scispace - formally typeset
Search or ask a question
Journal ArticleDOI

Application of Optimized Least Square Support Vector Machine and Genetic Programming for Accurate Estimation of Drilling Rate of Penetration

01 Oct 2018-Vol. 7, Iss: 4, pp 92-108
TL;DR: Two novel methods based on least square support vector machine (LSSVM) and genetic programming (GP) are presented and results indicate that LSSVM is superior over GP in terms of average relative error, average absolute relative errors, root mean square error, and the coefficient of determination.
Abstract: This article describes how the accurate estimation of the rate of penetration ROP is essential to minimize drilling costs. There are various factors influencing ROP such as formation rock, drilling...
Citations
More filters
Journal ArticleDOI
TL;DR: In this paper, the authors used genetic programming (GP), least square support vector machines (LSSVM), and radial basis function (RBF) neural networks to predict bottom-hole pressure in producing multiphase flow petroleum wells.
Abstract: Determining bottom-hole pressure in producing multiphase flow petroleum wells is a crucial issue that directly affects plans, infrastructures, and all the equipment required to develop an oil field. This study attempted to introduce the best method regarding accuracy and codes applicable in vertical oil and gas wells. Therefore, with the aid of genetic programming (GP), least-square support vector machines (LSSVM), and radial basis function (RBF) neural networks and using 450 producing wells data, three models are trained. Besides, five experimental and mechanistic correlations were used for taking more approaches into account to evaluate the accuracy of simulations. LSSVM and GP had the highest precision models among all the methods, proved by several analyses and calculation of the coefficient of determination (R2), average relative error (ARE), average absolute relative error (AARE), and root mean square error (RMSE). The models mentioned above performed better than previously developed correlations, where Ansari et al.'s (1994) model had the nearest outcomes to GP results. In addition to the generated models, the analyses' results introduced a new correlation for predicting wellbore pressure using available measurements of the wellhead data.

1 citations

Journal ArticleDOI
TL;DR: In this paper, a scheduling algorithm based on priority queue division is proposed to determine the number of priority queues according to number of input nodes of the directed DAG task set of the acyclic graph and divide the task queue into communication overhead and computational overhead.
Abstract: In a heterogeneous computing environment, task scheduling has always been a central issue in high-performance computing. This paper proposes a scheduling algorithm based on priority queue division. The algorithm determines the number of priority queues according to the number of input nodes of the directed DAG task set of the acyclic graph and divides the task queue into communication overhead and computational overhead. With the development of the marine economy, the pressure on the marine ecological environment is increasing, and the complexity of protection and governance is also increasing. Therefore, on the basis of heterogeneous computer technology, this paper has carried out a systematic study on the characteristics of marine organisms and has carried out a systematic study on the characteristics of marine ecology. This article finds out the many reasons for the destruction of the marine environment and proposes appropriate countermeasures to establish a complete marine protection and management system. In view of the increasing importance of international and national criminal responsibility of maritime transport rights, the establishment of environmental legal issues has become very important, which is essential for combating and punishing crimes related to marine pollution and maintaining the marine environment. This paper studies domestic and foreign taxation policies and the legal system of coordinated management in the ecological environment and mainly studies how to build a legal system of fiscal and taxation policies for the coordinated governance of the ecological environment and optimize the fiscal and taxation policies of the ecological environment. Based on the research and analysis of taxation policy optimization environment, taxation law, taxation policy, and joint management law, this article puts forward practical suggestions.
References
More filters
Journal ArticleDOI
TL;DR: A least squares version for support vector machine (SVM) classifiers that follows from solving a set of linear equations, instead of quadratic programming for classical SVM's.
Abstract: In this letter we discuss a least squares version for support vector machine (SVM) classifiers. Due to equality type constraints in the formulation, the solution follows from solving a set of linear equations, instead of quadratic programming for classical SVM‘s. The approach is illustrated on a two-spiral benchmark classification problem.

