The Design of New Soft Sensors Based on PCA and a Neural Network for Parameters Estimation of a Petroleum Reservoir

Alaei, Hesam Komari; Salahshoor, Karim

doi:10.1080/10916466.2010.512899

Cited by 7 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But in the area of cost estimating there exist only few applications. The works of Alaei and Salahshoor (2012) and Chen and Huang (2012) in the manufacturing industry, comprise alternative ANN models for cost estimating. Cheng et al (2009) developed a system that was based on a neural network that was trained to interpret cost estimates when a new technology was introduced for construction industry.…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Cost assessment of construction projects through neural networks

et al. 2013

View full text Add to dashboard Cite

Construction performance parameters have experienced greater international attention and discussion in recent years. In this study, the change in the load-bearing system cost of a reinforced concrete housing estate building was investigated in relation to the building importance factor, earthquake region, soil type, floor area, and the number of stories. Three different housing estate projects with seven and fifteen stories were investigated. The structural design calculations were performed according to four different soil types, four different earthquake regions, and four different importance factors. With regards to each combination, project costs were calculated. The changes in the cost were examined with artificial neural network and multiple regression models. According to the results of the analysis, the building importance factor was the most significant component, while earthquake region was the second most significant, followed by the factors of the number of floors and the soil type.Résumé : Les critères de performance en construction ont fait l'objet d'une forte attention internationale et ils ont été des sujets de discussions au cours des dernières années. Dans la présente étude, le changement dans le coût du système porteur d'un ensemble résidentiel en béton armé est examiné par rapport au coefficient de risque de l'immeuble, à la région sismique, au type de sol, à la superficie de plancher et au nombre d'étages. Trois différents ensembles résidentiels de sept et de quinze étages ont été examinés. Les calculs de conception structurale ont été réalisés pour quatre types de sols différents, quatre régions sismiques et quatre coefficients de risque. Les coûts de projet ont été calculés pour chaque combinaison de facteurs. Les changements dans les coûts ont été examinés à l'aide de réseaux neuronaux artificiels et de modèles de régression multiple. Selon les résultats de l'analyse, le coefficient de risque de l'immeuble était la composante la plus importante, la seconde était la région sismique, suivie du nombre d'étages et du type de sol. [Traduit par la Rédaction] Mots-clés : estimation des coûts, réseau neuronal artificiel, région sismique, coefficient de risque de l'immeuble, type de sol, ensemble residential.

show abstract

Section: Artificial Neural Networkmentioning

confidence: 99%

Cost assessment of construction projects through neural networks

et al. 2013

View full text Add to dashboard Cite

show abstract

“…In the last few years, artificial intelligence has been involved in solving many problems in different fields of science. Many authors have dealt with the application of neural networks (NNs) in solving fundamental problems in geophysical and petroleum engineering like Ahmadi et al (2012), Lashin and Din (2013), Kaydani et al (2013), Singh et al (2013), Maiti et al (2013), Alaei and Alaei (2013) and Alaei and Salahshoor (2012). Previous investigations (Ahmadi et al, 2012;Saemi et al, 2007;Wong et al, 2000;Aminian et al, 2000Aminian et al, , 2001 have indicated that artificial neural network (ANN) can predict formation permeability even in highly heterogeneous reservoirs using geophysical well log data with good accuracy.…”

Section: Introductionmentioning

confidence: 99%

Neural network using Bayesian algorithm for estimation of petroleum reservoir

Alaei

Yazdizadeh

2013

Kybernetes

View full text Add to dashboard Cite

Purpose -This paper is concerned with the estimation of reservoir parameters in the presence of noise and outliers using neural network (NN) and Bayesian algorithm. The paper aims to discuss these issues. Design/methodology/approach -Outlier detection is of great importance to prediction of time series data. A reliable predictive methodology is proposed based on NN and Bayesian algorithm to efficiency estimates of the parameters of a petroleum reservoir. This strategy is applied to estimate the parameters of Marun reservoir located in Ahwaz, Iran utilizing available geophysical well log data. Findings -For an evaluation purpose, the performance and generalization capabilities of Bayes-ANN are compared with the common technique of back propagation (BP). Practical implications -The experimental results demonstrate that the proposed hybrid Bayes-NN algorithm is able to reveal a better performance than conventional BP NN algorithms. Originality/value -Helped oil and gas companies to estimation of petroleum reservoir parameters more accurate than other methods in the presence of noise and outliers.

show abstract

Enhancing well log curve synthesis with selective attention long short-term memory network

Zhou,

2024

Acta Geophys.

View full text Add to dashboard Cite

The Design of New Soft Sensors Based on PCA and a Neural Network for Parameters Estimation of a Petroleum Reservoir

Cited by 7 publications

References 7 publications

Cost assessment of construction projects through neural networks

Cost assessment of construction projects through neural networks

Neural network using Bayesian algorithm for estimation of petroleum reservoir

Enhancing well log curve synthesis with selective attention long short-term memory network

Contact Info

Product

Resources

About