基于MIPSO-LBFGS混合算法的色谱光谱分离方法

Chromatographic spectrum separation method based on MIPSO-LBFGS hybrid algorithm

高效液相色谱联用二极管阵列检测器(HPLC-DAD)数据的分离工作是为了从仪器产生的混合物中提取所有成分的光谱曲线和色谱峰曲线。为了提高其分离精度和缩短训练时长,基于特定信号生成器(SSG)和广义高斯参考曲线测量模型(GGRCM),提出了多目标粒子群-拟牛顿混合算法(MIPSO-LBFGS)对HPLCDAD数据的分离方法,可以在预先不知道化合物数量的情况下,同时分离出色谱和光谱。实验结果验证了MIPSO-LBFGS算法在保证算法的全局收敛性的同时,又能有效发挥局部寻优作用,并且改善了多目标粒子群算法后期收敛速度慢的缺陷。

High Performance Liquid Chromatography-Diode Array Detector(HPLC-DAD)data is to extract spectral curve and chromatographic peak curve of all components from the mixture produced by instrument.In order to improve the separation accuracy and shorten the training time,based on the Specific Signal Generator(SSG)and the Generalized Gaussian Reference Curve Measurement Model(GGRCM),a Multitarget Intermittent Particle Swarm Optimization-Quasi Newton hybrid algorithm(MIPSO-LBFGS)for the separation of HPLC-DAD data is proposed,which can separate the chromatography and spectrum at the same time without knowing the number of compounds in advance.The experimental results show that the MIPSO-LBFGS algorithm can not only ensure the global convergence of the algorithm,but also effectively play the role of local optimization,and improve the defect of slow convergence speed of multi-objective particle swarm optimization algorithm in the later stage.