The development of a hybrid intelligent maintenance optimisation system (HIMOS)

This paper reports on the development of a hybrid intelligent maintenance optimisation system (HIMOS) for decision support. It is a follow-up to an earlier paper published in the Journal of the Operational Research Society in 1995. Both papers refer to systems where there are very many components which may break down independently. When a component breaks down, corrective action (CO) is required. The problem is to determine the optimal maintenance policy, essentially the frequency of preventive maintenance (PM) which minimises the sum of down time due to PM and CO.HIMOS, like its predecessor IMOS, uses an ‘intelligent’ decision support system to carry out an automated analysis of the maintenance history data. Maintenance data are presented to the system and the most suitable mathematical model from a model-base is identified utilising a hybrid knowledge/case based system (KBS/CBR). Thus initially a rule base is applied to select a model, as in the case of IMOS. If no model is matched, the system reverts to its historical case-base to match the current case with a similar case that has been previously modelled. This double reasoning adds to the system's true learning capabilities (intelligence) and increases the rate of success of model selection. A prototype system is written in Visual Basic® for an IBM compatible PC. The study results include optimal PM intervals for a sample of industrial data sets. The results of the validation exercise of HIMOS against expert advice has shown that the system functions satisfactorily.     

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.     

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.     

Ant colony optimization for power plant maintenance scheduling optimization—a five-station hydropower system

A number of algorithms have been developed for the optimization of power plant maintenance schedules. However, the true test of such algorithms occurs when they are applied to real systems. In this paper, the application of an Ant Colony Optimization formulation to a hydropower system is presented. The formulation is found to be effective in handling various constraints commonly encountered in practice. Overall, the results obtained using the ACO formulation are better than those given by traditional methods using engineering judgment, which indicates the potential of ACO in solving realistic power plant maintenance scheduling problems.     

非线性极大极小系统全局优化算法的分析

非线性极大极小系统的全局优化可用于柔性制造和智能交通的决策与控制.实现了非线性极大极小系统的全局优化算法的仿真,并进行了计算时间分析.数值实验表明了全局优化算法的可行性.算法的计算时间主要由系统的优化极大射影矩阵数目决定,而优化极大射影矩阵数目与系统解析式中单极大式的系数紧密相关,系数取值越分散,简约极大射影矩阵的效果越好,计算效率越高.     

带缓冲串行生产系统预防性维护建模及运行参数优化研究

为了保证串行生产系统的产能和提高系统可靠性,提出了带缓冲区的串行生产系统预防性维护决策模型。首先,分析了生产线各执行单元可靠性和运行参数之间的关系,建立了考虑执行单元运行参数和缓冲库存的维护模型。在此基础上,结合串行生产线的特点,建立综合考虑维护成本、有效运行速度和缓冲库存的多目标优化函数。最后,构建启发式算法求解目标函数,并以串行包装生产线为例进行仿真实验分析,结果表明本文所建模型是有效且实用的。     

运筹学在整车物流智能调度决策支持系统中的研究与应用

本文基于整车物流智能调度决策支持系统的研发、实施与运维的成功应用,论述运筹学在智能化上的应用路径以及实践驱动的学术路径。该系统是国内较早在汽车物流企业实现落地的智能化调度系统,其所形成的思想理论与方法技术揭示了运筹学在智能化应用上的核心价值,以及实践驱动的学术价值,对解决“卡脖子”难题提供示范性思路。本文提出运筹学在智能化研发上“三环七步”的整体研发框架。首先,分析智能化需求的运筹学特征,详细介绍汽车整车物流的发展趋势、瓶颈及智能调度需求;其次,论述运筹学系统模型的作用与建模方法,分析汽车整车物流系统模型的决策要素、目标及约束,提出汽车整车物流智能调度的运筹学应用问题。然后,提出“模式装箱”的新装箱理论问题,明确问题的计算难解性、可解性及核心科学特征。进一步,建立汽车整车物流调度应用问题与科学问题的混合整数线性规划模型;提出求解汽车整车物流调度问题的分支定界算法,以及大规模问题求解的时空分解及滚动求解方法与技术;提出面向运筹应用的生产测试及压力测试方法,给出汽车整车物流调度的测试分析的流程与结果。此外,提出深度集成整车运输管理系统与仓库管理系统、优化算法引擎驱动的分布式、多视图、多系统融合的智能调度决策支持系统。最后,论述该系统在实施过程中的推广使用和运维情况,并对运筹学应用及实践驱动的科学研究进行总结与展望。     

Convergence of a stochastic approximation algorithm for the GI/G/1 queue using infinitesimal perturbation analysis

Discrete-event systems to which the technique of infinitesimal perturbation analysis (IPA) is applicable are natural candidates for optimization via a Robbins-Monro type stochastic approximation algorithm. We establish a simple framework for single-run optimization of systems with regenerative structure. The main idea is to convert the original problem into one in which unbiased estimators can be derived from strongly consistent IPA gradient estimators. Standard stochastic approximation results can then be applied. In particular, we consider the GI/G/1 queue, for which IPA gives strongly consistent estimators for the derivative of the mean system time. Convergence (w.p.1) proofs for the problem of minimizing the mean system time with respect to a scalar service time parameter are presented.     

