基于KPCA-PSO-ELM算法的地表水化学需氧量紫外-可见吸收光谱检测研究

Study on the Detection Method of COD in Surface Water Based on UV-Vis Spectroscopy

化学需氧量(COD)是水质检测重要指标之一,反映水体有机物含量。传统的COD化学检测方法存在操作繁琐,等待时间长,二次污染等缺点。紫外-可见吸收光谱法是目前水体化学需氧量检测中应用最为广泛的方法之一,具有检测快速、无污染等特点。为了满足地表水化学需氧量快速、实时、在线监测等要求,采用紫外-可见吸收光谱进行测量,提出了内核主成分分析(KPCA)结合粒子群优化极限学习机(PSO-ELM)预测模型,满足当前对地表水化学需氧量快速、实时监测的要求。对光谱进行Savitzky-Golay(SG)滤波以降低随机噪声的影响;用积分光谱代替原光谱,以降低信号波动带来的影响;再将得到的光谱信息归一化,消除不同光谱数据量纲的影响。将预处理后的数据利用KPCA算法将全光谱数据压缩为5个特征,有效解决光谱信息冗余的问题;采用PSO算法对ELM的权重和偏置进行优化极大提高了模型的精度。对217个河流、长江及支流、湖库等地表水样本按照7∶3随机划分成训练集和测试集,并进行建模测试,其中训练集拟合优度(R2)为0.930 2、均方根误差(RMSE)为0.363 0 mg·L^(-1)、测试集拟合优度R2为0.931 9、均方根误差(RMSE)为0.400 7 mg·L^(-1)。为了验证提出的基于KPCA全光谱数据压缩方法对预测模型的提升效果,分别对比了主成分分析(PCA)、连续投影算法(SPA)、套索回归(LASSO)等特征处理算法。PCA-PSO-ELM模型的RMSE为0.715 1 mg·L^(-1)、 SPA-PSO-ELM模型的RMSE为0.473 7 mg·L^(-1)、 LASSO-PSO-ELM模型的RMSE为0.412 6 mg·L^(-1), KPCA-PSO-ELM模型较上述三种模型,RMSE分别降低了78.46%、 18.22%、 2.97%,结果表明KPCA是一种高效的光谱降维算法,能够有效消除光谱冗余信息,提升模型预测精度。基于KPCA-PSO-ELM预测模型结合紫外-可见吸收光谱可以实现对地表水COD快速、实时检测,为在线COD检测场景提供方法支撑。

Chemical Oxygen Demand(COD)is one of the important indicators of water quality detection,reflecting the organic content of water.Traditional chemical detection methods for COD have disadvantages,such as complicated operation,long waiting times and secondary pollution.UV-Vis spectrometer has been one of the most widely acceptable methods for detecting COD because of its rapidity detection and no pollution.In order to satisfy the requirement of detecting COD of surface water rapidity,real-time and on-line,a model of kernel principal component analysis(KPCA)combined with particle swarm optimization extreme learning machine(PSO-ELM)was developed for COD prediction of surface water based on UV-Vis spectrometer.Savitzky-Golay filtering was employed to smooth the spectrum.The integral spectrum was substituted for the processed spectrum to decrease the impact of fluctuations.In the meantime,spectrum normalisation was used to eliminate the impact caused by different dimensions of spectrum data.The KPAC algorithm was used to compress the whole spectrum into 5 features,effectively solving the spectral information redundancy problem.PSO algorithm was used to optimize the weight and bias of ELM,which improved the model s accuracy.217 surface water samples,such as rivers,Yangtze River,lakes and reservoirs,were randomly divided into training sets and test sets according to 7∶3,and modeling tests were conducted.The R-squared(R 2)of the training set was 0.9302,the root mean square error(RMSE)of the training set was 0.3630 mg·L^(-1),the R-squared(R 2)of the test set was 0.9319,and the root mean square error(RMSE)of test set was 0.4007 mg·L^(-1).In order to verify the improvement of the KPCA based on the full spectrum compression method,data Compression algorithms such as principal component analysis(PCA),successive projection algorithm(SPA)and Lassoregression(LASSO)were compared.The RMSE of PCA-PSO-ELM model,SPA-PSO-ELM model and LASSO-PSO-ELM model was 0.7151,0.4737 and 0.4126 mg·L^(-1),respectively.It was shown that the results of the KPCA-PSO-ELM model were better than the above three models,and RMSE decreased by 78.46%,18.22%and 2.97%,showing that KPCA is an efficient spectral dimension reduction algorithm,which can effectively eliminate spectral redundant information and improve the prediction accuracy of the model.The KPCA-PSO-ELM proposed can realize fast and real-time monitoring of COD in surface water,which can provide algorithm reference for the scene of online water quality monitoring of rapid pollution.As a basic chemical oxygen demand detection research,it provides method reference for online monitoring scenarios for chemical oxygen demand.