• International Journal of Reliability and Applications
• /
• v.2 no.2
• /
• pp.99-105
• /
• 2001

Delay time analysis is a pragmatic mathematical concept readily embraced by engineers which has been developed as a means to model maintenance decision problem. This paper considers an inspection period using delay time analysis for fishing vessel equipment. We assume that delay time has a Weibull distribution. In this paper, we determine the optimal inspection period which minimize the expected downtime per unit time. Explicit solutions for the optimal inspection are presented for illustrative purposes.

• Journal of the Korean Society of Systems Engineering
• /
• v.18 no.1
• /
• pp.84-89
• /
• 2022

For system maintenance optimization, it is necessary to establish a state information system by CBM+ including CBM and RCM, and sensor selection for CBM+ application requires system process for function model analysis at the early design stage. The study investigated the contents of CBM and CBM+, analyzed the function analysis tasks and procedures of the system, and thus presented a D-FMEA based sensor selection inference methodology at the early stage of design for CBM+ application, and established it as a D-FMEA based sensor selection inference process. The D-FMEA-based sensor inference methodology and procedure in the early design stage were presented for diesel engine sub assembly.

• Geomechanics and Engineering
• /
• v.14 no.6
• /
• pp.563-570
• /
• 2018

Ballast layer has an important role in vertical stiffness and stability of railway track. In most of the Middle East countries and some of the Asian ones, significant parts of railway lines pass through desert areas where the track (particularly ballast layer) is contaminated with sands. Despite considerable number of derailments reported in the sand contaminated tracks, there is a lack of sufficient studies on the influences of sand contamination on the ballast vertical stiffness as the main indicator of track stability. Addressing this limitation, the effects of sand contamination on the mechanical behavior of ballast were experimentally investigated. For this purpose, laboratory tests (plate load test) on ballast samples with different levels of sand contamination were carried out. The results obtained were analyzed leading to derive mathematical expressions for the strain modulus ($E_V$) as a function of the ballast level of contamination. The $E_V$ was used as an index for evaluation of the load-deformation characteristics and bearing capacity of track substructure. The critical limit of sand contamination, after which the $E_V$ of the ballast reduces drastically, was obtained. It was shown that the obtained research results improve the current track maintenance approach by providing key guides for the optimization of ballast maintenance planning (the timing of ballast cleaning or renewal).

• Nuclear Engineering and Technology
• /
• v.52 no.7
• /
• pp.1436-1442
• /
• 2020

Nuclear infrastructure systems play an important role in national security. The functions and missions of nuclear infrastructure systems are vital to government, businesses, society and citizen's lives. It is crucial to design nuclear infrastructure for scalability, reliability and robustness. To do this, we can use machine learning, which is a state of the art technology used in various fields ranging from voice recognition, Internet of Things (IoT) device management and autonomous vehicles. In this paper, we propose to design and develop a machine learning algorithm to perform predictive maintenance of nuclear infrastructure. Support vector machine and logistic regression algorithms will be used to perform the prediction. These machine learning techniques have been used to explore and compare rare events that could occur in nuclear infrastructure. As per our literature review, support vector machines provide better performance metrics. In this paper, we have performed parameter optimization for both algorithms mentioned. Existing research has been done in conditions with a great volume of data, but this paper presents a novel approach to correlate nuclear infrastructure data samples where the density of probability is very low. This paper also identifies the respective motivations and distinguishes between benefits and drawbacks of the selected machine learning algorithms.

• Structural Monitoring and Maintenance
• /
• v.6 no.3
• /
• pp.219-235
• /
• 2019

Scheduled inspections of common crossings are one of the main cost drivers of railway maintenance. Prognostics and health management (PHM) approach and modern monitoring means offer many possibilities in the optimization of inspections and maintenance. The present paper deals with data driven prognosis of the common crossing remaining useful life (RUL) that is based on an inertial monitoring system. The problem of scheduled inspections system for common crossings is outlined and analysed. The proposed analysis of inertial signals with the maximal overlap discrete wavelet packet transform (MODWPT) and Shannon entropy (SE) estimates enable to extract the spectral features. The relevant features for the acceleration components are selected with application of Lasso (Least absolute shrinkage and selection operator) regularization. The features are fused with time domain information about the longitudinal position of wheels impact and train velocities by multivariate regression. The fused structural health (SH) indicator has a significant correlation to the lifetime of crossing. The RUL prognosis is performed on the linear degradation stochastic model with recursive Bayesian update. Prognosis testing metrics show the promising results for common crossing inspection scheduling improvement.

