Selective disassembly sequencing is the problem of determining sequence operations to extract one or more target components a product. This study considers with random operation times in parallel environment which can be removed at same time by single operation. After representing all possible sequences using extended process graph, stochastic integer programming model developed for objective minimising sum and penalty costs, where costs consist sequence-dependent set-up cost expectation...

We consider a discrete optimization via simulation (DOvS) problem with stochastic constraints on secondary performance measures in which both objective and need to be estimated by simulation. To solve the problem, we develop new method called Penalty Function Memory (PFM). It is similar an existing penalty-type method—which consists of penalty parameter measure violation constraints—in sense that it converts DOvS into series unconstrained problems. However, PFM uses different parameter,...

We consider the problem of identifying source location a contaminant via analyzing changes in concentration levels observed by sensor network river system. To address this problem, we propose framework including two main steps: (i) pre-processing data; and (ii) training testing classification model. Specifically, first obtain data set presenting from simulation model, extract numerical characteristics set. Then, random forest models are generated assessed to identify contaminant. By using...

The problem of designing a water quality monitoring network for river systems is to find the optimal location finite number devices that minimizes expected detection time contaminant spill event while guaranteeing good reliability. When uncertainties in and rain events are considered, both reliability need be estimated by stochastic simulation. This formulated as discrete optimization via simulation (OvS) on with constraint reliability; it solved an OvS algorithm combined recently proposed...

We consider a discrete optimization via simulation problem with stochastic constraints on secondary performance measures where both objective and need to be estimated by simulation. To solve the problem, we present method called penalty function memory (PFM), which determines value for solution based history of feasibility check solution. PFM converts DOvS into series new problems without so that an existing algorithm can applied problem.

We consider a discrete optimization via simulation problem with stochastic constraints on secondary performance measures where both objective and need to be estimated by simulation. To solve the problem, we present method called penalty function memory (PFM), which determines value for solution based history of feasibility check solution. PFM converts DOvS into series new problems without so that an existing algorithm can applied problem.

We consider the problem of finding a set feasible or near-feasible systems among finite number simulated in presence stochastic constraints. When constraints are subjective, decision maker may want to test multiple threshold values for Or simply determine how changes as become more strict with objective pruning system best performance. only constraint thresholds change same underlying systems, it is natural reuse observations collected from feasibility check different value. present an...

The problem of designing a water quality monitoring network for river systems is to find the optimal location finite number devices that minimizes expected detection time contaminant spill event with good reliability. We formulate this as an optimization stochastic constraint on secondary performance measure where primary and propose new objective function integrates into original in way existing Optimization via Simulation (OvS) algorithms originally developed without any can be applicable...

The problem of designing a water quality monitoring network for river systems is to find the optimal location finite number devices that minimizes expected detection time contaminant spill event with good reliability. We formulate this as an optimization stochastic constraint on secondary performance measure where primary and propose new objective function integrates into original in way existing Optimization via Simulation (OvS) algorithms originally developed without any can be applicable...

We consider the problem of pruning inferior systems among a finite number simulated using constraints that are stochastic (in their performance measures need to be estimated through observations) and subjective thresholds can tightened or relaxed). With constraints, decision maker test multiple threshold values determine how set feasible changes as become stricter use this information prune identify system with best performance. When possible is large, may want start by obtaining feasibility...

In semiconductor manufacturing, it is important to rapidly estimate the values of line widths or height, called critical dimension (CD), a nanoscale structure. this paper, we consider optical CD measurement that designed figure out by comparing given measured spectrum with calculated spectra from simulation model. The main problem study identify posterior distributions using Bayesian inference high computational efficiency in measurement. delayed acceptance Metropolis-Hastings algorithm...

This study addresses the problem of identifying source location a contaminant spill in river system when sensor network returns observations containing random measurement errors. To solve this problem, we suggest new framework comprising three main steps: (i) detection, (ii) data preprocessing, and (iii) identification. Specifically, applied statistical process control chart to detect with errors while keeping false alarm rate at less than or equal user-specified value. After detecting...

Estimating a batch of parameter vectors nonlinear model is considered, where there exists interpreting the independent and dependent variables, are assumed to be sampled from multivariate normal distribution. The mean vector covariance matrix distribution can such referred as hypothetical underlying A new framework proposed, namely, distribution-guided heuristic search framework, which uses information with following two main concepts: (i) changing coordinate via linear transformation (ii)...