The large process plant is currently implementing predictive maintenance technology to transition from the traditional Time-Based Maintenance (TBM) approach to the Condition-Based Maintenance (CBM) approach in order to improve equipment maintenance and productivity. The traditional techniques for predictive maintenance involved managing upper/lower thresholds (Set-Point) of equipment signals or identifying anomalies through control charts. Recently, with the development of techniques for big analysis, machine learning-based AAKR (Auto-Associative Kernel Regression) and deep learning-based VAE (Variation Auto-Encoder) techniques are being actively applied for predictive maintenance. However, this predictive maintenance techniques is only effective during steady-state operation of plant equipment, and it is difficult to apply them during start-up and shutdown periods when rises or falls. In addition, unlike processes such as nuclear and thermal power plants, which operate for hundreds of days after a single start-up, because the pumped power plant involves repeated start-ups and shutdowns 4-5 times a day, it is needed the prediction and alarm algorithm suitable for its characteristics. In this study, we aim to propose an approach to apply the optimal predictive alarm algorithm that is suitable for the characteristics of Pumped Storage Power Plant(PSPP) facilities to the system by analyzing the predictive maintenance techniques used in existing nuclear and coal power plants.

There have been a lot of studies in the past for the method of predicting the failure of a machine, and recently, a lot of researches and applications have been generated to diagnose the physical condition of the machine and the parts and to calculate the remaining life through various methods. Survival models are also used to predict plant failures based on past anomaly cycles. In particular, special machine that reflect the fluid flow and process characteristics of chemical plants are connected to hundreds or thousands of sensors, so there are not many factors that need to be considered, such as process and material data as well as application of derivative variables. In this paper, the data were preprocessed through time series anomaly detection based on unsupervised learning to predict the abnormalities of these special machine. Next, clustering results reflecting clustering-based data characteristics were applied to produce additional variables, and a learning data set was created based on the history of past facility abnormalities. Finally, the prediction methodology based on the supervised learning algorithm was applied, and the model update was confirmed to improve the accuracy of the prediction of facility failure. Through this, it is expected to improve the efficiency of facility operation by flexibly replacing the maintenance time and parts supply and demand by predicting abnormalities of machine and extracting key factors.

본 연구에서는 고체로켓의 임무 수행 중 연소실 내압으로 인해 발생하는 고체로켓 케이스의 3가지 고장(응력파괴, 균열파괴, 볼트 체결 부 파손) 확률을 효과적으로 예측하는 기법을 개발하였다. 전체적인 확률계산 과정은 다음과 같다: 1) 고체로켓 모터의 고장모드에 영향을 주는 설계 변수선정 및 확률분포 부여, 2) 연소해석을 통한 로켓의 최대작동압력(maximum expected operating pressure, MEOP)의 확률분포 계산, 3) 케이스의 응력과 변형 형상을 구하기 위한 유한요소해석, 4) 3가지 고장함수에 대한 신뢰도예측의 수행. 계산의 편의를 위해 유한요소모델은 축대칭으로 가정하였고 볼트 체결 부의 접촉을 고려하였다. 효율적인 신뢰도예측을 위해 FORM(first-order reliability method) 기법을 통해 MPP(most probable failure point)를 탐색한 후, LHS(latin hypercube sampling)와 반응표면기법을 적용하여 고장모드를 다항식으로 근사화하며, 중요도 추출법을 적용하여 고장확률을 계산하였다.

The O&M (Operation and Maintenance) phase of offshore plants with a long life cycle requires heavy charges and more efforts than the construction phase, and the occurrence of an accident of an offshore plant causes catastrophic damage. So previous studies have focused on the development of advanced maintenance system to avoid unexpected failures. Nowadays due to the emerging ICTs (Information Communication Technologies) and sensor technologies, it is possible to gather the status data of equipment and send health monitoring data to administrator of an offshore plant in a real time way, which leads to having much concern on the condition based maintenance policy. In this study, we have reviewed previous studies associated with CBM (Condition-Based Maintenance) of offshore plants, and introduced an algorithm predicting the next failure time of the compressor which is one of essential mechanical devices in LNG FPSO (Liquefied Natural Gas Floating Production Storage and Offloading vessel). To develop the algorithm, continuous time Markov model is applied based on gathered vibration data.

The fault diagnosis is a systematic and unified method to find based on the observing data resulting in noises. This paper presents the fault prediction and diagnosis using fuzzy expert system technique to manipulate the uncertainties efficiently in predi

플랜트 및 설비가 대규모, 정교화, 복잡화 될수록 이로 인한 고장 및 오류에 의한 피해가 막대하기 때문에, 시스템의 신뢰성, 보전성 및 안전성 향상과 제품 품질 향상을 추구 및 안전성 유지에 대한 관심이 고조되고 있다. 고장진단은 잠재적으로 노이즈를 가지고 있다고 생각되는 데이터의 해석에 근거하여 시스템의 고장을 찾는 일련의 체계적이고 통합된 방법이다. 그러나 대부분의 방법들이 이진 논리에 기초를 둔 추론으로 불확실성을 제대로 결과에 반영하지 못하고 있다. 본 논문에서는 예방정비의 관점에서 시스템에 내재된 다양한 불확실성을 효율적으로 처리하기 위해 전문가의 직관과 경험등을 기초로 하여 언어학적 변량을 취하고, 이를 퍼지 기법을 이용하여 정량화 함으로써 불확실성을 고려한 판단이 가능하게 하는 퍼지 전문가 시스템을 제안한다.