School of Electrical and Information Engineering, Jiangsu University, Zhenjiang, 212013, Jiangsu, China.
School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, 212013, Jiangsu, China.
Sci Rep. 2020 Jul 15;10(1):11630. doi: 10.1038/s41598-020-68081-4.
The L-lysine fermentation process is a complex, nonlinear, dynamic biochemical reaction process with multiple inputs and multiple outputs. There is a complex nonlinear dynamic relationship between each state variable. Some key variables in the fermentation process that directly reflect the quality of the fermentation cannot be measured online in real-time which greatly limits the application of advanced control technology in biochemical processes. This work introduces a hybrid ICS-MLSSVM soft-sensor modeling method to realize the online detection of key biochemical variables (cell concentration, substrate concentration, product concentration) of the L-lysine fermentation process. First of all, a multi-output least squares support vector machine regressor (MLSSVM) model is constructed based on the multi-input and multi-output characteristics of L-lysine fermentation process. Then, important parameters ([Formula: see text], [Formula: see text], [Formula: see text]) of MLSSVM model are optimized by using the Improved Cuckoo Search (ICS) optimization algorithm. In the end, the hybrid ICS-MLSSVM soft-sensor model is developed by using optimized model parameter values, and the key biochemical variables of the L-lysine fermentation process are realized online. The simulation results confirm that the proposed regression model can accurately predict the key biochemical variables. Furthermore, the hybrid ICS-MLSSVM soft-sensor model is better than the MLSSVM soft-sensor model based on standard CS (CS-MLSSVM), particle swarm optimization (PSO) algorithm (PSO-MLSSVM) and genetic algorithm (GA-MLSSVM) in prediction accuracy and adaptability.
赖氨酸发酵过程是一个复杂的、非线性的、动态的生化反应过程，具有多个输入和多个输出。各状态变量之间存在复杂的非线性动态关系。发酵过程中的一些关键变量不能在线实时测量，这极大地限制了先进控制技术在生化过程中的应用。本工作提出了一种混合 ICS-MLSSVM 软测量建模方法，实现了赖氨酸发酵过程中关键生化变量（细胞浓度、基质浓度、产物浓度）的在线检测。首先，基于赖氨酸发酵过程的多输入多输出特点，构建了多输出最小二乘支持向量机回归器（MLSSVM）模型。然后，利用改进的布谷鸟搜索（ICS）优化算法对 MLSSVM 模型的重要参数（[公式：见文本]、[公式：见文本]、[公式：见文本]）进行优化。最后，利用优化后的模型参数值，开发了混合 ICS-MLSSVM 软测量模型，实现了赖氨酸发酵过程的关键生化变量的在线检测。仿真结果证实了所提出的回归模型能够准确预测关键生化变量。此外，与标准布谷鸟搜索（CS）算法（CS-MLSSVM）、粒子群优化（PSO）算法（PSO-MLSSVM）和遗传算法（GA-MLSSVM）相比，混合 ICS-MLSSVM 软测量模型在预测精度和适应性方面均具有优势。
