a remarkable 39.62 yuan/t net smelter return(NSR)increase compared to no sorting.These improvements were achieved by the PSO-SVM model with optimized input combinations and highest data quality(T=10,T is XRF testing times).The unsuitability of LR methods for XRF sensor-based sorting of investigated sample is illustrated.Input element selection and mineral association analysis elucidate element importance and influence mechanisms.

Research on Euclidean Algorithm and Reection on Its Teaching

In this paper,we prove that Euclid's algorithm,Bezout's equation and Divi-sion algorithm are equivalent to each other.Our result shows that Euclid has preliminarily established the theory of divisibility and the greatest common divisor.We further provided several suggestions for teaching.

基于SVM的字符验证码图像识别方法研究

验证码(CAPTCHA)是一种区分机器和人的操作的自动程序,可以防止批量注册、刷票、爬虫抓取等恶意访问行为。随着验证码技术的发展,验证码类型越来越多,安全隐患也越来越多,以传统字符型验证码作为研究对象,对验证码图像进行灰度化、二值化、去噪、分割等预处理,采用支持向量机(SVM)对数字字符验证码进行识别。实验结果表明,当训练数据达到一定数量时,机器对传统字符验证码的识别有较高的准确率。

基于特征融合的GA-SVM配电网单相接地故障选线方法

针对配电网单相接地故障数据量较少时,选线方法精度不高,提出一种基于特征融合的遗传算法优化支持向量机(genetic algorithm-support vector machine,GA-SVM)配电网单相接地故障选线方法,采用傅里叶变换、有功功率法以及小波包变换对不同故障工况下每一条线路的暂态零序电流进行分解,提取基波幅值、五次谐波幅值、平均有功功率分量及小波能量值四种特征,经主成分分析法对这四种特征进行融合,提取主成分分量,建立特征数据库,将特征数据库的80%作为训练集,20%作为测试集,通过GA-SVM对特征数据库中的样本进行训练,实现故障选线。通过MATLAB/Simulink搭建包含5条馈线的配电网仿真模型进行验证,结果表明,提出的算法可以通过小样本数据实现故障选线,选线精度较高,适用性强。

An Algorithm for Cloud-based Web Service Combination Optimization Through Plant Growth Simulation

In order to improve the efficiency of cloud-based web services,an improved plant growth simulation algorithm scheduling model.This model first used mathematical methods to describe the relationships between cloud-based web services and the constraints of system resources.Then,a light-induced plant growth simulation algorithm was established.The performance of the algorithm was compared through several plant types,and the best plant model was selected as the setting for the system.Experimental results show that when the number of test cloud-based web services reaches 2048,the model being 2.14 times faster than PSO,2.8 times faster than the ant colony algorithm,2.9 times faster than the bee colony algorithm,and a remarkable 8.38 times faster than the genetic algorithm.

Method for Estimating the State of Health of Lithium-ion Batteries Based on Differential Thermal Voltammetry and Sparrow Search Algorithm-Elman Neural Network

Precisely estimating the state of health(SOH)of lithium-ion batteries is essential for battery management systems(BMS),as it plays a key role in ensuring the safe and reliable operation of battery systems.However,current SOH estimation methods often overlook the valuable temperature information that can effectively characterize battery aging during capacity degradation.Additionally,the Elman neural network,which is commonly employed for SOH estimation,exhibits several drawbacks,including slow training speed,a tendency to become trapped in local minima,and the initialization of weights and thresholds using pseudo-random numbers,leading to unstable model performance.To address these issues,this study addresses the challenge of precise and effective SOH detection by proposing a method for estimating the SOH of lithium-ion batteries based on differential thermal voltammetry(DTV)and an SSA-Elman neural network.Firstly,two health features(HFs)considering temperature factors and battery voltage are extracted fromthe differential thermal voltammetry curves and incremental capacity curves.Next,the Sparrow Search Algorithm(SSA)is employed to optimize the initial weights and thresholds of the Elman neural network,forming the SSA-Elman neural network model.To validate the performance,various neural networks,including the proposed SSA-Elman network,are tested using the Oxford battery aging dataset.The experimental results demonstrate that the method developed in this study achieves superior accuracy and robustness,with a mean absolute error(MAE)of less than 0.9%and a rootmean square error(RMSE)below 1.4%.

