Finite element analysis of vent/hand hole designs for corrugated fibreboard boxes

Corrugated fibreboard is an economical and efficient material for fabricating shipping containers that are widely used for the distribution, transportation and storage of goods. Corrugated fibreboard is usually considered to be an orthotropic material because the principal fibre directions, machine direction (MD) and cross‐machine direction (CD), are identical to the fibres in paperboard, which has apparent directional property differences. The purpose of this study is to investigate the principal design parameters of ventilation holes and hand holes in the faces of the shipping container, (corrugated fibreboard boxes), using finite element analysis (FEA). Various designs of ventilation holes were studied with respect to stress distribution and stress level. It was found that the appropriate pattern and location of the ventilation holes were vertical oblong‐shaped and symmetrically positioned within a certain extent of distance to the right and left from the centre of the front and rear faces of the boxes. On the other hand, the appropriate location and pattern of the hand holes were a short distance from the centre to the top of the boxes on both side faces. The appropriate pattern was a modified shape, such as the radius of curvature of both sides in horizontal oblong. The pattern and location of both the ventilation holes and the hand holes determined by the FEA simulation generally agreed well with laboratory experimental results. The decrease in compression strength of the box could be minimized with identical area of the ventilation holes if the length of the major axis of the ventilation hole is less than 1/4 of the depth of the box and the ratio of the minor axis to the major axis is 1/3.5–1/2.5, provided that even‐numbered holes are located symmetrically. Copyright © 2006 John Wiley & son, Ltd.     

The effect of pallet top deck stiffness on the compression strength of asymmetrically supported corrugated boxes

During unitized shipment, the components of unit loads are interacting with each other. During floor stacking of unit loads, the load on the top of the pallet causes the top deck of the pallet to bend, which creates an uneven top deck surface resulting in uneven or asymmetrical support of the corrugated boxes. This asymmetrical support could significantly affect the strength of the corrugated boxes, and it depends on the top deck stiffness of the pallet. This study is aimed at investigating how the variations of pallet top deck stiffness and the resulting asymmetric support affect corrugated box compression strength. The study used a scaled-down unit load compression test on quarter-scale pallet designs with different deckboard thicknesses using four different corrugated box designs. Pallet top deck stiffness was determined to have a significant effect on box compression strength. There was a 27%–37% increase in box compression strength for boxes supported by high-stiffness pallets in comparison with low-stiffness pallets. The fact that boxes were weaker on low-stiffness pallets could be explained by the uneven pressure distribution between the pallet deck and bottom layer of boxes. Pressure data showed that a higher percentage of total pressure was located under the box sidewalls that were supported on the outside stringers of low-stiffness pallets in comparison with high-stiffness pallets. This was disproportionately loading one side of the box. Utilizing the effects of pallet top deck stiffness on box compression performance, a unit load cost analysis is presented showing that a stiffer pallet can be used to carry boxes with less board material; hence, it can reduce the total unit load packaging cost.     

Numerical and experimental investigation of the strength of corrugated board packages

The buckling behaviour of corrugated paper packages was studied by means of an experimental and theoretical analysis. Mechanical behaviour of paperboard was first evaluated experimentally, then a local geometry FEM model, able to reproduce with a very good accuracy buckling loads obtained experimentally in the standard edge compression test, was developed. In order to investigate the buckling of a complete package, a finite element ‘corrugated board’ was introduced by means of a dedicated homogenization procedure. The FEM model of the package, assembled with this new element, can accurately predict the experimental data of incipient buckling observed during the standard box compression test, despite the few degrees of freedom and the minimal computational effort. Copyright © 2003 John Wiley & Sons, Ltd.     

An artificial neural network model for virtual Superpave asphalt mixture design

This study presents an artificial neural network (ANN) model to predict the asphalt mixture volumetrics at Superpave gyration levels. The input data-set needed by the algorithm is composed of gradation of the mix, bulk specific gravity of aggregates, low- and high-performance grade of the binder, binder content of the mix and the target number of gyrations (i.e. N_ini, N_des and N_max). The proposed ANN model uses a three-layer scaled conjugate gradient back-propagation (feed-forward) network. The ANN was trained using data obtained from numerous roads with a total of 1817 different mix designs. Results revealed that the ANN was able to predict V_a within V_a (measured) ± 1.0% range 85–93% of the time and within V_a (measured) ± 0.5% range 60–70% of the time. Currently with the developed ANN model, Superpave mix design can take approximately between 1.5 and 4.5 days, which corresponds to 3–6 days of savings.     

