• Journal of the Korean Society of Safety
• /
• v.33 no.3
• /
• pp.83-91
• /
• 2018

This paper suggests a weibull time delay model to evaluate failure risks in FMEA(failure modes and effects analysis). Assuming three types of loss functions for delayed time in failure cause detection, the risk of each failure cause is evaluated as its occurring frequency and expected loss. Since the closed form solution of the risk metric cannot be obtained, a statistical computer software R program is used for numerical calculation. When the occurrence and detection times have a common shape parameter, though, some simple results of mathematical derivation are also available. As an enormous quantity of field data becomes available under recent progress of data acquisition system, the proposed risk metric will provide a more practical and reasonable tool for evaluating the risks of failure causes in FMEA.

• Communications for Statistical Applications and Methods
• /
• v.24 no.1
• /
• pp.29-41
• /
• 2017

The estimation problem of expected time to failure of units is studied in a discrete set up. A simple step-stress accelerated life testing is considered with a Type-I censored sample from geometric distribution that is a commonly used distribution to model the lifetime of a device in discrete case. Maximum likelihood estimators as well as the associated distributions are derived. Exact, approximate and bootstrap approaches construct confidence intervals that are compared via a simulation study. Optimal confidence intervals are suggested in view of the expected width and coverage probability criteria. An illustrative example is also presented to explain the results of the paper. Finally, some conclusions are stated.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.2
• /
• pp.587-596
• /
• 2008

This paper develops the optimal periodic preventive maintenance policies following the expiration of warranty: renewing warranty and non-renewing warranty. After the warranty period is expired, the system undergoes the PM periodically and is minimally repaired at each failure between two successive PMs. Firstly, we determine the expected cost rate per unit time and the expected downtime per unit time for the periodic PM model. Then the overall value function suggested by Jiang and Ji(2002) is applied to obtain the optimal PM period and the optimal PM number. Finally, the numerical examples are presented for illustrative purpose.

• Journal of Korean Institute of Industrial Engineers
• /
• v.39 no.2
• /
• pp.143-148
• /
• 2013

In FMEA, occurrence and detectability are not related to only failure modes itself but also their causes. It is assumed that any failure occurs after at least one cause corresponding to failure occurs in advance. Occurrence of the failure mode is described by occurrence time of its cause and elapsed time to the actual failure. Under the periodic monitoring plan, the monitoring interval is another factor to determine the detectability and occurrence of each failure mode. When a failure cause occurs, the failure does not occur if the cause is identified and remedied before it actually occurs. Under this situation, we construct an economic model for prioritizing failure modes. The loss function is based on the unfulfilled mission period. We also provide an optimal monitoring plan with an illustrative example.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.3
• /
• pp.743-752
• /
• 2006

This paper considers a Bayesian approach to replacement policy model with minimal repair. We use the criterion based on the expected cost and the expected downtime to determine the optimal replacement period. To do so, we obtain the expected cost rate per unit time and the expected downtime per unit time, respectively. When the failure time is Weibull distribution with uncertain parameters, a Bayesian approach is established to formally express and update the uncertain parameters for determining an optimal maintenance policy. Especially, the overall value function suggested by Jiagn and Ji(2002) is applied to obtain the optimal replacement period. The numerical examples are presented for illustrative purpose.

• Journal of the Korean Society of Safety
• /
• v.26 no.6
• /
• pp.104-110
• /
• 2011

In FMEA, the risk priority number(RPN) is used for risk evaluation on each failure mode. It is obtained by multiplying three components, i.e., severity, occurrence, and detectability of the corresponding failure mode. Each of the three components are usually determined on the basis of the past experience and technical knowledge. But this approach is not strictly objective in evaluating risk of a given failure mode and thus provide somewhat less scientific measure of risk. Assuming a homogeneous Poisson process for occurrence of the failures and causes, we propose a more scientific approach to evaluation of risk in FMEA. To quantify severity of each failure mode, the mission period is taken into consideration for the system. If the system faces no failure during its mission period, there are no losses. If any failure occurs during its mission period, the losses corresponding to the failure mode incurs. A longer remaining mission period is assumed to incur a larger loss. Detectability of each failure mode is then incorporated into the model assuming an exponential probability law for detection time of each failure cause. Based on the proposed model, an illustrative example and numerical analyses are provided.

• Journal of Korean Institute of Industrial Engineers
• /
• v.22 no.1
• /
• pp.51-63
• /
• 1996

In this paper, we develop two replacement-type reliability acceptance sampling plans(RASPs) for the gamma lifetime distribution assuming that the shape parameter is known. The two plans are respectively based upon failure-free period and hybrid life tests. We then compare the plans in terms of expected test time to reach a decision, power, etc. Computational results indicate among others that the failure-free period RASP has a shorter expected completion time than the corresponding hybrid RASP when the true scale parameter is 'large'. Finally, sensitivity analyses reveal that the effects of the uncertainties involved in the assumed shape parameter on the producer and the consumer risks are in favorable directions for both parties for both types of plans.

• Journal of Computing Science and Engineering
• /
• v.8 no.1
• /
• pp.17-24
• /
• 2014

In this paper, we propose a new implementation of a failure detector. The implementation uses a dual model of heartbeat and interaction. First, the heartbeat model is adopted to shorten the detection time, if the detection process does not receive the heartbeat message in the expected time. The interaction model is then used to check the process further. The expected time is calculated using the exponential smoothing method. Exponential smoothing can be used to estimate the next arrival time not only in the random data, but also in the data of linear trends. It is proven that the new detector in the paper can eventually be a perfect detector.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.28 no.5
• /
• pp.586-592
• /
• 2004

In this study, the failure analysis of a decanter is carried out and the methods of performance improvement are presented. The decanter is a centrifugal separator that is used to separate water and solids from municipal and industrial sludge. Therefore, the decanter should be designed to improve the dewatering of sludge. Besides high performance, the decanter should guarantee its life time under a severe using condition. For theses reasons, the failure analysis and performance improvement of the decanter are studied. It is found from this study that the failure is caused by mass unbalance, wear, clogging or crack. If these failure causes are prevented, the life time as well as the performance is expected to be improved.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.3
• /
• pp.78-89
• /
• 2022

The purpose of this study was to propose useful suggestion by analyzing preventive replacement policy under which there are minor and major failure. Here, major failure is defined as the failure of system which causes the system to stop working, however, the minor failure is defined as the situation in which the system is working but there exists inconvenience for the user to experience the degradation of performance. For this purpose, we formulated an expected cost rate as a function of periodic replacement time and the number of system update cycles. Then, using the probability and differentiation theory, we analyzed the cost rate function to find the optimal points for periodic replacement time and the number of system update cycles. Also, we present a numerical example to show how to apply our model to the real and practical situation in which even under the minor failure, the user of system is not willing to replace or repair the system immediately, instead he/she is willing to defer the repair or replacement until the periodic or preventive replacement time. Optimal preventive replacement timing using two variables, which are periodic replacement time and the number of system update cycles, is provided and the effects of those variables on the cost are analyzed.