基于PCC-RBF网络的风电功率短期预测方法

风电功率预测对风电场安全平稳运行、电网调度具有重要意义。针对风电功率短期预测指标选择不合理、预测精确度偏低的问题,提出一种基于皮尔逊相关系数(PCC)和径向基函数(RBF)神经网络的风电功率短期预测方法。该方法利用PCC筛选出与风电功率密切相关的3个指标,即电流、温度、风速,然后以这3个指标作为预测模型的输入对风电功率进行RBF样本训练与短期预测。试验结果表明,所提的预测模型预测误差更小,预测精度更高,能够满足风电功率短期预测的要求,具有广泛的应用前景。     

Curvature effects on electric-double-layer capacitance

Understanding the microscopic structure and thermodynamic properties of electrode/electrolyte interfaces is central to the rational design of electric-double-layer capacitors (EDLCs). Whereas practical applications often entail electrodes with complicated pore structures, theoretical studies are mostly restricted to EDLCs of simple geometry such as planar or slit pores ignoring the curvature effects of the electrode surface. Significant gaps exist regarding the EDLC performance and the interfacial structure. Herein the classical density functional theory (CDFT) is used to study the capacitance and interfacial behavior of spherical electric double layers within a coarse-grained model. The capacitive performance is associated with electrode curvature, surface potential, and electrolyte concentration and can be correlated with a regression-tree (RT) model. The combination of CDFT with machine-learning methods provides a promising quantitative framework useful for the computational screening of porous electrodes and novel electrolytes.     

Balanced multiple weighted linear discriminant analysis and its application to visual process monitoring

Visual process monitoring is important in complex chemical processes. To address the high state separation of industrial data, we propose a new criterion for feature extraction called balanced multiple weighted linear discriminant analysis(BMWLDA). Then, we combine BMWLDA with self-organizing map(SOM) for visual monitoring of industrial operation processes. BMWLDA can extract the discriminative feature vectors from the original industrial data and maximally separate industrial operation states in the space spanned by these discriminative feature vectors. When the discriminative feature vectors are used as the input to SOM, the training result of SOM can differentiate industrial operation states clearly.This function improves the performance of visual monitoring. Continuous stirred tank reactor is used to verify that the class separation performance of BMWLDA is more effective than that of traditional linear discriminant analysis, approximate pairwise accuracy criterion, max–min distance analysis, maximum margin criterion, and local Fisher discriminant analysis. In addition, the method that combines BMWLDA with SOM can effectively perform visual process monitoring in real time.     

Characterization of wet microalgal cells pretreated with steam for lipid extraction

Steam pretreatment was employed to disrupt microalgal cells for lipids extraction.Effects of steam pre-treatment on microstructure of microalgal cells were investigated through scanning electron microscopy(SEM) and transmission electron microscopy (TEM).Effect of treatment on lipid extraction was also stud-ied.Microalgal cell walls were distorted after steam pretreatment due to the hydrolysis of organic macro-molecules contained in cell wall.Maximum curvature was increased from 1.88 × 10-6 m-1 to 1.43 × 10-7 m-1 after treatment with the steam at 130 ℃.The fractal dimension of microalgal cells increased from 1.25 to 1.30 after pretreatment for 15 min,and further increased to 1.47 when the pre-treatment time was increased to 60 min.Increased steam pretreatment temperature and time enhanced the hydrolysis of organic macromolecules,and finally destroyed microalgal cell walls at pretreatment temperature of 130 ℃ and pretreatment time of 60 min.Lipid extracted from wet microalgal was signif-icantly increased (2.1-fold) after pretreatment.     

多孔结构耐磨超疏水薄膜的制备及性能

为了获得持久稳定的超疏水材料,本研究将聚偏氟乙烯共六氟丙烯共聚物（P(VDF-HFP)）和疏水改性的纳米三氧化二铝（Al2O3）进行复合并通过溶剂/非溶剂诱导相分离法制备了一种耐磨超疏水薄膜。采用SEM及能谱分析仪和接触角测量仪分别对薄膜的表面微观结构、化学组成和疏水性能进行表征。结果表明：制备的薄膜具有自相似微纳米复合微观结构。并且薄膜具有优异的自清洁性和耐机械摩擦性,即使经历360个周期的砂纸磨损（100 g载重）后仍保持超疏水性。除此之外薄膜具有优异耐化学溶液和紫外灯照射稳定性。     

N,N−二甲基−二硫代甲酰胺丙磺酸钠对THPED体系化学镀铜的影响

研究了N,N?二甲基?二硫代甲酰胺丙磺酸钠(DPS)作为添加剂对以四羟丙基乙二胺(THPED)为单一配位剂的化学镀铜体系的沉积速率、镀层形貌和晶体结构的影响。结果发现,当DPS的质量浓度从0 mg/L增大到1.0 mg/L时,沉积速率从2.91μm/h提高到6.73μm/h,所得镀层结晶均匀、细致。线性扫描伏安测量结果表明,DPS是通过促进甲醛的阳极氧化来加速化学镀过程。本体系的Cu镀层主要呈面心立方多晶取向,DPS的添加会令晶面取向从(220)转变为(111)。     

