基于流量测点的热网变动阻力系数优化辨识

随着供热计量系统的普及，系统可以根据负荷的变化进行调整，管网的阻力系数随即发生变化。对变动阻力系数进行优化辨识是了解供热管网实时运行状况的有效手段。提出一种基于流量监测数据的供热管网变动阻力系数优化辨识方法，并利用遗传算法进行求解。对洛阳市某小区供暖季管网实际运行数据进行验证，辨识结果的相对误差在5%以内。结果表明：该方法可以在只有流量观测数据时得到精度较高的供热管网变动阻力系数，为供热系统的运行调节提供指导。     

An artificial hummingbird algorithm based localization with reduced number of reference nodes for wireless sensor networks

Wireless Sensor Networks (WSN) are widely used in recent years due to the advancements in wireless and sensor technologies. Many of these applications require to know the location information of nodes. This information is useful to understand the collected data and to act on them. Existing localization algorithms make use of a few reference nodes for estimating the locations of sensor nodes. But, the positioning and utilization of reference nodes increase the cost and complexity of the network. To reduce the dependency on reference nodes, in this paper, we have developed a novel optimization based localization method using only two reference nodes for the localization of the entire network. This is achieved by reference nodes identifying a few more nodes as reference nodes by the analysis of the connectivity information. The sensor nodes then use the reference nodes to identify their locations in a distributive manner using Artificial Hummingbird Algorithm (AHA). We have observed that the localization performance of the reported algorithm at a lower reference node ratio is comparable with other algorithms at higher reference node ratios.     

Prediction of Concrete Meso-Model Stress-Strain Curves Based on GoogLeNet北大核心CSCD

非均质复合材料的宏观力学性能往往取决于细观组分的分布方式和力学性能，但是建立明确的关系表达式极其困难。为了应对这一挑战，以混凝土为研究对象，提出了一种基于深度学习的策略，能够高效、准确地通过细观模型图像信息获取应力-应变曲线。首先，使用基于卷积神经网络（convolutional neural network，CNN）的GoogLeNet模型进行图像信息识别和提取，并针对应力-应变曲线的复杂性特点，进行了数据预处理操作，并且设计了相应的多任务损失函数。数据集中的细观模型图像采用基于Monte-Carlo的随机骨料模型生成，并且使用数值模拟试验获取对应细观模型的单轴压缩应力-应变曲线。最后，通过对神经网络的训练和测试评估了所提出方法的可行性。结果表明，GoogLeNet模型训练效率和预测精度均优于AlexNet和ResNet模型，具有良好的泛化能力和鲁棒性。     

Design consideration and modelling studies of ultrasound and ultraviolet combined approach for shelf-life enhancement of pine apple juice

Although both ultraviolet (UV) radiation and ultrasound (US) treatment have their capabilities in microbial inactivation, applying any one method alone may require a high dose for complete inactivation, which may affect the sensory and nutritional properties of pineapple juice. Hence, this study was intended to analyse and optimise the effect of combined US and UV treatments on microbial inactivation without affecting the selected quality parameters of pineapple juice. US treatment (33 kHz) was done at three different time intervals, viz. 10 min, 20 min and 30 min., after which, juice samples were subjected to UV treatment for 10 min at three UV dosage levels, viz. 1 J/cm², 1.3 J/cm², and 1.6 J/cm². The samples were evaluated for total colour difference, pH, total soluble solids (TSS), titrable acidity (TA), and ascorbic acid content; total bacterial count and total yeast count; and the standardization of process parameters was done using Response Surface Methodology and Artificial Neural Network. The results showed that the individual, as well as combined treatments, did not significantly impact the physicochemical properties while retaining the quality characteristics. It was observed that combined treatment resulted in 5 log cycle reduction in bacterial and yeast populations while the individual treatment failed. From the optimization studies, it was found that combined US and UV treatments with 22.95 min and1.577 J/cm² ensured a microbiologically safe product while retaining organoleptic quality close to that of fresh juice.     

Highly Sensitive Electrochemical Immunosensor Based on Mesoporous PdPt Nanoparticles Anchored on a Three-dimensional PANI@CNTs Network as Nanozyme Labels