Short-TermWind Power Forecast Based on STL-IAOA-iTransformer Algorithm:A Case Study in Northwest China

Accurate short-term wind power forecast technique plays a crucial role in maintaining the safety and economic efficiency of smart grids.Although numerous studies have employed various methods to forecast wind power,there remains a research gap in leveraging swarm intelligence algorithms to optimize the hyperparameters of the Transformer model for wind power prediction.To improve the accuracy of short-term wind power forecast,this paper proposes a hybrid short-term wind power forecast approach named STL-IAOA-iTransformer,which is based on seasonal and trend decomposition using LOESS(STL)and iTransformer model optimized by improved arithmetic optimization algorithm(IAOA).First,to fully extract the power data features,STL is used to decompose the original data into components with less redundant information.The extracted components as well as the weather data are then input into iTransformer for short-term wind power forecast.The final predicted short-term wind power curve is obtained by combining the predicted components.To improve the model accuracy,IAOA is employed to optimize the hyperparameters of iTransformer.The proposed approach is validated using real-generation data from different seasons and different power stations inNorthwest China,and ablation experiments have been conducted.Furthermore,to validate the superiority of the proposed approach under different wind characteristics,real power generation data fromsouthwestChina are utilized for experiments.Thecomparative results with the other six state-of-the-art prediction models in experiments show that the proposed model well fits the true value of generation series and achieves high prediction accuracy.

Unveiling Effective Heuristic Strategies: A Review of Cross-Domain Heuristic Search Challenge Algorithms

The Cross-domain Heuristic Search Challenge(CHeSC)is a competition focused on creating efficient search algorithms adaptable to diverse problem domains.Selection hyper-heuristics are a class of algorithms that dynamically choose heuristics during the search process.Numerous selection hyper-heuristics have different imple-mentation strategies.However,comparisons between them are lacking in the literature,and previous works have not highlighted the beneficial and detrimental implementation methods of different components.The question is how to effectively employ them to produce an efficient search heuristic.Furthermore,the algorithms that competed in the inaugural CHeSC have not been collectively reviewed.This work conducts a review analysis of the top twenty competitors from this competition to identify effective and ineffective strategies influencing algorithmic performance.A summary of the main characteristics and classification of the algorithms is presented.The analysis underlines efficient and inefficient methods in eight key components,including search points,search phases,heuristic selection,move acceptance,feedback,Tabu mechanism,restart mechanism,and low-level heuristic parameter control.This review analyzes the components referencing the competition’s final leaderboard and discusses future research directions for these components.The effective approaches,identified as having the highest quality index,are mixed search point,iterated search phases,relay hybridization selection,threshold acceptance,mixed learning,Tabu heuristics,stochastic restart,and dynamic parameters.Findings are also compared with recent trends in hyper-heuristics.This work enhances the understanding of selection hyper-heuristics,offering valuable insights for researchers and practitioners aiming to develop effective search algorithms for diverse problem domains.

Multi-Objective Hybrid Sailfish Optimization Algorithm for Planetary Gearbox and Mechanical Engineering Design Optimization Problems

This paper introduces a hybrid multi-objective optimization algorithm,designated HMODESFO,which amalgamates the exploratory prowess of Differential Evolution(DE)with the rapid convergence attributes of the Sailfish Optimization(SFO)algorithm.The primary objective is to address multi-objective optimization challenges within mechanical engineering,with a specific emphasis on planetary gearbox optimization.The algorithm is equipped with the ability to dynamically select the optimal mutation operator,contingent upon an adaptive normalized population spacing parameter.The efficacy of HMODESFO has been substantiated through rigorous validation against estab-lished industry benchmarks,including a suite of Zitzler-Deb-Thiele(ZDT)and Zeb-Thiele-Laumanns-Zitzler(DTLZ)problems,where it exhibited superior performance.The outcomes underscore the algorithm’s markedly enhanced optimization capabilities relative to existing methods,particularly in tackling highly intricate multi-objective planetary gearbox optimization problems.Additionally,the performance of HMODESFO is evaluated against selected well-known mechanical engineering test problems,further accentuating its adeptness in resolving complex optimization challenges within this domain.

Enhanced Multi-Object Dwarf Mongoose Algorithm for Optimization Stochastic Data Fusion Wireless Sensor Network Deployment

