基于PLSR的多级制造过程关键质量特性识别方法

为解决多级制造过程关键质量特性识别中多质量特性之间的相关性问题,将偏最小二乘回归方法(Partial Least Squares Regression, PLSR)引入模型构建与分析中。首先应用状态空间方法建立多级制造过程关键质量特性识别模型,进而利用PLSR方法解决质量特性间的多重共线性问题并进行模型分析,识别关键质量特性,最后以卷烟生产过程为例介绍了该方法的应用。实例表明,该方法不仅可以有效识别多级制造过程关键质量特性,而且能够建立各级过程的输出质量对最终产品质量的影响及其质量特性之间相互关系的模型,反映多级生产过程的结构特征和各级过程质量特性之间的因果关系,为多级制造过程质量分析与控制提供依据。     

Using the EPQ for coordinated planning of a product with partial backordering and its components

While there has been considerable work over the years on multistage lot-sizing models, particularly in an MRP environment, there has been relatively little work on systems recognizing the WIP effects when there is gradual conversion of the components into the final product, as in production planning using the EPQ model for planning the final product. Here we consider lot-sizing planning for a two-stage system in which the final product is planned using an EPQ model with partial backordering and the production of the components is controlled using basic EPQ models without backordering.     

Network DEA: Additive efficiency decomposition

In conventional DEA analysis, DMUs are generally treated as a black-box in the sense that internal structures are ignored, and the performance of a DMU is assumed to be a function of a set of chosen inputs and outputs. A significant body of work has been directed at problem settings where the DMU is characterized by a multistage process; supply chains and many manufacturing processes take this form. Recent DEA literature on serial processes has tended to concentrate on closed systems, that is, where the outputs from one stage become the inputs to the next stage, and where no other inputs enter the process at any intermediate stage. The current paper examines the more general problem of an open multistage process. Here, some outputs from a given stage may leave the system while others become inputs to the next stage. As well, new inputs can enter at any stage. We then extend the methodology to examine general network structures. We represent the overall efficiency of such a structure as an additive weighted average of the efficiencies of the individual components or stages that make up that structure. The model therefore allows one to evaluate not only the overall performance of the network, but as well represent how that performance decomposes into measures for the individual components of the network. We illustrate the model using two data sets.     

Comparisons of models for estimation of safe doses using measures of the heaviness of tail of a distribution

Summary Procedures to estimate a dose of which the incidence probability is very small (e.g. 10⁻⁶) have been developed to evaluate the safety of chemical compounds. To compare models for estimation of safe doses quantitatively, a measure of the heaviness of tail of a distribution and a measure of tail at the origin are introduced. These measures have a theoretical basis for the comparison of tail behavior between distributions. Using the two measures, a tail ordering is defined to present a criterion for the comparison of models and is discussed for the probit, the logit, the Weibull, the (generalized) multihit, the (generalized) multitarget and the multistage models. The multistage model is most conservative among them, while the probit model has the reverse property. The Weibull model is more conservative than the logit. The multihit and multitarget models are found to be more sensitive than the Weibull and the logit. The Institute of Statistical Mathematics National Institute of Environmental Health Sciences     

On distributionally robust multiperiod stochastic optimization

This paper considers model uncertainty for multistage stochastic programs. The data and information structure of the baseline model is a tree, on which the decision problem is defined. We consider “ambiguity neighborhoods” around this tree as alternative models which are close to the baseline model. Closeness is defined in terms of a distance for probability trees, called the nested distance. This distance is appropriate for scenario models of multistage stochastic optimization problems as was demonstrated in Pflug and Pichler (SIAM J Optim 22:1–23, 2012). The ambiguity model is formulated as a minimax problem, where the the optimal decision is to be found, which minimizes the maximal objective function within the ambiguity set. We give a setup for studying saddle point properties of the minimax problem. Moreover, we present solution algorithms for finding the minimax decisions at least asymptotically. As an example, we consider a multiperiod stochastic production/inventory control problem with weekly ordering. The stochastic scenario process is given by the random demands for two products. We determine the minimax solution and identify the worst trees within the ambiguity set. It turns out that the probability weights of the worst case trees are concentrated on few very bad scenarios.     

On stochastic mortality modeling

In the last decennium a vast literature on stochastic mortality models has been developed. All well-known models have nice features but also disadvantages. In this paper a stochastic mortality model is proposed that aims at combining the nice features from the existing models, while eliminating the disadvantages. More specifically, the model fits historical data very well, is applicable to a full age range, captures the cohort effect, has a non-trivial (but not too complex) correlation structure and has no robustness problems, while the structure of the model remains relatively simple. Also, the paper describes how to incorporate parameter uncertainty in the model. Furthermore, a risk neutral version of the model is given, that can be used for pricing.     

On stochastic mortality modeling

In the last decennium a vast literature on stochastic mortality models has been developed. All well-known models have nice features but also disadvantages. In this paper a stochastic mortality model is proposed that aims at combining the nice features from the existing models, while eliminating the disadvantages. More specifically, the model fits historical data very well, is applicable to a full age range, captures the cohort effect, has a non-trivial (but not too complex) correlation structure and has no robustness problems, while the structure of the model remains relatively simple. Also, the paper describes how to incorporate parameter uncertainty in the model. Furthermore, a risk neutral version of the model is given, that can be used for pricing.     