用神经网络BP算法预测钨合金材料抗拉强度

为减少实验量,降低实验成本,采用人工神经网络BP算法处理了钨合金材料的抗拉强度的实验数据,包括钨含量、变形量对材料抗拉强度的影响,给出了在不同钨含量条件下变形量对材料抗拉强度的关系曲线,和不同变形量条件下钨含量对材料抗拉强度的关系曲线.通过本文的分析可知,采用BP算法来处理钨合金的实验数据是可行的.     

瓦楞纸箱抗压强度的计算方法及计算机辅助设计

论述了抗压强度的计算方法 ,其中 Kellicutt公式和 Makee公式为最主要的计算方法 ,并对一个实例进行计算 ,比较两种数学模型得到的结果 ,由此得到一些有用结论 ,并提出了相应的计算机程序 ,使计算准确合理     

Estimation of the compression strength of corrugated fibreboard boxes and its application to box design using a personal computer

Many papers have been published on the compression strength of corrugated fibreboard boxes, using such formulae as Kellicut's equation and McKee's equation for the calculation. These equations, however, require known values of the strength of linerboard or corrugated fibreboard, they do not include the influence of moisture content and they are inadequate in the case of wrap-around boxes. The present author measured the mechanical properties of a large number of fibreboard boxes, and has derived a statistical formula useful for estimating the compression strength of a box based on its specifications — grade of corrugated fibreboard, size of box, type of box, printed area and moisture content. The calculation gives fairly good agreement with experimental results. The estimation technique has further been converted into a personal computer program, which renders the design of corrugated fibreboard boxes an easier task.     

基于人工神经网络的多处损伤加筋板剩余强度预测

用BP神经网络算法对多处损伤加筋板的剩余强度数据进行训练学习,将预测值和3种经典分析方法的计算值与实验值进行对比,结果表明,ANN法预测值与实验值吻合得最好,LMC修正法和WSU3修正法次之,Swift塑性区连通法最差。最后用所建立的BP网络对不同主裂纹半长和韧带长度的剩余强度进行了预测,结果发现,在其他参数不变的情况下,不管是双筋条还是三筋条加筋板,剩余强度总是随主裂纹半长的增加而成线性降低,随韧带长度的增加而成线性增加,但双筋条加筋板比三筋条加筋板对主裂纹半长和韧带长度的变化更加敏感。     

基于人工神经网络的NiZn铁氧体结构不敏感性能的预测模型

为了系统研究配方对铁氧体电磁性能的影响,制备了一系列Mn2 、Ge4 和Si4 替代的NiZn铁氧体材料,建立了铁氧体配方与结构不敏感性能之间的人工神经网络预测模型.利用所建立的模型研究了ZnO对NiZn铁氧体3个结构不敏感性能居里温度、磁饱和强度及介电常数的影响规律,以及多个组分的交互作用.结果表明:模型的预测结果与实验结果吻合良好,二者的相对误差较小.ZnO含量的增加会导致铁氧体居里温度下降,但会提高饱和磁化强度和介电常数.NiO和ZnO的交互作用对铁氧体的结构不敏感性能影响明显.利用模型得到的铁氧体性能-成分等值线图对寻找最佳配方有较高参考价值.     

Application of beam on elastic foundation to the interaction between a corrugated box and pallet deckboard

Corrugated boxes are ubiquitous in shipping and warehousing logistics. In physical distribution, corrugated boxes are often shipped in a unit load form where the interaction between the components determines the effectiveness and safety of the overall system. When lower stiffness pallets are used to support the corrugated boxes, the compression strength of boxes is reduced due to the uneven support conditions caused by the deforming top deckboards of the pallet. In this study, a modification of the principle of beam on elastic foundation was used to predict the effect of pallet deck stiffness on the performance of a corrugated box. In the model, the corrugated box acts as the elastic foundation, and the deckboard is represented as the beam. Pallet deck stiffness, pallet connection stiffness, and package stiffness are required model inputs. The resulting model was capable of predicting the normalized distribution of forces along the boxes' length sidewall but was not capable of predicting the compression strength of the box at failure.     

