C. Richard Cassady

Selective maintenance modeling for industrial systems

In many industrial environments, systems are required to perform a sequence of operations (or missions) with finite breaks between each operation. During these breaks, it may be advantageous to perform repair on some of the system’s components. However, it may be impossible to perform all desirable maintenance activities prior to the beginning of the next mission due to limitations on maintenance resources. In this paper, a mathematical programming framework is established for assisting decision‐makers in determining the optimal subset of maintenance activities to perform prior to beginning the next mission. This decision‐making process is referred to as selective maintenance. The selective maintenance models presented allow the decision‐maker to consider limitations on maintenance time and budget, as well as the reliability of the system. Selective maintenance is an open research area that is consistent with the modern industrial objective of performing more intelligent and efficient maintenance.

Selective maintenance for support equipment involving multiple maintenance actions

Abstract Selective maintenance is the process of identifying a subset among sets of desirable maintenance actions. Previous works use mathematical programming models for making selective maintenance decisions for production equipment and military vehicles, which perform sequences of missions and are repaired only between missions. In this paper, extensions of these models are proposed. First, system component life is assumed to follow Weibull distributions. Second, the decision-maker is given multiple maintenance options: minimal repair on failed components, replacement of failed components, and replacement of functioning components (preventive maintenance).

An improved selective maintenance solution approach

Purpose – The purpose of this paper is to develop an improved, enumerative solution procedure for solving the original selective maintenance problems. Selective maintenance refers to the process of identifying the set of maintenance actions to perform from a desirable set of maintenance actions.Design/methodology/approach – A series of four improvements to a previously proposed enumerative solution procedure are presented. The improvements are defined and tested sequentially on an experimental set of problem instances. The improvements are characterized relative to the achieved reduction in CPU time for a software application.Findings – The improved enumerative procedure reduces the CPU time required to solve the selective maintenance problems by as much as 99 per cent. There is a corresponding increase in practical problem size of more than 200 per cent.Practical implications – Almost all organizations use a variety of repairable systems to achieve their mission. Typically, these systems have to share th...

Optimal maintenance policies for systems subject to a Markovian operating environment

Many stochastic models of repairable equipment deterioration have been proposed based on the physics of failure and the characteristics of the operating environment, but they often lead to time to failure and residual life distributions that are quite complex mathematically. The first objective of our study is to investigate the potential for approximating these distributions with traditional time to failure distribution. We consider a single-component system subject to a Markovian operating environment such that the systems instantaneous deterioration rate depends on the state of the environment. The system fails when its cumulative degradation crosses some random threshold. Using a simulation-based approach, we approximate the time to first failure distribution for this system with a Weibull distribution and assess the quality of this approximation. The second objective of our study is to investigate the cost benefit of applying a condition-based maintenance paradigm (as opposite to a scheduled maintenance paradigm) to the repairable system of interest. Using our simulation model, we assess the cost benefits resulting from condition-based maintenance policy, and also the impact of the random prognostic error in estimating system condition (health) on the cost benefits of the condition-based maintenance policy.

Genetic algorithms for total weighted expected tardiness integrated preventive maintenance planning and production scheduling for a single machine

Purpose – This paper seeks to improve solution procedures for solving a larger version of the integrated preventive maintenance planning and production scheduling model with a total weighted expected tardiness objective function introduced in a 2003 paper by Cassady and Kutanoglu using a genetic algorithm heuristic procedure.Design/methodology/approach – In this paper, heuristics based on genetic algorithms are developed to solve the integrated model.Findings – The performance of the proposed genetic algorithm heuristics are evaluated using multiple instances of several problem sizes. The results indicate that the proposed genetic algorithms can effectively be used to solve the integrated problem.Practical implications – The heuristics presented in this paper significantly improve the ability of the decision‐maker to consider larger instances of the integrated model. One may ask, “how significant is that improvement?” The answer depends on the specific industrial context under consideration and the defini...