Chance constrained programming models for refinery short-term crude oil scheduling problem

The main objective of this work is to put forward chance constrained mixed-integer nonlinear stochastic and fuzzy programming models for refinery short-term crude oil scheduling problem under demands uncertainty of distillation units. The scheduling problem studied has characteristics of discrete events and continuous events coexistence, multistage, multiproduct, nonlinear, uncertainty and large scale. At first, the two models are transformed into their equivalent stochastic and fuzzy mixed-integer linear programming (MILP) models by using the method of Quesada and Grossmann [I. Quesada, I E. Grossmann, Global optimization of bilinear process networks with multicomponent flows, Comput. Chem. Eng. 19 (12) (1995) 1219–1242], respectively. After that, the stochastic equivalent model is converted into its deterministic MILP model through probabilistic theory. The fuzzy equivalent model is transformed into its crisp MILP model relies on the fuzzy theory presented by Liu and Iwamura [B.D. Liu, K. Iwamura, Chance constrained programming with fuzzy parameters, Fuzzy Sets Syst. 94 (2) (1998) 227–237] for the first time in this area. Finally, the two crisp MILP models are solved in LINGO 8.0 based on scheduling time discretization. A case study which has 267 continuous variables, 68 binary variables and 320 constraints is effectively solved with the solution approaches proposed.     

Modelling hematopoiesis in health and disease

Hematopoiesis is the process responsible for maintaining the number of circulating blood cells that are undergoing continuous turnover. At the root of this process are the hematopoietic stem cells (HSC), that replicate slowly to self-renew and give rise to progeny cells that proceed along the path of differentiation. The process is complex, with the cells responding to a wide variety of cytokines and growth factors. We discuss the mathematics of hematopoiesis based on stochastic cell behavior. Multiple compartments are introduced to keep track of each cell division process and increasing differentiation. The same mathematical model that describes normal hematopoiesis across mammals as a stable steady state of a hierarchical stochastic process is also used to understand the detailed dynamics of various disorders both in humans and in animal models. The microecology of the multitude of cell lineages that constitute what we call troubled hematopoiesis evolves in time under mutation and selection, the paradigmatic components of Darwinian evolution. Thus, the present approach provides a novel perspective for looking at cancer progression and cure.     

基于特殊选择的抽象进化算法的收敛性

There has been a growing interest in mathematical models to character the evolutionary algorithms. The best-known one of such models is the axiomatic model colled the abstract evolutionary algorithm. In this paper, we first introduce the definitions of the abhstract selection and evolution operators, and that of the abstract evolutionary algorithm, which describes the evolution as an abstract stochastic process composed of these two fundamental abstract operators. In particular, a kind of abstract evolutionary algorithms based on a special selection mechansim is discussed. According to the sorting for the state space, the properties of the single step transition matrix for the algorithm are anaylzed. In the end, we prove that the limit probability distribution of the Markov chains exists. The present work provides a big step toward the establishment of a unified theory of evolutionary computation.     

Adaptation in a stochastic multi-resources chemostat model

We are interested in modeling the Darwinian evolution resulting from the interplay of phenotypic variation and natural selection through ecological interactions, in the specific scales of the biological framework of adaptive dynamics. Adaptive dynamics so far has been put on a rigorous footing only for direct competition models (Lotka–Volterra models) involving a competition kernel which describes the competition pressure from one individual to another one. We extend this to a multi-resources chemostat model, where the competition between individuals results from the sharing of several resources which have their own dynamics. Starting from a stochastic birth and death process model, we prove that, when advantageous mutations are rare, the population behaves on the mutational time scale as a jump process moving between equilibrium states (the polymorphic evolution sequence of the adaptive dynamics literature). An essential technical ingredient is the study of the long time behavior of a chemostat multi-resources dynamical system. In the small mutational steps limit this process in turn gives rise to a differential equation in phenotype space called canonical equation of adaptive dynamics. From this canonical equation and still assuming small mutation steps, we prove a rigorous characterization of the evolutionary branching points.     

基于效用比的多工序并联制造过程能力分析

多工序制造过程通常包含串联和并联两种结构,具有串并联混合结构的多工序制造过程是实践中最为常见的形式,而不同模式的并联结构其上游工序质量波动对下游工序及总过程能力的影响不同。针对多工序制造过程并联结构特点,本文从波动减少的角度重点对多工序并联制造过程中并行、分散和收敛三种基本模式进行过程能力分析,研究多工序制造过程中各子过程波动对整体过程能力的影响,并根据各子过程质量波动减少的“困难度”和“效用比”评价质量改进的效果,给出多工序并联过程能力改进策略选择依据。通过实例表明,本方法能较好地识别各工序质量波动减少对本工序过程能力和总过程能力的不同影响,确定质量改进的优先顺序,实现多工序制造过程的经济性质量改进和优化。     

