论文部分内容阅读
针对生物发酵过程中一些生物参量难以用仪表进行在线检测的问题,提出一种基于连续隐Markov模型(CHMM)的发酵过程软测量建模方法.为减少建模过程的计算量,提出了改进最小分类误差准则,用于CHMM软测量模型参数估计.为避免软测量结果在发酵过程监测与控制实际应用中存在的盲目性,提出了在线评价软测量结果可靠性的可信度评价指标.实验结果表明了所提出方法的有效性以及可信度评价指标的实际意义.
Aiming at the problem that it is difficult to measure some biological parameters on-line with the instrument during the process of bio-fermentation, a soft-sensing modeling method based on continuous hidden Markov model (CHMM) is proposed. In order to reduce the computational complexity of the modeling process, Classification error criterion for parameter estimation of CHMM soft measurement model.In order to avoid the blindness of soft measurement results in the practical application of monitoring and control of fermentation process, a reliability evaluation index for on-line evaluation of the reliability of soft measurement results is proposed.Experimental results It shows the effectiveness of the proposed method and the practical significance of the credibility evaluation index.