In the nuclear fuel cycle (NFC) facilities, the failure of Heating Ventilation and Air Conditioning (HVAC) system starts with minor component failures and can escalate to affecting the entire system, ultimately resulting in radiological consequences to workers. In the field of air-conditioning and refrigerating engineering, the fault detection and diagnosis (FDD) of HVAC systems have been studied since faults occurring in improper routine operations and poor preventive maintenance of HVAC systems result in excessive energy consumption. This paper aims to provide a systematic review of existing FDD methods for HVAC systems therefore explore its potential application in nuclear field. For this goal, typical faults and FDD methods are investigated. The commonly occurring faults of HVAC are identified through various literature including publications from International Energy Agency (IEA) and American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE). However, most literature does not explicitly addresses anomalies related to pressure, even though in nuclear facilities, abnormal pressure condition need to be carefully managed, particularly for maintaining radiological contamination differently within each zone. To build simulation model for FDD, the whole-building energy system modeling is needed because HVAC systems are major contributors to the whole building’s energy and thermal comfort, keeping the desired environment for occupants and other purposes. The whole-building energy modeling can be grouped into three categories: physics-based modeling (i.e., white-box models), hybrid modeling (i.e., grey-box models), and data-driven modeling (i.e., black-box models). To create a white-box FDD model, specialized tools such as EnergyPlus for modeling can be used. The EnergyPlus is open source program developed by US-DOE, and features heat balance calculation, enabling the dynamic simulation in transient state by heat balance calculation. The physics based modeling has the advantage of explaining clear cause-and-effect relationships between inputs and outputs based on heat and mass transfer equations, while creating accurate models requires time and effort. Creating a black-box FDD model requires a sufficient quantity and diverse types of operational data for machine learning. Since operation data for HVAC systems in existing nuclear cycle facilities are not fully available, so efforts to establish a monitoring system enabling the collection, storage, and management of sensor data indicating the status of HVAC systems and buildings should be prioritized. Once operational data are available, well-known machine learning methods such as linear regression, support vector machines, random forests, artificial neural networks, and recurrent neural networks (RNNs) can be used to classify and diagnose failures. The challenge with black-box models is the lack of access to failure data from operating facilities. To address this, one can consider developing black-box models using reference failure data provided by IEA or ASHRAE. Given the unavailability of operation data from the operating NFC facilities, there is a need for a short to medium-term plan for the development of a physics-based FDD model. Additionally, the development of a monitoring system to gather useful operation data is essential, which could serve both as a means to validate the physics-based model and as a potential foundation for building data-driven model in the long term.

Failure diagnoses on large diesel engine are commonly detected when a deviation or fluctuation in its temperature, pressure, vibration or noise set parameter limits arises. These parameters can be easily monitored and can provide information of the engine’s present state depending on external environment and operating conditions. On the other hand, long term monitoring and condition management can be interfaced into the engine’s existing operating system. The approach is seen to keep track of monitored machines’ status using resonance and vibration amplitude. In particular, these signals will be able to identify complex vibration characteristic pertaining to such as engine torque output and support mounts. In this paper, a basic research for large diesel engine diagnosis was carried-out. The failure diagnosis collects and monitors the vibration state time history by using various vibration signals with reference to ISO 13373-1. Further, this monitoring system in the field of large diesel engines has not been applied practically and the results of this study are presented herein.

In this paper, each controller's unique ID and PICO oscilloscope were used to measure the voltage waveform of each CAN communication line, and compare and analyze the serial decoding results. Using the voltage change level of the CAN communication line, it was possible to check whether the CAN-High line and the Low line were disconnected. And it was possible to infer the circuit disconnection point between the controller and the controller only with the unique ID information of each controller. And when the CAN-High circuit was disconnected, the voltage of the high line was measured at the same voltage level as the Low line.

머신러닝 기법의 발달과 함께 기계에서 발생하는 다양한 종류(진동, 온도, 유량 등)의 데이터를 활용하여 기계의 상태를 진단하고 이상 탐지 및 비정상 분류 연구도 활발히 진행되고 있다. 특히 진동 데이터를 활용한 회전 기계의 상태 진단은 전통적인 기계 상태 모니터링 분야로 오랜 기간 동안 연구가 진행되었고, 연구 방법 또한 매우 다양하다. 본 연구에서는 가정용 에어컨에 사용되는 로터리 압축기에 가속도계를 직접 설치하여 진동 데이터를 수집하는 실험을 진행하였다. 데이터 부족 문제를 해결하기 위해 데이터 분할을 수행하였으며, 시간 영역에서의 진동 데이터로부터 통계적, 물리적 특징들을 추출한 후, Chi-square 검증을 통해 고장 분류 모델의 주요 특징을 추출하였다. SVM(Support Vector Machine) 모델은 압축기의 정상 혹은 이상 유무를 분류하기 위해 개발되었으며, 파라미터 최적화를 통해 분류 정확도를 개선하였다.

