Optimal Maintenance Decisions Research Articles

Stochastic Filtering Approach for Condition-Based Maintenance Considering Sensor Degradation

This paper proposes a condition-based maintenance (CBM) policy for a deteriorating system whose state is monitored by a degraded sensor. In the literature of CBM, it is commonly assumed that inspection of system state is perfect or subject to measurement error. The health condition of the sensor, which is dedicated to inspect the system state, is completely ignored during system operation. However, due to the varying operation environment and aging effect, the sensor itself will suffer a degradation process and its performance deteriorates with time. In the presence of sensor degradation, the Kalman filter is employed in this paper to progressively estimate the system and the sensor state. Since the estimation of system state is subject to uncertainty, maintenance solely based on the estimated state will lead to a suboptimal solution. Instead, predictive reliability is used as a criterion for maintenance decision-making, which is able to incorporate the effect of estimation uncertainty. Preventive replacement is implemented when the estimated system reliability at inspection hits a specific threshold, which is obtained by minimizing the long-run maintenance cost rate. An example of wastewater treatment plant is used to illustrate the effectiveness of the proposed maintenance policy. It can be concluded through our research that: 1) disregarding the sensor degradation while it exists will significantly increase the maintenance cost and 2) the negative impact of sensor degradation can be diminished via proper inspection and filtering methods. Note to Practitioners —This paper was motivated by the observation of sensor degradation in wastewater treatment plants but the developed approach also applies to other systems such as manufacturing systems, chemical plants, and pharmaceutical factories, where sensors are dedicated to a long-time operation in a harsh environment. This paper investigates the impact of sensor degradation on CBM and suggests that the effect of sensor degradation should be carefully addressed while making maintenance decisions. Otherwise, it will lead to a suboptimal maintenance decision and increase the operating cost. An optimal maintenance decision, which contains the optimal inspection interval and reliability threshold, is achieved via minimizing the long-run cost rate. In the presence of measurement noise and intrinsic uncertainty from degradation, a stochastic filtering approach is employed to estimate the system and sensor state. Based on the estimated states and the calculated reliability, a dynamic maintenance decision is obtained at each inspection. This paper can be further extended considering non-Gaussian noise and alternative degradation processes.

Decision Support System for the Maintenance Management of Road Network Considering Multi-Criteria

Maintenance management of a large road network with limited resources is a challenging task in developing countries like India. Road agencies expect that the condition of their road infrastructure should always above the desired level of performance even under restricted resources. This requires an integrated decision support system considering all aspects of maintenance. In this paper, a framework for optimal maintenance decisions by multi-objective approach is formulated for a road network by considering functional condition of the pavement quantified in terms of roughness and structural condition quantified in terms of rebound deflection. A multiobjective optimization model is developed using Integer Linear Programming (ILP). A novel approach to track the age of pavement is applied in the formulation of the mathematical model. The e-constraint method is adopted to generate non-dominated solutions. Budget bound optimizing model is formulated and implemented for a typical road network of four roads and optimal maintenance scheduling is arrived.

Stochastic dependency in life-cycle cost analysis of multi-component structures

It is crucial to assure that civil engineering structures can operate properly and safely, as damages during the service life may lead to catastrophic loss of property, fatalities and long-term consequences. The approaches for structural management through a life-cycle cost analysis need to address explicitly the dependencies between elements. The evaluation of the life-cycle maintenance cost of structures in this article considers stochastic, degradation and economic dependencies. A new approach to include stochastic and degradation dependencies, structural redundancy and load redistribution in structural management is developed herein. The proposed model uses the fault tree analysis and the conditional probabilities to take into account stochastic dependencies between the structural elements. The degradation consequences are evaluated and a method is proposed to account for load redistribution. Also, a practical formulation to approximate the reliability of systems formed by interrelated components is proposed, by the mean of a redundancy factor that can be computed by structural analysis. The proposed approach provides effective optimal maintenance decisions for civil engineering structures by considering the interaction between elements.

