人工神经网络及其在窑炉动态温度场的模拟研究

本文阐述了人工神经网络的发展、基本原理以及前馈神经网络的反向传播学习算法，并应用单孢层网络进行了窑炉烧嘴温度场分布的仿真研究。结果表明。用非线性神经元网络模拟在窑炉温度场预测和控制方面是可行的。     

Analytical ray tracing system: Introducing art, a C-library designed for seismic applications

Ray tracing technique is an important tool not only to forward but also for inverse problems in Geophysics, which most of the seismic processing steps depend on. However, implementing ray tracing codes can be very time consuming. This article presents a computer library to trace rays in 2.5D media composed by a stack of layers. The velocity profile inside each layer is such that the eikonal equation can be analytically solved. Therefore, the ray tracing within such profile is made fast and accurate. The great advantage of an analytical ray tracing library is the numerical precision of the quantities computed and the fast execution of the implemented codes. Even though ray tracing programs exist for a long time, for example the seis88 package by ?ervený, most of those programs use a numerical approach to compute the ray. Regardless of the fact that numerical methods can solve more general problems, the analytical ones could be part of a more sophisticated simulation process, where the ray tracing time is completely relevant. We demonstrate the feasibility of our codes using several examples (Miqueles et al., 2013)  [1]. The library can also be used for other applications besides seismic, e.g., optics and tomography.     

Investigating dependencies in software requirements for change propagation analysis

ContextThe dependencies between individual requirements have an important influence on software engineering activities e.g., project planning, architecture design, and change impact analysis. Although dozens of requirement dependency types were suggested in the literature from different points of interest, there still lacks an evaluation of the applicability of these dependency types in requirements engineering.ObjectiveUnderstanding the effect of these requirement dependencies to software engineering activities is useful but not trivial. In this study, we aimed to first investigate whether the existing dependency types are useful in practise, in particular for change propagation analysis, and then suggest improvements for dependency classification and definition.MethodWe conducted a case study that evaluated the usefulness and applicability of two well-known generic dependency models covering 25 dependency types. The case study was conducted in a real-world industry project with three participants who offered different perspectives.ResultsOur initial evaluation found that there exist a number of overlapping and/or ambiguous dependency types among the current models; five dependency types are particularly useful in change propagation analysis; and practitioners with different backgrounds possess various viewpoints on change propagation. To improve the state-of-the-art, a new dependency model is proposed to tackle the problems identified from the case study and the related literature. The new model classifies dependencies into intrinsic and additional dependencies on the top level, and suggests nine dependency types with precise definitions as its initial set.ConclusionsOur case study provides insights into requirement dependencies and their effects on change propagation analysis for both research and practise. The resulting new dependency model needs further evaluation and improvement.     

Development of bond strength model for FRP plates using back‐propagation algorithm

For the flexural reinforcement of bridge and building structure, synthetic materials whose dynamic properties are superior and those containing the merit of corrosion‐proof are widely used as the substitute for a steel plate. Since FRP plate has improved bond strength owing to the fibers externally adhering to the plate, many researches regarding the bond strength improvement have been substantially performed. To search out such bond strength improvement, previous researchers had ever examined the bond strength of FRP plate through their experiment by setting up many variables. However, since the experiment for a research on the bond strength takes much of expenditure for setting up the equipment and is time‐consuming, also is difficult to be carried out, it is limitedly conducted. The purpose of this study was to develop the most suitable artificial neural network model by application of various neural network models and algorithm to the data of the bond strength experiment conducted by previous researchers. Many variables were used as input layers against bond strength: depth, width, modulus of elasticity, tensile strength of FRP plate and the compressive strength, tensile strength, and width of concrete. The developed artificial neural network model has been applied back‐propagation, and its error was learned to be converged within the range of 0.001. Besides, the process for the over‐fitting problem has been dissolved by Bayesian technique. The verification on the developed model was executed by comparison with the test results of bond strength made by other previous researchers, which was never been utilized to the learning as yet. © 2006 Wiley Periodicals, Inc. J Appl Polym Sci 100: 5119–5127, 2006     

