Farhad Azadivar

Simulation optimization methodologies

Simulation models can be used as the objective function and/or constraint functions in optimizing stochastic complex systems. This tutorial is not meant to be an exhaustive literature search on simulation optimization techniques. It does not concentrate on explaining well-known general optimization and mathematical programming techniques either. Its emphasis is mostly on issues that are specific to simulation optimization. Even though a lot of effort has been spent to provide a reasonable overview of the field, still there are methods and techniques that have not been covered and valuable works that may not have been mentioned.

Facility layout optimization using simulation and genetic algorithms

Traditionally, the objective of a facility layout problem has been to minimize the material handling cost of the manufacturing system. While it is important to reduce the amount of material handling, the traditional methods do not address the actual time at which the material is transported. In todays short cycle time production environments, the timing of material movement may have a bigger impact on the productivity of the system than its cost. In this paper, a facility layout optimization technique is presented that takes into consideration the dynamic characteristics and operational constraints of the system as a whole, and is able to solve the facility layout design problem based on a systems performance measures, such as the cycle time and productivity. Each layout solution is presented in the form of a string that is suitable for analysis by a genetic algorithm technique. These solutions are then translated into simulation models by a specially designed automated simulation model generator. Genetic algorithms are used to optimize the layout for manufacturing effectiveness while simulation serves as a system performance evaluation tool. Combined with a statistical comparison technique to reduce the simulation burden, the test results demonstrate that the proposed approach overcomes the limitations of traditional layout optimization methods and is capable of finding optimal or near optimal solutions.

A tutorial on simulation optimization

This tutorial discusses the issues and procedures for using simulation as a tool for optimization of stochastic complex systems that are modeled by computer simulation. It is intended to be a tutorial rather than an exhaustive literature search. Its emphasis is mostly on issues that are specific to simulation optimization instead of concentrating on the general optimization and mathematical programming techniques, Even though a lot of effort has been spent to provide a comprehensive overview of the field, still there are methods and techniques that have not been covered and valuable works that may not have been mentioned.

Simulation optimization with qualitative variables and structural model changes: A genetic algorithm approach

In many common simulation optimization methods the structure of the system stays the same and only the set of values for certain parameters of the system such as the number of machines in a station or the in-process inventory is varied from one evaluation to the next. The methodology described in this paper is a simulation-optimization process where the qualitative variables and the structure of the system are the subjects of optimization. Here, the optimum response sought is a function of design and operation characteristics of the system such as the type of machines to use, dispatching rules, sequence of processing operations, etc. In the methodology developed here simulation models are automatically generated through an object-oriented process and are evaluated for various candidate configurations of the system. These candidates are suggested by a Genetic Algorithm (GA) that automatically guides the system towards better solutions. After simulating the alternatives, the results are returned to the GA to be utilized in selection of the next generation of configurations to be evaluated. This process continues until a satisfactory solution is obtained for the system.

Optimal design methodologies for configuration of supply chains

This paper describes a methodology developed for designing an optimal configuration for a supply chain. A typical configuration for a supply chain consists of defining components of the system, assigning values to characteristics parameters of each component and setting operation policies for governing the interrelationships among these components. As such, each configuration will be defined by a set of values for quantitative parameters of the system as well as a set of policy and qualitative characteristics. Examples of quantitative variable include inventory levels and frequency of ordering where as location of distribution centres and mode of transportation between suppliers and the original equipment manufacturers (OEM) are the decision variables of policy and qualitative nature. The methodology presented here consists of a supply chain model builder coupled with two optimisation algorithms that automatically build a sequence of configurations that systematically move towards an optimum design. A combination of mixed integer programming and a genetic algorithm is used to determine simultaneously the values of quantitative as well as policy variables. The solution consists of strategic decisions regarding facility locations, stocking locations, supplier selection, production policies, production capacities, and transportation modes.

Optimization of stochastic simulation models

An algorithm called SAMOPT is developed for optimizing the response function of simulation models that describe systems exhibiting stochastic behavior. Because of the stochastic nature of these simulated systems, the result of each evaluation of response by simulation is only a noisy (i.e., uncertain) observation of the true response. The SAMOPT algorithm uses these noisy responses to find a set of values for decision variables of the system such that the true response is optimized. Principles of the Stochastic Approximation Method have been used in developing this algorithm. The SAMOPT algorithm also allows for the case where the decision variables are subject to a set of linear constraints. Comparison of results between applications of SAMOPT and another well-known method are given for problems and a simulation model.

Genetic algorithms in optimizing simulated systems

Advances have been made in optimizing quantitative variables within a simulation model, and many methodologies now exist for this purpose. However, many of the design decisions which confront a systems users involve policy alternatives. Often, variables used to represent these alternatives are not only discrete but qualitative. This work seeks to develop a simulation-optimization methodology which can operate on qualitative variables. The proposed approach is to link a genetic algorithm with an object-oriented simulation model generator. The system designs recommended by the genetic algorithm are converted to simulation models and executed. The results then guide the genetic algorithm in its selection of future designs. A simulation model generator for a class of manufacturing systems and a genetic algorithm which can interface with the generator have been developed. The methodology has shown positive results.

A methodology for solvng multi-objective simulation-optimization problems

Abstract For many practical and industrial optimization problems where some or all of the system components are stochastic, the objective functions cannot be represented analytically. Due to the difficulties involved in the analytical expression, simulation may be the most effective means of studying these complex systems. Furthermore, many of these problems are characterized by the presence of multiple and conflicting objectives. The goal of this paper is to introduce a new methodology through an interactive algorithm for solving this multi-objective simulation optimization problem.

MAINTENANCE POLICY SELECTION FOR JIT PRODUCTION SYSTEMS

In a Just-in-Time production environment, due to the limited amount of in-process inventory, machine failures have a greater impact on the productivity. In this paper, we explore some characteristic factors of several classes of JIT systems that could play a role in selection of a suitable maintenance policy for each class. The study is also extended to assessment of the changes in the performance of a system under a given policy as a function of the changes in the values of these factors. In order to accomplish this, production and maintenance functions were considered as two inter-related components of the total system. Furthermore, sixteen simple and composite factors were identified as the characteristic factors defining JIT systems. An extensive experimentation on various systems defined by these factors revealed that these factors can be categorized into three relatively distinct classes. The first class includes those factors that play a major role in how effective a particular maintenance policy i...

The effect of joint position errors of industrial robots on their performance in manufacturing operations

To position and orient the hand of an industrial robot to perform a particular manufacturing process, the joints are commanded to assume certain angles and/or displacements. However, due to position errors at joints, the assumed positions are almost always different from those commanded. These deviations induce a random error to the position and orientation of the hand. The ability of the hand to perform according to the required accuracy depends, among other things, on the extent of joint position errors. The effect of these errors on the accuracy of the operations are studied using a stochastic model. In addition, a procedure is suggested for determining the optimum position error to aim at in a given manufacturing situation. The results are applied to a T3type robot performing an assembly operation.