Towards An Intelligent Maintenance Optimization System

This paper is concerned with the evaluation and enhancement of the maintenance routines of large and complex technical systems. An ‘intelligent decision support system’ approach is suggested as a method for overcoming the difficulties associated with the scale, variability and changeability of such systems. The main features of the proposed intelligent maintenance optimization system (IMOS) are identified. A prototype system is then presented and its main mathematical models of maintenance are introduced. Some sample test data and the results produced from them are presented. Other aspects discussed include dealing with censored data, optimization criteria, the development of a maintenance model selection rule base, the recognition of data patterns and models' robustness. Results of IMOS system validation against expert advice have shown a high measure of consistency.     

On the evolution of an intelligent maintenance optimization system

In this paper the author reviews the development of an intelligent maintenance optimization system over the past 16 years. The paper starts with discussion of the initial motivation behind developing the system and the designs of the early versions of a computer program to access maintenance history data and provide an analysis. The concept behind this system was gradually developed to incorporate a rule base for the selection of a suitable model for preventive maintenance (PM) scheduling and then to a fully developed knowledge-based system for decision support. The need to incorporate case-based reasoning thus creating a hybrid system that can learn with use in addition to using elicited knowledge from experts is discussed. The experience with system validation with two versions of the system is analysed. The paper also reviews the extensive fundamental work on developing appropriate PM models that can deal with real data patterns. Finally, the scope for future development is presented.     

A practical approach for reliability prediction of pipeline systems

Pipelines play an important role in the modern society. Failures of pipelines can have great impacts on economy, environment and community. Preventive maintenance (PM) is often conducted to improve the reliability of pipelines. Modern asset management practice requires accurate predictability of the reliability of pipelines with multiple PM actions, especially when these PM actions involve imperfect repairs. To address this issue, a split system approach (SSA) based model is developed in this paper through an industrial case study. This new model enables maintenance personnel to predict the reliability of pipelines with different PM strategies and hence effectively assists them in making optimal PM decisions.     

Economic production lot-sizing for an unreliable machine under imperfect age-based maintenance policy

This paper is concerned with the joint determination of both economic production quantity and preventive maintenance (PM) schedules under the realistic assumption that the production facility is subject to random failure and the maintenance is imperfect. The manufacturing system is assumed to deteriorate while in operation, with an increasing failure rate. The system undergoes PM either upon failure or after having reached a predetermined age, whichever of them occurs first. As is often the case in real manufacturing applications, maintenance activities are imperfect and unable to restore the system to its original healthy state. In this work, we propose a model that could be used to determine the optimal number of production runs and the sequence of PM schedules that minimizes the long-term average cost. Some useful properties of the cost function are developed to characterize the optimal policy. An algorithm is also proposed to find the optimal solutions to the problem at hand. Numerical results are provided to illustrate both the use of the algorithm in the study of the optimal cost function and the latter’s sensitivity to different changes in cost factors.     

Integration of particle swarm optimization-based fuzzy neural network and artificial neural network for supplier selection

This study is intended to develop an intelligent supplier decision support system which is able to consider both the quantitative and qualitative factors. It is composed of (1) the collection of quantitative data such as profit and productivity, (2) a particle swarm optimization (PSO)-based fuzzy neural network (FNN) to derive the rules for qualitative data, and (3) a decision integration model for integrating both the quantitative data and fuzzy knowledge decision to achieve the optimal decision. The results show that the decision support system developed in this study make more precise and favorable judgments in selecting suppliers after taking into account both qualitative and quantitative factors.     

多部件系统故障预防工作的组合优化

研究了实践中常见的四种预防工作组合类型,即定时维修、功能检测、使用检查及检查与定时维修的组合策略,以单位时间维修费用最小为目标建立了多部件故障预防工作的组合优化模型.在此基础上,提出了两个故障预防工作的组合优化算法,并给出了计算示例以说明模型和算法的性能.     

