A training algorithm for optimal margin classifiers
COLT '92 Proceedings of the fifth annual workshop on Computational learning theory
The nature of statistical learning theory
The nature of statistical learning theory
Machine Learning
Neural Computation
Incorporating expert knowledge when estimating parameters of the proportional hazards model
RAMS '06 Proceedings of the RAMS '06. Annual Reliability and Maintainability Symposium, 2006.
| Hi-index | 0.00 |
Kyushu Electric Power CO.,Inc. collects different sensor data and weather information to maintain the safety of hydroelectric power plants while the plants are running. It is very rare to occur trouble condition in equipment of hydroelectric power plants. It is hard to construct experimental power generation plant and hydroelectric power plant to collect the trouble condition data. The cost is too high. In this situation, we have to find trouble condition sign. In this paper, we propose a trouble condition sign discovery method, which consists of two detection stages. In the first stage, we can discover trouble condition signs, which are different from usual condition data. And in the second stage, we can monitor aging degradation. Our proposed method is based on a one class support vector machine and a normal support vector machine. This paper shows experimental results of detecting trouble condition signs of bearing vibration from the collected different sensor data by our proposed method. The experimental results show that our proposed method can find trouble condition signs, which are different from usual condition data, and monitor aging degradation. Therefore, the proposed method may be useful for trouble condition signs discovery for hydroelectric power plants.