The Soft Measurement of Catalyst Activity in VAc Synthesis

2014 ◽  
Vol 602-605 ◽  
pp. 2000-2003
Author(s):  
Hua Meng ◽  
Long Liu ◽  
Yue Ying Wang
Keyword(s):  
Support Vector Machine ◽  
Zinc Acetate ◽  
Catalyst Activity ◽  
Space Velocity ◽  
Molar Ratio ◽  
Main Trend ◽  
Support Vector ◽  
Soft Measurement ◽  
Change Trend ◽  
Main Change

Zinc acetate serves as the catalyst in the synthesis reaction of VAc, the activity of zinc acetate will lose with the changes of the using time, temperature, space velocity, molar ratio. For the realization of soft measurement of the catalyst activity, the mathematical regression method and support vector machine (SVM) method are combined to model. By adopting the method of mathematical regression, the main change trend of catalyst activity can be illuminated with the change of response time; The support vector machine (SVM) method is used to amend the main trend to truly achieve the accurate and reliable soft measurement of catalyst activity[1]。The simulation is proceed by the MATLAB to compare to the field datas, the simulation results show that the model established by the mixed modeling approach is high-precision and reliable. The requirements of the soft measurement for catalyst activity in VAc synthesis can be satisfied.

scholarly journals Zinc Acetate Immobilized on Mesoporous Materials by Acetate Ionic Liquids as Catalysts for Vinyl Acetate Synthesis

2015 ◽  
Vol 2015 ◽  
pp. 1-5 ◽  
Author(s):  
Hang Xu ◽  
Tianlong Yu ◽  
Mei Li
Keyword(s):  
Ionic Liquid ◽  
Ionic Liquids ◽  
Vinyl Acetate ◽  
Silica Gel ◽  
Catalyst Activity ◽  
Catalyst Layer ◽  
Space Velocity ◽  
Molar Ratio ◽  
Vinyl Acetate Monomer ◽  
Adsorption Desorption

Ionic liquid containing active ingredient Zn(CH3COO)2was loaded in mesoporous silica gel to form supported ionic liquids catalyst (SILC) which was used to synthesize vinyl acetate monomer (VAM). SILC was characterized by1HNMR, FT-IR, TGA, BET, and N2adsorption/desorption and the acetylene method was used to evaluate SILC catalytic activity and stability in fixed reactor. The result shows that 1-allyl-3-acetic ether imidazole acetate ionic liquid is successfully fixed within mesoporous channel of silica gel. The average thickness of ionic liquid catalyst layer is about 1.05 nm. When the catalytic temperature is 195°C, the acetic acid (HAc) conversion is 10.9% with 1.1 g vinyl acetate yield and 98% vinyl acetate (VAc) selectivity. The HAc conversion is increased by rise of catalytic temperature and molar ratio of C2H2 : HAc and decreased by mass space velocity (WHSV). The catalyst activity is not significantly reduced within 7 days and VAc selectivity has a slight decrease.

Modeling and Simulation of the GA_LSSVM-Based Soft Measurement for Torque

2010 ◽  
Vol 44-47 ◽  
pp. 733-737
Author(s):  
Zhen Chen ◽  
An Yi Huang
Keyword(s):  
Support Vector Machine ◽  
Genetic Algorithms ◽  
Modeling And Simulation ◽  
Traditional Method ◽  
Measurement Accuracy ◽  
Cross Validation ◽  
Measurement Methods ◽  
Small Sample ◽  
Support Vector ◽  
Soft Measurement

Given the traditional method of direct measurement which is of high cost, difficult installation and poor reliability,this paper is presented a new model of the torque soft measure method based on least squares support vector machine using genetic algorithms optimization:genetic algorithms replaces the previous cross-validation method for model parameter’s optimization, in order to avoid the blindness of the parameter choices.Verified by simulation, the model can effectively address the deficiencies of traditional measurement methods and obtain better measurement accuracy and speed , possessing benefits of an outstanding ability for small sample study and being easy to compute.

