Partial least squares (PLS) model maximizes the covariance between process variables and quality variables,making it widely used in quality-related fault detection.However,traditional PLS methods focus primarily on li...Partial least squares (PLS) model maximizes the covariance between process variables and quality variables,making it widely used in quality-related fault detection.However,traditional PLS methods focus primarily on linear processes,leading to poor performance in dynamic nonlinear processes.In this paper,a novel quality-related fault detection method,named DiCAE-PLS,is developed by combining dynamic-inner convolutional autoencoder with PLS.In the proposed DiCAE-PLS method,latent features are first extracted through dynamic-inner convolutional autoencoder (DiCAE) to capture process dynamics and nonlinearity from process variables.Then,a PLS model is established to build the relationship between the extracted latent features and the final product quality.To detect quality-related faults,Hotelling's T^(2) statistic is employed.The developed quality-related fault detection is applied to the widely used industrial benchmark of the Tennessee.展开更多
目的建立不同产地喜树果中9个成分含量同步检测方法,筛选影响其质量的差异标志物,并对其进行质量评价。方法对7省18个批次喜树果样品进行回流提取,提取物采用高效液相色谱法检测;采用正交偏最小二乘判别分析(Orthogonal partial least s...目的建立不同产地喜树果中9个成分含量同步检测方法,筛选影响其质量的差异标志物,并对其进行质量评价。方法对7省18个批次喜树果样品进行回流提取,提取物采用高效液相色谱法检测;采用正交偏最小二乘判别分析(Orthogonal partial least squares discriminant analysis,OPLS-DA)和加权逼近理想解排序(Technique for order preference by similarity to an ideal solution,TOPSIS)法建立喜树果质量优劣评价模型,对其质量差异性进行综合评价。结果3,4′-O-二甲基鞣花酸、丁香酸、10-羟基喜树碱、喜树碱、10-甲氧基喜树碱、三叶豆苷、短小蛇根草苷、金丝桃苷和喜果苷分别在0.51-12.75、0.23-5.75、3.21-80.25、4.45-111.25、1.88-47.00、0.41-10.25、2.05-51.25、0.34-8.50和7.95-198.75μg·mL^(-1)范围内线性关系良好(r>0.999),平均加样回收率96.95%-100.06%(RSD<2.0%);18批样品聚为3类;喜果苷、10-羟基喜树碱、喜树碱、10-甲氧基喜树碱和短小蛇根草苷可能是影响喜树果产品质量主要潜在标志物;加权TOPSIS法分析结果显示18批喜树果质量评价贴近度(Jb)在0.1090-0.7385,其中S14最大(0.7385)。结论建立了同时测定喜树果中9种成分含量的方法,操作简便、结果准确;采用OPLS-DA及加权TOPSIS法进行客观全面评价,可用于喜树果质量差异性评价。展开更多
The total nitrogen(TN)is a major factor contributing to eutrophication and is a crucial parameter in assessing surface water quality.Accurate and rapid methods are crucial for determining the TN content in water.Herei...The total nitrogen(TN)is a major factor contributing to eutrophication and is a crucial parameter in assessing surface water quality.Accurate and rapid methods are crucial for determining the TN content in water.Herein,a fast,highly sensitive,and pollution-free approach is proposed,which combines ultraviolet(UV)absorption spectroscopy with Bayesian optimized least squares support vector machine(LSSVM)for detecting TN content in water.Water samples collected from sampling points near the Yangtze River basin in Chongqing of China were analyzed using national standard methods to measure TN content as reference values.The prediction of TN content in water was achieved by integrating the UV absorption spectra of water samples with LSSVM.To make the model quickly and accurately select the optimal parameters to improve the accuracy of the prediction model,the Bayesian optimization(BO)algorithm was used to optimize the parameters of the LSSVM.Results show that the prediction model performs well in predicting TN concentration,with a high coefficient of prediction determination(R^(2)=0.9413)and a low root mean square error of prediction(RMSE=0.0779 mg/L).Comparative analysis with previous studies indicates that the model used in this paper achieves lower prediction errors and superior predictive performance.展开更多
Nuclear mass is an important property in both nuclear and astrophysics.In this study,we explore an improved mass model that incorporates a higher-order term of symmetry energy using algorithms.The sequential least squ...Nuclear mass is an important property in both nuclear and astrophysics.In this study,we explore an improved mass model that incorporates a higher-order term of symmetry energy using algorithms.The sequential least squares programming(SLSQP)algorithm augments the precision of this multinomial mass model by reducing the error from 1.863 MeV to 1.631 MeV.These algorithms were further examined using 200 sample mass formulae derived from theδE term of the E_(isospin) mass model.The SLSQP method exhibited superior performance compared to the other algorithms in terms of errors and convergence speed.This algorithm is advantageous for handling large-scale multiparameter optimization tasks in nuclear physics.展开更多
In the variance component estimation(VCE)of geodetic data,the problem of negative VCE is likely to occur.In the ordinary additive error model,there have been related studies to solve the problem of negative variance c...In the variance component estimation(VCE)of geodetic data,the problem of negative VCE is likely to occur.In the ordinary additive error model,there have been related studies to solve the problem of negative variance components.However,there is still no related research in the mixed additive and multiplicative random error model(MAMREM).Based on the MAMREM,this paper applies the nonnegative least squares variance component estimation(NNLS-VCE)algorithm to this model.The correlation formula and iterative algorithm of NNLS-VCE for MAMREM are derived.The problem of negative variance in VCE for MAMREM is solved.This paper uses the digital simulation example and the Digital Terrain Mode(DTM)to prove the proposed algorithm's validity.The experimental results demonstrated that the proposed algorithm can effectively correct the VCE in MAMREM when there is a negative VCE.展开更多
基金supported in part by the National Natural Science Foundation of China(62573387)the Natural Science Foundation of Zhejiang province,China(LY24F030004)the Fundamental Research Funds of Zhejiang Sci-Tech University(25222139-Y).
