论文部分内容阅读
针对软测量模型在实际应用中遇到的问题,结合Ada Boost集成学习思想,提出适用于软测量回归的集成学习算法,以提高传统软测量模型的精度.为了克服模型更新技术对软测量实际应用的制约,将增量学习机制加入软测量集成建模中,使软测量模型具有在线实时更新的增量学习能力.对浆纱过程使用新方法建立上浆率软测量模型,并使用实际生产数据对模型进行检验,检验结果表明,该模型具有很好的预测精度,并能够较好地实现在线更新.
In view of the problems encountered in the practical application of soft sensor model, combined with Ada Boost integrated learning thinking, an integrated learning algorithm suitable for soft sensor regression is proposed to improve the accuracy of traditional soft sensor model.In order to overcome the practical application of model updating technology in soft sensor measurement , The incremental learning mechanism is added to the soft-sensing integrated modeling so that the soft-sensing model has online learning in real-time and incremental learning.A new method of sizing soft sensing model is established for the sizing process and the actual production data The test results show that the model has a good prediction accuracy and can be better online update.