Process Modeling and Optimization Strategies Integrating Support Vector Regression and Differential Evolution: A Study of Industrial Ethylene Oxide Reactor

2008 ◽  
Vol 3 (1) ◽  
Author(s):  
Sandip Kumar Lahiri ◽  
Nadeem Khalfe
Keyword(s):  
Ethylene Oxide ◽  
Differential Evolution ◽  
Support Vector Regression ◽  
Process Modeling ◽  
Operating Conditions ◽  
Support Vector ◽  
Process Data ◽  
Support Vector Regression Model ◽  
Catalyst Selectivity ◽  
Modeling And Optimization

This paper presents artificial intelligence-based process modeling and optimization strategies, namely, support vector regression – differential evolution (SVR-DE) for modeling and optimization of catalytic industrial ethylene oxide (EO) reactor. In the SVR-DE approach, a support vector regression model is constructed for correlating process data comprising values of operating and performance variables. Next, model inputs describing process operating variables are optimized using Differential Evolution (DE) with a view to maximize the process performance. DE possesses certain unique advantages over the commonly used gradient-based deterministic optimization algorithms. The SVR-DE is a new strategy for chemical process modeling and optimization. The major advantage of the strategy is that modeling and optimization can be conducted exclusively from the historic process data wherein the detailed knowledge of process phenomenology (reaction mechanism, kinetics, etc.) is not required. Using SVR-DE strategy, a number of sets of optimized operating conditions leading to maximized EO production and catalyst selectivity were obtained. The optimized solutions, when verified in an actual plant, resulted in a significant improvement in the EO production rate and catalyst selectivity.

scholarly journals Soft sensor development and optimization of the commercial petrochemical plant integrating support vector regression and genetic algorithm

2009 ◽  
Vol 15 (3) ◽  
pp. 175-187 ◽  
Author(s):  
S.K. Lahiri ◽  
Nadeem Khalfe
Keyword(s):  
Genetic Algorithm ◽  
Support Vector Regression ◽  
Soft Sensor ◽  
Operating Conditions ◽  
Support Vector ◽  
Petrochemical Plant ◽  
Process Data ◽  
Soft Sensing ◽  
Modeling And Optimization ◽  
Sensor Modeling

Soft sensors have been widely used in the industrial process control to improve the quality of the product and assure safety in the production. The core of a soft sensor is to construct a soft sensing model. This paper introduces support vector regression (SVR), a new powerful machine learning method based on a statistical learning theory (SLT) into soft sensor modeling and proposes a new soft sensing modeling method based on SVR. This paper presents an artificial intelligence based hybrid soft sensormodeling and optimization strategies, namely support vector regression - genetic algorithm (SVR-GA) for modeling and optimization of mono ethylene glycol (MEG) quality variable in a commercial glycol plant. In the SVR-GA approach, a support vector regression model is constructed for correlating the process data comprising values of operating and performance variables. Next, model inputs describing the process operating variables are optimized using genetic algorithm with a view to maximize the process performance. The SVR-GA is a new strategy for soft sensor modeling and optimization. The major advantage of the strategies is that modeling and optimization can be conducted exclusively from the historic process data wherein the detailed knowledge of process phenomenology (reaction mechanism, kinetics etc.) is not required. Using SVR-GA strategy, a number of sets of optimized operating conditions were found. The optimized solutions, when verified in an actual plant, resulted in a significant improvement in the quality.

scholarly journals The Support Vector Regression with the parameter tuning assisted by a differential evolution technique: Study of the critical velocity of a slurry flow in a pipeline

2008 ◽  
Vol 14 (3) ◽  
pp. 191-203 ◽  
Author(s):  
S.K. Lahiri ◽  
K.C. Ghanta
Keyword(s):  
Differential Evolution ◽  
Support Vector Regression ◽  
Critical Velocity ◽  
Parameter Tuning ◽  
Operating Conditions ◽  
Superior Performance ◽  
Support Vector ◽  
Slurry Flow ◽  
Wide Range ◽  
Liquid Slurry

