scispace - formally typeset
Open accessJournal ArticleDOI: 10.1016/J.PTLRS.2021.02.004

Comparison of accuracy and computational performance between the machine learning algorithms for rate of penetration in directional drilling well

02 Mar 2021-Petroleum Research (Elsevier)-Vol. 6, Iss: 3, pp 271-282
Abstract: Oil and gas reservoirs are of the main assets of countries possessing them. Production from these reservoirs is one of the main concerns of engineers, which can be achieved by drilling oil and gas reservoirs. Construction of hydrocarbon wells is one of the most expensive operations in the oil industry. One of the most important parameters affecting drilling cost is the rate of penetration (ROP). This paper predicts the rate of penetration using artificial intelligence and hybrid models on Kaboud oil field well #7 in the directional stage. In this study, different models were constructed through various approaches based on 1878 dataset obtained from drilling operation in the well#7. Then, the accuracy of the constructed models was compared with each other. It was found that the MLP-ABC algorithm predicts the rate of penetration more accurately, by far, as compared with other methods. The MLP-ABC algorithm achieves impressive ROP prediction accuracy (RMSE = 0.007211 m/h; AAPD = 0.1871%; R2 = 1.000 for the testing subset). Consequently, it can be concluded that this method is applicable to predict the drilling rate in that oilfield.

... read more

Topics: Rate of penetration (63%), Directional drilling (58%), Oil field (56%)

6 results found

Open accessJournal ArticleDOI: 10.1016/J.PTLRS.2021.05.009
Anirbid Sircar1, Kriti Yadav1, Kamakshi Rayavarapu1, Namrata Bist1  +1 moreInstitutions (1)
04 Jun 2021-Petroleum Research
Abstract: Oil and gas industries are facing several challenges and issues in data processing and handling. Large amount of data bank is generated with various techniques and processes. The proper technical analysis of this database is to be carried out to improve performance of oil and gas industries. This paper provides a comprehensive state-of-art review in the field of machine learning and artificial intelligence to solve oil and gas industry problems. It also narrates the various types of machine learning and artificial intelligence techniques which can be used for data processing and interpretation in different sectors of upstream oil and gas industries. The achievements and developments promise the benefits of machine learning and artificial intelligence techniques towards large data storage capabilities and high efficiency of numerical calculations. In this paper a summary of various researchers work on machine learning and artificial intelligence applications and limitations is showcased for upstream and sectors of oil and gas industry. The existence of this extensive intelligent system could really eliminate the risk factor and cost of maintenance. The development and progress using this emerging technologies have become smart and makes the judgement procedure easy and straightforward. The study is useful to access intelligence of different machine learning methods to declare its application for distinct task in oil and gas sector.

... read more

7 Citations

Open accessJournal ArticleDOI: 10.22059/JCHPE.2021.314719.1341
Abstract: Determining BPP is one of the critical parameters for the development of oil and gas reservoirs and have this parameter requires a lot of time and money. As a result, this study aims to develop a new predictive model for BPP that uses some available input variables such as solution oil ratio (Rs), gas specific gravity (γg), API Gravity (API). In this study, two innovatively combined hybrid algorithms, DWKNN-GSA and DWKNN-ICA, are developed to predict BPP. The outcomes of the study show the models developed are capable of predicting BPP with promising performance, where the best result was achieved for DWKNN-ICA (RMSE = 0.90276 psi and R2 = 1.000 for the test dataset). Moreover, the performance comparison of the developed hybrid models with some previously developed models revealed that the DWKNN-ICA outperforms the former empirical models with respect to perdition accuracy. In addition to presenting new techniques in the present study, the effect of each of the input parameters on BPP was evaluated using Spearman's correlation coefficient, where the API and Rs have the lowest and the highest impact on the BPP.

... read more

3 Citations

Journal ArticleDOI: 10.1016/J.JNGSE.2021.104210
Abstract: Gas condensate reservoirs display unique phase behavior and are highly sensitive to reservoir pressure changes. This makes it difficult to determine their PVT characteristics, including their condensate viscosity, which is a key variable in determining their flow behavior. In this study, a novel machine learning approach is developed to predict condensate viscosity in the near wellbore regions (μc) from five input variables: pressure (P), temperature (T), initial gas to condensate ratio (RS), gas specific gravity (γg), and condensate gravity (API). Due to the absence of accurate recombination methods for determining μc machine learning methods offer a useful alternative approach. Nine machine learning and hybrid machine learning algorithms are evaluated including novel multiple extreme learning machine (MELM), least squares support vector machine (LSSVM) and multi-layer perceptron (MLP) and each hybridized with a particle swarm optimizer (PSO) and genetic algorithm (GA). The new MELM algorithm has some advantages including 1) rapid execution, 2) high accuracy, 3) simple training, 4) avoidance of overfitting, 5) non-linear conversion during training, 6) no trapping at local optima, 6) fewer optimization steps than SVM and LSSVM. Combining MELM with PSO, to find the best control parameters, further improves its performance. Analysis indicates that the MELM-PSO model provides the highest μc prediction accuracy achieving a root mean squared error (RMSE) of 0.0035 cP and a coefficient of determination (R2) of 0.9931 for a dataset of 2269 data records compiled from gas-condensate fields around the world. The MELM-PSO algorithm generates no outlying data predictions. Spearman correlation coefficient analysis identifies that P, γg and Rs are the most influential variables in terms of condensate viscosity based on the large dataset studied.

