In the past few years, support vector machines (SVMs) have been applied to many fields, such as pattern recognition and data mining, etc. However there still exist some problems to be solved. One of them is that the S...In the past few years, support vector machines (SVMs) have been applied to many fields, such as pattern recognition and data mining, etc. However there still exist some problems to be solved. One of them is that the SVM is very sensitive to outliers or noises because of over-fitting problem. In this paper, a fuzzy support vector regression (FSVR) method is presented to deal with this problem. Strategies based on k nearest neighbor (kNN) and support vector data description (SVDD) are adopted to set the fuzzy membership values of data points in FSVR.The proposed FSVR soft sensor models based on kNN and SVDD are employed to predict the concentration of 4-carboxy-benzaldehyde (4-CBA) in purified terephthalic acid (PTA) oxidation process. Simulation results indicate that the proposed method indeed reduces the effect of outliers and yields higher accuracy.展开更多
It is difficult to treat 2-amino-thiazoline-4-carboxylic acid （ATC） waste liquid effectively at present for its characteristics of high chemical oxygen demand （COD）, high salinity and low biodegradability. In orde...It is difficult to treat 2-amino-thiazoline-4-carboxylic acid （ATC） waste liquid effectively at present for its characteristics of high chemical oxygen demand （COD）, high salinity and low biodegradability. In order to solve this problem, this paper presents several kinds of physical-chemical treatment unit techniques, including acid separation, catalytic oxidation and coagulation. First of all, acid separation was adopted to precipitate relevant organics at isoelectric point. When the temperature and pH value of acid separation were controlled at about 5 ℃ and 2.2 respectively, the COD removal rate could reach 27.600. Secondly, oxidation was used to break chemical constitution of refractory organics. The optimal reaction parameters of catalytic oxidation should be 20 ℃, pH adjusted to 5.0 and [Fe2+] 300 mg/L. Then with 500 H2O2 added and after one-hour reaction, the COD removal rate could achieve about 5200. Finally, coagulation was adopted to remove a portion of refractory organics, and 1500 polymeric molysite flocculant was the best for the coagulation, and the COD removal rate could reach about 1500. Therefore, the proposed feasible process of physical-chemical pretreatment for ATC waste liquid could have about 7000 COD removed in total.展开更多
基金National Key Technologies Research and Development Program in the 10th five-year plan，国家杰出青年科学基金
文摘In the past few years, support vector machines (SVMs) have been applied to many fields, such as pattern recognition and data mining, etc. However there still exist some problems to be solved. One of them is that the SVM is very sensitive to outliers or noises because of over-fitting problem. In this paper, a fuzzy support vector regression (FSVR) method is presented to deal with this problem. Strategies based on k nearest neighbor (kNN) and support vector data description (SVDD) are adopted to set the fuzzy membership values of data points in FSVR.The proposed FSVR soft sensor models based on kNN and SVDD are employed to predict the concentration of 4-carboxy-benzaldehyde (4-CBA) in purified terephthalic acid (PTA) oxidation process. Simulation results indicate that the proposed method indeed reduces the effect of outliers and yields higher accuracy.
文摘It is difficult to treat 2-amino-thiazoline-4-carboxylic acid （ATC） waste liquid effectively at present for its characteristics of high chemical oxygen demand （COD）, high salinity and low biodegradability. In order to solve this problem, this paper presents several kinds of physical-chemical treatment unit techniques, including acid separation, catalytic oxidation and coagulation. First of all, acid separation was adopted to precipitate relevant organics at isoelectric point. When the temperature and pH value of acid separation were controlled at about 5 ℃ and 2.2 respectively, the COD removal rate could reach 27.600. Secondly, oxidation was used to break chemical constitution of refractory organics. The optimal reaction parameters of catalytic oxidation should be 20 ℃, pH adjusted to 5.0 and [Fe2+] 300 mg/L. Then with 500 H2O2 added and after one-hour reaction, the COD removal rate could achieve about 5200. Finally, coagulation was adopted to remove a portion of refractory organics, and 1500 polymeric molysite flocculant was the best for the coagulation, and the COD removal rate could reach about 1500. Therefore, the proposed feasible process of physical-chemical pretreatment for ATC waste liquid could have about 7000 COD removed in total.
