• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권5호
• /
• pp.1186-1207
• /
• 2024

Bearings are one of the main components of mechanical equipment and one of the primary components prone to faults. Therefore, conducting fault diagnosis on bearings is a key issue in mechanical equipment research. Belief rule base (BRB) is essentially an expert system that effectively integrates qualitative and quantitative information, demonstrating excellent performance in fault diagnosis. However, class imbalance often occurs in the diagnosis task, which poses challenges to the diagnosis. Models with interpretability can enhance decision-makers' trust in the output results. However, the randomness in the optimization process can undermine interpretability, thereby reducing the level of trustworthiness in the results. Therefore, a hierarchical BRB model based on extreme gradient boosting (XGBoost) feature selection with interpretability (HFS-IBRB) is proposed in this paper. Utilizing a main BRB alongside multiple sub-BRBs allows for the conversion of a multi-classification challenge into several distinct binary classification tasks, thereby leading to enhanced accuracy. By incorporating interpretability constraints into the model, interpretability is effectively ensured. Finally, the case study of the actual dataset of bearing fault diagnosis demonstrates the ability of the HFS-IBRB model to perform accurate and interpretable diagnosis.

• Journal of Power Electronics
• /
• 제16권4호
• /
• pp.1415-1425
• /
• 2016

This paper presents a new approach for fault diagnosis in three-level neutral point clamped inverters. The proposed method is based on the average values of the positive and negative parts of normalized output currents. This method is capable of detecting and locating multiple open-circuit faults in the controlled power switches of converters in half of a fundamental period of those currents. The implementation of this diagnostic approach only requires two output currents of the inverter. Therefore, no additional sensors are needed other than the ones already used by the control system of a drive based on this type of converter. Moreover, through the normalization of currents, the diagnosis is independent of the load level of the converter. The performance and effectiveness of the proposed diagnostic technique are validated by experimental results obtained under steady-state and transient conditions.

• Journal of Electrical Engineering and information Science
• /
• 제2권5호
• /
• pp.45-50
• /
• 1997

This paper present an advanced fault diagnosis expert system to assist the operators at local control center. The system utilizes all th information available in a local control center for the better diagnostic performance. The major feature of the system is dealing with multiple faults diagnosis based on the certainty factor method for the reasoning process. the overall performance and the generality are also enhanced by utilizing the general topological knowledge. ASCADA simulator is also developed for he test and demonstration.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.852-855
• /
• 1997

In this paper, the vibration diagnosis system of a rotating machinery is introduced, in which the vibration signals of multiple accelerometers and displacement sensors are used combinedly as input parameters and their characteristics of the vibration response and mutual relationships between each sensor signal are considered to improve the reliability of the diagnosis system. The fuzzy logic is utilized for inferencing the fault from the vibration signal patterns.

• 한국정밀공학회지
• /
• 제22권10호
• /
• pp.80-89
• /
• 2005

In this paper, time-frequency analysis using wavelet packet transform and advanced-MDSA (Multiple Dimensional Spectral Analysis) which based on wavelet packet transform is applied fur fault source identification and diagnosis of early detection of fault non-stationary sound/vibration signals. This method is analyzing the signal in the plane of instantaneous time and instantaneous frequency. The results of ordinary coherence function, which obtained by wavelet packet analysis, showed the possibility of early fault detection by analysis at the instantaneous time. So, by checking the coherence function trend, it is possible to detect which signal contains the major fault signal and to know how much the system is damaged. Finally, It is impossible to monitor the system is damaged or undamaged by using conventional method, because crest factor is almost constant under the range of magnitude of fault signal as its approach to normal signal. However instantaneous coherence function showed that a little change of fault signal is possible to monitor the system condition. And it is possible to predict the maintenance time by condition based maintenance for any stationary or non-stationary signals.

• Nuclear Engineering and Technology
• /
• 제27권5호
• /
• pp.670-686
• /
• 1995

본 논문의 저자는 원자력 발전소와 같은 복잡한 대규모의 시스템의 실시간 고장진단 방법을 1994년 IEEE TNS Vol. 41, No. 4 호[1］에 발표하였다. 이번 논문에서는 고장전파모델(FPM)로서 같은 'Timed SDG Model' 를 사용하고 있으나 고장전파시간( FPT)을 에메논리 개념을 이용하여 정확하게 구하기 어려운 FPT을 실질적으로 이용할 수 있도록 했으며, 또한 고장전파확율(FPP)개념을 도입하여 하나이상의 고장원인 절점 (Node)들을 절점고장율과 더불어, 보다 효과적으로 판별할 수 있도록 했다. 또 FPM내에서 고장의 전파확율를 고려함으로서 보다 실질적인 고장 진단방법을 제시하였으며 본 제안된 방법을 고리 원전 2호기 1차계통에 적용하여 1차계통 FPM내의 각 FPP이 ‘1’인 경우에 한하여 그 성능을 입증하여 보았다.