Integrated production and quality model under various preventive maintenance policies

In this paper, we investigate the effect of various preventive maintenance policies on the joint optimisation of the economic production quantity (EPQ) and the economic design of control chart. This has been done for a deteriorating process where the in-control period follows a general probability distribution with increasing hazard rate. In the proposed model, preventive maintenance (PM) activities reduce the shift rate of the system to the out-of-control state proportional to the PM level. For each policy, the model determines the EPQ, the optimal design of the control chart and the optimal preventive maintenance level. The effects of the three PM policies on EPQ and quality costs are illustrated using an example of a Weibull shock model with an increasing hazard rate.     

Optimal production time and number of maintenance actions for an imperfect production system under equal-interval maintenance policy

This paper deals with the optimal production/maintenance (PM) policy for a deteriorating production system which may shift from the in-control state to the out-of-control state while producing items. The process is assumed to have a general shift distribution. Under the commonly used maintenance policy, equal-interval maintenance, the joint optimizations of the PM policy are derived such that the expected total cost per unit time is minimized. Different conditions for optimality, lower and upper bounds and uniqueness properties on the optimal PM policy are provided. The implications of another commonly used policy, to perform a maintenance action only at the end of the production run, are also discussed. Structural properties for the optimal policy are established so that an efficient solution procedure is obtained. In the exponential case, some extensions of the results obtained previously in the literature are presented. A numerical example is provided to illustrate the solution procedure for the optimal production and maintenance policy.     

Delay-time-based preventive maintenance modelling for a production plant: a case study in a steel mill

This paper presents a case study of delay-time-based preventive maintenance (PM) modelling for a production plant system. Since production stoppages caused by waiting for raw materials provide windows to inspect and maintain the system, these production stoppages can be incorporated into the PM model. Considering the nature of different defects that can cause failures, two types of defects are modelled: small and large defects. Small defects are normally dealt with during production stoppages, but both small and large defects can be dealt with over a longer duration during PM. The parameters of the model are estimated using the maximum-likelihood method based on the real data. The model aims to find the optimal PM interval by minimizing the expected total downtime within an overhaul cycle. Management suggestions are also recommended.     

Age-reduction models for imperfect maintenance

Maintenance of a deteriorating system is often imperfect, withthe state of the system after maintenance being at a level somewherebetween new and its prior condition.In this paper, the conceptof reduction in virtual or effective age is used to model theeffect of both imperfect corrective maintenance (CM) and imperfectpreventive maitnenance (PM). Results from counting-process theorythen produce a likelihood function necessary for parameter estimation,and the method is tested on known maintenance data. Finally,it is shown how to evaluate, by simulation, the expected numberofsystem failures up to time t under a given periodic PM strategy.This measure is incorporated into a cost rate function whichis then minimized to find the optimal length of a PM intervaland the optimal number of PMs to carry out before system replacement     

The impact of inspection errors,imperfect maintenance and minimal repairs on an imperfect production system

This paper develops an integrated model of production lot-sizing, maintenance and quality for considering the possibilities of inspection errors, preventive maintenance (PM) errors and minimal repairs for an imperfect production system with increasing hazard rates. In this study, a PM activity is imperfect in that a production system cannot be recovered as good as new and might cause the production system to shift to the out-of-control state with a certain probability. Numerical analyses are used to simulate the effect of changes in various parameters on the optimal solution for which the time that the process remains in the in-control state is assumed to follow a Weibull distribution. In addition, we investigate the effects of inspection errors and PM errors on the minimum total cost of the optimal inspection interval, inspection frequency and production quantity.     

An integrative evaluation framework for intelligent decision support systems

Evaluation of the overall effectiveness of decision support systems (DSS) has been a research topic since the early 1980s. As artificial intelligence methods have been incorporated into systems to create intelligent decision support systems (IDSS), researchers have attempted to quantify the value of the additional capabilities. Despite the useful and relevant insights generated by previous research, existing evaluation methodologies offer only a fragmented and incomplete view of IDSS value and the contribution of its technical infrastructure. This paper proposes an integrative, multiple criteria IDSS evaluation framework through a model that links the decision value of an IDSS to both the outcome from, and process of, decision making and down to specific components of the IDSS. The proposed methodology provides the designer and developer specific guidance on the intelligent tools most useful for a specific user with a particular decision problem. The proposed framework is illustrated by evaluating an actual IDSS that coordinates management of urban infrastructures.     