An Imitation medical diagnosis method of hydro-turbine generating unit based on Bayesian network

In order to improve the intelligent level of fault diagnosis and condition maintenance of hydropower units, an Imitation medical diagnosis method (IMDM) is proposed in this study. IMDM uses Bayesian networks (BN) as the technical framework, including three components: machine learning BN model, expert empirical BN model, and maintenance decision model. Its characteristics are as follows: (i) the machine learning model uses a new node selection method to solve the problem that the traditional fault diagnosis model is difficult to connect with the state monitoring system. (ii) The expert experience BN model improves the traditional method: using the fault tree model to transform the BN structure, Noisy-Or model to simplify conditional probability table, and fuzzy comprehensive evaluation method to obtain the conditional probability. (iii) By introducing the expected utility theory, a maintenance decision model is innovated, which makes sure the optimal maintenance decision scheme after the fault can be better selected. The performance of this proposed method is evaluated by using the experimental data. The results show that the accuracy of the fault reasoning model is higher than 80%, and the maintenance decision model successfully selects 236 optimal maintenance decision schemes from 3159 schemes generated by 13 faults.

Application of gamma process and maintenance cost for fatigue damage of wind turbine blade

The blades of offshore wind turbines accumulate structural damage such as fatigue due to aerodynamic loading by various wind speeds during their service time, leading to premature structural failures. This paper investigates the fatigue damage by the blade element momentum theory (BEMT) method and the cost of operation and maintenance by the integrating models. Three prediction models have been proposed for lifetime performance assessment and management of wind turbine blade, i.e. fatigue prediction model (FPM), the reliable stochastic model (SRM) and cost benefit model (CBM). The fatigue model is discussed to reproduce the fatigue damage evolution in composite blades subjected to aerodynamic loadings by cyclical winds. The lifetime probability of fatigue failure of the composite blades is estimated by stochastic deterioration modelling such as gamma process. On the basis of the cost model, an optimised maintenance policy is determined to make optimal maintenance decision for the composite blades. A numerical example is employed to investigate the effectiveness of predicting fatigue damage and estimating the probability of fatigue failure to determine an opportunistic maintenance policy. The results from the numerical study show that the stochastic gamma process together with the fatigue models can provide a useful tool for remaining useful life predictions and optimum maintenance strategies of the composite blades of offshore wind turbines.

Optimal Maintenance Decision Method for Urban Gas Pipelines Based on as Low as Reasonably Practicable Principle

In the transportation process of urban gas pipelines, there are various uncontrollable risks and uncertainties possibly leading to the failure of gas pipelines and thereby serious consequences, such as city gas shutdown, nearby casualties, and environmental pollution. To avoid these hazards, numerous studies have been performed in identifying and evaluating the occurrence of risks and uncertainties to pipelines. However, discussions on risk reduction and other maintenance work are scarce; therefore, a scientific method to guide decision making is non-existent, thereby resulting in excessive investment in maintenance and reduced maintenance cost of other infrastructures. Therefore, the as low as reasonably practicable (ALARP) principle combined with optimization theory is used to discuss pipeline maintenance decision-making methods in unacceptable regions and ALARP regions. This paper focuses on the analysis of pipeline risk reduction in the ALARP region and proposes three optimization decision models. The case study shows that maintenance decision making should consider the comprehensive impact of maintenance cost to reduce risk and loss cost caused by pipeline failure, and that the further cost–benefit analysis of measures should be performed. The proposed pipeline maintenance decision-making method is an economical method for pipeline operators to make risk decisions under the premise of pipeline safety, which can improve the effectiveness of the use of maintenance resources.

Condition State–Based Civil Infrastructure Deterioration Model on a Structure System Level

AbstractThe successful prediction of civil infrastructure’s deterioration process is crucial for making optimal maintenance, rehabilitation, and replacement (MR&R) decisions under financial constra...

Modeling Product Failures and Determining Optimal Upgrade, Preventive Maintenance, and Price Decisions in Two-Dimensional Extended Warranty Contracts

Modeling Product Failures and Determining Optimal Upgrade, Preventive Maintenance, and Price Decisions in Two-Dimensional Extended Warranty Contracts

In Situ Data Analysis for Condition Assessment of an Existing Prestressed Concrete Bridge

AbstractCondition assessment of existing bridge structures is a valuable tool for bridge owners to make reasonable and optimal maintenance and management decisions. Structural condition assessment ...

Optimizing maintenance decisions in railway wheelsets: A Markov decision process approach

This article models the decision problem of maintaining railway wheelsets as a Markov decision process, with the aim to provide a way to support condition-based maintenance for railway wheelsets. A discussion on the role of the railway wheelsets is provided, as well as some background on the technical standards that guide maintenance decisions. A practical example is explored with the estimation of Markov transition matrices for different condition states that depend on the wheelset diameter, its mileage since last turning action (or renewal) and the damage occurrence. Bearing in mind all the possible maintenance actions, an optimal strategy is achieved, providing a map of best actions depending on the current state of the wheelset.

