The General Technique of Selected Harmonics Elimination for Multilevel Converters

Forhigh power applications,multilevel converters have many advantages in comparison with other circuit topologies with output transformers. Cascaded inverters are one type of multilevel converters,they are easy to implement,very suitable for modularized layout and packaging.Their manufacturing cost is low.A multilevel PWM technique,called as General Technique of Selected Harmonics Elimination (GTSHE) ,is proposed in the paper. A general harmonic elimination equation for N cells,M pulses per half cycle,nth harmonic is derived,and verified by simulation results.

A feature selection method combined with ridge regression and recursive feature elimination in quantitative analysis of laser induced breakdown spectroscopy

In the spectral analysis of laser-induced breakdown spectroscopy,abundant characteristic spectral lines and severe interference information exist simultaneously in the original spectral data.Here,a feature selection method called recursive feature elimination based on ridge regression(Ridge-RFE)for the original spectral data is recommended to make full use of the valid information of spectra.In the Ridge-RFE method,the absolute value of the ridge regression coefficient was used as a criterion to screen spectral characteristic,the feature with the absolute value of minimum weight in the input subset features was removed by recursive feature elimination(RFE),and the selected features were used as inputs of the partial least squares regression(PLS)model.The Ridge-RFE method based PLS model was used to measure the Fe,Si,Mg,Cu,Zn and Mn for 51 aluminum alloy samples,and the results showed that the root mean square error of prediction decreased greatly compared to the PLS model with full spectrum as input.The overall results demonstrate that the Ridge-RFE method is more efficient to extract the redundant features,make PLS model for better quantitative analysis results and improve model generalization ability.

Study and Design of a DC/AC Energy Converter for PV System Connected to the Grid Using Harmonic Selected Eliminated (HSE) Approach

Nowadays, distributing network-connected photovoltaic (PV) systems are expanded by merging a PV system and a Direct Current (DC)/Alternating Current (AC) energy converter. DC/AC conversion of PV energy is in great demand for AC applications. The supply of electrical machines and transfer energy to the distribution network is a typical case. In this work, we study and design a DC/AC energy converter using harmonic selective eliminated (HSE) method. To this end, we have combined two power stages connected in derivation. Each power stage is constituted of transistors and transformers. The connection by switching of the two rectangular waves, delivered by each of the stages, makes it possible to create a quasi-sinusoidal output voltage of the inverter. Mathematical equations based on the current-voltage characteristics of the inverter have been developed. The simulation model was validated using experimental data from a 25.2 kWp grid-coupled (PV) system, connected to Gridfit type inverters. The data were exported and implemented in programming software. A good agreement was observed and this shows all the robustness and the technical performances of the energy converter device. It emerges from this analysis that the inverter output voltage and the phase angle thus simulated are very important to control in order to orientate the transfer of the power flow from the continuous cell to cell to the alternating part. Simulated and field-testing results also show that increases in the value of the modulation factor (m) for low power output are highly significant. This study is an important tool for DC/AC inverter designers during initial planning stages. A short presentation of the design model of the inverter has been proposed in this article.

Selective harmonic elimination method for wide range of modulation indexes in multilevel inverters using ICA

Selective harmonic elimination(SHE) in multilevel inverters is an intricate optimization problem that involves a set of nonlinear transcendental equations which have multiple local minima. A new advanced objective function with proper weighting is proposed and also its efficiency is compared with the objective function which is more similar to the proposed one. To enhance the ability of the SHE in eliminating high number of selected harmonics, at each level of the output voltage, one slot is created. The SHE problem is solved by imperialist competitive algorithm(ICA). The conventional SHE methods cannot eliminate the selected harmonics and satisfy the fundamental component in some ranges of modulation indexes. So, to surmount the SHE defect, a DC-DC converter is applied. Theoretical results are substantiated by simulations and experimental results for a 9-level multilevel inverter. The obtained results illustrate that the proposed method successfully minimizes a large number of identified harmonics which consequences very low total harmonic distortion of output voltage.