Industrial Motors diagnostic equipment is highly dependent on the automation system, so if there are defects in the automation equipment, it can only rely on the operator’s intuitive judgment.To help with intuitive judgment, Park’s Vactor Approach(PVA) represents the current signal as a pattern of circles, so it can tell if a fault occurs when the circle is distorted. However, the failure to judge the degree of distortion of the circle pattern is the basis of the fault, so it will face difficulties. In this paper, in order to compare the faults of PVA, the period of d-axis current of PVA pulsation was mastered, so that two phase differences occurred in the same signal source. Through experiments, it is confirmed that this is a 90 degree cross formation of PVA, which is convenient for judging from the vision that there is no fault, thus helping the operator to make intuitive judgment.

Ocean economy plays a crucial role in the strengthening maritime safety industry and in the welfare of human beings. Electric Submersible Pumps (ESP) have been widely used in floating platforms on the sea to provide oil for machines. However, the ESP fault may lead to ocean environment pollution, on the other hand, a timely fault diagnosis of ESP can improve the ocean economy. In order to meet the strict regulations of the ocean economy and environmental protection, the fault diagnosis of ESP system has become more and more popular in many countries. The vibration mechanical models of typical faults have been able to successfully diagnose the faults of ESP. And different types of sensors are used to monitor the vibration signal for the signal analysis and fault diagnosis in the ESP system. Meanwhile, physical sensors would increase the fault diagnosis challenge. Nowadays, the method of neural network for the fault diagnosis of ESP has been applied widely, which can diagnose the fault of an electric pump accurately based on the large database. To reduce the number of sensors and to avoid the large database, in this paper, algorithms are designed based on feature extraction to diagnose the fault of the ESP system. Simulation results show that the algorithms can achieve the prospective objectives superbly.

In order to reduce damages to major railroad components, which have the potential to cause interruptions to railroad services and safety accidents and to generate unnecessary maintenance costs, the development of rolling stock maintenance technology is switching from preventive maintenance based on the inspection period to predictive maintenance technology, led by advanced countries. Furthermore, to enhance trust in accordance with the speedup of system and reduce maintenances cost simultaneously, the demand for fault diagnosis and prognostic health management technology is increasing. The objective of this paper is to propose a highly reliable learning model using various machine learning algorithms that can be applied to critical rolling stock components. This paper presents a model for railway rolling stock component fault diagnosis and conducts a mechanical failure diagnosis of motor components by applying the machine learning technique in order to ensure efficient maintenance support along with a data preprocessing plan for component fault diagnosis. This paper first defines a failure diagnosis model for rolling stock components. Function-based algorithms ANFIS and SMO were used as machine learning techniques for generating the failure diagnosis model. Two tree-based algorithms, RadomForest and CART, were also employed. In order to evaluate the performance of the algorithms to be used for diagnosing failures in motors as a critical railroad component, an experiment was carried out on 2 data sets with different classes (includes 6 classes and 3 class levels). According to the results of the experiment, the random forest algorithm, a tree-based machine learning technique, showed the best performance.

본 논문은 상대적으로 새로운 기법인 Parzen Density Estimation과 Multi-class SVM을 이용한 지능형 고장 탐색과 진단 방법을 제안하고 있다. 본 연구에서는 롤링 베어링을 대상으로 고장을 탐색하고 진단하기 위한 방법을 제안하는데 Parzen Density Estimation과 Multi-class SVM은 고장 클래스를 잘 표현할 수 있다. Parzen Density Estimation은 새로운 패턴 데이터의 거절과 알려진 데

The condition of the manufacturing process in a factory should be diagnosed and maintained efficiently because any unexpected disorder in the process will be reason to decrease the efficiency of the overall system. However, if an expert experienced in this system leaves, there will be a problem for the efficient process diagnosis and maintenance, because disorder diagnosis within the process is normally dependent on the expert's experience. This paper suggests a process diagnosis using data mining based on the collected data from the coil-spring manufacturing process. The rules are generated for the relations between the attributes of the process and the output class of the product using a decision tree after selecting the effective attributes. Using the generated rules from decision tree, the condition of the current process is diagnosed and the possible maintenance actions are identified to correct any abnormal condition. Then, the appropriate maintenance action is recommended using the decision network.

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.