On a single discrete scale for preventive maintenance with two shock processes affecting a complex system

A new approach to optimal maintenance of systems (networks) is suggested. It is applied to systems subject to two external independent shock processes. A system ‘consists’ of two parts, and each shock process affects only its own part. A new notion of bivariate signature is suggested and used for obtaining survival characteristics of a system and further optimization of the preventive maintenance actions. The preventive maintenance optimization is considered in the univariate discrete scale that counts the overall numbers of shocks of both types. An example of a transportation network is considered. Copyright © 2016 John Wiley & Sons, Ltd.     

Dynamic maintenance decision-making for series–parallel manufacturing system based on MAM–MTW methodology

Proper maintenance schedule is required to improve manufacturing systems’ profitability and productivity. A novel dynamic maintenance strategy is thus developed to incorporate both the single-machine optimization and the whole-system schedule for series–parallel system. Firstly, multiple attribute value theory and maintenance effects are considered in the single-machine optimization. A developed multi-attribute model (MAM) is used to determine the optimal maintenance intervals. Then, a series–parallel structure of the system is investigated in terms of the whole-system schedule. Maintenance time window (MTW) programming is presented to make a cost-effective system schedule by dynamically utilizing maintenance opportunities. The maintenance scheme achieved by using the proposed MAM–MTW methodology is demonstrated through a case study in a hydraulic steering factory. It is concluded that proper consideration of maintenance effects and time window leads to a significant cost reduction.     

高层电梯系统运行方案的建模与求解

随着社会的发展,运用垂直交通系统的高层建筑和智能化建筑不断出现。而有效的电梯交通配置,是垂直交通系统高效运行的基本保证。本文针对高层商务建筑中的电梯运行管理方案设计问题,分析了影响电梯耗能和用户满意度的主要因素。分别建立了电梯数目已知和电梯数目未知情况下的电梯调度优化模型,并设计相应动态规划算法和遗传算法。结合算例,求解算例中的电梯优化调度方案,以验证模型的合理性。最后根据我们建立的电梯调度模型,借助VC++作出可视化的电梯调度示意界面,将本文的研究结果用于实际的电梯调度中。     

Reliability Analysis of a One-Unit System with Unrepairable Spare Units and its Optimization Applications

It is assumed that a unit is either in operation or is in repair. When the main unit is under repair, spare units which cannot be repaired are used. In this system the following quantities are of interest: (i) The time distribution and the mean time to first-system failure, given that the n spare units are provided at time 0. (ii) The probability that the number of the failed spare units are equal to exactly n during the interval (0, t], and its expected number during the interval (0, t]. These quantities are derived by solving the renewal-type equations.Two optimization problems are discussed using the results obtained, viz.: (i) The expected cost of two systems, one with both a main unit and spare units and the other with only spare units is considered. (ii) A preventive maintenance policy of the main unit is considered in order to minimize the expected cost rate. Some policies of the two problems are discussed under suitable conditions. Numerical examples are also presented.     

Optimal Parameter Tuning for Multiclass Support Vector Machines in Machinery Health State Estimation

The increasing demand for high reliability, safety and availability of technical systems calls for innovative maintenance strategies. The use of prognostic health management (PHM) approach where maintenance action is taken based on current and future health state of a component or system is rapidly gaining popularity in the maintenance industry. Multiclass support vector machines (MC-SVM) has been identified as a promising algorithm in PHM applications due to its high classification accuracy. However, it requires parameter tuning for each application, with the objective of minimizing the classification error. This is a single objective optimization problem which requires the use of optimization algorithms that are capable of exhaustively searching for the global optimum parameters. This work proposes the use of hybrid differential evolution (DE) and particle swarm optimization (PSO) in optimally tuning the MC-SVM parameters. DE identifies the search limit of the parameters while PSO finds the global optimum within the search limit. The feasibility of the approach is verified using bearing run-to-failure data and the results show that the proposed method significantly increases health state classification accuracy. (© 2014 Wiley-VCH Verlag GmbH & Co. KGaA, Weinheim)     

Optimization of component reliability in the design phase of capital goods

We introduce a quantitative model to support the decision on the reliability level of a critical component during its design. We consider an OEM who is responsible for the availability of its systems in the field through service contracts. Upon a failure of a critical part in a system during the exploitation phase, the failed part is replaced by a ready-for-use part from a spare parts inventory. In an out-of-stock situation, a costly emergency procedure is applied. The reliability levels and spare parts inventory levels of the critical components are the two main factors that determine the downtime and corresponding costs of the systems. These two levels are decision variables in our model. We formulate the portions of Life Cycle Costs (LCC) which are affected by a component’s reliability and its spare parts inventory level. These costs consist of design costs, production costs, and maintenance and downtime costs in the exploitation phase. We conduct exact analysis and provide an efficient optimization algorithm. We provide managerial insights through a numerical experiment which is based on real-life data.     

