Soft sensor is an efficacious solution to predict the hard-to-measure target variable by using the process variables.In practical application scenarios, however, the feedback cycle of target variable is usually larger...Soft sensor is an efficacious solution to predict the hard-to-measure target variable by using the process variables.In practical application scenarios, however, the feedback cycle of target variable is usually larger than that of the process variables, which causes the deficiency of prediction errors. Consequently soft sensor cannot be calibrated timely and deteriorates. We proposed a soft sensor calibration method by using Just-in-time modeling and Ada Boost learning method. A moving window consisting of a primary part and a secondary part is constructed.The primary part is made of history data from certain number of constant feedback cycles of target variable and the secondary part includes some coarse target values estimated initially by Just-in-time modeling during the latest feedback cycle of target variable. The data set of the whole moving window is processed by Ada Boost learning method to build an auxiliary estimation model and then target variable values of the latest corresponding feedback cycle are reestimated. Finally the soft sensor model is calibrated by using the reestimated target variable values when the target feedback is unavailable; otherwise using the feedback value. The feasibility and effectiveness of the proposed calibration method is tested and verified through a series of comparative experiments on a pH neutralization facility in our laboratory.展开更多
This paper deals with investigations on corrosion of marble SO2. We have simulated oxidation of SO2 by photochemical process in the atmosphere. The experiments indicate that formation of SO3 aerosols is related to the...This paper deals with investigations on corrosion of marble SO2. We have simulated oxidation of SO2 by photochemical process in the atmosphere. The experiments indicate that formation of SO3 aerosols is related to the concentration of SO2, the UV light intensity, the time of irradiation and the humidity of the air. The corrosion feature of surfaces of the marble and the depth profiles of sulphur were obtained by SEM (Scanning electron microscope), EDXA (Energy-dispersive X-ray analyzer) and SIMS (Secondary ion mass spectrometer). The results of experiments show the corrosive extent of marble depends on its compositions and microareas of marble, which contain lower silicon content can be easily corroded by SO2.展开更多
基金Supported by the National Basic Research Program of China(2012CB720500)
文摘Soft sensor is an efficacious solution to predict the hard-to-measure target variable by using the process variables.In practical application scenarios, however, the feedback cycle of target variable is usually larger than that of the process variables, which causes the deficiency of prediction errors. Consequently soft sensor cannot be calibrated timely and deteriorates. We proposed a soft sensor calibration method by using Just-in-time modeling and Ada Boost learning method. A moving window consisting of a primary part and a secondary part is constructed.The primary part is made of history data from certain number of constant feedback cycles of target variable and the secondary part includes some coarse target values estimated initially by Just-in-time modeling during the latest feedback cycle of target variable. The data set of the whole moving window is processed by Ada Boost learning method to build an auxiliary estimation model and then target variable values of the latest corresponding feedback cycle are reestimated. Finally the soft sensor model is calibrated by using the reestimated target variable values when the target feedback is unavailable; otherwise using the feedback value. The feasibility and effectiveness of the proposed calibration method is tested and verified through a series of comparative experiments on a pH neutralization facility in our laboratory.
文摘This paper deals with investigations on corrosion of marble SO2. We have simulated oxidation of SO2 by photochemical process in the atmosphere. The experiments indicate that formation of SO3 aerosols is related to the concentration of SO2, the UV light intensity, the time of irradiation and the humidity of the air. The corrosion feature of surfaces of the marble and the depth profiles of sulphur were obtained by SEM (Scanning electron microscope), EDXA (Energy-dispersive X-ray analyzer) and SIMS (Secondary ion mass spectrometer). The results of experiments show the corrosive extent of marble depends on its compositions and microareas of marble, which contain lower silicon content can be easily corroded by SO2.