文摘Partial least squares (PLS) model maximizes the covariance between process variables and quality variables,making it widely used in quality-related fault detection.However,traditional PLS methods focus primarily on linear processes,leading to poor performance in dynamic nonlinear processes.In this paper,a novel quality-related fault detection method,named DiCAE-PLS,is developed by combining dynamic-inner convolutional autoencoder with PLS.In the proposed DiCAE-PLS method,latent features are first extracted through dynamic-inner convolutional autoencoder (DiCAE) to capture process dynamics and nonlinearity from process variables.Then,a PLS model is established to build the relationship between the extracted latent features and the final product quality.To detect quality-related faults,Hotelling's T^(2) statistic is employed.The developed quality-related fault detection is applied to the widely used industrial benchmark of the Tennessee.
文摘目的建立不同产地喜树果中9个成分含量同步检测方法,筛选影响其质量的差异标志物,并对其进行质量评价。方法对7省18个批次喜树果样品进行回流提取,提取物采用高效液相色谱法检测;采用正交偏最小二乘判别分析(Orthogonal partial least squares discriminant analysis,OPLS-DA)和加权逼近理想解排序(Technique for order preference by similarity to an ideal solution,TOPSIS)法建立喜树果质量优劣评价模型,对其质量差异性进行综合评价。结果3,4′-O-二甲基鞣花酸、丁香酸、10-羟基喜树碱、喜树碱、10-甲氧基喜树碱、三叶豆苷、短小蛇根草苷、金丝桃苷和喜果苷分别在0.51-12.75、0.23-5.75、3.21-80.25、4.45-111.25、1.88-47.00、0.41-10.25、2.05-51.25、0.34-8.50和7.95-198.75μg·mL^(-1)范围内线性关系良好(r>0.999),平均加样回收率96.95%-100.06%(RSD<2.0%);18批样品聚为3类;喜果苷、10-羟基喜树碱、喜树碱、10-甲氧基喜树碱和短小蛇根草苷可能是影响喜树果产品质量主要潜在标志物;加权TOPSIS法分析结果显示18批喜树果质量评价贴近度(Jb)在0.1090-0.7385,其中S14最大(0.7385)。结论建立了同时测定喜树果中9种成分含量的方法,操作简便、结果准确;采用OPLS-DA及加权TOPSIS法进行客观全面评价,可用于喜树果质量差异性评价。
基金supported by the National Natural Science Foundation of China(Nos.32171627 and 62105252)the Science and Technology Research Program of Chongqing Municipal Education Commission(No.KJZD-M202200602)the Hangzhou Science and Technology Development Project(No.202204T04).
文摘The total nitrogen(TN)is a major factor contributing to eutrophication and is a crucial parameter in assessing surface water quality.Accurate and rapid methods are crucial for determining the TN content in water.Herein,a fast,highly sensitive,and pollution-free approach is proposed,which combines ultraviolet(UV)absorption spectroscopy with Bayesian optimized least squares support vector machine(LSSVM)for detecting TN content in water.Water samples collected from sampling points near the Yangtze River basin in Chongqing of China were analyzed using national standard methods to measure TN content as reference values.The prediction of TN content in water was achieved by integrating the UV absorption spectra of water samples with LSSVM.To make the model quickly and accurately select the optimal parameters to improve the accuracy of the prediction model,the Bayesian optimization(BO)algorithm was used to optimize the parameters of the LSSVM.Results show that the prediction model performs well in predicting TN concentration,with a high coefficient of prediction determination(R^(2)=0.9413)and a low root mean square error of prediction(RMSE=0.0779 mg/L).Comparative analysis with previous studies indicates that the model used in this paper achieves lower prediction errors and superior predictive performance.
基金supported by the National Natural Science Foundation of China(Nos.U2267205 and 12475124)a ZSTU intramural grant(22062267-Y)Excellent Graduate Thesis Cultivation Fund(LW-YP2024011).
文摘Nuclear mass is an important property in both nuclear and astrophysics.In this study,we explore an improved mass model that incorporates a higher-order term of symmetry energy using algorithms.The sequential least squares programming(SLSQP)algorithm augments the precision of this multinomial mass model by reducing the error from 1.863 MeV to 1.631 MeV.These algorithms were further examined using 200 sample mass formulae derived from theδE term of the E_(isospin) mass model.The SLSQP method exhibited superior performance compared to the other algorithms in terms of errors and convergence speed.This algorithm is advantageous for handling large-scale multiparameter optimization tasks in nuclear physics.
基金supported by the National Natural Science Foundation of China(No.42174011)。
文摘In the variance component estimation(VCE)of geodetic data,the problem of negative VCE is likely to occur.In the ordinary additive error model,there have been related studies to solve the problem of negative variance components.However,there is still no related research in the mixed additive and multiplicative random error model(MAMREM).Based on the MAMREM,this paper applies the nonnegative least squares variance component estimation(NNLS-VCE)algorithm to this model.The correlation formula and iterative algorithm of NNLS-VCE for MAMREM are derived.The problem of negative variance in VCE for MAMREM is solved.This paper uses the digital simulation example and the Digital Terrain Mode(DTM)to prove the proposed algorithm's validity.The experimental results demonstrated that the proposed algorithm can effectively correct the VCE in MAMREM when there is a negative VCE.
