A novel method for developing a reliable data driven soft sensor to improve the prediction accuracy of sulfur content in hydrodesulfurization(HDS) process was proposed. Therefore, an integrated approach using support ...A novel method for developing a reliable data driven soft sensor to improve the prediction accuracy of sulfur content in hydrodesulfurization(HDS) process was proposed. Therefore, an integrated approach using support vector regression(SVR) based on wavelet transform(WT) and principal component analysis(PCA) was used. Experimental data from the HDS setup were employed to validate the proposed model. The results reveal that the integrated WT-PCA with SVR model was able to increase the prediction accuracy of SVR model. Implementation of the proposed model delivers the best satisfactory predicting performance(EAARE=0.058 and R2=0.97) in comparison with SVR. The obtained results indicate that the proposed model is more reliable and more precise than the multiple linear regression(MLR), SVR and PCA-SVR.展开更多
针对产品的性能退化轨迹呈现为非线性特性,且个体的性能退化数据为小样本的情形,为了充分利用同类产品的性能退化数据进行特定个体的实时寿命预测,从研究退化轨迹相似性的角度出发,提出一类基于小波支持向量回归机(Wavelet support vect...针对产品的性能退化轨迹呈现为非线性特性,且个体的性能退化数据为小样本的情形,为了充分利用同类产品的性能退化数据进行特定个体的实时寿命预测,从研究退化轨迹相似性的角度出发,提出一类基于小波支持向量回归机(Wavelet support vector regression,WSVR)和模糊C均值(Fuzzy c-means,FCM)聚类的实时寿命预测方法.该方法分为离线和实时两个阶段:离线阶段先采用WSVR对同类产品的性能退化数据进行规范化处理,接着对规范化数据进行FCM聚类,然后,基于WSVR建立各聚类中心的退化轨迹模型;在实时阶段,针对特定个体的历史测量数据是否规范化,分别提出两种实时退化轨迹建模和寿命预测方法—隶属度加权法和误差加权法.最后,通过两个实例分析验证了所提方法的有效性.展开更多
为改进小麦冠层含氮率的高光谱测定模型,以正交试验筛选出小波去噪的最优参数组合(小波类型取haar,分解层数为5,阈值方案选择Fixed form threshold,噪声结构定为Unscaled white noise),并利用去噪后的小麦冠层光谱建立偏最小二乘回归(P...为改进小麦冠层含氮率的高光谱测定模型,以正交试验筛选出小波去噪的最优参数组合(小波类型取haar,分解层数为5,阈值方案选择Fixed form threshold,噪声结构定为Unscaled white noise),并利用去噪后的小麦冠层光谱建立偏最小二乘回归(PLS)模型,对不同预处理方法进行比较分析。发现采用小波去噪结合一阶导数能最有效消除原始光谱的背景信息,此时PLS模型校正集均方根误差(RMSEC)为0.260,预测集均方根误差(RMSEP)为0.288。对经一阶导数结合小波去噪后的光谱用主成分分析(PCA)进行降维,以前6个主成份为输入变量,建立最小二乘支撑向量机回归模型(LS-SVR),其RMSEC与RMSEP分别为0.154与0.259,具有比PLS模型更高的精度。结果表明:以小波去噪结合一阶导数去除小麦冠层反射光谱中的土壤背景信息以提高模型的精度是可行的,且LS-SVR是建模的优选方法。展开更多
文摘A novel method for developing a reliable data driven soft sensor to improve the prediction accuracy of sulfur content in hydrodesulfurization(HDS) process was proposed. Therefore, an integrated approach using support vector regression(SVR) based on wavelet transform(WT) and principal component analysis(PCA) was used. Experimental data from the HDS setup were employed to validate the proposed model. The results reveal that the integrated WT-PCA with SVR model was able to increase the prediction accuracy of SVR model. Implementation of the proposed model delivers the best satisfactory predicting performance(EAARE=0.058 and R2=0.97) in comparison with SVR. The obtained results indicate that the proposed model is more reliable and more precise than the multiple linear regression(MLR), SVR and PCA-SVR.
文摘针对产品的性能退化轨迹呈现为非线性特性,且个体的性能退化数据为小样本的情形,为了充分利用同类产品的性能退化数据进行特定个体的实时寿命预测,从研究退化轨迹相似性的角度出发,提出一类基于小波支持向量回归机(Wavelet support vector regression,WSVR)和模糊C均值(Fuzzy c-means,FCM)聚类的实时寿命预测方法.该方法分为离线和实时两个阶段:离线阶段先采用WSVR对同类产品的性能退化数据进行规范化处理,接着对规范化数据进行FCM聚类,然后,基于WSVR建立各聚类中心的退化轨迹模型;在实时阶段,针对特定个体的历史测量数据是否规范化,分别提出两种实时退化轨迹建模和寿命预测方法—隶属度加权法和误差加权法.最后,通过两个实例分析验证了所提方法的有效性.
文摘为改进小麦冠层含氮率的高光谱测定模型,以正交试验筛选出小波去噪的最优参数组合(小波类型取haar,分解层数为5,阈值方案选择Fixed form threshold,噪声结构定为Unscaled white noise),并利用去噪后的小麦冠层光谱建立偏最小二乘回归(PLS)模型,对不同预处理方法进行比较分析。发现采用小波去噪结合一阶导数能最有效消除原始光谱的背景信息,此时PLS模型校正集均方根误差(RMSEC)为0.260,预测集均方根误差(RMSEP)为0.288。对经一阶导数结合小波去噪后的光谱用主成分分析(PCA)进行降维,以前6个主成份为输入变量,建立最小二乘支撑向量机回归模型(LS-SVR),其RMSEC与RMSEP分别为0.154与0.259,具有比PLS模型更高的精度。结果表明:以小波去噪结合一阶导数去除小麦冠层反射光谱中的土壤背景信息以提高模型的精度是可行的,且LS-SVR是建模的优选方法。
