Development of soft sensors for isomerization process based on support vector machine regression and dynamic polynomial models

Herceg, Srečko; Andrijić, Željka Ujević; Bolf, Nenad

doi:10.1016/j.cherd.2019.06.034

Cited by 47 publications

(15 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…To minimise the forecasting errors, SVR individualises the hyperplane by maximising the margin. To solve a nonlinear regression problem, the following linear estimation function is considered [51]:…”

Section: Rfe-svrmentioning

confidence: 99%

Day-ahead electricity price prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling

Li¹,

Becker²

2021

Preprint

View full text Add to dashboard Cite

The availability of accurate day-ahead electricity price forecasts is pivotal for electricity market participants. In the context of trade liberalisation and market harmonisation in the European markets, accurate price forecasting becomes even more difficult to obtain. The increasing power market integration has complicated the forecasting process, where electricity forecasting requires considering features from both the local market and ever-growing coupling markets. In this paper, we apply state-of-the-art deep learning models, combined with feature selection algorithms for electricity price prediction under the consideration of market coupling. We propose three hybrid architectures of long-short term memory (LSTM) deep neural networks and compare the prediction performance, in terms of various feature selections. In our empirical study, we construct a broad set of features from the Nord Pool market and its six coupling countries for forecasting the Nord Pool system price. The results show that feature selection is essential to achieving accurate prediction. Superior feature selection algorithms filter meaningful information, eliminate irrelevant information, and further improve the forecasting accuracy of LSTM-based deep neural networks. The proposed models obtain considerably accurate results.

show abstract

Section: Rfe-svrmentioning

confidence: 99%

Day-ahead electricity price prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling

Li¹,

Becker²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…For modeling and controlling these systems, there are plenty of methods including fuzzy theory, support vector machine (SVM), and NNs, of which the potential has been shown in the existing literature. [173][174][175][176][177][178] More specifically, fuzzy logic deals with the problem that cannot be expressed as a binary choice: ''true'' and ''false,'' but rather as ''partially true.'' And applications of fuzzy logic can be found in controller design, estimation, and fault diagnosis.…”

Section: Nn-based Techniquesmentioning

confidence: 99%

Developments of attitude determination and control system of microsats: A survey

Ma²,

Guo

et al. 2020

Proceedings of the Institution of Mechanical Engineers, Part I:

View full text Add to dashboard Cite

This study surveys the developments in satellite attitude determination and control system, especially for microsats. This survey is not intended to be complete but is limited to the most significant developments of sensors, actuators, and algorithms in the last two decades. First, attitude determination methods including algorithms and sensors together with actuator-based control methods are introduced. Furthermore, current problems in alignment error, flexible satellites, and low redundancy of microsats attitude determination and control system are discussed. Moreover, developments of some deep-neural-networks-based methods, which have great potential in solving current problems, are summarized.

show abstract

“…One method is to build a soft sensor based on the theoretical model of the distillation column, but due to the complexity or nonlinear of the industrial distillation process, its realization is very difficult and some important parameters in the mechanism model are unknown. The other method is to use data-driven model for soft-sensor modeling, in which many algorithms can be used, including regression analysis, partial least square (PLS), artificial neural network (Singh et al, 2019), support vector machine (SVM) (Herceg et al, 2019), and so on (Liu et al, 2019). Among these technologies, the soft sensors based on artificial neural network are used more and more widely.…”

Section: Introductionmentioning

confidence: 99%

A soft-sensing method for product quality monitoring based on particle swarm optimization deep belief networks

Yang

et al. 2022

Transactions of the Institute of Measurement and Control

View full text Add to dashboard Cite

A novel soft-sensing method for quality parameters of aviation kerosene in atmospheric distillation column based on least absolute shrinkage and selection operator and particle swarm optimization deep belief network (LASSO-PSO-DBN) is proposed. First, to reduce the dimension of the input variables, the least absolute shrinkage and selection operator (LASSO) algorithm is used to select the input variables that are irrelevant to the soft sensor of aviation kerosene quality parameters. Then, to improve the generalization of soft sensor model, a deep learning algorithm, deep belief network (DBN), is proposed for soft sensing of aviation kerosene quality parameters. Considering that the structure characteristics and parameters of DBN algorithm have a great impact on the learning and prediction results, the parameters of DBN are optimized based on particle swarm optimization (PSO) algorithm. The benchmark data sets and the industrial atmospheric distillation column data are used for simulation analysis and evaluation of the soft-sensing performance. The simulation results show that the novel proposed algorithm can effectively reduce the dimension of the input variables and simplify the structure of the soft sensor model. It also has good generalization ability and the predicted value is in good agreement with the actual measured value.

show abstract

Development of soft sensors for isomerization process based on support vector machine regression and dynamic polynomial models

Cited by 47 publications

References 16 publications

Day-ahead electricity price prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling

Day-ahead electricity price prediction applying hybrid models of LSTM-based deep learning methods and feature selection algorithms under consideration of market coupling

Developments of attitude determination and control system of microsats: A survey

A soft-sensing method for product quality monitoring based on particle swarm optimization deep belief networks

Contact Info

Product

Resources

About