11 sonuçlar
Arama Sonuçları
Listeleniyor 1 - 10 / 11
Yayın A DBN based reactive maintenance model for a complex system in thermal power plants(Elsevier Sci Ltd, 2019-10) Özgür Ünlüakın, Demet; Türkali, Busenur; Karacaörenli, Ayşe; Aksezer, Sezgin ÇağlarThermal power plants consist of several complex systems having many interacting hidden components. Any unexpected failure may lead to prolonged downtime and serious lost profits. Therefore, implementing an effective maintenance policy is crucial for this sector. Although preventive maintenance has become a more popular strategy, it does not completely prevent the need for corrective maintenance. Our aim in this study is to tackle the corrective maintenance implementation problem of a multi-component partially observable dynamic system based on a regenerative air heater in a thermal power plant. We propose eight methods having different efficiency measures with respect to time, effect and probability criteria to minimize the total number of maintenance activities in a given planning horizon. Performances of these methods are evaluated under corrective maintenance strategy using dynamic Bayesian networks. The results show that fault effect methods with best working state probability measure perform better than the others considering both the total amount of maintenance activities and also the solution time. We also point out how the methods can be implemented in real-life and how the results can be used for requirements planning. Furthermore, the proposed methods can be used for the corrective maintenance of all systems having hidden interacting components.Yayın Cost-effective fault diagnosis of a multi-component dynamic system under corrective maintenance(Elsevier Ltd, 2021-04) Özgür Ünlüakın, Demet; Türkali, Busenur; Aksezer, Sezgin ÇağlarMaintenance planning and execution are challenging tasks for every system with complex structure. Interdependent nature of the components that builds up the system may have significant effect on system integrity. While preventive maintenance actions can be carried out in a more planned fashion, corrective actions are more time sensitive as they directly affect the availability of the system. This study proposes a cost-effective dynamic Bayesian network modeling scheme to be used in the planning of corrective maintenance actions on systems having hidden components which have stochastic and structural dependencies. In such context, the regenerative air heater system which is a key element of a power plant is taken into consideration. The proposed maintenance framework offers several methods, each aiming to balance the cost with the probability effect using a normalization procedure. The methodologies are extensively simulated for sensitivity analysis under various downtime cost values. Fault effect methods with worst state probability efficiency measures give the least total cost for all downtime cost values and their distinction becomes significant as this value increases. Further statistical analysis concludes that considerable gains on maintenance costs can be achieved by the proposed approach.Yayın Maintenance policy analysis of the regenerative air heater system using factored POMDPs(Elsevier Ltd, 2022-03) Kıvanç, İpek; Özgür Ünlüakın, Demet; Bilgiç, TanerMaintenance optimization of multi-component systems is a difficult problem. Partially Observable Markov Decision Processes (POMDPs) are powerful tools for such problems under uncertainty in stochastic environments. In this study, the main POMDP solution approaches and solvers are surveyed. Then, based on experimental models with different complexities in the size of the system space, selected POMDP solvers using different representation patterns for modeling and different procedures for updating the value function while solving are compared. Furthermore, to show that factored representations are advantageous in modeling and solving the maintenance problem of multi-component systems where there exist also stochastic dependencies among the components, the maintenance problem of the one-line regenerative air heater system available in thermal power plants is modeled and solved with factored POMDPs. In-depth sensitivity analyses are performed on the obtained policy. The results show that factored POMDPs enable compact modeling, efficient policy generation and practical policy analysis for the tackled problem. Furthermore, they also motivate the use of factored POMDPs in the generation and analysis of maintenance policies for similar multi-component systems.Yayın Developing an effective maintenance policy for control gates in hydroelectric power plants(IEOM Society, 2018) Aktel, Mehmet Burak; Özgür Ünlüakın, DemetEnergy consumption has been increasing rapidly in the world. That is why production of energy from renewable resources is getting more and more important today. Hydroelectric power is the largest source of renewable electricity generation in the world. Countries that have large resources of hydropower use hydroelectricity as a base load energy source because of its secure and reliable energy production. Maintenance scheduling in energy production plants is very crucial since any unexpected malfunction leads to very serious economic losses. It is essential to decide how and when to perform maintenance activities for power plants, especially if they are among base load electricity producers. The control gates are one of the vital components in hydroelectric power plants which control the movement of water. In this study, we formulate the maintenance problem of control gates using Markov Decision Processes. Our aim is to find an optimum maintenance policy for the gates by considering maintenance related losses such as equipment cost, lost sales and time spent during maintenance. We create and analyze different scenarios based on the physical conditions