Abstract: An online 2-D changepoint detection algorithm for sensor-based fault detection, is proposed. The algorithm consists of a differential detector and a standard detector and can detect anomalies and meaningful changepoints while maintaining a low false-alarm rate. A new approach for determining a threshold is introduced and the efficiency of the algorithm is validated by an industrial example. It is thereby shown that the proposed algorithm can be used as an early warning indicator and prevent impending unit failures.

• Publication Date: 11-Dec-2015
• DOI: 10.15224/978-1-63248-077-4-15
• Views: 0
• Downloads: 0

Abstract: Non-metallic inclusions are one of the main problems in steel industry. They are formed by chemical reactions during the steel production process. Non-metallic inclusions have negative effects on mechanical properties of steel. Thus, the detection and the classification of them are very important for the product quality. In this paper, we have developed a sulfide type non-metallic inclusion detection and classification system employing image processing algorithms according to internationally accepted standards. In addition, the system has been analyzed using Gumbel Extreme Value Distributions to predict the expected extreme valued length of inclusion. The system has been tested with AISI 1040 steel as an example, and successful results have been obtained.

• Publication Date: 11-Dec-2015
• DOI: 10.15224/978-1-63248-077-4-16
• Views: 0
• Downloads: 0