Development of a variable selection method for soft sensor using artificial neural network and nonnegative garrote

Sun, Kai; Liu, Jialin; Kang, Jia-Lin; Jang, Shi-Shang; Wong, David Shan-Hill; Chen, Ding-Sou

doi:10.1016/j.jprocont.2014.05.010

Cited by 45 publications

(17 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The standard back-propagation (BP) technique was used for ANN learning and the Levenberg Marquardt (LM) algorithm was used as a training function [8]. A network structure developed in this research was shown in Fig.…”

Section: Neural Network Modelingmentioning

confidence: 99%

A Neural Network Based Soft Sensor for Online Vapor Product Quality Estimation of a Refinery Debutanizer Column

Wanichodom¹,

Neamsuwan²,

Bumroongsri³

2015

IJMLC

View full text Add to dashboard Cite

Abstract-In order to keep crude oil refining products within the specifications, online monitoring and laboratory testing are usually required. Time delay in process monitoring and control may occur since the products from distillation columns must be analyzed in the laboratory. To overcome this problem, a neural network based soft sensor for online measurement of product quality was developed in this paper. A refinery debutanizer was chosen as a study case. Various structures of neural networks with different numbers of neurons in each hidden layer were created and tested for their performance on the estimation of propane composition in the distillate stream. The simulation results showed that the neural network containing 5 and 10 neurons in the first and second hidden layers, respectively, gave the best performance as compared to real industrial data.Index Terms-Artificial neural network, debutanizer column, online soft sensor, vapor product quality estimation.

show abstract

Section: Neural Network Modelingmentioning

confidence: 99%

A Neural Network Based Soft Sensor for Online Vapor Product Quality Estimation of a Refinery Debutanizer Column

Wanichodom¹,

Neamsuwan²,

Bumroongsri³

2015

IJMLC

View full text Add to dashboard Cite

show abstract

“…With the development of the theory of a nonlinear dynamic system and the theory of nonlinear system control, such as fuzzy control [8], bifurcation and chaos control [9,10], nonlinear decoupling control based on differential geometry theory [11,12], sliding mode control [13], artificial neural network control [14], particle swarm optimization algorithm [15], artificial sheep algorithm [16], fractional order PID control [17], nonlinear predictive control [18,19] and nonlinear H ∞ control [20], and the improvement of the calculation and simulation capability of computer, now it is possible to study this special nonlinear dynamic system and design proper advanced control strategies. The nonlinear control methods in [8][9][10][11][12][13][14][15][16][17][18][19][20] are widely used in dynamic systems, such as mechanic and power systems. As an intelligent method, the fuzzy logic controller is widely used in industrial processes due to its inherent robustness [8].…”

Section: Introductionmentioning

confidence: 99%

Nonlinear Disturbance Decoupling Control for Hydro-Turbine Governing System with Sloping Ceiling Tailrace Tunnel Based on Differential Geometry Theory

Guo¹

2018

Energies

View full text Add to dashboard Cite

For hydropower stations with sloping ceiling tailrace tunnel (SCTT), the regulation quality of hydro-turbine governing system (HTGS) under the proportional-integral-derivative (PID) strategy is poor. In order to improve the regulation quality of HTGS, the nonlinear disturbance decoupling control (NDDC) based on differential geometry theory is firstly applied into the HTGS with SCTT. The rigorous and complete construction method of nominal output function is proposed. Based on the obtained nominal output function, a novel NDDC strategy for HTGS with SCTT is designed. The application and performance of NDDC strategy on HTGS with SCTT are revealed. The results indicate that the regulation quality of the HTGS with SCTT under NDDC strategy is obviously better than that under PID strategy. The NDDC strategy has a favorable applicability on SCTT. The robustness of the HTGS with SCTT under NDDC strategy is excellent. In real engineering cases, the NDDC strategy can be adopted to optimize the design of the governor and improve the power supply quality of hydropower station.

show abstract

“…Moreover, they can detect fault and validate the measurements of physical sensors as a backup sensor [4]. Generally, inferential sensors can be divided to two main categories which are the model-driven and datadriven inferential sensors.…”

Section: Introductionmentioning

confidence: 99%

Inferential Sensor for Estimation of the Concentration of Benzene in the Distillation Column Using TSK Fuzzy System Based on Modified Clustering Approach

Ghanaati¹

2017

AJCHE

View full text Add to dashboard Cite

An inferential sensor is a computer program used for inferring the process variables, which are very hard to measure from the available measurement data. Measurement noises can affect the quality of the data which can be improved by wavelet denoising method. The objective of this paper is to design an inferential sensor for estimation of Benzene concentration in a typical distillation column. Selection of the most relevant input variables for estimation can improve the performance of inferential sensor which is done by Principal Component Analysis (PCA) technique. In this paper an inferential sensor is proposed based on a novel modification of the nearest neighbor distance-based clustering for developing a TakagiSugeno-Kang (TSK) fuzzy model optimized by the Particle Swarm Optimization (PSO) algorithm. The proposed technique was compared against the conventional nearest neighbor distance-based clustering approach optimized by PSO. The simulation results confirm that the designed inferential sensor based on the proposed method is more accurate even for a noisy data set.

show abstract

Development of a variable selection method for soft sensor using artificial neural network and nonnegative garrote

Cited by 45 publications

References 25 publications

A Neural Network Based Soft Sensor for Online Vapor Product Quality Estimation of a Refinery Debutanizer Column

A Neural Network Based Soft Sensor for Online Vapor Product Quality Estimation of a Refinery Debutanizer Column

Nonlinear Disturbance Decoupling Control for Hydro-Turbine Governing System with Sloping Ceiling Tailrace Tunnel Based on Differential Geometry Theory

Inferential Sensor for Estimation of the Concentration of Benzene in the Distillation Column Using TSK Fuzzy System Based on Modified Clustering Approach

Contact Info

Product

Resources

About