The Study on Computational Intelligence Based Fault Diagnosis and Prediction of Rotary Kiln Refractory
2018
Hochschulschrift
Zugriff:
106
The rotary kiln is a pyroprocessing device that is the core piece of equipment in a cement plant. The most crucial component of the kiln is its steel shell. The interior of the kiln’s steel shell is protected by refractory bricks that insulate it from the high temperatures inside the kiln as well as protect it from the corrosive properties of the processed material. To maintain and extend the life of the refractory brick, forming an effective coating on its surface is necessary. If coating collapse occurs and is significantly large, the refractory bricks can be damaged, requiring a shutdown; the cost of production loss and maintenance for each shutdown is approximately NT$30 million. Modern cement plants install a kiln shell temperature monitoring system (KSTMS) to monitor the temperature of the entire rotary kiln shell. Regarding the repair work required after refractory brick failure, in addition to replacing the damaged refractory bricks, only manual inspection of other undamaged refractory bricks increases the risk of downtime. Therefore, this dissertation proposes a Hilbert–Huang transform–based KSTMS time series data analysis method to determine the relationship between the time at which refractory bricks fall off and the frequency variation in temperature. The information provided can be used as a reference for the health level of rotary kiln refractory bricks. In addition, cement plants rely on manual observation of the variations in the current trend of the rotary kiln drive motor to determine whether coating collapse has occurred. Therefore, this study combined empirical mode decomposition with computational intelligence to develop an intelligent coating collapse detection method. It easily identifies the occurrence of coating collapse, solves problems caused by personnel negligence or omission, and automatically searches for the location of the coating collapse. The proposed method can be applied to analyzing the correlations between coating collapse and refractory brick falling in the future to predict the health index of refractory bricks, thereby improving the alarm function for abnormal refractory bricks and the reliability and availability of rotary kiln equipment as well as reducing the production losses caused by downtime and maintenance.
Titel: |
The Study on Computational Intelligence Based Fault Diagnosis and Prediction of Rotary Kiln Refractory
|
---|---|
Autor/in / Beteiligte Person: | Yang, Ming-Chin ; 楊明欽 |
Link: | |
Veröffentlichung: | 2018 |
Medientyp: | Hochschulschrift |
Sonstiges: |
|