8,811 citations

Proceedings Article
01 Jan 2010
TL;DR: It is shown that the low-order "multigene" GP methods implemented by GPTIPS can provide a useful alternative, as well as a complementary approach, to currently accepted empirical modelling and data analysis techniques.
Abstract: In this contribution GPTIPS, a free, open source MATLAB toolbox for performing symbolic regression by genetic programming (GP) is introduced. GPTIPS is specifically designed to evolve mathematical models of predictor response data that are "multigene" in nature, i.e. linear combinations of low order non-linear transformations of the input variables. The functionality of GPTIPS is demonstrated by using it to generate an accurate, compact QSAR (quantitative structure activity relationship) model of existing toxicity data in order to predict the toxicity of chemical compounds. It is shown that the low-order "multigene" GP methods implemented by GPTIPS can provide a useful alternative, as well as a complementary approach, to currently accepted empirical modelling and data analysis techniques. GPTIPS and documentation is available for download at http://sites.google.com/site/gptips4matlab/.

322 citations

Posted Content
TL;DR: GPTIPS is a free, open source MATLAB based software platform for symbolic data mining that uses a multigene variant of the biologically inspired machine learning method of genetic programming as the engine that drives the automatic model discovery process.
Abstract: GPTIPS is a free, open source MATLAB based software platform for symbolic data mining (SDM). It uses a multigene variant of the biologically inspired machine learning method of genetic programming (MGGP) as the engine that drives the automatic model discovery process. Symbolic data mining is the process of extracting hidden, meaningful relationships from data in the form of symbolic equations. In contrast to other data-mining methods, the structural transparency of the generated predictive equations can give new insights into the physical systems or processes that generated the data. Furthermore, this transparency makes the models very easy to deploy outside of MATLAB. The rationale behind GPTIPS is to reduce the technical barriers to using, understanding, visualising and deploying GP based symbolic models of data, whilst at the same time remaining highly customisable and delivering robust numerical performance for power users. In this chapter, notable new features of the latest version of the software are discussed with these aims in mind. Additionally, a simplified variant of the MGGP high level gene crossover mechanism is proposed. It is demonstrated that the new functionality of GPTIPS 2 (a) facilitates the discovery of compact symbolic relationships from data using multiple approaches, e.g. using novel gene-centric visualisation analysis to mitigate horizontal bloat and reduce complexity in multigene symbolic regression models (b) provides numerous methods for visualising the properties of symbolic models (c) emphasises the generation of graphically navigable libraries of models that are optimal in terms of the Pareto trade off surface of model performance and complexity and (d) expedites real world applications by the simple, rapid and robust deployment of symbolic models outside the software environment they were developed in.

157 citations

Journal ArticleDOI

157 citations


Additional excerpts

  • ...…Volume 7 • Issue 4 • October-December 2018 93 AliteraturereviewshowsthatseveralmethodshavebeenusedforpredictionofROPincluding analyticalmodels(Maurer,1962;GalleandWoods,1963;Motahharietal.,2009),multipleregression…...

    [...]

  • ...International Journal of Energy Optimization and Engineering Volume 7 • Issue 4 • October-December 2018 93 AliteraturereviewshowsthatseveralmethodshavebeenusedforpredictionofROPincluding analyticalmodels(Maurer,1962;GalleandWoods,1963;Motahharietal.,2009),multipleregression analysisandnumericalcorrelations(BourgoyneandYoung,1973;BourgoyneandYoung,1974; Tanseu,1975;Al-Betairietal.,1988;Fear,1999),computerbasedprograms(MechemandFullerton, 1965;MaidlaandOhara,1991;Shirkavandetal.,2010;Hankinsetal.,2014,Shishavanetal.,2015), stochasticmethods(Rittoetal.,2010),semianalyticalmodels(AlumandEgbon,2011),evolutionary algorithms(Pingetal.,2014),responsesurfacemethodology(KeshavarzMoravejiandNaderi,2016), andartificialneuralnetwork (WangandSalehi,2015,Elkatatnyetal.,2017,Asadietal.,2017; Eskandarianetal.,2017),machinelearningmethods(HegdeandGray,2017;Hegdeetal.,2017)....

    [...]