Harmonic Minimization in Seven Level Cascaded Multilevel Inverter Using Selective Harmonic Elimination PWM Techniques

This paper concentrates on enhancing the productivity of the multilevel inverter and nature of yield voltage waveform. Seven level lessened switches topology has been actualized with just seven switches. Essential Switching plan and Selective Harmonics Elimination were executed to diminish the Total Harmonics Distortion (THD) esteem. Selective Harmonics Elimination Stepped Waveform (SHESW) strategy is executed to dispense with the lower order harmonics. Fundamental switching plan is utilized to control the switches in the inverter. The proposed topology is reasonable for any number of levels. The harmonic lessening is accomplished by selecting fitting switching angles. It indicates would like to decrease starting expense and unpredictability consequently it is able for modern applications. In this paper, third and fifth level harmonics have been disposed of. Simulation work is done utilizing the MATLAB/Simulink programming results have been displayed to accept the hypothesis.

Accelerated Recursive Feature Elimination Based on Support Vector Machine for Key Variable Identification

Key variable identification for classifications is related to many trouble-shooting problems in process indus-tries. Recursive feature elimination based on support vector machine (SVM-RFE) has been proposed recently in applica-tion for feature selection in cancer diagnosis. In this paper, SVM-RFE is used to the key variable selection in fault diag-nosis, and an accelerated SVM-RFE procedure based on heuristic criterion is proposed. The data from Tennessee East-man process (TEP) simulator is used to evaluate the effectiveness of the key variable selection using accelerated SVM-RFE (A-SVM-RFE). A-SVM-RFE integrates computational rate and algorithm effectiveness into a consistent framework. It not only can correctly identify the key variables, but also has very good computational rate. In comparison with contribution charts combined with principal component aralysis (PCA) and other two SVM-RFE algorithms, A-SVM-RFE performs better. It is more fitting for industrial application.

纤维肌痛综合征生物标记物的筛选及免疫细胞浸润分析

背景:纤维肌痛综合征作为常见风湿病,其发病与中枢敏化及免疫异常有关,但具体过程尚未阐明,缺乏特异性诊断标志物,不断探索该病的发病机制具有重要的临床意义。目的:基于加权基因共表达网络分析(WGCNA)等生物信息学方法和机器学习算法筛选纤维肌痛综合征潜在的诊断相关标志基因,并分析其免疫细胞浸润特征。方法:对来自基因表达综合数据库(GEO)的纤维肌痛综合征数据集转录谱进行差异分析和WGCNA分析,整合筛选出差异共表达基因,进一步采用机器学习套索回归(LASSO)算法、支持向量机递归特征消除(SVM-RFE)机器学习算法来识别核心生物标志物,并绘制受试者工作特征(ROC)曲线以评估诊断价值。最后,采用单样本基因集富集分析(ssGSEA)和基因集富集分析(GSEA)评估纤维肌痛综合征的免疫细胞浸润情况及通路富集。结果与结论:①对GSE67311数据集按照log2|(FC)|>0,P<0.05的条件进行差异分析后获得8个下调的差异表达基因;进行WGCNA分析后获得正相关性最高(r=0.22,P=0.04)的模块(MEdarkviolet)内含基因497个,负相关性最高(r=-0.41,P=6×10-5)的模块(MEsalmon2)内含基因19个;将差异表达基因与WGCNA的2个高相关性模块基因取交集,获得7个基因。②对上述7个基因进行LASSO回归算法筛选出4个基因,进行SVM-RFE机器学习算法筛选出5个基因,两者取交集后确定了3个核心基因,分别为重组1号染色体开放阅读框150蛋白(germinal center associated signaling and motility like,GCSAML)、整合素β8(Integrin beta-8,ITGB8)和羧肽酶A3(carboxypeptidase A3,CPA3);绘制3个核心基因的ROC曲线下面积分别为0.744,0.739,0.734,提示均具有很好的诊断价值,可作为纤维肌痛综合征的生物标志物。③免疫浸润分析结果显示,与对照组相比纤维肌痛综合征患者记忆B细胞、CD56 bright NK细胞和肥大细胞显著下调(P<0.05),且与上述3个生物标志物显著正相关(P<0.05)。④富集分析结果提示,纤维肌痛综合征的富集途径包括9条,主要与嗅觉传导、神经活性配体-受体相互作用及感染等通路密切相关。⑤上述结果显示,纤维肌痛综合征的发生发展与多基因参与、免疫调节异常及多个通路失调有关,但这些基因与免疫细胞之间的相互作用,以及它们与各通路之间的关系尚需进一步研究。