Zenith Troposphere Delay Prediction based on BP Neural Network and Least Squares Support Vector Machine

2020 ◽  
Author(s):  
Tianhe Xu ◽  
Song Li ◽  
Nan Jiang
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Least Squares ◽  
Bp Neural Network ◽  
Main Trend ◽  
Support Vector ◽  
Space Domain ◽  
High Efficient ◽  
New Strategy ◽  
Delay Prediction

<p><strong>Abstract</strong><strong>:</strong> With the rapid development of artificial intelligence, machine learning has become an high-efficient tool applied in the fields of GNSS data analysis and processing, such as troposphere, ionosphere or satellite clock modeling and prediction. In this paper, zenith troposphere delay (ZTD) prediction algorithms based on BP neural network (BPNN) and least squares support vector machine (LSSVM) are proposed in the time and space domain. The main trend terms in ZTD time series are deducted by polynomial fitting, and the remaining residuals are reconstructed and modeled by BPNN and LSSVM algorithm respectively. The test results show that the performance of LSSVM is better than that of BPNN in term of prediction stability and accuracy by using ZTD products of International GNSS Service (IGS) of 20 stations in time domain. In order to further improve LSSVM prediction accuracy, a new strategy of training samples selection based on correlation analysis is proposed. The results show that using the proposed strategy, about 80% to 90% of the 1-hour prediction deviation of LSSVM can reach millimeter level depending on the season, and the percentage of the prediction deviation value less than 5 mm is about 60% to 70%, which is 5% to 20% higher than that of the classical random selection in different month. The mean values of RMSE in all 20 stations using the new strategy are 1-3mm smaller than those of the classical one. Then different prediction span from 1 to 12 hours is conducted to show the performance of the proposed method. Finally, the ZTD predictions based on BPNN and LSSVM in space domain are also verified and compared using GNSS CORS network data of Hong Kong, China.</p><p><strong>Keywords</strong><strong>:</strong> ZTD, BP Neural Network, Support Vector Machine, Least Squares, GNSS</p><p><strong>Acknowledgments:</strong> This work was supported by Natural Science Foundation of China (41874032) and the National Key Research and Development Program (2016YFB0501701)</p><p> </p>

Catalytic Combustion of Vinyl Chloride Emission over a TiO2–MnOx Catalyst

2017 ◽  
Vol 42 (3) ◽  
pp. 259-268 ◽  
Author(s):  
Yiling Wan ◽  
Xiangyu Xie ◽  
Xiaojun Chen
Keyword(s):  
Vinyl Chloride ◽  
Catalytic Combustion ◽  
Active Oxygen Species ◽  
Catalyst Activity ◽  
Sol Gel ◽  
Space Velocity ◽  
Catalytic Performance ◽  
Molar Ratio ◽  
Preparation Conditions ◽  
Diffraction Peaks

TiO2–MnO x catalyst samples with different Ti/(Ti + Mn) molar ratios (2:3, 3:4, 4:5, 5:6, 6:7 and 1) prepared by the citric acid (CA) sol-gel method were studied in the catalytic combustion of vinyl chloride (VC) emission. The effects of preparation conditions and operation parameters on the catalytic performance of TiO2–MnO x were investigated. The catalyst samples were characterised by N2 adsorption, X-ray diffraction (XRD) and H2-temperature programmed reduction (H2-TPR). In the catalytic combustion of VC over TiO2–MnO x, products containing HCl, CO2, and H2O were obtained and there were no by-products such as chlorohydrocarbons and chlorine. The TiO2–MnO x catalyst with the molar ratio of CA/Mn/Ti = 0.30:0.20:0.80 showed the best catalytic performance and had better operating flexibility over the ranges of gas hourly space velocity (GHSV) of 15000–100000 h−1 and VC concentration of 0.05–2.00%. The temperatures at 50% conversion (140 °C) and at 99% conversion (220 °C) were achieved at a VC concentration of 0.1% and GHSV of 15000 h−1. XRD characterisation indicated that only the characteristic diffraction peaks of TiO2 with the anatase structure appeared and no characteristic diffraction peaks of MnO x species appeared for the TiO2–MnO x catalyst. XRD and H2-TPR results indicated that Mn ions were incorporated into the TiO2 lattice to form a Ti–Mn–O solid solution, which enhanced the reactivity of active oxygen species on the catalyst surface and thereby promoted the catalyst activity.