Prediction of the concrete compressive strength by means of core testing using GMDH-type neural network and ANFIS models

Assessment of insitu concrete strength by means of cores cut from hardened concrete is accepted as the most common method, but may be affected by many factors. Group method of data handling (GMDH) type neural networks and adaptive neuro-fuzzy inference systems (ANFIS) were developed based on results obtained experimentally in this work along with published data by other researchers. Genetic algorithm (GA) and singular value decomposition (SVD) techniques are deployed for optimal design of GMDH-type neural networks. Samples incorporated six parameters with core strength, length-to-diameter ratio, core diameter, aggregate size and concrete age considered as inputs and standard cube strength regarded as the output. The results show that a generalized GMDH-type neural network and ANFIS have great ability as a feasible tool for prediction of the concrete compressive strength on the basis of core testing. Moreover, sensitivity analysis has been carried out on the model obtained by GMDH-type neural network to study the influence of input parameters on model output.     

Artificial neural network model of the strength of thin rectangular plates with weld induced initial imperfections

Probabilistic assessment of post-buckling strength of thin plate is a difficult problem because of computational effort needed to evaluate single collapse load. The difficulties arise from the nonlinear behaviour of an in-plane loaded plate showing up multiple equilibrium states with possible bifurcations, snap-through or smooth transitions of states. The plate strength depends heavily on the shape of geometrical imperfection of the plate mid-surface. In this paper, an artificial neural network (ANN) is employed to approximate the collapse strength of plates as a function of the geometrical imperfections. For the training set, mainly theoretical imperfections with the corresponding collapse loads of plate calculated by FEM are considered. The ANN validation is based on the measured imperfections of ship plating and FEM strength.     

GA改进BP神经网络在抗滑桩孔爆破开挖中的应用

目前桩孔开挖主要依靠工程类比进行,不同设计者设计的爆破参数往往因掌握的爆破理论和经验的不同而有所差异,爆破质量参差不齐。为此,提出基于遗传算法GA改进BP神经网络(GA-BP)建立爆破参数优化设计模型,该法不仅可以利用已有爆破经验数据和工程地质条件,同时,使用遗传算法优化BP神经网络阈值和权值可以弥补BP神经网络不稳定的缺陷,以达到获得更优爆破参数的目的。实践表明,基于遗传算法改进BP神经网络相比一般BP神经网络预测相对误差较小,同时GA-BP神经网络得到的优化爆破参数进行现场试验,取得了良好的爆破效果。因此,GA-BP神经网络模型应用于抗滑桩孔开挖爆破参数设计是可行的,可用于指导爆破施工。     

GA改进BP神经网络在抗滑桩孔爆破开挖中的应用

目前桩孔开挖主要依靠工程类比进行,不同设计者设计的爆破参数往往因掌握的爆破理论和经验的不同而有所差异,爆破质量参差不齐。为此,提出基于遗传算法GA改进BP神经网络(GA-BP)建立爆破参数优化设计模型,该法不仅可以利用已有爆破经验数据和工程地质条件,同时,使用遗传算法优化BP神经网络阈值和权值可以弥补BP神经网络不稳定的缺陷,以达到获得更优爆破参数的目的。实践表明,基于遗传算法改进BP神经网络相比一般BP神经网络预测相对误差较小,同时GA-BP神经网络得到的优化爆破参数进行现场试验,取得了良好的爆破效果。因此,GA-BP神经网络模型应用于抗滑桩孔开挖爆破参数设计是可行的,可用于指导爆破施工。     

Optimization and evaluation of time-dependent tablets comprising an immediate and sustained release profile using artificial neural network

The aim of this work was to optimize time-dependent tablets using artificial neural network (ANN). The time-dependent tablet consisted of a tablet core, which contained sustained release pellets (70% isosorbide-5-mononitrate [5-ISMN]), immediate release granules (30% 5-ISMN), superdisintegrating agent (sodium carboxymethylstarch, CMS-Na), and other excipients, surrounded by a coating layer composed of a water-insoluble ethylcellulose and a water-soluble channeling agent. The chosen independent variables, i.e., X₁ coating level of tablets, X₂ coating level of pellets, and X₃ CMS-Na level, were optimized with a three-factor, three-level Box-Behnken design. Data were analyzed for modeling and optimizing the release profile using ANN. Response surface plots were used to relate the dependent and the independent variables. The optimized values for the factors X₁-X₃ were 4.1, 14.1, and 29.8%, respectively. Optimized formulations were prepared according to the factor combinations dictated by ANN. In each case, the observed drug release data of the optimized formulations were close to the predicted release pattern. An in vitro model for predicting the effect of food on release behavior of optimized products was used in this study. It was concluded that neural network technique could be particularly suitable in the pharmaceutical technology of time-dependent dosage forms where systems were complex and nonlinear relationships often existed between the independent and the dependent variables.     