基于机器学习的高维数据分类特征选择

针对高维数据中弱相关特征的消除和有价值特征的识别问题,提出一种递归消除—决策树特征选择算法,以提高高维数据分类性能。为了验证该算法的有效性,从UCI数据库中选择了电离层、胶质瘤和恶意软件3个数据集,通过探索无特征选取、递归消除、决策树和混合算法递归消除—决策树4种特征选择方法,并分别和逻辑回归、随机森林、支持向量机、线性回归不同分类器组合进行实验。实验结果表明,对给定的数据集及4种分类器,递归消除—决策树算法在准确率、召回率等意义下均优于无特征选取、递归消除及决策树特征选择算法,与此同时,随机森林方法在所有实验组中表现最好。

Parameters selection in gene selection using Gaussian kernel support vector machines by genetic algorithm

In microarray-based cancer classification, gene selection is an important issue owing to the large number of variables and small number of samples as well as its non-linearity. It is difficult to get satisfying results by using conventional linear sta- tistical methods. Recursive feature elimination based on support vector machine (SVM RFE) is an effective algorithm for gene selection and cancer classification, which are integrated into a consistent framework. In this paper, we propose a new method to select parameters of the aforementioned algorithm implemented with Gaussian kernel SVMs as better alternatives to the common practice of selecting the apparently best parameters by using a genetic algorithm to search for a couple of optimal parameter. Fast implementation issues for this method are also discussed for pragmatic reasons. The proposed method was tested on two repre- sentative hereditary breast cancer and acute leukaemia datasets. The experimental results indicate that the proposed method per- forms well in selecting genes and achieves high classification accuracies with these genes.

Online quantitative analysis of soluble solids content in navel oranges using visible-nearinfrared spectroscopy and variable selection methods

Variable selection is applied widely for visible-near infrared(Vis-NIR)spectroscopy analysis of internal quality in fruits.Different spectral variable selection methods were compared for online quantitative analysis of soluble solids content(SSC)in navel oranges.Moving window partial least squares(MW-PLS),Monte Carlo uninformative variables elimination(MC-UVE)and wavelet transform(WT)combined with the MC-UVE method were used to select the spectral variables and develop the calibration models of online analysis of SSC in navel oranges.The performances of these methods were compared for modeling the Vis NIR data sets of navel orange samples.Results show that the WT-MC-UVE methods gave better calibration models with the higher correlation cofficient(r)of 0.89 and lower root mean square error of prediction(RMSEP)of 0.54 at 5 fruits per second.It concluded that Vis NIR spectroscopy coupled with WT-MC-UVE may be a fast and efective tool for online quantitative analysis of SSC in navel oranges.

改进蛇算法的七电平逆变器SHEPWM研究

多电平逆变器控制策略中的特定谐波消除脉宽调制(SHEPWM)能够以较低的开关频率得到较好的电压输出波形,重点在于开关角的求取。在多电平逆变器SHEPWM调制的开关角求解算法上提出改进蛇优化算法,对传统蛇优化算法采用Tend混沌映射初始种群,使初始种群分布更加均匀;引入Levy飞行策略增强算法的全局搜素能力,能够更加精准快速得到全局开关角的最优解。仿真结果表明,改进蛇优化算法所求的开关角相较于传统算法更好地消除低次谐波,并降低了输出线电压的畸变率,充分验证了该方法的可行性。