of the plant and cost structures.Yayın An effective maintenance policy for a multi-component dynamic system using factored POMDPs(Springer Verlag, 2019-09-20) Kıvanç, İpek; Özgür Ünlüakın, DemetWith the latest advances in technology, almost all systems are getting substantially more uncertain and complex. Since increased complexity costs more, it is challenging to cope with this situation. Maintenance optimization plays a critical role in ensuring effective decision-making on the correct maintenance actions in multi-component systems. A Partially Observable Markov Decision Process (POMDP) is an appropriate framework for such problems. Nevertheless, POMDPs are rarely used for tackling maintenance problems. This study aims to formulate and solve a factored POMDP model to tackle the problems that arise with maintenance planning of multi-component systems. An empirical model consisting of four partially observable components deteriorating in time is constructed. We resort to Symbolic Perseus solver, which includes an adapted variant of the point-based value iteration algorithm, to solve the empirical model. The obtained maintenance policy is simulated on the empirical model in a finite horizon for many replications and the results are compared to the other predefined maintenance policies. Drawing upon the policy results of the factored representation, we present how factored POMDPs offer an effective maintenance policy for the multi-component systems.Yayın Maintenance policy simulation for a factored partially observable system(The Society for Modeling and Simulation International, 2019-07) Özgür Ünlüakın, Demet; Kıvanç, İpekTaking maintenance decisions is one of the well-known stochastic sequential decision problems under uncertainty. Partially Observable Markov Decision Processes (POMDPs) are powerful tools for such problems. Nevertheless, POMDPs are rarely used for tackling maintenance problems of multi-component systems because their state spaces grow exponentially with the increasing number of components. Factored representations have been proposed for POMDPs taking advantage of the factored structure already available in the nature of the problem. Our aim in this study is to show how to formulate a factored POMDP model for the maintenance problem of a multi-component dynamic system and how to simulate and evaluate the obtained policy before implementing it in real life. The sensitivity of the methodology is analyzed under several cost values, and the methodology is compared to other predefined policies. The results show that the policies generated via the POMDP solver perform better than the predefined policies.Yayın Performance analysis of an aggregation and disaggregation solution procedure to obtain a maintenance plan for a partially observable multi-component system(Elsevier Sci Ltd, 2017-11) Özgür Ünlüakın, Demet; Bilgiç, TanerWe 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.Yayın Evaluation of proactive maintenance policies on a stochastically dependent hidden multi-component system using DBNs(Elsevier Ltd, 2021-07) Özgür Ünlüakın, Demet; Türkali, BusenurIn complex systems with stochastically dependent components which are not observed directly, determining an effective maintenance policy is a difficult task. In this paper, a dynamic Bayesian network based maintenance decision framework is proposed to evaluate proactive maintenance policies for such systems. Two preventive and one predictive maintenance strategies from a cost perspective are designed for multi-component dependable systems which aim to reduce maintenance cost while increasing system reliability at the same time. Tabu procedure is employed to avoid repetitive similar actions. The performances of the policies are compared with a reactive maintenance strategy and also with each other using different strategy parameters on a real life system confronted in thermal power plants for six different scenarios. The scenarios are designed considering different structures of system dependability and reactive cost. The results show that the threshold based maintenance which is the predictive strategy gives the minimum cost and maintenance number in almost all scenarios.Yayın A DBN based prognosis model for a complex dynamic system: a case study in a thermal power plant(Springer Nature Switzerland AG, 2018-08-15) Özgür Ünlüakın, Demet; Kıvanç, İpek; Türkali, Busenur; Aksezer, Sezgin ÇağlarWith the development of industry, complexity of systems and equipment has increased extensively. This results in the introduction of many interdependencies (stochastic, structural and economic) among the components of systems. Neglecting these interdependencies, when planning maintenance actions, leads to undesirable outcomes such as prolonged downtime and higher costs. That is why a multi-component system approach needs to be taken into account in maintenance planning models. However, maintenance planning is a difficult task in multi-component systems because of their complexities. Energy production systems are notable examples of such complex structures consisting of many interacting components. Maintenance planning is extremely crucial for this sector since any unexpected malfunction leads to very serious costs. Therefore, the aim of this study is to formulate the maintenance problem of a multi-component dynamic system in thermal power plants focusing on system reliability prognosis. Bayesian networks (BN) are probabilistic graphical models that have been extensively used to represent and model the causal relations. A dynamic Bayesian network (DBN) is an extended BN which has a temporal dimension. We propose to use DBNs to prognose the reliabilities of components and processes of a dynamic system in a thermal power plant and show that this representation is efficient to model the interdependencies and degradations in such a system.