基于改进Adaptive Lasso的多工序制造过程关键质量特性识别

为解决多工序制造过程关键质量特性识别中存在的质量特性间具有多重相关性以及数据高维度, 小样本等问题,本文采用主成分回归改进Adaptive Lasso方法并融合状态空间思想和Bootstrap方法实现多工序过程关键质量特性识别。首先引入状态空间思想构建多工序过程关键质量特性识别模型,然后利用Bootstrap方法重构样本,扩大样本量;进而采用改进Adaptive Lasso方法识别关键质量特性,并通过仿真验证改进Adaptive Lasso方法与Lasso,Adaptive Lasso和岭回归方法在质量特性间不同相关度下识别的有效性;最后通过实例说明改进Adaptive Lasso的具体应用过程,仿真及实例结果显示,改进Adaptive Lasso方法对多工序过程有良好的关键质量特性识别能力,特别当质量特性间有较强相关性时显著优于其它两种方法。     

The system dynamics of future warfare

The dissolution of the Warsaw Pact, the fall of the Berlin Wall and the unification of Germany have led to a new world order in which political structures have undergone substantial realingnent. NATO has been at the centre of this process of change which has led to the collapse of Soviet communism and the liberation of eastern Europe. Defence Operational Analysis (or Operational Research) played a significant part in this process. However, with the rapid changes of the last few years, many models and assumptions suddenly became irrelevant. A need arose for a major Land/Air conflicts across a range of future scenarios. This paper describes the structure of a System Dynamics model developed to meet this need. It also indicates the way in which the model has changed to take account of rapidly evolving political perceptions and concepts of operation.     

Evolution of Mechanical Properties in Tissues Undergoing Deformation-Related Fiber Remodeling Processes

We consider a biological fibrous soft tissue in which fibers are distributed in all directions. The mechanical properties of the fibers evolve due to a continuous remodeling process. The model to describe these fiber properties is based on the strain energy density of the protofibers and a survival kernel which describes the deformation-related property changes. In particular, this study investigates the development of the fiber orientation density for different choices of the fiber creation rate and fiber dissolution rate models. It has been shown that the fiber orientation density depends on both the history of the deformation and the deformation state of the fibers at the time of their creation. (© 2015 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim)     

Stochastic variational inequalities: single-stage to multistage

Variational inequality modeling, analysis and computations are important for many applications, but much of the subject has been developed in a deterministic setting with no uncertainty in a problem’s data. In recent years research has proceeded on a track to incorporate stochasticity in one way or another. However, the main focus has been on rather limited ideas of what a stochastic variational inequality might be. Because variational inequalities are especially tuned to capturing conditions for optimality and equilibrium, stochastic variational inequalities ought to provide such service for problems of optimization and equilibrium in a stochastic setting. Therefore they ought to be able to deal with multistage decision processes involving actions that respond to increasing levels of information. Critical for that, as discovered in stochastic programming, is introducing nonanticipativity as an explicit constraint on responses along with an associated “multiplier” element which captures the “price of information” and provides a means of decomposition as a tool in algorithmic developments. That idea is extended here to a framework which supports multistage optimization and equilibrium models while also clarifying the single-stage picture.     

广义抽象进化算法的性质分析

There has been a growing interest in mathematical models to character the evolutionary algorithms. The best-known one of such models is the axiomatic model called the abstract evolutionary algorithm (AEA), which unifies most of the currently known evolutionary algorithms and describes the evolution as an abstract stochastic process composed of two fundamental abstract operators: abstract selection and evolution operators. In this paper, we first introduce the definitions of the generalized abstract selection and evolution operators. Then we discuss the characterization of some parameters related to generalized abstract selection and evolution operators. Based on these operators, we finally give the strong convergence of the generalized abstract evolutionary algorithm. The present work provides a big step toward the establishment of a unified theory of evolutionary computation.     

A mixed integer programming model for multistage mean–variance post-tax optimization

In this paper, we introduce a mixed integer stochastic programming approach to mean–variance post-tax portfolio management. This approach takes into account of risk in a multistage setting and allows general withdrawals from original capital. The uncertainty on asset returns is specified as a scenario tree. The risk across scenarios is addressed using the probabilistic approach of classical stochastic programming. The tax rules are used with stochastic linear and mixed integer quadratic programming models to compute an overall tax and return-risk efficient multistage portfolio. The incorporation of the risk term in the model provides robustness and leads to diversification over wrappers and assets within each wrapper. General withdrawals and risk aversion have an impact on the distribution of assets among wrappers. Computational results are presented using a study with different scenario trees in order to show the performance of these models.     

A demand adjustment process

The aspiration approach to cooperative games, which has been studied by a number of authors, including Cross, Turbay, Albers, Selten and Bennett, presumes that players in a game bargain over their reservation prices, or aspirations. A number of aspiration-based solution concepts have been put forth, and aspiration solutions have been connected to non-cooperative bargaining models. Missing in this approach has been theory of how aspirations themselves arise. The present paper is an attempt to fill this gap. It describes a very general demand adjustment process, using the framework of set-valued dynamical systems developed by Maschler and Peleg. This demand adjustment process always converges; sufficient conditions are given in order that it converge to an aspiration, and that it converge in a finite number of steps.