混合级联H桥逆变器的新型SHEPWM功率均衡控制策略

对于直流侧电压比为1∶1∶2的混合级联H桥逆变器,传统的指定谐波消除脉宽调制法(SHEPWM)存在各单元间输出功率不均衡问题,因此,提出一种双层功率均衡调制策略。首先,通过对消谐方程组中的基波幅值方程表达式进行等效拆分,使2个低压H桥单元的输出电压基波幅值之和与高压H桥单元的输出电压基波幅值相等,实现了高低压H桥单元间的功率均衡,即外层功率均衡。其次,利用逻辑运算的方法对低压单元的初始驱动信号进行逻辑重组,实现2个低压单元间的功率均衡,即内层功率均衡;然后使用改进的实数型遗传算法(IRCGA-2)求出消谐方程组的解,消除指定的谐波,得到高质量的输出电压。最后,通过仿真和实验证明了调制策略的正确性与有效性。

基于改进型随机森林算法的页岩岩性识别——以准噶尔盆地芦草沟组为例

在储集层岩性识别的应用中,特别是对页岩等非均质性较强的非常规储集层的岩性识别,机器学习算法的高效性、准确性和有效信息整合能力已经得到了充分验证。考虑到岩性识别的特征参数优选问题,优选自然伽马、T2几何平均值、结构指数、骨架密度指数、密度和深侧向电阻率,采用结合递归特征消除的随机森林算法,对准噶尔盆地中二叠统芦草沟组页岩储集层的主要岩性进行识别;利用传统的随机森林算法和支持向量机法,对同一套资料进行岩性预测,并与岩石薄片鉴定结果对比。结合递归特征消除的随机森林算法只需选择一半的测井参数,便能够达到更好的效果,而且通过优选特征参数,缩短了算法的运行时间。因此,结合递归特征消除的随机森林算法能够实现测井特征参数的优选,提高页岩岩性识别的准确率,缩短运行时间,为复杂岩性识别和多参数选择提供了新的思路。

基于随机森林算法的短期降水预测及对农业生产的影响——以庆阳市为例

准确有效地预测降水量有利于农业生产发展的规划、水资源管理以及自然灾害的预防等方面,对于干旱半干旱地区作用更为显著。该文利用庆阳市2023年1月至2024年1月的降水数据,基于包装法中的递归特征消除,迭代移除不重要的特征,后使用随机森林模型对该数据进行分析和预测。结果表明,通过对2种方法的整合使用,能够使模型具有良好的预测性能,且对庆阳市降水时刻与降水量作出较好的预测。该文研究内容对其他地市的降水量预测具有参考价值,也对当地的水资源合理利用以及促进当地社会经济可持续发展具有十分重要的意义。

Self-adaptive hydrogel for breast cancer therapy via accurate tumor elimination and on-demand adipose tissue regeneration

The irregular defects and residual tumor tissue after surgery are challenges for effective breast cancer treatment.Herein,a smart hydrogel with self-adaptable size and dual responsive cargos release was fabricated to treat breast cancer via accurate tumor elimination,on-demand adipose tissue regeneration and effective infection inhibition.The hydrogel consisted of thiol groups ended polyethylene glycol(SH-PEG-SH)and doxorubicin encapsulated mesoporous silica nanocarriers(DOX@MSNs)double crosslinked hyaluronic acid(HA)after loading of antibacterial peptides(AP)and adipose-derived stem cells(ADSCs).A pH-cleavable unsaturated amide bond was pre-introduced between MSNs and HA frame to perform the tumor-specific acidic environment dependent DOX@MSNs release,meanwhile an esterase degradable glyceryl dimethacrylate cap was grafted on MSNs,which contributed to the selective chemotherapy in tumor cells with over-expressed esterase.The bond cleavage between MSNs and HA would also cause the swelling of the hydrogel,which not only provide sufficient space for the growth of ADSCs,but allows the hydrogel to fully fill the irregular defects generated by surgery and residual tumor atrophy,resulting in the on-demand regeneration of adipose tissue.Moreover,the sustained release of AP could be simultaneously triggered along with the size change of hydrogel,which further avoided bacterial infection to promote tissue regeneration.

