• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.44 no.4
• /
• pp.227-233
• /
• 2021

Predictive maintenance has been one of important applications of data science technology that creates a predictive model by collecting numerous data related to management targeted equipment. It does not predict equipment failure with just one or two signs, but quantifies and models numerous symptoms and historical data of actual failure. Statistical methods were used a lot in the past as this predictive maintenance method, but recently, many machine learning-based methods have been proposed. Such proposed machine learning-based methods are preferable in that they show more accurate prediction performance. However, with the exception of some learning models such as decision tree-based models, it is very difficult to explicitly know the structure of learning models (Black-Box Model) and to explain to what extent certain attributes (features or variables) of the learning model affected the prediction results. To overcome this problem, a recently proposed study is an explainable artificial intelligence (AI). It is a methodology that makes it easy for users to understand and trust the results of machine learning-based learning models. In this paper, we propose an explainable AI method to further enhance the explanatory power of the existing learning model by targeting the previously proposedpredictive model [5] that learned data from a core facility (Hyper Compressor) of a domestic chemical plant that produces polyethylene. The ensemble prediction model, which is a black box model, wasconverted to a white box model using the Explainable AI. The proposed methodology explains the direction of control for the major features in the failure prediction results through the Explainable AI. Through this methodology, it is possible to flexibly replace the timing of maintenance of the machine and supply and demand of parts, and to improve the efficiency of the facility operation through proper pre-control.

• Journal of Applied Reliability
• /
• v.17 no.2
• /
• pp.103-111
• /
• 2017

Purpose: Accelerated degradation tests can speed time to market and reduce the test time and costs associated with long term reliability tests to verify the required service life of a product or material. This paper proposes a service life prediction method for components or materials using an accelerated degradation tests based on the relationships between temperature and the rate of failure-causing chemical reaction. Methods: The relationship between performance degradation and the rate of a failure-causing chemical reaction is assumed and least square estimation is used to estimate model parameters from the degradation model. Results: Methods of obtaining acceleration factors and predicting service life using the degradation model are presented and a numerical example is provided. Conclusion: Service life prediction of a component or material is possible at an early stage of the degradation test by using the proposed method.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2002.05a
• /
• pp.873-876
• /
• 2002

This paper presents the effect of internal corrosion, external corrosion, material properties, operation condition, earthquake, traffic load and design thickness in pipeline on the failure prediction using a failure probability model. A nonlinear corrosion is used to represent the loss of pipe wall thickness with time. The effects of environmental, operational, and design random variables such as a pipe diameter, earthquake, fluid pressure, a corrosion rate, a material yield stress and a pipe thickness on the failure probability are systematically investigated using a failure probability model for the corrosion pipeline.

• Proceedings of the Korean Reliability Society Conference
• /
• 2002.06a
• /
• pp.403-410
• /
• 2002

This paper presents the effect of internal corrosion, external corrosion, material properties, operation condition, earthquake, traffic load and design thickness in pipeline on the failure prediction using a failure probability model. A nonlinear corrosion is used to represent the loss of pipe wall thickness with time. The effects of environmental, operational, and design random variables such as a pipe diameter, earthquake, fluid pressure, a corrosion rate, a material yield stress and a pipe thickness on the failure probability are systematically investigated using a failure probability model for the corrosion pipeline.

• Proceedings of the Korean Society For Composite Materials Conference
• /
• 2002.10a
• /
• pp.179-182
• /
• 2002

Rapid Prototyping (RP) technologies provide the ability to fabricate initial prototypes from various model materials. Stratasys' Fused Deposition Modeling (FDM) is a typical RP process that can fabricate prototypes out of plastic materials, and the parts made from FDM were often used as load-carrying elements. Because FDM deposits materials in about $300\mutextrm{m}$ thin filament with designated orientation, parts made from FDM show anisotropic material properties. This paper proposes an analytic model to predict the tensile strength of FDM parts. Applying the Classical Lamination Theory, which was developed for laminated composite materials, a computer code was implemented. Tsai-Wu failure criterion was added to the code to predict the failure of the FDM parts. The tensile strengths predicted by the analytic model were compared with experimental data. The data and prediction agreed reasonably well to prove the validity of the model. In addition, a web-based advisory service was developed to provide to strength prediction and design rules for FDM parts.