置换流水车间调度问题的中心引力优化算法求解

目前求解置换流水车间调度问题的智能优化算法都是随机型优化方法,存在的一个问题是解的稳定性较差。针对该问题,本文给出一种确定型智能优化算法——中心引力优化算法的求解方法。为处理基本中心引力优化算法对初始解选择要求高的问题,利用低偏差序列生成初始解,提高初始解质量;利用加速度和位置迭代方程更新解的状态;利用两位置交换排序法进行局部搜索,提高算法的优化性能。采用置换流水车间调度问题标准测试算例进行数值实验,并和基本中心引力优化算法、NEH启发式算法、微粒群优化算法和萤火虫算法进行比较。结果表明该算法不仅具有更好的解的稳定性,而且具有更高的计算精度,为置换流水车间调度问题的求解提供了一种可行有效的方法。     

Human resource allocation applications of stochastic maintenance models with super‐reserve backups

This article deals with stochastic maintenance models that include a repair facility and three types of ‘unreliable’ machines: the main facility of working and reserve machines, and an auxiliary facility of ‘super‐reserve’ machines. Working machines breakdown exponentially and are immediately replaced by available reserve machines. Defective machines line up for repair and refurbished machines are returned to the main facility. This system falls into the category of closed queues with hot standbys and has more options than the basic model. If the main facility is restored to its original quantity and the repair facility leaves on routine maintenance, all reserve machines are temporarily blocked and renewals come from the super‐reserve group until the latter is exhausted. Explicit formulas obtained demonstrate a relatively effortless use of functionals of the main stochastic characteristics, and optimization of their objective function. Human resource applications are included as optimization examples. Copyright © 2005 John Wiley & Sons, Ltd.     

Optimal preventive maintenance policy for electric power distribution systems based on the fuzzy AHP methods

In power distribution systems, with their great vastness and various outage causes, one of the most important problems of power distribution companies is to select a suitable maintenance strategy of system elements and method of financial planning for the maintenance of system elements with the two objectives of decrease in outage costs and improvement of system reliability. In this article, a practical method is introduced for the selection of a suitable system elements maintenance strategy; moreover, to plan the preventive maintenance budget for the system elements, two methods are offered: the cost optimization method and the fuzzy Analytic Hierarchy Process (AHP) method. In the former method, a new model of system maintenance cost is offered. This model, based on system outage information, the elements maintenance costs are determined as functions of system reliability indices and preventive maintenance budget. The latter method, too, a new guideline is introduced for considering the cost and reliability criteria in the trend of preventive maintenance budget planning. In this method, the preventive maintenance budget for the elements is determined based on relative priority of elements with reliability criteria. © 2015 Wiley Periodicals, Inc. Complexity 21: 70–88, 2016     

Preventive maintenance scheduling of multi-cogeneration plants using integer programming

Maintenance scheduling of cogeneration plants, which produce both electric power and desalinated water, is a typical complex process with long-term operations and planning problems. The plants' maintenance scheduling process has to determine the appropriate schedule for preventive maintenance, while satisfying all the system constraints and maintaining adequate system availability. It is an optimization problem and the maintenance and system constraints include the crew constraint, maintenance window constraint and time limitation constraint. In this paper, an integer linear-programming model, which has been developed, is described which schedules the preventive maintenance tasks in a multi-cogeneration plant. Results of a test example of such a plant situated in Kuwait are presented to show the applicability of the approach.     

Considerations for building knowledge-based expert systems in highway maintenance planning

Genuine, nontrivial planning problems in pavement and bridge maintenance are generally beyond the capabilities of expert systems. However, the diagnostic, interpretive and predictive features of such systems can be combined with algorithmic planning tools to produce comprehensive maintenance planning and management systems.After a discussion of the relevant issues, this paper addresses the potential application areas for knowledgebased expert systems in highway maintenance planning. The foxus is on how and where expert systems can interface with optimization models to yield meaningful results.     

Maintenance of continuously monitored degrading systems

This paper considers a condition-based maintenance model for continuously degrading systems under continuous monitoring. After maintenance, the states of the system are randomly distributed with residual damage. We investigate a realistic maintenance policy, referred to as condition-based availability limit policy, which achieves the maximum availability level of such a system. The optimum maintenance threshold is determined using a search algorithm. A numerical example for a degrading system modeled by a Gamma process is presented to demonstrate the use of this policy in practical applications.