A benchmark data set for two-phase Coriolis metering

For more than a decade there has been growing interest in the use of Coriolis mass flow metering applied to two-phase (gas/liquid) and multiphase (oil/water/gas) conditions. It is well-established that the mass flow and density measurements generated from multiphase flows are subject to large errors, and a variety of physical models and correction techniques have been proposed to explain and/or to compensate for these errors. One difficulty is the absence of a common basis for comparing correction techniques, because different flowtube designs and configurations, as well as liquid and gas properties, may result in quite different error curves. Furthermore, some researchers with interests in the modelling aspects of the field may not have suitable multiphase laboratory facilities to generate their own data sets. This paper offers a small data set that may be used by researchers as a benchmark i.e. a common data set for comparing correction techniques. The data set was collected at the UK National Flow Laboratory TUV-NEL, using air and a viscous oil, and provides experimental points over a wide flow range (8:1 turndown) and with Gas Volume Fraction (GVF) values up to 60%. As a first investigation using the benchmark data set, we consider how data sparsity (i.e. the flow rate and GVF spacing in the experimental grid) affects the accuracy of a correction model. A range of neural network models are evaluated, based on different subsets of the benchmark data set. The data set and some exemplary code are provided with the paper. Additional data sets are available on a web site created to support this initiative.     

基于多元神经网络融合的分布式资源空间文本分类研究

针对实体产业对科技资源的服务需求,以服务效应作为资源文本分类标准,提出一种基于多元神经网络融合的分布式资源空间文本分类模型。设计了包含词嵌入层、卷积层、双向门控循环单元层、注意力机制层和softmax层的多元神经网络通路;在此基础上采用基于需求—效应—资源分类策略,完成了从定性科技资源需求到定量资源服务效应求解,再到定性科技资源输出的映射变换,重点解决了分布式科技资源局部和全局语义特征形式多样、文本长距离依赖特征显著、重要资源信息难以准确识别的问题,进而从分布式科技资源空间中快速准确地获取效应知识,提升实体产业产品研发效率和创新能力;通过万方专利科技资源数据集验证了所提方法的可行性和有效性,为更加全面地挖掘资源文本特征和按需服务实体产业提供了一种新的思路和手段。     

基于混合时间序列卷积神经网络的轴承故障诊断

在传统滚动轴承故障诊断中,绝大多数方法采用了从振动信号提取特征的诊断模式,但是这种模式必然会使原始信号降维进而导致故障信息的丢失。卷积神经网络(CNN)通过权重共享和稀疏连接直接对原始信号进行操作,实现自适应特征提取,最大化保留故障信息。受CNN原理启发,开发出了一种基于工业振动信号特征的新型诊断框架,称之为混合时间序列CNN(HTS-CNN)。首先,利用估计总体比例的方法自适应确定模型训练样本数目;其次,通过对时间序列片段进行随机组合的方式,使模型能够提取非相邻信号特征;最后,利用Softmax激活函数在模型输出端执行多分类任务。通过对凯斯西储大学及CUT-2平台轴承数据进行分析,实验结果表明:该方法能够准确、有效的对滚动轴承故障进行分类。     

Using hybridized ANN-GA prediction method for DOE performed drying experiments

Abstract

Coal is an important component in the energy industry and plays a key role in energy-producing facilities. Moisture is a common condition that has a considerable impact on coal. Coal drying has long been a question of great interest in a wide range of fields. Defining parameters in the coal drying is obtained by experiments. High costs, time constraints, and repetition of an experiment are one of the most frequently stated problems with experimental works. Using qualitative methods with experiments can be more useful for identifying and characterizing the coal drying process. The purpose of this article is finding the effective parameters in the coal drying process by using a hybridized prediction method. Genetic Algorithm (GA) and Artificial Neural Network (ANN) are hybridized with each other to identify and characterize the coal drying process. GA-ANN algorithm is applied to the coal drying process to predict the moisture of coal, but it does not provide a decent result at first. Later, the Design of Experiment (DoE) methodology is performed to determine the main effects of six parameters. Two scenarios are generated because two parameters are not statistically significant. The first scenario excludes the air relative humidity parameter, and the second scenario excludes the air relative humidity and the velocity of air parameters. Following the application of the DoE method, GA-ANN reaches decent results in scenario-2.     