This paper describes a robust Support Vector regression (SVR) methodology, which can offer a superior performance for important process engineering problems. The method incorporates hybrid support vector regression and a differential evolution technique (SVR-DE) for the efficient tuning of SVR meta parameters. The algorithm has been applied for the prediction of critical velocity of the solid-liquid slurry flow. A comparison with selected correlations in the literature showed that the developed SVR correlation noticeably improved the prediction of critical velocity over a wide range of operating conditions, physical properties, and pipe diameters.

Stress evaluation in seven-wire strands based on singular value feature of ultrasonic guided waves

2021 ◽  
pp. 147592172110053
Author(s):  
Qian Ji ◽  
Li Jian-Bin ◽  
Liu Fan-Rui ◽  
Zhou Jian-Ting ◽  
Wang Xu
Keyword(s):  
Dispersion Curve ◽  
Support Vector Regression ◽  
Stress Level ◽  
Guided Waves ◽  
Guided Wave ◽  
Singular Value ◽  
Support Vector ◽  
Support Vector Regression Model ◽  
Various Boundary Conditions ◽  
Wave Methods

The seven-wire strands are the crucial components of prestressed structures, though their performance inevitably degrades with the passage of time. The ultrasonic guided wave methods have been intensely studied, owing to its tremendous potential for full-scale applications, among the existing nondestructive testing methods, for evaluating the stress status of strands. We have employed the theoretical and finite element methods to solve the dispersion curve of single wire and steel strands under various boundary conditions. Thereafter, the singular value decomposition was adopted to work with the simulated and experimental signals for extracting a feature vector that carries valuable stress status information. The effectiveness of the vector was verified by analyzing the relationship between the vector and the stress level. The vector was also used as an input to establish a support vector regression model. The accuracy of the model has been discussed for different sample sizes. The results show that the fundamental mode dispersion curve offset on the high-frequency part and cut-off frequency increases as the boundary constraints enhance. Simulated and experimental results have demonstrated the effectiveness and potential of the proposed support vector regression method for evaluating the stress level in the strands. This method performs well even at low stress levels and the reliability can be enhanced by adding more samples.

scholarly journals Hotspot Temperature Prediction of Dry-Type Transformers Based on Particle Filter Optimization with Support Vector Regression

Symmetry ◽  
2021 ◽  
Vol 13 (8) ◽  
pp. 1320
Author(s):  
Yuanyuan Sun ◽  
Gongde Xu ◽  
Na Li ◽  
Kejun Li ◽  
Yongliang Liang ◽  
...  
Keyword(s):  
Particle Filter ◽  
Support Vector Regression ◽  
Heat Dissipation ◽  
Hot Spot ◽  
Load Capacity ◽  
Regression Method ◽  
Support Vector ◽  
Temperature Prediction ◽  
Support Vector Regression Model ◽  
Load Rate

Both poor cooling methods and complex heat dissipation lead to prominent asymmetry in transformer temperature distribution. Both the operating life and load capacity of a power transformer are closely related to the winding hotspot temperature. Realizing accurate prediction of the hotspot temperature of transformer windings is the key to effectively preventing thermal faults in transformers, thus ensuring the reliable operation of transformers and accurately predicting transformer operating lifetimes. In this paper, a hot spot temperature prediction method is proposed based on the transformer operating parameters through the particle filter optimization support vector regression model. Based on the monitored transformer temperature, load rate, transformer cooling type, and ambient temperature, the hotspot temperature of a dry-type transformer can be predicted by a support vector regression method. The hyperparameters of the support vector regression are dynamically optimized here according to the particle filter to improve the optimization accuracy. The validity and accuracy of the proposed method are verified by comparing the proposed method with a traditional support vector regression method based on the real operating data of a 35 kV dry-type transformer.

Sign in / Sign up

Export Citation Format

Share Document