[成形过程仿真优化与集成计算材料工程]限定加热管布局的快速热循环注塑成形模具电加热系统优化

针对管道布局、最大允许能耗给定条件下快速热循环注塑成形（RHCM）注塑模具型腔表面快速均匀加热的问题，提出以单根加热棒热流密度为设计变量，以模具型腔表面升温效率和温度分布均匀性为目标，结合有限元模拟、响应面设计以及多目标粒子群优化技术来优化RHCM模具电加热系统。与优化前相比，加热系统优化后，模具型腔表面最大温差降低63.4%，加热系统总能耗降低9%。对比了不同注塑成形工艺条件下成形的平板塑件表面质量，结果表明，相对传统注塑成形（CIM）工艺，RHCM工艺将制品表面粗糙度Ra从320 nm降低到118 nm，并有效抑制了制品表面熔接痕、缩痕等缺陷；发现制品表面粗糙度与型腔表面对应点温度成负相关，说明优化后的型腔表面温度分布更有利于提升制品表面质量。     

Anderson Acceleration for Nonconvex ADMM Based on Douglas-Rachford Splitting

The alternating direction multiplier method (ADMM) is widely used in computer graphics for solving optimization problems that can be nonsmooth and nonconvex. It converges quickly to an approximate solution, but can take a long time to converge to a solution of high-accuracy. Previously, Anderson acceleration has been applied to ADMM, by treating it as a fixed-point iteration for the concatenation of the dual variables and a subset of the primal variables. In this paper, we note that the equivalence between ADMM and Douglas-Rachford splitting reveals that ADMM is in fact a fixed-point iteration in a lower-dimensional space. By applying Anderson acceleration to such lower-dimensional fixed-point iteration, we obtain a more effective approach for accelerating ADMM. We analyze the convergence of the proposed acceleration method on nonconvex problems, and verify its effectiveness on a variety of computer graphics including geometry processing and physical simulation.     

基于卷积神经网络的葡萄叶片氮含量识别方法

为实现对葡萄叶片氮素含量快速、便捷的识别，在卷积神经网络VGG-16网络结构基础上，将数据增广后的图像按不同梯度划分进行模型训练，通过十折交叉验证法探究最佳的训练集与验证集分配比例，并构建4个不同深度的网络模型进行训练对比，采用全局平均池化代替全连接层约简网络参数量。训练结果表明，氮含量梯度设为0.70%、0.35%和0.175%时，室内简单背景识别准确率分别为85.9%、76.2%和71.1%；晴天室外复杂背景下识别准确率分别为44.6%、35.0%和30.4%。研究结果表明利用VGG-16建立的网络学习模型对葡萄叶片氮含量识别提供了一种新的便捷方法，对农业信息化和智能化技术应用具有一定促进作用。     

Adaptive neuro-fuzzy algorithm applied to predict and control multi-phase flow rates through wellhead chokes

A Takagi-Sugeno adaptive neuro-fuzzy inference system (TSFIS) model is developed and applied to a dataset of wellhead flow-test data for the Resalat oil field located offshore southern Iran, the objective is to assist in the prediction and control of multi-phase flow rates of oil and gas through the wellhead chokes. For this purpose, 182 test data points (Appendix 1) related to the Resalat field are evaluated. In order to predict production flow rate (Q_L) expressed as stock-tank barrels per day (STB/D), this dataset includes four selected input variables: upstream pressure (Pwh); wellhead choke sizes (D64); gas to liquid ratio (GLR); and, base solids and water including some water-soluble oil emulsion (BS&W). The test data points evaluated include a wide range of oil flow rate conditions and values for the four input variables recorded. The TSFIS algorithm applied involves five data processing steps: a) pre-processing, b) fuzzification, c) rules base and adaptive neuro-fuzzy inference engine, d) defuzzification, and e) post-processing of the fuzzy model. The developed TSFIS model for the Resalat oil field database predicted oil flow rate to a high degree of accuracy (root mean square error = 247 STB/D, correlation coefficient = 0.9987), which improves substantially on the commonly used empirical algorithms used for such predictions. TSFIS can potentially be applied in wellhead choke fuzzy controllers to stabilize flow in specific wells based on real-time input data records.     