Performance degradation prediction of proton exchange membrane fuel cell using a hybrid prognostic approach

The proton exchange membrane fuel cell has been widely used for industrial systems; however, its performance gradually degrades during use. Therefore, the study on the performance degradation prediction of fuel cells is helpful to extend its lifespan. In this paper, a novel hybrid approach using a combination of model-based adaptive Kalman filter and data-driven NARX neural network is proposed to predict the degradation of fuel cells. The overall degradation trend (i.e., irreversible degradation process) is captured by an empirical aging model and adaptive Kalman filter. Meanwhile, the detail degradation information (i.e., reversible degradation process) is depicted by the NARX neural network. Moreover, the correlation analysis of the reversible voltage time series is carried out to obtain the number of delays of the NARX neural network based on the autocorrelation function and the partial autocorrelation function. Then, the total degradation prediction is the sum of the overall degradation prediction and the detail degradation prediction. Finally, the prognostic capability of the proposed method is verified by two aging datasets, and the results show the effectiveness and superiority of the proposed method which can provide accurate degradation forecasting and remaining useful life.     

Latent communities of digital publications: The role of editors,followers, and advertisers

This research explores how digital publications may be turned into something more than just a meeting point for people who are seeking information and may become a latent community. The paper proposes that the network of editors, followers, and advertisers of digital publications determine the user sense of community towards the publication. While the pattern of connections among editors and followers reinforces the sense of community, advertisers act as intruders who weaken the feasibility of building a community. Data were collected from followers of digital publications. The dynamics of the sense of community is described as a process in which informational value and identification are essential to nurturing readers’ soft or hard commitment. Findings indicate that the strong ties between editors and followers as well as the diversity positively impacts on informational value and identification, whereas advertising intrusiveness diminishes the informational value.     

A datamining approach to classify,select and predict the formation enthalpy for intermetallic compound hydrides

In this paper, two techniques of datamining tools were adopted, a principal component analysis (PCA) and artificial neural network (ANN). A PCA to classify, select and identify several combinations between transition element A and B (B = Ti, Zr, Hf, Sc, Y, La and Th) and ANN to predict ΔH for ternary hydrides. Based on the datasets selected from different works, a principal component analysis (PCA) has been applied to select, classify and identify around 76 possible combinations between transition metal elements A and B. The results showed that the clustering of combinations A-B are significantly influenced by the atomic parameters of element A, such atomic radius (R_A), Pauling's electronegativity (χ_A) and atomic electron density (Z_A/R_A³). From 76 combinations, 55 systems which have χ_A ≥ 1.5, Z_A/R_A³>1.28 and R_A < 1.46 Å are categorized as group 1. On the other hand, 21 systems which have χ_A < 1.5, Z_A/R_A³ < 1.28, and R_A > 1.46 Å are categorized as group 2. From the first group, 46 different combinations are identified and have a negative ΔH, within 18 well-known promising binary alloys of hydrogen storage.An (6-15-1) architecture of artificial neural network (ANN) has been developed to estimate the ΔH for the other ternary hydrides selected from different published works. The performance indices such as relative error, coefficient of determination (R²) and mean square error (MSE) were used to control the performance of obtained results. In addition to this, the ΔH obtained from ANN model were compared with those experimental data and theoretical results available in the literature.     

神经网络全局势函数在多相催化中的应用

当今的多相催化研究需要新的技术和方法从原子尺度上表征活性中心结构和反应中间体。本文作者课题组近期开发了理论模拟新技术来探索催化剂活性位点结构，即基于神经网络势函数的大规模原子模拟（LASP）软件中实现的全局神经网络势函数计算方法。本文介绍了该方法可以显著降低催化体系的计算代价，而维持与密度泛函理论同一级别的计算精度，从而解决多相催化中的许多复杂问题。本文对神经网络势函数方法的实现细节和目前已实现的应用场景进行了详细介绍。神经网络势函数可以用来预测材料晶体结构，理解高压氢化条件下TiO₂表面的结构演化和确定三元氧化物ZnCrO晶相中合成气制甲醇活性位点。最后文章分析了神经网络势函数的局限性和今后可能的三个研究方向，即材料性质预测、多元素体系神经网络势函数构造和化学反应拟合。     

Food recognition using neural network classifier and multiple hypotheses image segmentation

ABSTRACT

This paper proposes the multiple-hypotheses image segmentation and feed-forward neural network classifier for food recognition to improve the performance. Initially, the food or meal image is given as input. Then, the segmentation is applied to identify the regions, where a particular food item is located using salient region detection, multi-scale segmentation, and fast rejection. Then, the features of every food item are extracted by the global feature and local feature extraction. After the features are obtained, the classification is performed for each segmented region using a feed-forward neural network model. Finally, the calorie value is computed with the aid of (i) food volume and (ii) calorie and nutrition measure based on mass value. The experimental results and performance evaluation are validated. The outcome of the proposed method attains 0.947 for Macro Average Accuracy (MAA) and 0.959 for Standard Accuracy (SA), which provides better classification performance.