Research and Development of Sucrose Supersaturation Soft Measurement System Based on Least Square Support Vector Machine

2013 ◽  
Vol 694-697 ◽  
pp. 1229-1232
Author(s):  
Yan Mei Meng ◽  
Guan Cheng Lu ◽  
Quan Zhou ◽  
Chun Wa Qin ◽  
Hai Feng Pang ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Principal Component ◽  
Measurement Model ◽  
Least Square ◽  
Support Vector ◽  
Auxiliary Variables ◽  
Noise Interference ◽  
Kernel Partial Least Squares ◽  
Soft Measurement ◽  
Measurement Principle

Nowadays, it's difficult to stably measure sucrose supersaturation through an online instrument directly. This paper is Nowadays, it's difficult to stably measure sucrose supersaturation through an online instrument directly. This paper is based on the soft measurement principle，extracting the principal component of auxiliary variables in sucrose supersaturation soft measuring with the method of kernel partial least squares, and eliminating the multiple nonlinear correlation among the auxiliary variables and noise interference, building an online soft measurement of sucrose supersaturation and offline soft measurement model，and improving the accuracy of soft measurement . The paper develops the system of sucrose supersaturation soft measurement by using VC + +6.0.

scholarly journals Combined soft measurement on key indicator parameters of new competitive advantages for China's export

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Taosheng Wang ◽  
Hongyan Zuo ◽  
C. H. Wu ◽  
B. Hu
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Measurement Model ◽  
Evaluation Index System ◽  
Support Vector ◽  
Competitive Advantages ◽  
Entropy Weight ◽  
Soft Sensing ◽  
Soft Measurement ◽  
Sensing Model

AbstractThe estimation of the difference between the new competitive advantages of China's export and the world’s trading powers have been the key measurement problems in China-related studies. In this work, a comprehensive evaluation index system for new export competitive advantages is developed, a soft-sensing model for China’s new export competitive advantages based on the fuzzy entropy weight analytic hierarchy process is established, and the soft-sensing values of key indexes are derived. The obtained evaluation values of the main measurement index are used as the input variable of the fuzzy least squares support vector machine, and a soft-sensing model of the key index parameters of the new export competitive advantages of China based on the combined soft-sensing model of the fuzzy least squares support vector machine is established. The soft-sensing results of the new export competitive advantage index of China show that the soft measurement model developed herein is of high precision compared with other models, and the technical and brand competitiveness indicators of export products have more significant contributions to the new competitive advantages of China's export, while the service competitiveness indicator of export products has the least contribution to new competitive advantages of China's export.

Support vector machine? – not only for MRI-images

2020 ◽  
Author(s):  
V Vasilevska ◽  
K Schlaaf ◽  
H Dobrowolny ◽  
G Meyer-Lotz ◽  
HG Bernstein ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Support Vector

KLASIFIKASI SMS SPAM MENGGUNAKAN SUPPORT VECTOR MACHINE

2019 ◽  
Vol 15 (2) ◽  
pp. 275-280
Author(s):  
Agus Setiyono ◽  
Hilman F Pardede
Keyword(s):  
Data Mining ◽  
Support Vector Machine ◽  
Decision Tree ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Support Vector ◽  
Spam Detection ◽  
Support Vector Machine Algorithm ◽  
Data Mining Techniques ◽  
To Receive

It is now common for a cellphone to receive spam messages. Great number of received messages making it difficult for human to classify those messages to Spam or no Spam.  One way to overcome this problem is to use Data Mining for automatic classifications. In this paper, we investigate various data mining techniques, named Support Vector Machine, Multinomial Naïve Bayes and Decision Tree for automatic spam detection. Our experimental results show that Support Vector Machine algorithm is the best algorithm over three evaluated algorithms. Support Vector Machine achieves 98.33%, while Multinomial Naïve Bayes achieves 98.13% and Decision Tree is at 97.10 % accuracy.

Sign in / Sign up

Export Citation Format

Share Document