• 대한기계학회논문집
• /
• 제17권7호
• /
• pp.1783-1793
• /
• 1993

Pattern recognition technique using fuzzy c-means algorithm and multilayer perceptron was applied to classify tool wear states in turning. The tool wear states were categorized into the three regions 'Initial', 'Normal', 'Severe' wear. The root mean square(RMS) value of acoustic emission(AE) and current signal was used for the classification of tool wear states. The simulation results showed that a fuzzy c-means algorithm was better than the conventional pattern recognition techniques for classifying ambiguous informations. And normalized RMS signal can provide good results for classifying tool wear. In addition, a fuzzy c-means algorithm(success rate for tool wear classification : 87%) is more efficient than the multilayer perceptron(success rate for tool wear classification : 70%).

• Journal of Biosystems Engineering
• /
• 제29권3호
• /
• pp.261-266
• /
• 2004

This study was Performed to classify the acoustic emission(AE) signal due to surface cracking and moisture movement in the flat-sawn boards of oak(Quercus Variablilis) during drying using the principal component analysis(PCA) and artificial neural network(ANN). To reduce the multicollinearity among AE parameters such as peak amplitude, ring-down count event duration, ring-down count divided by event duration, energy, rise time, and peak amplitude divided by rise time and to extract the significant AE parameters, correlation analysis was performed. Over 96 of the variance of AE parameters could be accounted for by the first and second principal components. An ANN analysis was successfully used to classify the Af signals into two patterns. The ANN classifier based on PCA appeared to be a promising tool to classify the AE signals from wood drying.

• 한국전기전자재료학회논문지
• /
• 제11권10호
• /
• pp.940-945
• /
• 1998

In this paper, we obtained the data, which is required in training the neural network and diagnosing the degradation degree, by introducing the AE detection that is effective method in ordinary degradation diagnosis on activation. Aa the results of generalization tests by appling neural network to the unknown AE patterns obtained from two kinds of specimen, firstly as to evaluate an objective performance of neural network, the recognition ration for no-void specimen and 1[mm] -void specimen are appeared to be 98.9% and 92.5%, respectively. Also, in the evaluation of the adaptability of neural network with a new type of 0.2[mm] -void specimen, it is confirmed that the result appears to be 64% of recognition ratio at 94% of confidence interval coefficient in expectation output 0.2. On the other hand, the recognition capability of the neural network was confirmed by data from no-void and 1[mm] void specimen. The results prove the promising possibility of the application of ANN to discriminate specific void affecting as main degradation source at partial discharge condition in insulator containing multi-void by accummulated data base.

• 융합신호처리학회논문지
• /
• 제20권2호
• /
• pp.78-83
• /
• 2019

소리 기반 기계 고장 진단은 기계의 음향 방출 신호에서 비정상적인 소리를 자동으로 감지하는 것이다. 수학적 모델을 사용하는 기존의 방법은 기계 시스템의 복잡성과 잡음과 같은 비선형 요인이 존재하기 때문에 기계 고장 진단이 어려웠다. 따라서 기계 고장 진단의 문제를 패턴 인식 문제로 해결하고자 한다. 본 논문에서 DWT와 인공신경망 기반 패턴 인식 기법을 이용한 자동화 기계 고장 진단 기법을 제안한다. 기계의 결함을 효과적으로 탐지하기 위해 DWT를 이용해 대역별 분해 후 최상위 고주파 부대역과 최하위 저주파 부대역을 제외한 나머지 부대역의 PSD를 구하여 인공신경망 기반 분류기의 입력으로 사용한다. 그 결과 본 연구에서 제안한 방법은 효과적으로 결함을 탐지할 뿐만 아니라 소리 기반의 다양한 자동 진단 시스템에도 효과적으로 활용될 수 있음을 보여준다.