Integrated decision support for aviation safety inspectors

This paper presents a systems viewpoint for developing an advanced decision support system for aircraft safety inspectors. Research results from a Federal Aviation Administration (FAA) sponsored project to use neural network and expert systems technology to analyze aircraft maintenance databases are summarized. One of the main objectives of this research is to define more refined “alert” indicators for national comparison purposes that can signal potential problem areas by aircraft type for safety inspector consideration.

Integration aspects are addressed on two levels: (1) integration of the various technical components of the decision support system, and (2) integration of the decision support system with individual behavior, management systems and organizational structure, as well as corporate culture across both formal and informal dimensions. The paper summarizes the creation of strategic “inspection profiles” for aging aircraft and reliability curve fitting for structural components both based upon using neural network technology. Also, the potential use of a model-based expert system to facilitate field inspection diagnostics is presented. Finally, a framework for developing an intelligent decision system to support aircraft safety inspections is proposed that links expert systems, neural networks, as well as a paradigm of the decision making process typically used in unstructured situations.     

Generalized stationary models for scheduling single and multiple preventive maintenance routines

This paper is concerned with the development and applicationof stationary models for scheduling single and multiple preventivemaintenance (PM) situations focusing on issues of model implementation.The first part of the paper deals with the practical implementationof the basic single PM scheduling model based on the renewalprocess. The main practical difficulty is lifetime-distributionselection for small data sets which is typical in PM situations.Thus a sensitivity analysis of optimal PM interval to selectedlife distributions following PM and failures (corrective maintenance)is carried out. It has been found that the selected pair ofdistributions using AIC criteria as well as the Weibull–Weibullfitted pair have the smallest availability loss in estimatingthe optimal PM interval. The second part of this paper is concernedwith modelling multi-PM situations—something which hasreceived very little attention in the literature despite itsfrequent implementation in real life. A multi-PM model basedon the renewal process is discussed. The model assumes a multi-PMinterval which is an integer multiple of the single PM intervalsand different renewal functions following each type of PM. Theprocedure of model implementation is discussed through numericalexample.     

Model for imperfect age-based preventive maintenance with age reduction

The effect of ageing on the deterioration rate of most repairable systems cannot be ignored. Preventive maintenance (PM) is performed in the hope of restoring fully the performance of these systems. However, in most practical cases, PM activities will be only able to restore part of the performance. Bridging the gap between theory and practice in this area requires realistic modelling of the effect of PM activities on the failure characteristics of maintainable systems. Several sequential PM models have been developed for predetermined PM interval policies but much less effort has been devoted to age-based ones. The purpose of this paper is to develop an age-based model for imperfect PM. The proposed model incorporates adjustment factor in the effective age of the system. The system undergoes PM either at failure or after a predetermined time interval whichever of them occurs first. After a certain number of such PMs, the system is replaced. The problem is to determine both the optimal number of PMs and the optimal PM's schedule that minimize the total long-term expected cost rate. Model analysis relating to the existence and uniqueness of the optimal solutions is provided. Numerical examples are presented to study the sensitivity of the model to different cost function's factors and to illustrate the use of the algorithm.     

IDSSF<Emphasis Type="SmallCaps">LEX</Emphasis>: an intelligent DSS for the design and evaluation of flexible manufacturing systems

This paper describes IDSSFLEX, a computer system for the analysis and evaluation of Flexible Manufacturing System (FMS) design configurations. IDSSFLEX is an intelligent decision support system which selects from among several configurations and control strategy alternatives of design, the most appropriate one for a specific case. In order to accomplish such an objective, the system presents simultaneously the following features: ability to quantify subjective factors, ability to account for individual preferences, and ability to cope with multiple criteria decision making. A case study illustrates the effectiveness of the computer system.     

