A MKL based on-line prediction for gasholder level in steel industry

作者：Zhao, Jun^*; Liu, Ying; Zhang, Xiaoping; Wang, Wei

来源：Control Engineering Practice, 2012, 20(6): 629-641.

DOI：10.1016/j.conengprac.2012.03.003

• Gasholder level prediction
• Non-flat function estimation
• Multiple kernel learning
• Reduced gradient method
• Least square support vector machine

The real-time prediction for gasholder level is significant for gas scheduling in steel enterprises. In this study, we extended the least squares support vector regression (LSSVR) to multiple kernel learning (MKL) based on reduced gradient method. The MKL based LSSVR, using the optimal linear combination of kernels, improves the generalization of the model and reduces the training time. The experiments using the classical non-flat function and the practical problem shows that the proposed method achieves well performance and high computational efficiency. And, an application system based on the approach is developed and applied to the practice of Shanghai Baosteel Co. Ltd.

• 出版日期2012-6
• 单位大连理工大学; 天津科技大学