用人工神经网络研究合金元素对NdFeB永磁体磁性能的影响

为了系统研究合金元素对Nd-Fe-Co-Zr-B系永磁合金磁性能的影响，采用均匀设计方法设计了Nd、Co、Zr和B的4因素6水平U18（6^4）试验方案，根据试验结果，建立了合金成分与磁性能之间的人工神经网络（ANN）预测模型。利用该预测模型获得的成分-性能的二维曲线、三维曲面及等高线图，研究了单个合金元素以及多元素间的交互作用对NdFeB磁体磁性能的影响规律。结果表明：预测结果与实测结果吻合良好，预测精度高；Nd、Zr为提高矫顽力Hcj而降低剩磁Br的元素；Co、B则对提高Br有利而对提高Hcj不利；合金元素对Hcj与Br的影响呈相反的趋势；元素间交互作用对磁性能影响显著。     

Modeling the corrosion behavior of Ni-Cr-Mo-V high strength steel in the simulated deep sea environments using design of experiment and artificial neural network

Corrosion in complex coupling environments is an important issue in corrosion field, because it is difficult to take into account a large number of environment factors and their interactions. Design of Experiment (DOE) can present a methodology to deal with this difficulty, although DOE is not commonly spread in corrosion field. Thus, modeling corrosion of Ni-Cr-Mo-V steel in deep sea environment was performed in order to provide example demonstrating the advantage of DOE. In addition, an artificial neural network mapping using back-propagation method was developed for Ni-Cr-Mo-V steel such that the ANN model can be used to predict polarization curves under different complex sea environments without experimentation. Furthermore, roles of environment factors on corrosion of Ni-Cr-Mo-V steel in deep sea environment were discussed.     

基于BP神经网络的生物质发泡材料性能预测模型及应用

以EVA（乙烯-醋酸乙烯酯）和淀粉质量比、甘油含量、NaHCO₃含量为3个输入量,以拉伸强度和回弹率为输出量,建立3层BP（back propagation）神经网络,并将淀粉挤出发泡的正交实验结果作为样本对其进行训练,用以预测淀粉发泡材料的性能。研究结果证明,该BP神经网络能准确预测淀粉发泡材料的性能;同时发现,随着甘油含量的增加,淀粉发泡材料的回弹率逐渐增加,而拉伸强度则逐渐减小;NaHCO₃发泡剂的质量分数为3%时,淀粉发泡材料的拉伸强度最小。研究结果将为提高生物质发泡材料的性能以及扩展其使用范围提供信息。     

近红外光谱结合神经网络判别茶鲜叶产地

为快速、无损的判别鲜叶产地,维护恩施玉露的地理标志产品属性,采集恩施市芭蕉乡、白果乡和咸丰县茶鲜叶近红外光谱,经光谱预处理后,对校正集66个样品光谱数据进行主成分分析,然后建立BP神经网络预测模型,对验证集鲜叶样品的产地进行了预测,建立了8(输入节点)-4(隐含层节点)-1(输出节点)三层网络模型,验证集样品判别准确率为100%.近红外光谱技术结合神经网络能够快速、准确地判别茶鲜叶产地.     

Fabrication and modelling of the macro-mechanical properties of cross-ply laminated fibre-reinforced polymer composites using artificial neural network

The mechanical behaviour of fibre-reinforced polymer composites (FRPCs) is considered very complex due to many factors such as composition, material type, manufacturing process and end user applications. This article presents the mechanical properties and artificial neural network (ANN) modelling results of cross-ply laminated FRPCs. Twenty composite samples were fabricated by varying the number of layers of carbon fibre and glass fibre as reinforcement and polyphenylene sulphide and high-density polyethylene as matrix. Mechanical properties were measured in terms of flexural modulus, hardness, impact and transverse rupture strength. Multilayer feed-forward backpropagation ANN approach was used to predict the mechanical properties by using material type, composition and number of reinforcement and matrix layers as input variables. From 20 data patterns, 16 were used for network training and remaining 4 were used to test the models. Furthermore, trend analysis was also performed to understand the influence of inputs on developed models. It is evident from the ANN prediction results that there is good correlation between predicted and actual values within acceptable mean absolute error. The outcomes of this research will help to reduce cost and time by eliminating tedious composite property measurements and to fabricate tailored composites meeting application requirements.