Thermomechanical stability and inelastic energy dissipation as durability criteria for fuel cell gas diffusion media with pre-assembly effects

In this article, pre-assembly hot-press pressure and thermal expansion effects in gas-diffusion layers (GDLs) are addressed to explore the practicalities of the constitutive model reported in the companion article. A facile technique is proposed to include deformation history dependent residual strain effects. The model is implemented in the numerical environment and compared with widely followed conventional models such as isotropic and orthotropic material models. With the normal and accelerated thermal expansion effects no significant variation in stresses or strains is reported with the compressible GDL model in contrast to the conventional incompressible form of the GDL model. The present work identifies the critical differences with advanced and extended variants of the model along with conventional GDL material models in terms of planar stress/strain distribution and the membrane response. Finally, the model is simulated for micro-cyclic stress loads of varying amplitudes that imitate the real working conditions of fuel cell. The inelastic energy dissipation in GDLs is predicted using the proposed model, which is utilized further to distinguish the safe (elastic) and unsafe (inelastic shakedown) operating limits. The inelastic collapse of GDLs is shown to be a active function of high amplitude micro-cyclic load with high initial clamping load.     

Tabular data: Deep learning is not all you need

A key element in solving real-life data science problems is selecting the types of models to use. Tree ensemble models (such as XGBoost) are usually recommended for classification and regression problems with tabular data. However, several deep learning models for tabular data have recently been proposed, claiming to outperform XGBoost for some use cases. This paper explores whether these deep models should be a recommended option for tabular data by rigorously comparing the new deep models to XGBoost on various datasets. In addition to systematically comparing their performance, we consider the tuning and computation they require. Our study shows that XGBoost outperforms these deep models across the datasets, including the datasets used in the papers that proposed the deep models. We also demonstrate that XGBoost requires much less tuning. On the positive side, we show that an ensemble of deep models and XGBoost performs better on these datasets than XGBoost alone.     

Generation,validation and application of dynamic load profiles in flow measurement using cavitating Herschel–Venturi nozzles

Today, utility meters for water are tested for measurement behavior at stable operating conditions at specified flow rates as part of the approval process. The measurement error that occurs during start and stop or when changing between flow rates may not be taken into account. In addition, there are new technologies whose measuring behavior under real-world conditions is only known to a limited extend. To take these facts into account, a new method has been developed and tested to determine the measurement behavior of water meters under dynamic load profiles as they occur in the real application. For this purpose, a test rig for flow rate measurement was extended by a cavitation nozzle apparatus and the generation of dynamic load profiles was validated. For the cavitation nozzles used, possible factors influencing the flow rate, such as temperature and purity of the water as well as the upstream pressure were investigated. Using different types of domestic water meters, the applicability of the dynamic test procedure was demonstrated and the measurement behavior of the meters was characterised.     

Effect of heat treatment and zircon addition on the properties of low-cement castables based on recycled alumina grog

In this investigation, low-cement castables were prepared using 70% alumina grog aggregates obtained from crushed alumina brick waste. The aggregates were thermally treated at 1550 °C for 3 h. Four types of low-cement castables were prepared with various types of aggregates (alumina grog with or without thermal treatment) and fillers (with or without zircon addition), and they were evaluated in terms of their physical, thermal, and chemical properties. Microstructural analysis via scanning electron microscopy (SEM) was performed on the castables before and after slag attack. Compared to the other fabricated castables, the thermally treated alumina grog castables with zircon showed better physical properties, such as a higher bulk density, cold crushing strength, and modulus of rupture and a lower apparent porosity and water absorption. In addition, they had a higher positive linear thermal expansion, refractoriness under load, permanent linear change, and hot modulus of rupture. The results of the SEM with energy dispersive X-ray analysis of the prepared castables confirmed that the mullite and anorthite phases were predominant when zircon was not added and the zircon–mullite phase additionally appeared upon the incorporation of zircon. A quantitative elemental analysis via X-ray fluorescence spectroscopy was employed to determine the composition of the castables. X-ray diffraction analysis showed that the alumina grog castables had a high mullite and low anorthite content, and the thermally treated alumina grog had a high anorthite, low mullite, and high zircon content. The improvement in the mechanical and thermo-mechanical properties of the castables with thermally treated alumina grog and added zircon can be attributed to the formation of the zircon–mullite phase with a low mullite phase content.     

Identifying catalyst layer compositions of proton exchange membrane fuel cells through machine-learning-based approach

Membrane electrode assembly (MEA) is considered a key component of a proton exchange membrane fuel cell (PEMFC). However, developing a new MEA to meet desired properties, such as operation under low-humidity conditions without a humidifier, is a time- and cost-consuming process. This study employs a machine-learning-based approach using K-nearest neighbor (KNN) and neural networks (NN) in the MEA development process by identifying a suitable catalyst layer (CL) recipe in MEA. Minimum redundancy maximum relevance and principal component analysis were implemented to specify the most important predictor and reduce the data dimension. The number of predictors was found to play an essential role in the accuracy of the KNN and NN models although the predictors have self-correlations. The KNN model with a K of 7 was found to minimize the model loss with a loss of 11.9%. The NN model constructed by three corresponding hidden layers with nine, eight, and nine nodes can achieve the lowest error of 0.1293 for the Pt catalyst and 0.031 for PVA as a good additive blending in the CL of the MEA. However, even if the error is low, the prediction of PVA seems to be inaccurate, regardless of the model structure. Therefore, the KNN model is more appropriate for CL recipe prediction.     