眼动技术在连弧纹铭带镜设计因子提取中的应用

通过使用眼动仪对连弧纹铭带镜中的设计因子进行提取,达到优化新文创时代下文创产品设计开发的目的。运用眼动实验分析20名被试观看连弧纹铭带镜的视觉热区,依据实验数据对被试在连弧纹铭带镜中的兴趣区域进行划分。结合层次分析法确定被试主要兴趣区域,采用归纳与演绎对其中的显性设计因子和隐形设计因子进行提取。将提取的设计因子应用于文创产品设计当中,并对所设计的产品与其他文创产品进行对比测试。通过实验数据验证眼动仪对于文物中设计因子提取的可行性。     

离散差分模块在癫痫脑电分类中的应用

针对癫痫脑电信号多分类的精度提升问题,提出了一种基于信号转差分模块与卷积模块结合的分类算法。信号转差分模块对原始脑电信号进行多阶差分运算,得到描述其波动特征的差分表示;然后卷积模块动态学习的方式将差分脑电信号转换为图片,利用预训练的卷积神经网络来提取信号特征并实现自动分类。分类结果表明,与现有研究相比,所提出的方法的最高提升了8.1%的分类准确率。在两分类问题上达到了99.8%的分类准确率,在三分类问题上获得了92.8%的准确率,在五分类问题上取得了86.7%的准确率。说明信号转差分模块对于脑电信号分类问题有积极作用。     

基于S变换相关度和深度学习的配电网单相接地故障选线新方法

针对配电网发生单相接地故障时特征信息不明显,且现有选线方法易受故障条件和环境噪声影响的问题,基于S变换相关度和深度学习,提出一种具有强抗噪声能力和高泛化水平的配电网单相接地故障选线新方法.首先,利用S变换获取零序电流时频信息,基于各线路零序电流的全频段信息计算线路故障信息相关度;其次,为提高故障特征的可辨识度和抗干扰性,提出一种S变换相关度图形(SCF)构建方法;在此基础上,建立含SCF层的卷积神经网络深度学习模型(S-CNN),并利用Simulink仿真模型生成的故障数据对其结构参数和超参数进行分步训练;最后,通过S-CNN提取配电网故障零序电流深层特征,实现故障选线,并测试了S-CNN在配电网不同运行状况和故障条件下的选线效果.仿真结果和实际配电网故障数据测试表明:在强噪声干扰场景中,基于S-CNN的故障选线模型在不同故障位置、故障相角、过渡电阻条件下可实现高正确率选线,且在各线路零序电流采样不同步条件下仍具有较强的鲁棒性.     

Trace Identification and Visualization of Multiple Benzimidazole Pesticide Residues on Toona sinensis Leaves Using Terahertz Imaging Combined with Deep Learning

Molecular spectroscopy has been widely used to identify pesticides. The main limitation of this approach is the difficulty of identifying pesticides with similar molecular structures. When these pesticide residues are in trace and mixed states in plants, it poses great challenges for practical identification. This study proposed a state-of-the-art method for the rapid identification of trace (10 mg·L⁻¹) and multiple similar benzimidazole pesticide residues on the surface of Toona sinensis leaves, mainly including benzoyl (BNL), carbendazim (BCM), thiabendazole (TBZ), and their mixtures. The new method combines high-throughput terahertz (THz) imaging technology with a deep learning framework. To further improve the model reliability beyond the THz fingerprint peaks (BNL: 0.70, 1.07, 2.20 THz; BCM: 1.16, 1.35, 2.32 THz; TBZ: 0.92, 1.24, 1.66, 1.95, 2.58 THz), we extracted the absorption spectra in frequencies of 0.2–2.2 THz from images as the input to the deep convolution neural network (DCNN). Compared with fuzzy Sammon clustering and four back-propagation neural network (BPNN) models (TrainCGB, TrainCGF, TrainCGP, and TrainRP), DCNN achieved the highest prediction accuracies of 100%, 94.51%, 96.26%, 94.64%, 98.81%, 94.90%, 96.17%, and 96.99% for the control check group, BNL, BCM, TBZ, BNL + BCM, BNL + TBZ, BCM + TBZ, and BNL + BCM + TBZ, respectively. Taking advantage of THz imaging and DCNN, the image visualization of pesticide distribution and residue types on leaves was realized simultaneously. The results demonstrated that THz imaging and deep learning can be potentially adopted for rapid-sensing detection of trace multi-residues on leaf surfaces, which is of great significance for agriculture and food safety.