• Korean Journal of Construction Engineering and Management
• /
• v.10 no.1
• /
• pp.45-57
• /
• 2009

BTL (Build-Transfer-Lease) Project for Education Facilities are contracted as a package which consists of several education facilities. The general maintenance period of BTL project for education facilities is 20 years. Thus, total cost variation largely depends on the accuracy of the maintenance cost forecasting in the early stage in the life cycle of the BTL Project. This research develops a cost forecasting system using complete linkage algorithm and branch & bound algorithm to help in finding optimal bundling combination. This system helps owner's decision-making to estimate the total project cost with various constraints changing. The result of this research suggests more reasonable and effective forecasting model for the maintenance facilities package in the BTL project.

• Journal of the Korean Society for Railway
• /
• v.12 no.2
• /
• pp.291-301
• /
• 2009

This paper presents the optimal design and analysis method of the train overhaul maintenance facility based on the simulation. Because the train is composed of a coach or more, we design the simulation model after analyzing the operation of train into train, coach, coach's body parts and wheel parts and soon. In simulation analysis, we consider the critical (dependent) factors and design (independent) parameters for the selection of alternatives and optimal design. Therefore, Multi Criteria Decision Making (MCDM) is proposed for the selection of alternatives and optimal method in order to find the optimal design factors. The case study for the above approach is used for the electronic locomotive overhaul maintenance facility. This paper provides a comprehensive framework for the train overhaul maintenance facility design using the simulation, MCDM and optimal methods. Therefore, the method developed for this research can be adopted for other enhancements in different but comparable situation.

• Proceedings of the KIEE Conference
• /
• 1991.07a
• /
• pp.333-336
• /
• 1991

In this paper, Hopfield & Tank model-like artificial neural network structure is proposed, which can be used for the optimal path planning problems such as the unit commitment problems or the maintenance scheduling problems which have been solved by the dynamic programming method or the branch and bound method. To construct the structure of the neural network, an energy function is defined, of which the global minimum means the optimal path of the problem. To avoid falling into one of the local minima during the optimization process, the simulated annealing method is applied via making the slope of the sigmoid transfer functions steeper gradually while the process progresses. As a result, computer(IBM 386-AT 34MHz) simulations can finish the optimal unit commitment problem with 10 power units and 24 hour periods (1 hour factor) in 5 minites. Furthermore, if the full parallel neural network hardware is contructed, the optimization time will be reduced remarkably.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.12
• /
• pp.2319-2323
• /
• 2010

The existing contact-type bearings using rolling or sliding require continuous maintenance due to abrasion caused by friction and are not suitable for high-speed rotation and slimming. A magnetic bearing without contact can overcome such problems but the performance depends on the allocation of magnets and the structure of bearings. This paper proposes a method designing parameters of a passive magnetic bearing to improve levitation force. The proposed method employs Halbach array as the allocation of magnets, uses particle swam optimization to determine the structure of bearings. The numerical experiment shows that the levitation force is improved by the proposed method compared with the existing one using finite element analysis.

• Structural Monitoring and Maintenance
• /
• v.1 no.4
• /
• pp.427-449
• /
• 2014

A hybrid optimization method for the identification of state-space models is presented in this study. Hybridization is succeeded by combining the advantages of deterministic and stochastic algorithms in a superior scheme that promises faster convergence rate and reliability in the search for the global optimum. The proposed hybrid algorithm is developed by replacing the original stochastic mutation operator of Evolution Strategies (ES) by the Levenberg-Marquardt (LM) quasi-Newton algorithm. This substitution results in a scheme where the entire population cloud is involved in the search for the global optimum, while single individuals are involved in the local search, undertaken by the LM method. The novel hybrid identification framework is assessed through the Monte Carlo analysis of a simulated system and an experimental case study on a shear frame structure. Comparisons to subspace identification, as well as to conventional, self-adaptive ES provide significant indication of superior performance.