Establishing Maintenance Resource Levels Using Selective Maintenance

We address the performance of a repairable system that is required to perform a sequence of equally spaced, identical missions with breaks between missions. The system is series-parallel in structure, and component repair can only be performed during breaks between missions. Due to limitations on maintenance resources, it may be impossible to make all necessary repairs before the next mission. Such situations require the use of selective maintenance, the process of identifying the subset of maintenance actions to perform from a set of desirable maintenance actions. We build upon previous research in selective maintenance by addressing decisions related to establishing capacities for the limited maintenance resources. We model mission-to-mission changes in maintenance resource capacity, and we develop a methodology for establishing constant resource capacities for a sequence of missions. Finally, we develop a methodology for integrating redundancy allocation and maintenance resource allocation decisions.

Joint production and maintenance planning with machine deterioration and random yield

Production, yield and maintenance are three key components for sustaining the competitiveness of a manufacturing firm. In this paper, we investigate a joint production and maintenance planning problem in a periodic review environment subject to stochastic demand and random yields. The manufacturing system deteriorates from period to period according to a discrete-time Markov chain. The objective is to find an integrated lot sizing and maintenance policy for the system such that the aggregate cost associated with production, holding, backlogging and maintenance is minimised. We formulate this integrated planning problem as a Markov decision process and analyse the structural properties of the optimal policies. We prove that the optimal production and the maintenance policies both exhibit a control limit structure and show that the solution to the finite-horizon problems converges to that of the infinite-horizon problem.

Evaluation and comparison of alternative fleet-level selective maintenance models

Fleet-level selective maintenance refers to the process of identifying the subset of maintenance actions to perform on a fleet of repairable systems when the maintenance resources allocated to the fleet are insufficient for performing all desirable maintenance actions. The original fleet-level selective maintenance model is designed to maximize the probability that all missions in a future set are completed successfully. We extend this model in several ways. First, we consider a cost-based optimization model and show that a special case of this model maximizes the expected value of the number of successful missions in the future set. We also consider the situation in which one or more of the future missions may be canceled. These models and the original fleet-level selective maintenance optimization models are nonlinear. Therefore, we also consider an alternative model in which the objective function can be linearized. We show that the alternative model is a good approximation to the other models.

Ranking Sports Teams: A Customizable Quadratic Assignment Approach

Ranking sports teams in the absence of full round-robin tournaments is big business, especially for NCAA Division I-A college football. The Bowl Championship Series awards millions of dollars each year to the conferences whose teams are awarded bids. We formulated the sports-team-ranking problem as a customizable quadratic-assignment problem. Decision makers can tailor our model to suit their personal definitions of the degree of victory for each game played and the relative distance between ranking positions. We developed a parameter-section procedure for determining these customized values and executed it using the 2004 college football season. Because the problem size is so large, we developed a heuristic solution procedure based on a genetic algorithm and local search techniques. This heuristic performs well on a special problem instance in which we can easily identify the optimal ranking. To examine the behavior of our approach, we implemented the heuristic for the 1999 through 2004 college football seasons. We concluded that our approach works best when the margin of victory of individual games is not considered, the location of games is considered, and the date of games is considered. Finally, we evaluated how our approach would have weighed in on several recent controversies in NCAA Division I-A college football and found that our approach generally agrees with traditional schools of thought regarding these controversies.

Evaluating and Implementing 3-Level Acceptance Sampling Plans

There are many situations in which product quality can be described by classifying a product using three or more discrete levels. For example, a food product may be classified as good, marginal, or bad depending on the concentration of harmful microorganisms in the product. In this paper, a generic framework is defined for establishing 3-level acceptance sampling plans. These plans utilize what we refer to as quality value functions. The Operating Characteristic function for these plans is constructed and used to develop an approximate parameter selection method based on the Central Limit Theorem. The results of testing this method using numerical examples are presented. The problem of quality value function selection is also addressed. A detailed example is presented, which includes the implementation of both the parameter and quality value function selection methods.