Maintenance decision methodology of petrochemical plant based on fuzzy curvelet neural network

The maintenance decision of petrochemical plant is a main factor to ensure the reliability and safety of petrochemical plant, in order to make the optimal maintenance decision of petrochemical plant, and the fuzzy curvelet neural network is constructed to solve this problem. The maintenance model of petrochemical plant is established through considering economy and reliability, and the failure rate and maintenance cost models of petrochemical plant are deduced. The architectural framework of fuzzy curvelet neural network is designed, which concludes five layers, and the optimal algorithm procedure is designed based on improved particle swarm algorithm. The simulation analysis of predicting maintenance cost and failure rate for 1 million tons/year gasoline hydrodesulphurization unit is carried out based on three different decision methods, the new method has best precision by comparing simulation results with actual data, and the maintenance cost and failure rate of the unit from 2017 to 2022 are predicted. In addition, the best maintenance plans are confirmed through predicting simulation bases on the proposed method. The proposed maintenance decision model offers scientific guidance as a basis for action by overhaul decision makers of a petrochemical plant.

Optimal selective maintenance decisions for large serial k-out-of-n: G systems under imperfect maintenance

The selective maintenance problem (SMP) arises in many large multicomponent systems which are operated for consecutive missions interspersed with finite breaks during which only a selected set of component repairs or replacements can be carried out due to limited time, budget, or resources. The problem is to decide which components and degree of repairs should be performed in order to guarantee a pre-specified performance level during the subsequent mission. Current SMP formulations in the literature are nonlinear, deal mainly with basic or series-parallel systems and mostly use heuristic methods to obtain solutions.This paper introduces the first SMP model for serial k-out-of-n systems. Two nonlinear formulations are developed, which can be used to solve the problem for small to moderate size k-out-of-n systems. For large k-out-of-n systems or complex reliability structures, we develop a new two-phase approach which transforms the problem into a multidimensional multiple-choice knapsack problem (MMKP). The new approach is shown to be efficient through multiple sets of numerical experiments.

Optimal Inspection and Replacement Policies for Multi-Unit Systems Subject to Degradation

Condition-based maintenance (CBM) is proved to be effective in reducing the long-run operational cost for a system subject to degradation failure. Most existing research on CBM focuses on single-unit systems where the whole system is treated as a black box. However, a system usually consists of a number of components and each component has its failure behavior. When degradation of the components is observable, CBM can be applied to the component level to improve the maintenance efficiency. This paper aims to study the optimal inspection/replacement CBM strategy for a multi-unit system. Degradation of each component is assumed to follow a Wiener process and periodic inspection is considered. We cast the problem into a Markov decision framework and derive the optimal maintenance decisions that minimize the maintenance cost. To better illustrate the optimal maintenance strategy, we start from a 1-out-of-2: G system and show that the optimal maintenance policy is a two-dimensional control limit policy. The argument used in the 1-out-of-2: G system can be readily extended to general cases in a similar way. The value iteration algorithm is used to find the optimal control limits, and the optimal inspection interval is subsequently determined through a one-dimensional search. A numerical study and a comprehensive sensitivity analysis are provided to illustrate the optimal maintenance strategy.

Identification of optimal preventive maintenance decisions for composite components

Abstract This research proposes a decision support tool which identifies cost-optimal maintenance decisions for a given planning period. Simultaneously, the reliability state of the component is kept at or below a given reliability threshold: a failure limit policy applies. The tool is developed to support repair-or-replacement decision making for composite components likely to suffer impact damage. As a core part of the tool, a cost minimization problem is defined and solved using a search tree algorithm with heuristic constraints. Application to a case study which utilizes historical damage data and subsequent simulation shows the potential of the tool to identify cost-minimal maintenance decisions. The decision support tool is capable of incorporating a wide range of parameters to study preventive maintenance decision making in depth.