... read more

Topics: Overfitting (54%), Least squares support vector machine (53%), Extreme learning machine (53%) ... read more

1 Citations

Open accessJournal ArticleDOI: 10.1016/J.EGYR.2021.06.080
Heng Chen, Jinying Duan, Rui Yin, Vadim V. Ponkratov1  +1 moreInstitutions (2)
25 Jun 2021-Energy Reports
Abstract: Field information analysis is the main element of reducing costs and improving drilling operations. Therefore, the development of field data analysis tools is one of the ways to improve drilling operations. This paper uses mathematical programming and optimization-based methods to present and review learning models for data classification. A comprehensive multi-objective optimization model is proposed by extracting commonalities and the same philosophy of some of the most popular mathematical optimization models in the last few years. The geometric representation of the model will be to make it easier to understand the characteristics of the proposed model. Then it is shown that a large number of models studied in the past and present are subsets, and exceptional cases of this proposed comprehensive model and how to convert the proposed comprehensive model to these methods will be examined. This seeks to bridge the gap between new multi-objective programming models and the powerful and improved CSA-LSSVM methods presented for classification in data mining and to generalize studies to improve each of these methods.

... read more

Topics: Support vector machine (53%), Data classification (52%), Programming paradigm (52%) ... read more

1 Citations

Open accessJournal ArticleDOI: 10.1007/S13202-021-01321-Z
Abstract: One of the challenges in reservoir management is determining the fracture density (FVDC) in reservoir rock. Given the high cost of coring operations and image logs, the ability to predict FVDC from various petrophysical input variables using a supervised learning basis calibrated to the standard well is extremely useful. In this study, a novel machine learning approach is developed to predict FVDC from 12-input variable well-log based on feature selection. To predict the FVDC, combination of two networks of multiple extreme learning machines (MELM) and multi-layer perceptron (MLP) hybrid algorithm with a combination of genetic algorithm (GA) and particle swarm optimizer (PSO) has been used. We use a novel MELM-PSO/GA combination that has never been used before, and the best comparison result between MELM-PSO-related models with performance test data is RMSE = 0.0047 1/m; R2 = 0.9931. According to the performance accuracy analysis, the models are MLP-PSO < MLP-GA < MELM-GA < MELM-PSO. This method can be used in other fields, but it must be recalibrated with at least one well. Furthermore, the developed method provides insights for the use of machine learning to reduce errors and avoid data overfitting in order to create the best possible prediction performance for FVDC prediction.

... read more

Topics: Supervised learning (59%), Overfitting (58%), Perceptron (56%) ... read more


63 results found

Journal ArticleDOI: 10.1016/0893-6080(89)90020-8
01 Jul 1989-Neural Networks
Abstract: This paper rigorously establishes that standard multilayer feedforward networks with as few as one hidden layer using arbitrary squashing functions are capable of approximating any Borel measurable function from one finite dimensional space to another to any desired degree of accuracy, provided sufficiently many hidden units are available. In this sense, multilayer feedforward networks are a class of universal approximators.

... read more

15,834 Citations

Open accessJournal ArticleDOI: 10.5555/70405.70408
01 Jul 1989-Neural Networks

9,800 Citations

Open accessBook
16 Oct 1996-
Abstract: Preface. RESERVOIR ENGINEERING. Basic Principles, Definitions, and Data. Formation Evaluation. Pressure Transient Testing of Oil and Gas Wells. Mechanisms and Recovery of Hydrocarbons by Natural Means. Material Balance and Volumetric Analysis. Decline-Curve Analysis. Reserve Estimates. Secondary Recovery. Fluid Movement in Waterflooded Reservoirs. Estimating Waterflood Residual Oil Saturation. Enhanced Oil Recovery Methods. References. PRODUCTION ENGINEERING. Properties of Hydrocarbon Mixtures. Flow of Fluids. Natural Flow Performance. Artificial Lift Methods. Stimulation and Remedial Operations. Surface Oil Production Systems. Gas Production Engineering. Corrosion and Scaling. Environmental Considerations. Offshore Operations. References. PETROLEUM ECONOMICS. Estimating Oil and Gas Reserves. Classification of Petroleum Products. Methods for Estimating Reserves. Non-Associated Gas Reservoirs. Production Stimulation. Determining the Value of Future Production. The Market for Petroleum. Economics and the Petroleum Engineer. Preparation of a Cash Flow. Valuation of Oil and Gas Properties. Risk Analysis. References. Appendix: Units and Conversions (SI). Index.

... read more

Topics: Petroleum production engineering (72%), Petroleum (62%), Reservoir engineering (62%) ... read more

374 Citations

Open accessJournal ArticleDOI: 10.1038/S41597-020-00642-8
12 Oct 2020-Scientific Data
Abstract: The availability of high-quality RNA-sequencing and genotyping data of post-mortem brain collections from consortia such as CommonMind Consortium (CMC) and the Accelerating Medicines Partnership for Alzheimer’s Disease (AMP-AD) Consortium enable the generation of a large-scale brain cis-eQTL meta-analysis. Here we generate cerebral cortical eQTL from 1433 samples available from four cohorts (identifying >4.1 million significant eQTL for >18,000 genes), as well as cerebellar eQTL from 261 samples (identifying 874,836 significant eQTL for >10,000 genes). We find substantially improved power in the meta-analysis over individual cohort analyses, particularly in comparison to the Genotype-Tissue Expression (GTEx) Project eQTL. Additionally, we observed differences in eQTL patterns between cerebral and cerebellar brain regions. We provide these brain eQTL as a resource for use by the research community. As a proof of principle for their utility, we apply a colocalization analysis to identify genes underlying the GWAS association peaks for schizophrenia and identify a potentially novel gene colocalization with lncRNA RP11-677M14.2 (posterior probability of colocalization 0.975).

... read more

241 Citations