Key Laboratory of Agricultural Measurement and Control Technology and Equipment for Mechanical Industrial Facilities, School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, China.
Sensors (Basel). 2024 May 9;24(10):3017. doi: 10.3390/s24103017.
This paper proposes a novel soft sensor modeling approach, MIC-TCA-INGO-LSSVM, to address the decline in performance of soft sensor models during the fermentation process of , caused by changes in working conditions. Initially, the transfer component analysis (TCA) method is utilized to minimize the differences in data distribution across various working conditions. Subsequently, a least squares support vector machine (LSSVM) model is constructed using the dataset adapted by TCA, and strategies for improving the northern goshawk optimization (INGO) algorithm are proposed to optimize the parameters of the LSSVM model. Finally, to further enhance the model's generalization ability and prediction accuracy, considering the transfer of knowledge from multiple-source working conditions, a sub-model weighted ensemble scheme is proposed based on the maximum information coefficient (MIC) algorithm. The proposed soft sensor model is employed to predict cell and product concentrations during the fermentation process of . Simulation results indicate that the of the INGO-LSSVM model in predicting cell and product concentrations is reduced by 47.3% and 42.1%, respectively, compared to the NGO-LSSVM model. Additionally, TCA significantly enhances the model's adaptability when working conditions change. Moreover, the soft sensor model based on TCA and the MIC-weighted ensemble method achieves a reduction of 41.6% and 31.3% in the for predicting cell and product concentrations, respectively, compared to the single-source condition transfer model TCA-INGO-LSSVM. These results demonstrate the high reliability and predictive performance of the proposed soft sensor method under varying working conditions.
本文提出了一种新的软测量建模方法 MIC-TCA-INGO-LSSVM，用于解决 发酵过程中由于工作条件变化导致软测量模型性能下降的问题。首先，利用传递成分分析（TCA）方法最小化不同工作条件下数据分布的差异。然后，使用 TCA 自适应数据集构建最小二乘支持向量机（LSSVM）模型，并提出了改进北方鹰优化（INGO）算法的策略来优化 LSSVM 模型的参数。最后，为了进一步提高模型的泛化能力和预测精度，考虑从多源工作条件转移知识，提出了一种基于最大信息系数（MIC）算法的子模型加权集成方案。所提出的软测量模型用于预测 发酵过程中的细胞和产物浓度。仿真结果表明，与 NGO-LSSVM 模型相比，INGO-LSSVM 模型在预测细胞和产物浓度方面的均方根误差分别降低了 47.3%和 42.1%。此外，TCA 显著提高了模型在工作条件变化时的适应性。此外，基于 TCA 和 MIC 加权集成方法的软传感器模型在预测细胞和产物浓度方面的均方根误差分别降低了 41.6%和 31.3%，与单源条件转移模型 TCA-INGO-LSSVM 相比。这些结果表明，所提出的软测量方法在不同工作条件下具有较高的可靠性和预测性能。