In this study, a novel strategy to amplify electrochemical signals by mesoporous PdPt nanoparticles with core-shell structures anchored on a three-dimensional PANI@CNTs network as nanozyme labels (PdPt/PANI@CNTs) was proposed for the sensitive monitoring of α-fetoprotein (AFP, Ag). First, the mesoporous PdPt nanoparticles prepared by a facile chemical reduction method had excellent biocompatibility with biomolecules, which could capture a large amount of AFP-Ab₂ (Ab₂) and exhibit plentiful pores to entrap more thionine (Thi) into mesoporous PdPt nanoparticles with enhanced loading and abundant active sites. Furthermore, the resulting mesoporous PdPt nanoparticles were abundantly dotted on the surface of a three-dimensional PANI@CNTs network with excellent conductivity and a high specific surface area through the bonding of the amino group to form PdPt/PANI@CNTs nanozyme labels. Most importantly, the as-prepared PdPt/PANI@CNTs nanozyme labels exhibited unexpected enzyme-like activity towards the reduction of hydrogen peroxide owing to the highly indexed facets, enhancing the current response to realize signal amplification. In view of the advantages of nanozyme labels and the involvement of gold nanoparticles (AuNPs, which behave as electrode materials) for the sensitive determination of AFP, the as-developed immunosensor could obtain a dynamic working range of 0.001 ng mL^−1–100.0 ng mL⁻¹ at a detection limit of 0.33 pg mL⁻¹ via DPV (at 3σ). Furthermore, the nanozyme-based electrochemical immunosensor exhibited remarkable analytical performance, which brought about feasible ideas for disease diagnosis in the future.     

Biomarkers based on multiplatform comprehensive analysis: A systematic analysis of Geng-Nian-Shu in perimenopausal syndrome

Although Geng-Nian-Shu has been shown to be clinically effective in perimenopausal syndrome, its active components and mechanism have not yet been elucidated. To demonstrate the mechanism-based biomarkers of Geng-Nian-Shu in treating perimenopausal syndrome, a total of 135 chemical constituents including 52 prototype blood constituents were identified via high-performance liquid chromatography-quadrupole-time of flight/mass spectrometry. Then, network pharmacology showed significant enrichment for the PhosphoInositide-3 Kinase/Akt pathway, suggesting that it may be the main regulatory pathway for the Geng-Nian-Shu treatment of the perimenopausal syndrome. Subsequently, multivariate analysis was performed between the Geng-Nian-Shu sham-treated and Geng-Nian-Shu ovariectomy-treated groups and further screened out 18 prototype blood constituents by correlation analysis with plasma estrogen levels to identify potential biomarkers associated with Geng-Nian-Shu treat the ovariectomy-induced perimenopausal syndrome. Finally, the results of pharmacological experimental verification and Pearson correlation analysis indicated that catalpol, ligustilide, paeoniflorin, and gallic acid were selected as biomarkers of Geng-Nian-Shu which were strongly and positively correlated with PhosphoInositide-3 Kinase/Akt signaling pathway. In this study, based on high-performance liquid chromatography-quadrupole-time of flight/mass spectrometry combined with pharmacodynamics, network pharmacology, pharmacology, and other disciplines, we explored the effects and mechanisms of Geng-Nian-Shu in the treatment of perimenopausal syndrome at multiple levels. Using multiplatform technology to investigate the role of Geng-Nian-Shu represents a new strategy for the selection and verification of biomarkers of Geng-Nian-Shu and provides a basis for further development and utilization of Geng-Nian-Shu.     

基于LSTM的浮选钼精矿品位软测量模型

战略性稀有金属钼矿品位低,组分复杂、嵌布粒度细等特点,其有价金属分离回收难。浮选作为微细粒钼矿分离回收的主要选矿方法之一,其浮选钼精矿品位一直是选厂的关键性产品指标。国内大多数选厂采取轮班制采样,人工化验得到精矿品位结果,但此方式严重滞后于浮选工艺,难以满足对生产过程进行实时监测和操作指导。LSTM是一种特殊的循环神经网络,引入门机制有效的传递或选择性遗忘长时间序列中的信息,解决RNN中的长期依赖、梯度消失和爆炸问题。本文分析整理东坡选厂中各平台源数据,结合选厂浮选工艺及机理,筛选出多个影响浮选钼精矿品位的变量作为模型输入;将输入变量进行异常值判定,缺失值填充和数据降噪等数据预处理,建立高质量浮选钼精矿品位数据库;软测量模型采用PyCharm软件编码,使用BatchNorm批量规范化处理样本数据,加入Dropout正则化防止过拟合,建立基于LSTM的浮选钼精矿品位软测量模型,通过前向传播算法更新神经网络结构参数,并于Linear模型和CNN模型的预测性能指标结果比较。结果表明：基于LSTM的浮选钼精矿品位软测量模型预测准确度高,样本数据误差波动平稳,浮动范围小,模型泛化能力强,模型平均绝对百分比误差MAPE为1.13%,均方根误差RMSE为0.7049%,决定系数R2为0.8763,实现了浮选钼精矿品位的在线预测。     

A way of constructing translation network operators by Bernstein operators

In the present paper,we provide a way of constructing translation network operators by Bernstein-Durrmeyer operators.