The design of robust value-creating supply chain networks: A critical review

This paper discusses Supply Chain Network (SCN) design problem under uncertainty, and presents a critical review of the optimization models proposed in the literature. Some drawbacks and missing aspects in the literature are pointed out, thus motivating the development of a comprehensive SCN design methodology. Through an analysis of supply chains uncertainty sources and risk exposures, the paper reviews key random environmental factors and discusses the nature of major disruptive events threatening SCN. It also discusses relevant strategic SCN design evaluation criteria, and it reviews their use in existing models. We argue for the assessment of SCN robustness as a necessary condition to ensure sustainable value creation. Several definitions of robustness, responsiveness and resilience are reviewed, and the importance of these concepts for SCN design is discussed. This paper contributes to framing the foundations for a robust SCN design methodology.     

Maximum cut in fuzzy nature: Models and algorithms

The maximum cut (Max-Cut) problem has extensive applications in various real-world fields, such as network design and statistical physics. In this paper, a more practical version, the Max-Cut problem with fuzzy coefficients, is discussed. Specifically, based on credibility theory, the Max-Cut problem with fuzzy coefficients is formulated as an expected value model, a chance-constrained programming model and a dependent-chance programming model respectively according to different decision criteria. When these fuzzy coefficients are represented by special fuzzy variables like triangular fuzzy numbers and trapezoidal fuzzy numbers, the crisp equivalents of the fuzzy Max-Cut problem can be obtained. Finally, a genetic algorithm combined with fuzzy simulation techniques is designed for the general fuzzy Max-Cut problem under these models and numerical experiment confirms the effectiveness of the designed genetic algorithm.     

“I can name that Bayesian network in two matrixes!”

For a number of situations, a Bayesian network can be split into a core network consisting of a set of latent variables describing the status of a system, and a set of fragments relating the status variables to observable evidence that could be collected about the system state. This situation arises frequently in educational testing, where the status variables represent the student proficiency and the evidence models (graph fragments linking competency variables to observable outcomes) relate to assessment tasks that can be used to assess that proficiency. The traditional approach to knowledge engineering in this situation would be to maintain a library of fragments, where the graphical structure is specified using a graphical editor and then the probabilities are entered using a separate spreadsheet for each node. If many evidence model fragments employ the same design pattern, a lot of repetitive data entry is required. As the parameter values that determine the strength of the evidence can be buried on interior screens of an interface, it can be difficult for a design team to get an impression of the total evidence provided by a collection of evidence models for the system variables, and to identify holes in the data collection scheme. A Q-matrix - an incidence matrix whose rows represent observable outcomes from assessment tasks and whose columns represent competency variables - provides the graphical structure of the evidence models. The Q-matrix can be augmented to provide details of relationship strengths and provide a high level overview of the kind of evidence available. The relationships among the status variables can be represented with an inverse covariance matrix; this is particularly useful in models from the social sciences as often the domain experts’ knowledge about the system states comes from factor analyses and similar procedures that naturally produce covariance matrixes. The representation of the model using matrixes means that the bulk of the specification work can be done using a desktop spreadsheet program and does not require specialized software, facilitating collaboration with external experts. The design idea is illustrated with some examples from prior assessment design projects.     

折现的未决赔款准备金估计的随机逼近

凸序意义下的随机界是估计具有相依性随机变量和分布的良好工具.在考虑货币时间价值的基础上,通过随机上下界的两种不同形式的凸组合对未决赔款准备金的估计进行逼近,并通过矩匹配法,给出了最优权数的计算公式.通过一个实例对所述方法进行验证.     

基于伽玛与对数正态分布假设下的广义线性模型的比较和应用

本文在假设每次损失金额的变异系数相同,且它们服从伽玛分布或对数正态分布的条件下,讨论了加法模型和乘法模型的参数估计和拟合优度检验,并应用一组实际损失数据对上述模型进行了实证比较。结果表明,对于一组特定的损失数据,对数正态分布假设下的广义线性模型可能优于伽玛分布假设下的广义线性模型。     

指数Lévy跳-扩散模型下欧式期权的COS定价方法

主要研究指数Lévy形式的跳-扩散模型下欧式期权的定价问题.首先,给出了模型在均值修正等价鞅测度下的风险中性特征函数;然后,基于特征函数给出了欧式期权的傅里叶COS定价方法,并对COS方法进行修正,得到了指数Lévy形式跳-扩散模型的期权定价公式;最后,通过数值实验和实证分析检验了COS定价方法有效性,结果表明COS方...     

Identification of stiffness, dissipation and input parameters of randomly excited non-linear systems: Capability of restricted potential models (RPM)

A dynamic identification technique in the time domain for time invariant systems under random external forces is presented. This technique is based on the use of the class of restricted potential models (RPM), which are characterized by a non-linear stiffness and a special form of damping, that is a product of the input power spectral density (PSD) matrix and the velocity gradient of a non-linear function of the total mechanical energy. By applying stochastic differential calculus and by specific analytical manipulations, some algebraic equations, depending on the response statistics and on the mechanic parameters that characterize RPM, are obtained. These equations can be used for the dynamic identification of the above mechanic parameters once the response statistics of the system to be identified are evaluated. The proposed technique allows one to identify single-degree-of-freedom or multi-degrees-of-freedom systems in the case of unmeasurable input. Further, the probabilistic characteristics of the external forces can be completely estimated in terms of PSD matrix.     

Magnetic field generation by convective flows in a plane layer

Hydrodynamic and magnetohydrodynamic convective attractors in a plane horizontal layer 0≤z≤1 are investigated numerically. We consider Rayleigh-Bénard convection in Boussinesq approximation assuming stress-free boundary conditions on horizontal boundaries and periodicity with the same period L in the x and y directions. Computations have been performed for the Prandtl number P=1 for and Rayleigh numbers 0<R≤4000, and for L=4, 0<R≤2000. Fifteen different types of hydrodynamic attractors are found, including two types of steady states distinct from rolls, travelling waves, periodic and quasiperiodic flows, and chaotic attractors of heteroclinic nature. Kinematic dynamo problem has been solved for the computed convective attractors. Out of the 15 types of the observed attractors only 6 can act as kinematic dynamos. Nonlinear magnetohydrodynamic regimes have been explored assuming as initial conditions convective attractors capable of magnetic field generation, and a small seed magnetic field. After initial exponential growth, in the saturated regime magnetic energy remains much smaller than the flow kinetic energy. The final magnetohydrodynamic attractors are either quasiperiodic or chaotic.