基于MPSO算法的特定谐波消除技术研究

目的对于级联H桥逆变器的调制,特定谐波消除技术具有开关损耗小,能够消除特定次谐波,变换效率高等优点,但传统粒子群优化算法(Particle Swarm Optimization,PSO)在求解消谐方程组时收敛性差,容易局部最优,提出一种改进的粒子群优化算法(Modified Particle Swarm Optimization,MPSO)。方法该算法用非线性惯性权重取代线性变化的惯性权重,并在非线性惯性权重引入混沌映射以产生随机性更好的随机量,新的惯性权重可权衡粒子的全局搜索和局部搜索能力,使粒子具有后期跳出局部最优的能力;另外,该算法优化了速度和位置的更新机制,以增强算法的收敛速度,并保证粒子在后期仍具有一定种群多样性优势。结果根据级联H桥型逆变器的非线性消谐方程组,在保证输出电压基波的前提下最大化降低目标次谐波,建立适应度函数,将MPSO算法应用于级联H桥型逆变器的SHEPWM,能够在1~1.2的调制度范围内得到优化的开关角,提高收敛精度和求解成功率。通过七电平CHB逆变器仿真平台验证了MPSO算法所求的优化开关角能够有效地消除5次、7次谐波。结论通过使用非线性惯性权重和优化粒子的速度和位置更新机制,可以增加开关角求解成功率,所得解可以有效地消除目标次谐波。

中波发射台站防雷工程技术选型研究

以山东省济宁市广播电视传输保障中心的防雷工程技术选型实践为例,深入剖析中波发射台站弱电子信息设备遭受雷击导致损坏的原因,提出一种基于感应消雷技术的并联浪涌保护器(Surge Protection Device,SPD)模式升级方案,通过应用实践检验得出结论,该技术可有效消除由雷击引起中波发射台地电势叠加造成电源电压异常的影响,进而为中波发射台站的弱电子信息设备提供充分保护。

基于改进型粒子群优化算法的非对称级联开关电容多电平逆变器

针对粒子群优化PSO(particle swarm optimization)算法在应用到逆变器的特定谐波、消除脉宽调制SHEPWM(vselective harmonic elimination pulse-width modulation)所存在的全局搜索能力差、且容易陷入局部最优等问题,提出1种改进型PSO。通过在搜索过程中引入遗传算法中的垂直交叉运算,以及采用精英保留策略来提高算法的全局搜索能力、局部搜索能力和保留优秀的个体,由此提高开关角精确度,改善SHEPWM的性能。使用所提算法对新型非对称级联开关电容多电平逆变器的SHEPWM非线性超越方程进行求解,解决了传统数值法对初值依赖性高及传统PSO求解开关角精确度低等问题。仿真及实验结果验证了所提拓扑结构的可行性和所提算法应用到SHEPWM中的有效性。

基于特征选择的方言辨别模型

为了从语音样本中选择数量最少的相关特征变量,并让基于随机森林(RF)的贵州汉语方言辨别模型达到所需的精度。该研究采用基于随机森林的差异排序向后消除法(SDBE),利用Python 3.6,对贵州3个市县群的汉语方言语音样本进行特征选择,并与其他先进的特征选择方法进行比较,最后对随机森林分类模型进行改进。结果显示,该方法从39个特征变量中选取了8个最相关的梅尔频率倒谱系数(MFCC),显著优于与之比较的特征选择方法。经过改进的随机森林模型分类精确度为96.64%。该研究采用的特征选择算法和改进的随机森林模型,让方言辨别模型的性能得到显著提升。

基于RFE-LGB算法的上市公司财务造假分析和预测

针对上市公司财务造假预测问题,采用结合了LightGBM与递归特征消除法(RFE)的方法进行数据建模。LightGBM以其超参数量少、强大的稳健性及对不平衡数据的高敏感性等特点著称。RFE作为一种封装式特征选择方法,能高度匹配所用预测模型,并通过设定特征子集评价函数作为停止条件,自动确定最优特征数量,这在特征选择领域具有较大优势。此外,选用平衡精度(BAcc)作为模型预测性能的评估指标,并通过调整LightGBM的分类权重参数来解决样本不平衡的问题。在5个不同行业财务数据集上的实验结果表明,所提出的RFE-LGB模型在上市公司财务造假预测任务中表现出良好的平衡性、稳健性和泛化性。该模型能有效识别与财务造假相关的关键指标,且仅使用较少的核心特征即可达到较高的预测精度。