• Journal of Information Processing Systems
• /
• 제17권2호
• /
• pp.242-252
• /
• 2021

Following the intuition that the local information in time instances is hardly incorporated into the posterior sequence in long short-term memory (LSTM), this paper proposes an attention augmented mechanism for fault diagnosis of the complex chemical process data. Unlike conventional fault diagnosis and classification methods, an attention mechanism layer architecture is introduced to detect and focus on local temporal information. The augmented deep network results preserve each local instance's importance and contribution and allow the interpretable feature representation and classification simultaneously. The comprehensive comparative analyses demonstrate that the developed model has a high-quality fault classification rate of 95.49%, on average. The results are comparable to those obtained using various other techniques for the Tennessee Eastman benchmark process.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2004년도 ICEIC The International Conference on Electronics Informations and Communications
• /
• pp.371-375
• /
• 2004

Fault diagnosis is one of the most studied problems in process engineering. Recently, great research interest has been devoted to approaches that use classification methods to detect faults. This paper presents an application of a newly developed classification method - support vector machines - for fault diagnosis in an industrial case. A real set of operation data of a motor pump was used to train and test the support vector machines. The experiment results show that the support vector machines give higher correct detection rate of faults in comparison to rule-based diagnostics. In addition, the studied method can work with fewer training instances, what is important for online diagnostics.

• Journal of Power Electronics
• /
• 제9권3호
• /
• pp.377-385
• /
• 2009

In this paper, a diagnosis method for switch open-circuit faults in three-phase PWM inverters is proposed, which employs support vector machine (SVM) as classifying method. At first, a discrete wavelet transform (DWT) is used to detect a discontinuity of currents due to the fault, and then the features for fault diagnosis are extracted. Next, these features are employed as inputs for the SVM training. After training, the SVM produces an optimized boundary which is used identifying the fault. Finally, the fault classification is performed online with instantaneous features. The experimental results have verified the validity of the proposed estimation algorithm.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.539-542
• /
• 2003

A motor is the workhorse of our industry. The issues of preventive and condition-based maintenance, online monitoring, system fault detection, diagnosis, and prognosis are of increasing importance. Different internal motor faults (e.g., inter-turn short circuits, broken bearings, broken rotor bars) along with external motor faults (e.g., phase failure, mechanical overload, blocked rotor) are expected to happen sooner or later. This paper introduces the fault detection technique of induction motors based upon the stator current. The fault motors have rotor bar broken or rotor unbalance defect, respectively. The stator currents are measured by the current meters and stored by the time domain. The time domain is not suitable to represent the current signals, so the frequency domain is applied to display the signals. The Fourier Transformer is used for the conversion of the signal. After the conversion of the signals, the features of the signals have to be extracted by the signal processing methods like a wavelet analysis, a spectrum analysis, etc. The discovered features are entered to the pattern classification model such as a neural network model, a polynomial neural network, a fuzzy inference model, etc. This paper describes the fault detection results that use wavelet decomposition. The wavelet analysis is very useful method for the time and frequency domain each. Also it is powerful method to detect the features in the signals.

• 한국지능시스템학회논문지
• /
• 제18권5호
• /
• pp.718-723
• /
• 2008

베어링은 각종 설비에서 활용되는 중요한 기계요소 중 하나이다. 설비고장의 상당수는 베어링의 결함이나 파손에 기인하고 있다. 따라서 베어링에 대한 온라인모니터링기술은 설비의 정지를 예방하고 손실을 줄이는 데 필수적이다. 본 논문은 진동 신호를 이용하여 베어링의 상태를 예측하기 위한 온라인모니터링에 대해 연구한다. 프로파일로 주어지는 진동신호는 이산 웨이블릿 변환을 통해 분석되고, 분해수준별 웨이블릿 계수로부터 얻은 통계적 특징 중 유의한 것을 선별하고자 분산분석 (ANOVA)을 이용한다. 선별된 특징벡터는 Support Vector Machine (SVM)의 입력이 되는 데, 본 논문에서는 다중클래스 분류문제를 다루기 위한 계층적 SVM 트리를 제안한다. 수치실험 결과, 제안된 방법은 베어링의 결함을 분류하는 데 우수한 성능을 갖는 것으로 나타났다.