Neural network-based flight control systems: Present and future

As the first review in this field, this paper presents an in-depth mathematical view of Intelligent Flight Control Systems (IFCSs), particularly those based on artificial neural networks. The rapid evolution of IFCSs in the last two decades in both the methodological and technical aspects necessitates a comprehensive view of them to better demonstrate the current stage and the crucial remaining steps towards developing a truly intelligent flight management unit. To this end, in this paper, we will provide a detailed mathematical view of Neural Network (NN)-based flight control systems and the challenging problems that still remain. The paper will cover both the model-based and model-free IFCSs. The model-based methods consist of the basic feedback error learning scheme, the pseudocontrol strategy, and the neural backstepping method. Besides, different approaches to analyze the closed-loop stability in IFCSs, their requirements, and their limitations will be discussed in detail. Various supplementary features, which can be integrated with a basic IFCS such as the fault-tolerance capability, the consideration of system constraints, and the combination of NNs with other robust and adaptive elements like disturbance observers, would be covered, as well. On the other hand, concerning model-free flight controllers, both the indirect and direct adaptive control systems including indirect adaptive control using NN-based system identification, the approximate dynamic programming using NN, and the reinforcement learning-based adaptive optimal control will be carefully addressed. Finally, by demonstrating a well-organized view of the current stage in the development of IFCSs, the challenging issues, which are critical to be addressed in the future, are thoroughly identified. As a result, this paper can be considered as a comprehensive road map for all researchers interested in the design and development of intelligent control systems, particularly in the field of aerospace applications.     

Predicting Prostephanus truncatus (Horn) (Coleoptera: Bostrichidae) populations and associated grain damage in smallholder farmers’ maize stores: A machine learning approach

Prostephanus truncatus is a notorious pest of stored-maize grain and its spread throughout sub-Saharan Africa has led to increased levels of grain storage losses. The current study developed models to predict the level of P. truncatus infestation and associated damage of maize grain in smallholder farmer stores. Data were gathered from grain storage trials conducted in Hwedza and Mbire districts of Zimbabwe and correlated with weather data for each site. Insect counts of P. truncatus and other common stored grain insect pests had a strong correlation with time of year with highest recorded numbers from January to May. Correlation analysis showed insect-generated grain dust from boring and feeding activity to be the best indicator of P. truncatus presence in stores (r = 0.70), while a moderate correlation (r = 0.48) was found between P. truncatus numbers and storage insect parasitic wasps, and grain damage levels significantly correlated with the presence of Tribolium castaneum (r = 0.60). Models were developed for predicting P. truncatus infestation and grain damage using parameter selection algorithms and decision-tree machine learning algorithms with 10-fold cross-validation. The P. truncatus population size prediction model performance was weak (r = 0.43) due to the complicated sampling and detection of the pest and eight-week long period between sampling events. The grain damage prediction model had a stronger correlation coefficient (r = 0.93) and is a good estimator for in situ stored grain insect damage. The models were developed for use under southern African climatic conditions and can be improved with more input data to create more precise models for building decision-support tools for smallholder maize-based production systems.     

蛋类礼盒包装结构的缓冲性能研究

目的研究蛋类礼盒包装结构的缓冲性能。方法以蛋类尺寸为基础,建立可发性聚乙烯(expandable polyethylene. EPE)缓冲单元结构和组合结构,进行静态仿真分析和实验验证,比较结构在形状、叠合层数、组合形式等参数变化时的载荷与位移。结果结构层数变化相同时,单元结构的极限载荷从143N增加到236 N,组合结构的极限载荷从224 N增加到476 N,均呈近线性增长。结论蛋类礼盒包装中,组合结构的承载能力优于单元结构,通过单元结构的组合,可满足不同蛋类的包装要求。     

A review of topic modeling methods

Topic modeling is a popular analytical tool for evaluating data. Numerous methods of topic modeling have been developed which consider many kinds of relationships and restrictions within datasets; however, these methods are not frequently employed. Instead many researchers gravitate to Latent Dirichlet Analysis, which although flexible and adaptive, is not always suited for modeling more complex data relationships. We present different topic modeling approaches capable of dealing with correlation between topics, the changes of topics over time, as well as the ability to handle short texts such as encountered in social media or sparse text data. We also briefly review the algorithms which are used to optimize and infer parameters in topic modeling, which is essential to producing meaningful results regardless of method. We believe this review will encourage more diversity when performing topic modeling and help determine what topic modeling method best suits the user needs.     

基于启发式BP算法的软件缺陷预测模型

针对软件缺陷预测时缺陷数据集中存在的类别分布不平衡问题，结合上采样算法SMOTE与Edited Nearest Neighbor (ENN) 数据清洗策略，提出了一种基于启发式BP神经网络算法的软件缺陷预测模型。模型中采用上采样算法SMOTE增加少数类样本以改善项目中的数据不平衡状况，并针对采样后数据噪声问题进行ENN数据清洗，结合基于启发式学习的模拟退火算法改进四层BP神经网络后建立分类预测模型，在AEEEM数据库上使用交叉验证对提出的方案进行性能评估，结果表明所提出的算法能够有效提高模型在预测类不平衡数据时的分类准确度。