A stochastic model for joint spare parts inventory and planned maintenance optimisation

Spare parts demands are usually generated by the need of maintenance either preventively or at failures. These demands are difficult to predict based on historical data of past spare parts usages, and therefore, the optimal inventory control policy may be also difficult to obtain. However, it is well known that maintenance costs are related to the availability of spare parts and the penalty cost of unavailable spare parts consists of usually the cost of, for example, extended downtime for waiting the spare parts and the emergency expedition cost for acquiring the spare parts. On the other hand, proper planned maintenance intervention can reduce the number of failures and associated costs but its performance also depends on the availability of spare parts. This paper presents the joint optimisation for both the inventory control of the spare parts and the Preventive Maintenance (PM) inspection interval. The decision variables are the order interval, PM interval and order quantity. Because of the random nature of plant failures, stochastic cost models for spare parts inventory and maintenance are derived and an enumeration algorithm with stochastic dynamic programming is employed for finding the joint optimal solutions over a finite time horizon. The delay-time concept developed for inspection modelling is used to construct the probabilities of the number of failures and the number of the defective items identified at a PM epoch, which has not been used in this type of problems before. The inventory model follows a periodic review policy but with the demand governed by the need for spare parts due to maintenance. We demonstrate the developed model using a numerical example.     

Optimal maintenance of two stochastically deteriorating machines with an intermediate buffer

We consider a manufacturing system in which an input generating installation transfers a raw material to a subsequent production unit. Both machines deteriorate stochastically with usage and may fail. For each machine the deteriorating process is described by some known transition probabilities between different degrees of deterioration. A buffer has been built between the two machines in order to cope with unexpected failures of the installation. A discrete-time Markov decision model is formulated for the optimal preventive maintenance of both machines. The maintenance times are geometrically distributed and the cost structure includes operating costs, storage costs, maintenance costs and costs due to the lost production. It is proved that for fixed buffer content and for fixed deterioration degree of one machine, the average-cost optimal policy initiates a preventive maintenance of the other machine if and only if its degree of deterioration exceeds some critical level. We study, by means of numerical results, the effect of the variation of some parameters on the optimal policy and on the minimum average cost. For the case in which the maintenance times follow continuous distributions, an approximate discrete-time Markov decision model is proposed.     

Optimizing Preventive Maintenance Models

We deal with the problem of scheduling preventive maintenance (PM) for a system so that, over its operating life, we minimize a performance function which reflects repair and replacement costs as well as the costs of the PM itself. It is assumed that a hazard rate model is known which predicts the frequency of system failure as a function of age. It is also assumed that each PM produces a step reduction in the effective age of the system. We consider some variations and extensions of a PM scheduling approach proposed by Lin et al. [6]. In particular we consider numerical algorithms which may be more appropriate for hazard rate models which are less simple than those used in [6] and we introduce some constraints into the problem in order to avoid the possibility of spurious solutions. We also discuss the use of automatic differentiation (AD) as a convenient tool for computing the gradients and Hessians that are needed by numerical optimization methods. The main contribution of the paper is a new problem formulation which allows the optimal number of occurrences of PM to be determined along with their optimal timings. This formulation involves the global minimization of a non-smooth performance function. In our numerical tests this is done via the algorithm DIRECT proposed by Jones et al. [19]. We show results for a number of examples, involving different hazard rate models, to give an indication of how PM schedules can vary in response to changes in relative costs of maintenance, repair and replacement. Part of this work was carried out while the first author was a Visiting Professor in the Department of Mechanical Engineering at the University of Alberta in December 2003.     

Optimal economic production quantity policy for imperfect process with imperfect repair and maintenance

This study integrates maintenance and production programs with the economic production quantity (EPQ) model for an imperfect process involving a deteriorating production system with increasing hazard rate: imperfect repair and rework upon failure (out of control state). The imperfect repair performs some restorations and restores the system to an operating state (in-control state), but leaves its failure until perfect preventive maintenance (PM) is performed. There are two types of PM, namely imperfect PM and perfect PM. The probability that perfect PM is performed depends on the number of imperfect maintenance operations performed since the last renewal cycle. Mathematical formulas are obtained for deriving the expected total cost. For the EPQ model, the optimum run time, which minimizes the total cost, is discussed. Various special cases are considered, including the maintenance learning effect. Finally, a numerical example is presented to illustrate the effects of PM, setup, breakdown and holding costs.