基于局部自适应先验MRF模型的快速BP图像分割算法

针对常规MRF分割模型不能有效描述图像的局部特征、常导致图像的过分割现象,提出了一种局部自适应先验的MRF模型。该模型利用图像的邻接区域信息建立了一种局部自适应特征MRF模型。基于提出的模型,建立了一种具有快速收敛策略的区域BP算法对MRF模型的区域消息进行传递,有效解决了区域BP算法的计算量大的问题。实验结果表明,与常规区域BP算法相比,提出的分割方法具有更快的分割速度和精度。     

Ignition and Combustion of Dust-Gas Suspensions

The ignition and combustion of dust-gas suspensions are considered. It is shown that the ability of these systems to accumulate heat is determined not only by their kinetic and thermal properties but also by the relation between their reaction surface and the heat-removal surface (f). Experimental information on flame temperatures, ignition delays, and flame propagation over gas suspensions is processed using the parameter f, and the postulate on the stimulating role of the developed reaction surface in activating these processes is validated. It is shown that during overall burning, diffusion combustion of particles occurs only for rather small values of f. The ambiguous effect of the parameter f on the ignition and combustion processes leads to the necessity of optimizing the fuel size distribution and concentration for the effective operation of the power devices. The role of the macroparameters of two-phase flames of refractory metals in the synthesis of combustion nanoproducts is analyzed. __________ Translated from Fizika Goreniya i Vzryva, Vol. 41, No. 6, pp. 3–14, November–December, 2005.     

Failure load prediction of structural adhesive joints : Part 2: Experimental study

The objective of this study was to determine how the fracture of adhesive joints depends on elastic beam parameters describing the adherends and the applied loads. The basic specimen geometry was the cracked lap shear joint constructed of aluminium alloy with various adherend and bondline thicknesses. Loads were applied in different combinations of bending, tension and shear to generate a failure envelope for each adhesive and specimen geometry. It was found that crack propagation for precracked specimens occured at a critical strain energy release rate but was also a function of the G_I/G_II ratio and the bondline thickness. The experiments also showed that the loads required to propagate a crack in a precracked specimen were always lower than the loads required to break the fillet. Hence, by treating uncracked joints as being cracked, where the fictitious crack tip is assumed to coincide with the location of the fillet, a conservative estimate of the failure load is obtained.     

互联网金融平台中高违约风险用户识别算法

在我国金融科技不断创新的背景下,互联网金融平台中通过网络分析技术开展用户风险识别已经成为当前的热点技术发展方向。以某互联网金融平台的用户交易数据为对象,通过分析其中借贷逾期违约的传播行为,提出通过传播特征构建模型算法识别互联网金融平台的高风险用户。在构建基于阈值传播和随机传播的SIS模型和SIR模型基础上,将模型转换为可评价用户风险值的算法,并进一步与实际违约数据进行验证对比。对比结果显示在前5%和10%高风险群体划分条件下,算法具有较高的召回率和良好的结构关联性。     

基于CT扫描的致密砂岩脆性破坏裂纹扩展规律研究

岩石在荷载作用下产生宏观破坏,其破裂面细观形态变化可以直接地反映出结构破坏特征。目前,常采用扫描电镜法、透镜法和CT扫描技术对岩石细观结构进行表征。运用CT扫描技术对典型脆性岩样单轴压缩破坏后破裂面及全断面进行扫描,获取全断面的细观形态,分析和总结了典型脆性岩样破坏细观裂纹扩展的发展规律:每一条独立裂纹都以一恒定曲率半径系数K随层位向试样内部扩展,直至裂纹曲率半径趋近于无穷。此时若无其他因素影响,其曲率半径则不会再随层位继续扩展;并通过分析定义出岩石脆性破坏状态时裂纹的聚集域和非聚集域,同时根据能量守恒定律得出了衍生裂纹及新次生裂纹产生的判据。