Sensitivity of optimal replacement policies to lifetime parameter estimates

This paper analyzes three time-based replacement policies when the parameters of the time-to-failure distribution are unknown. Under the hypothesis of a large sample data, the unknown parameters are estimated via maximum likelihood method. The uncertainty around the point estimates impacts the maintenance decision rules. Based on the asymptotic normality of the parameter estimators and delta-method, the asymptotic distribution of the optimal decision parameter and the average cost is derived. This distribution permits to measure the uncertainty around the optimal maintenance decision rule induced by the point estimates. The sensitivity analysis of the replacement policies to the maintenance unit costs and lifetime distribution parameters is carried out. Application to two time-to-failure distributions is provided.

Optimal Facility-Specific Inspection and Maintenance Decisions under Measurement Uncertainty: Unifying Framework

AbstractMonitoring and maintaining a system of degradable infrastructure facilities imposes considerable costs on transportation agencies. To find the optimal timing and type of maintenance, rehabi...

Performance analysis of an aggregation and disaggregation solution procedure to obtain a maintenance plan for a partially observable multi-component system

We analyze the performance of an aggregation and disaggregation procedure in giving the optimal maintenance decisions for a multi-component system under partial observations in a finite horizon. The components deteriorate in time and their states are hidden to the decision maker. Nevertheless, it is possible to observe signals about the system status and to replace components in each period. The aim is to find a cost effective replacement plan for the components in a given time horizon. The problem is formulated as a partially observable Markov decision process (POMDP). We aggregate states and actions in order to reduce the problem space and obtain an optimal aggregate policy which we disaggregate by simulating it using dynamic Bayesian networks (DBN). The procedure is statistically compared to an approximate POMDP solver that uses the full state space information. Cases where aggregation performs relatively better are isolated and it is shown that k-out-of-n systems belong to this class.

Survival analysis at multiple scales for the modeling of track geometry deterioration

Defects in track geometry have a notable impact on the safety of rail transportation. In order to make the optimal maintenance decisions to ensure the safety and efficiency of railroads, it is necessary to analyze the track geometry defects and develop reliable defect deterioration models. In general, standard deterioration models are typically developed for a segment of track. As a result, these coarse-scale deterioration models may fail to predict whether the isolated defects in a segment will exceed the safety limits after a given time period or not. In this paper, survival analysis is used to model the probability of exceeding the safety limits of the isolated defects. These fine-scale models are then used to calculate the probability of whether each segment of the track will require maintenance after a given time period. The model validation results show that the prediction quality of the coarse-scale segment-based models can be improved by exploiting information from the fine-scale defect-based deterioration models.

A Bayesian network model for prediction of weather-related failures in railway turnout systems

Railway turnout systems are one of the most critical elements in railway infrastructure. They are also one of the most vulnerable assets that are likely to be affected by the adverse weather. Therefore, effective methods for modeling weather-related failure of turnouts enable railway administrations to make optimal maintenance decisions. This paper presents a failure prediction model based on Bayesian network to evaluate the effect of weather on railway turnouts. Different failure causes related to weather are extracted as model variables. An Entropy Minimization based method is presented to discretize model variables for the purpose of reducing the input type and capturing better performance. By taking advantage of the independence of causal interactions, a causal noisy MAX model is applied to boost the efficiency of specifying the conditional probability table from small data sets. Prediction accuracy of the proposed method is compared to other advanced methods in order to evaluate the model’s performance. Our experiments by using the data from a railway corporation demonstrate that the proposed method has high prediction accuracy.

Robust Control of Partially Observable Failing Systems

This paper is concerned with optimal maintenance decision making in the presence of model misspecification. Specifically, we are interested in the situation where the decision maker fears that a nominal Bayesian model may be miss-specified or unrealistic, and would like to find policies that work well even when the underlying model is flawed. To this end, we formulate a robust dynamic optimization model for condition-based maintenance in which the decision maker explicitly accounts for distrust in the nominal Bayesian model by solving a worst-case problem against a second agent, “nature,” who has the ability to alter the underlying model distributions in an adversarial manner. The primary focus of our analysis is on establishing structural properties and insights that hold in the face of model miss-specification. In particular, we prove (i) an explicit characterization of nature’s optimal response through an analysis of the robust dynamic programming equation, (ii) convexity results for both the robust value function and the optimal robust stopping region, (iii) a general robustness result for the preventive maintenance paradigm, and (iv) the optimality of a robust control limit policy for the important subclass of Bayesian change point detection problems. We illustrate our theoretical result on a real-world application from the mining industry.