• Journal of Platform Technology
• /
• v.11 no.6
• /
• pp.3-12
• /
• 2023

In today's system operation, it is difficult to detect failures and take immediate action in the case of a shortage of manpower compared to the number of equipment or failures in vulnerable time zones, which can lead to delays in failure recovery. In addition, various algorithms exist to detect abnormal symptom data, and it is important to select an appropriate algorithm for each problem. In this paper, an ensemble-based isolation forest model was used to efficiently detect multivariate point anomalies that deviated from the mean distribution in the data set generated to predict system failure and minimize service interruption. And since significant changes in memory space usage are observed together with changes in CPU usage, the problem is solved by using LSTM-Auto Encoder for a collective anomaly in which another feature exhibits an abnormal pattern according to a change in one by comparing two or more features. did In addition, evaluation indicators are set for the performance evaluation of the model presented in this study, and then AI model evaluation is performed.

• Geomechanics and Engineering
• /
• v.20 no.2
• /
• pp.113-120
• /
• 2020

Rock damage is the main cause of accidents in underground engineering. It is difficult to predict rock damage accurately by using only one parameter. In this study, a rock failure prediction model was established by using stress, energy, and damage. The prediction level was divided into three levels according to the ratio of the damage threshold stress to the peak stress. A classification predicting model was established, including the stress, energy, damage and AE impact rate using Bayesian method. Results show that the model is good practicability and effectiveness in predicting the degree of rock failure. On the basis of this, a multi-parameter classification predicting deterioration model of rock failure was established. The results provide a new idea for classifying and predicting rockburst.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2002.05a
• /
• pp.897-902
• /
• 2002

The failure of flat plate connection is successive failure process accompanying with stress redistribution, hence it is necessary to compute the contributions of each resistance components at ultimate state. In the present study, the interactions of resultant forces at each faces of connection, i.e. shear, bending moment and torsional moment are considered in the assessment of strength of slab. As a result the strength prediction model for connection is made up as combination of bending resistance, shear resistance and torsional resistance. The proposed method is verified by the experimental data and numerical data of continuous slabs.

• Journal of the Korean Society of Systems Engineering
• /
• v.12 no.1
• /
• pp.105-112
• /
• 2016

An aircraft must be designed to minimize system failure rate for obtaining the aircraft safety, because the aircraft system failure causes a fatal accident. The safety of the aircraft system can be predicted by analyzing availability, reliability, and maintainability of the system. In this study, the reliability and the maintainability of the hydraulic system are analysed except the availability, and therefore the reliability and the maintainability analysis process and the results are presented for a helicopter hydraulic system. For prediction of the system reliability, the failure rate model presented in MIL-HDBK-217F is used, and MTBF is calculated by using the Part Stress Analysis Prediction and quality/temperature/environmental factors described in NPRD-95 and MIL-HDBK-338B. The maintainability is predicted by FMECA(Failure Mode, Effect & Criticality Analysis) based on MIL-STD-1629A.

• Journal of Applied Reliability
• /
• v.17 no.4
• /
• pp.305-315
• /
• 2017

Purpose: The purpose of this research is to propose procedure and methodology for developing failure rate databook which is suitable for Korean operation environment. Methods: To this end, we investigate failure databooks used in foreign countries and study the procedure and methodology for collecting failure data, organizing the data, estimating failure rate and summarizing results. Results: We develop the procedure of development of failure databook, the items for data collection, database schema of part details and part summary and contents of failure databook by considering the application environment in Korea. Conclusion: The results of our research could be utilized for the development of Korean failure rate databook and research of reliability prediction model and could ultimately contribute to improve the accuracy of reliability prediction.