S6-11综放工作面回风巷支护设计优化

针对常村矿回采巷道变形严重,影响正常生产的问题,通过对矿井赋存条件、巷道现有支护形式和围岩变形过程分析,采用新型联合支护技术对S6-11回风巷道支护进行优化。现场实测巷道顶底板相对移近量最大120mm,两帮相对移近量最大140mm,均在允许正常范围之内。     

Optimal design of Raman fibre amplifier based on terminal value optimization strategy and shuffled frog leaping algorithm

This paper introduces an evolutionary algorithm, Shuffled Frog Leaping Algorithm (SFLA), to solve the optimization problem in designing the multi-pumped Raman Fibre Amplifier (RFA). SFLA is a powerful optimizer tool because of its efficient mathematical expressions and global search capability. We utilize SFLA to determine the optimal pump wavelengths and pump powers by minimizing the gain ripple of RFA. To accelerate calculations, a terminal value optimization strategy (TVOS) is incorporated into the evolution of SFLA. This proposed strategy takes the terminal power values of pumps as the decision variables in optimization. Then, the optimal original power values of the pumps are obtained by solving the Power Coupled Equations once, without using the traditional method of repetitive guesses.The combination of SFLA and TVOS enhances the efficiency of optimization and accelerates calculation, while satisfying the design requirements of RFA.The simulation results show that nearly 65% of computational time has been saved compared with the traditional average power analysis. The 4-pumped C+L band of backward multi-pumped RFA with the average net gain of 0 dB, 1 dB and 2 dB are designed individually, where the gain ripple is less than 0.64 dB. The combination of SFLA and TVOS enhance the optimization efficiency and improve the performance of RFA with good gain profile.     

利用调度优化模型研究原油调合方案的可行性

针对某沿海炼油企业拟投用原油调合系统以稳定混炼原油的性质,设计方案要求将部分码头罐的操作模式由混储改为单储的情况,采用约束规划与数学规划复合建模,实现了码头至厂区大容积长输线模拟,建立了该企业的原油调度优化模型并研究了设计方案的可行性。针对240h调度周期、10种可加工原油、3艘到港油轮的复杂工况进行了优化计算。结果表明:该设计方案具备可行性,且油轮仍可实现到港即卸油,蒸馏装置混炼油种也可长时间保持稳定;模型的优化计算时间较短(小于15min),且对长输线收付及存油情况模拟准确,复合建模方法满足工业应用要求。     

R2D2: A scalable deep learning toolkit for medical imaging segmentation

Deep learning has gained a significant popularity in recent years thanks to its tremendous success across a wide range of relevant fields of applications, including medical image analysis domain in particular. Although convolutional neural networks (CNNs) based medical applications have been providing powerful solutions and revolutionizing medicine, efficiently training of CNNs models is a tedious and challenging task. It is a computationally intensive process taking long time and rare system resources, which represents a significant hindrance to scientific research progress. In order to address this challenge, we propose in this article, R2D2, a scalable intuitive deep learning toolkit for medical imaging semantic segmentation. To the best of our knowledge, the present work is the first that aims to tackle this issue by offering a novel distributed versions of two well-known and widely used CNN segmentation architectures [ie, fully convolutional network (FCN) and U-Net]. We introduce the design and the core building blocks of R2D2. We further present and analyze its experimental evaluation results on two different concrete medical imaging segmentation use cases. R2D2 achieves up to 17.5× and 10.4× speedup than single-node based training of U-Net and FCN, respectively, with a negligible, though still unexpected segmentation accuracy loss. R2D2 offers not only an empirical evidence and investigates in-depth the latest published works but also it facilitates and significantly reduces the effort required by researchers to quickly prototype and easily discover cutting-edge CNN configurations and architectures.     

A stiffness parameter and truncation error criterion for adaptive path following in structural mechanics

We explore a truncation error criterion to steer adaptive step length refinement and coarsening in incremental-iterative path following procedures, applied to problems in large-deformation structural mechanics. Elaborating on ideas proposed by Bergan and collaborators in the 1970s, we first describe an easily computable scalar stiffness parameter whose sign and rate of change provide reliable information on the local behavior and complexity of the equilibrium path. We then derive a simple scaling law that adaptively adjusts the length of the next step based on the rate of change of the stiffness parameter at previous points on the path. We show that this scaling is equivalent to keeping a local truncation error constant in each step. We demonstrate with numerical examples that our adaptive method follows a path with a significantly reduced number of points compared to an analysis with uniform step length of the same fidelity level. A comparison with Abaqus illustrates that the truncation error criterion effectively concentrates points around the smallest-scale features of the path, which is generally not possible with automatic incrementation solely based on local convergence properties.