Wireless sensor network deployment optimization is a classic NP-hard problem and a popular topic in academic research.However,the current research on wireless sensor network deployment problems uses overly simplistic models,and there is a significant gap between the research results and actual wireless sensor networks.Some scholars have now modeled data fusion networks to make them more suitable for practical applications.This paper will explore the deployment problem of a stochastic data fusion wireless sensor network(SDFWSN),a model that reflects the randomness of environmental monitoring and uses data fusion techniques widely used in actual sensor networks for information collection.The deployment problem of SDFWSN is modeled as a multi-objective optimization problem.The network life cycle,spatiotemporal coverage,detection rate,and false alarm rate of SDFWSN are used as optimization objectives to optimize the deployment of network nodes.This paper proposes an enhanced multi-objective mongoose optimization algorithm(EMODMOA)to solve the deployment problem of SDFWSN.First,to overcome the shortcomings of the DMOA algorithm,such as its low convergence and tendency to get stuck in a local optimum,an encircling and hunting strategy is introduced into the original algorithm to propose the EDMOA algorithm.The EDMOA algorithm is designed as the EMODMOA algorithm by selecting reference points using the K-Nearest Neighbor(KNN)algorithm.To verify the effectiveness of the proposed algorithm,the EMODMOA algorithm was tested at CEC 2020 and achieved good results.In the SDFWSN deployment problem,the algorithm was compared with the Non-dominated Sorting Genetic Algorithm II(NSGAII),Multiple Objective Particle Swarm Optimization(MOPSO),Multi-Objective Evolutionary Algorithm based on Decomposition(MOEA/D),and Multi-Objective Grey Wolf Optimizer(MOGWO).By comparing and analyzing the performance evaluation metrics and optimization results of the objective functions of the multi-objective algorithms,the algorithm outperforms the other algorithms in the SDFWSN deployment results.To better demonstrate the superiority of the algorithm,simulations of diverse test cases were also performed,and good results were obtained.

基于SVM的TBM盾构施工滚刀更换周期预测

滚刀作为TBM的重要部件,其磨损严重影响掘进效率和安全性,准确预测更换周期至关重要,然而传统方法主要依赖经验判断和简单数学模型,在复杂地质条件下效果欠佳。为此提出利用支持向量机(SVM)智能算法,结合实际工程数据,包括地质条件、推力、扭矩、转速等,建立滚刀更换周期的预测模型。重点分析了影响滚刀磨损的主要因素,并选择了线性、多项式和径向基函数(RBF)3种SVM核函数进行模型优化。研究数据来源包含13 080个样本,按80%用于训练,20%用于测试。结果显示,径向基函数SVM核函数模型在不同地层条件下预测准确率均超过80%,优于其他核函数。模型的准确率、精度和误分类率进一步验证了其在不同地质条件下的可靠性。基于SVM的预测模型能捕捉掘进过程中复杂非线性关系,具有较强的泛化能力。

基于WOA-SVM模型的边坡安全系数预测

由于边坡失稳对人们的生命财产造成的威胁日益突出,所以对边坡的稳定性进行评价对于边坡灾害防治具有重要意义,而在使用传统的支持向量机模型对边坡安全系数进行估算时,其精度较低、收敛性较差,对边坡安全系数估算的误差也就比较大。所以针对此类问题,采用了鲸鱼优化算法来对支持向量机(SVM)模型进行优化,使用WOA来寻找SVM的最佳惩罚系数c和核函数参数g,由此建立WOA-SVM模型,并将优化后的WOA-SVM模型用来对边坡安全系数进行预测,以达到提高估算边坡安全系数准确性的目的。结果显示,WOA-SVM模型的平均绝对误差(MAE)、均方根误差(RMSE)和平均绝对百分比误差(MAPE)均优于其他模型,说明对边坡安全系数估算的精确度要高于其他模型,所以该模型对于边坡稳定性分析有一定的参考价值。

基于改进CNN-SVM的光伏组件红外图像故障诊断方法

为识别光伏组件故障类型,提高光伏系统发电效率,提出了一种基于改进CNN-SVM模型的光伏组件红外图像故障诊断方法。首先以光伏组件红外图像为输入样本构建改进CNN模型,采用全局平均池化层代替传统CNN模型的全连接层,在进行图像特征提取的同时降低模型参数量;利用数据增强和批归一化技术提高模型泛化能力,降低模型过拟合。其次采用非线性支持向量机SVM代替传统CNN模型中的Softmax分类器,以提高光伏组件红外图像故障识别准确率。最后采用Infrared Solar Modules数据集对所提模型进行了实例验证。结果表明:与传统CNN模型相比,改进CNN-SVM模型故障诊断准确率高,对各故障类型的识别能力强。