• Journal of Electrical Engineering and Technology
• /
• 제13권1호
• /
• pp.89-96
• /
• 2018

When a fault occurs in a power system, the existing analytic models for the power system fault diagnosis could generate multiple solutions under the condition of one or more protective relays (PRs) and/or circuit breakers (CBs) malfunctioning, and/or an alarm or alarms of these PRs and/or CBs failing. Therefore, this paper presents an improved analytic model addressing the above problem. It takes into account the interaction between the uncertainty involved with PR operation and CB tripping and the uncertainty of the alarm reception, which makes the analytic model more reasonable. In addition, the existing analytic models apply the penalty function method to deal with constraints, which is influenced by the artificial setting of the penalty factor. In order to avoid the penalty factor's effects, this paper transforms constraints into an objective function, and then puts forward an improved immune clonal multi-objective optimization algorithm to solve the optimal solution. Finally, the cases of the power system fault diagnosis are served for demonstrating the feasibility and efficiency of the proposed model and method.

• 전자공학회논문지B
• /
• 제32B권12호
• /
• pp.1687-1696
• /
• 1995

An integrated fault diagnosis system for heterogeneous manufacturing environments is developed. This system has a contrast with existing diagnosis systems in the respect that they are mostly for diagnosing faults on individual machines. In addition to the usual (e.g., audio, electrical) diagnostic signals, the characteristics of products from the machines are considered as the unifying diagnostic parameters among heterogeneous machines in the diagnosis. The system is composed of a knowledge representation scheme and a diagnostic query processing mechanism. Its knowledge representation scheme allows the diagnostic knowledges from heterogeneous unit diagnostic systems to be uniformly expressed in terms of the causal relations among relevant data items. It is flexible in the sense that causes for one relation can be effects for another may be reflected on our knowledge representation scheme. The diagnosis mechanism is based on a probabilistic inferencing method. This probablistic diagnosis mechanism provides more general diagnosis than existing ones in that it accommodates multiple causes and takes complication among causes into account. These scheme and mechanism are applied to a typical example to demonstrate how our system works.

• 한국지능시스템학회논문지
• /
• 제15권6호
• /
• pp.673-681
• /
• 2005

원자력 발전소는 안정성 및 신뢰성 확보가 가장 중요하므로 고장의 감지 및 진단 시스템의 개발은 원전 자체가 구축하고 있: 다중의 하드웨어 중첩도(hardware redundancy)에도 불구하고 가장 중요한 문제로 취급되고 있다. 본 논문에서는 원저 PWR 증기발생기에서 발생한 고장을 진단하기 위한 알고리듬의 개발을 위해 시스템에서 발생한 고장을 감지하고 분류할 수 있는 ART2 시경회로망 기반 고장진단방법을 제안한다. 고장진단시스템은 발생한 고장을 감지하기 위한 고장감지부, 변화된 시스템파라미터를 추정하기 위한 파라미터 추정부 및 발생한 고장의 종류를 알아내기 위한 고장분류부로 구성된다. 고장분류부는 여러 경계인수를 갖는 ART2(adaptive resonance theory 2) 신경회로망을 이용한 고장분류기로 구성된다. 제안한 고장진단 알고리듬을 증기발생기의 고장진단문제에 적용하여 성능을 확인하였다.

• Journal of Electrical Engineering and Technology
• /
• 제12권2호
• /
• pp.830-839
• /
• 2017

Support vector machine (SVM) is introduced as an effective fault diagnosis technique based on dissolved gases analysis (DGA) for oil-immersed transformers with maximum generalization ability; however, the applicability of the SVM is highly affected due to the difficulty of selecting the SVM parameters appropriately. Therefore, a novel approach combing SVM with improved imperialist competitive algorithm (IICA) for fault diagnosis of oil-immersed transformers was proposed in the paper. The improved ICA, which is proved to be an effective optimization approach, is employed to optimize the parameters of SVM. Cross validation and normalizations were applied in the training processes of SVM and the trained SVM model with the optimized parameters was established for fault diagnosis of oil-immersed transformers. Three classification benchmark sets were studied based on particle swarm optimization SVM (PSOSVM) and IICASVM with four multiple classification schemes to select the best scheme for transformer fault diagnosis. The results show that the proposed model can obtain higher diagnosis accuracy than other methods. The comparisons confirm that the proposed model is an effective approach for classification problems.