基于WOA-VMD与PSO-SVM的滚动轴承故障诊断

滚动轴承工作环境恶劣且振动信号容易受到噪声干扰,使得轴承故障不易被识别。针对此问题,提出了鲸鱼优化算法变分模态分解(whale optimization algorithm variational mode decomposition,WOA-VMD)和粒子群算法优化支持向量机(particle swarm optimization support vector machine,PSO-SVM)的滚动轴承故障诊断方法,首先,采用WOA-VMD寻找分解层数和惩罚因子最优参数组合;其次,将轴承正常信号以及故障信号作为输入进行变分模态分解(variational mode decomposition,VMD),得到若干个本征模态函数(intrinsic mode function,IMF),计算各模态分量的样本熵值作为特征向量;再次,将特征向量分成训练集和测试集;最后,将分组的特征向量分别输入到支持向量机(support vector machine,SVM)模型与PSO-SVM模型中进行训练与故障诊断。结果表明,SVM模型故障诊断率分别为89.1667%和86.2500%,PSO-SVM模型故障诊断率分别为100%和99.5833%,轴承故障得到了有效识别。

GWO和LSSVM混合算法对空气质量的预测研究

针对空气质量受多种因素影响预测难度大的问题,提出一种灰狼算法(GWO)优化最小二乘支持向量机(LSSVM)的空气质量预测模型,该模型利用灰狼算法对最小二乘支持向量机的核函数和惩罚因子进行迭代寻优,减少参数选择的盲目性,提高预测精度。为了验证该模型的优越性,将其预测结果与最小二乘支持向量机、遗传算法优化最小二乘支持向量机和BP神经网络的预测结果进行比较。结果表明:(1)相对于传统的单一预测模型,混合预测模型的拟合优度更好。(2)在混合模型中灰狼算法优化最小二乘支持向量机的拟合优度高于遗传算法优化最小二乘支持向量机的拟合优度。因此,灰狼算法优化最小二乘支持向量机对空气质量指数的预测具有现实利用价值。

基于全矢CEEMDAN能量矩和AMHSSA-SVM的滚动轴承故障诊断

为充分利用滚动轴承的故障特征信息,提高故障诊断的准确性和可靠性,文中提出了一种基于全矢自适应噪声完全集成经验模态分解(Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise,CEEMDAN)能量矩和自适应多种群混合麻雀搜索算法(Adaptive Multi-population Hybrid Sparrow Search Algorithm,AMHSSA)优化支持向量机(Support Vector Machine,SVM)的故障诊断方法。首先,采用全矢谱技术融合同源双通道信号;其次,采用CEEMDAN算法处理融合信号,选择相关系数较大的前5阶IMF分量,并计算其能量矩作为支持向量机模型的特征输入;最后,提出AMHSSA算法并优化支持向量机模型的参数,建立AMHSSA-SVM故障诊断模型。对该模型进行测试,结果表明:此模型有效提高了识别准确性,与类似模型对比,进一步证明了其在分类精度和优化时间方面的优越性。

基于Borderline-SMOTE和OOA-SVM的心脏病诊断预测模型

为实现心脏病精准预测,构建了一种预测准确率较高的心脏病诊断预测模型.首先对原始数据集进行pearson相关性分析和归一化处理;然后采用过采样技术Borderline-SMOTE算法,平衡训练数据集的少数类;之后利用鱼鹰优化算法(Osprey Optimization Algorithm,OOA)优化支持向量机(support vector machine,SVM),获得最优参数组合(C,g);最后在测试数据集上进行分类预测.与SSA-SVM、SMA-SVM和SVM相比,本文方法OOA-SVM的预测准确率最高,达到了95.08%,且模型稳定性最好.

结合SVM与XGBoost的链式多路径覆盖测试用例生成

机器学习方法可很好地与软件测试相结合,增强测试效果,但少有学者将其运用于测试数据生成方面.为进一步提高测试数据生成效率,提出一种结合SVM(support vector machine)和XGBoost(extreme gradient boosting)的链式模型,并基于此模型借助遗传算法实现多路径测试数据生成.首先,利用一定样本训练若干个用于预测路径节点状态的子模型(SVM和XGBoost),通过子模型的预测精度值筛选最优子模型,并根据路径节点顺序将其依次链接,形成一个链式模型C-SVMXGBoost(chained SVM and XGBoost).在利用遗传算法生成测试用例时,使用训练好的链式模型代替插桩法获取测试数据覆盖路径(预测路径),寻找预测路径与目标路径相似的路径集,对存在相似路径集的预测路径进行插桩验证,获取精确路径,计算适应度值.在交叉变异过程中引入样本集中路径层级深度较大的优秀测试用例进行重用,生成覆盖目标路径的测试数据.最后,保留进化生成中产生的适应度较高的个体,更新链式模型C-SVMXGBoost,进一步提高测试效率.实验表明,C-SVMXGBoost较其他各对比链式模型更适合解决路径预测问题,可提高测试效率.并且通过与已有经典方法相比,所提方法在覆盖率上提高可达15%,平均进化代数也有所降低,在较大规模程序上其降低百分比可达65%.