Half a century experience in rate of penetration management: Application of machine learning methods and optimization algorithms - A review

Najjarpour, Mohammad; Jalalifar, Hossein; Norouzi-Apourvari, Saeid

doi:10.1016/j.petrol.2021.109575

Cited by 30 publications

(8 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The dataset, including 62 experimental values, was randomly divided into a training subset of 44 values (approximation of 70%), a test subset of 9 values (approximation of 15%), and a CV subset of 9 values (approximation of 15%). [ 16 ] The architecture of the neural network is I(6)‐HL(m)‐O(1), in which six neurons of the input layer I(6) are dipole, 5 C, 4 N, fw, xc3, and ka1; the output layer with one neuron the logβ 12 values. The number of neurons of the hidden layer (m) was surveyed, and the initial values of the m neurons are indicated in table 4.…”

Section: Resultsmentioning

confidence: 99%

“…Generally, an artificial neural network (ANN) is a machine learning method and it is widely used in the modeling technique and applied in many fields. [ 16 ] This study used to be training deep neural networks (DNN), namely multi‐layer perceptron (MLP) type and Levenberg‐Marquardt back‐propagation algorithm, [ 17 ] so the architecture of ANN includes three layers I( k )‐HL( m )‐O( n ) that is an input layer, one hidden layer, and an output layer. The number of neurons in the input layer ( k ) is the descriptor of the MLR model, an output layer ( n ) is the stability constant (logβ 12 ), and the number of hidden neurons ( m ) is determined by neurons on the input and output layer.…”

Section: Methodsmentioning

confidence: 99%

“…(approximation of 15%). [16] The architecture of the neural network is I(6)-HL(m)-O(1), in which six neurons of the input layer I(6) are dipole, 5 C, 4 N, fw, xc3, and ka1; the output layer with one neuron the log12 values. The number of neurons of the hidden layer (m) was surveyed, and the initial values of the m neurons are indicated in table 4.…”

Section: Constructing Qsprmlr Modelsmentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Design, virtual screening and in silico QSPR modeling for the development of new thiosemicarbazone‐based complexes

Quang,

Chau,

Hoa

et al. 2023

Vietnam Journal of Chemistry

View full text Add to dashboard Cite

Eighteen new thiosemicarbazone ligands and 30 new ligand‐based complexes were developed from quantitative structure‐property relationships (QSPR) methods. Stability constants (logβ12) of complexes were calculated on QSPR models that were built by methods of multivariate linear regression (MLR) and artificial neural network (ANN). Six descriptors, including dipole, 5C, 4N, fw, xc3, and ka1 were discovered in the best QSPRMLR model with the good statistical criteria: R2train = 0.892, Q2CV = 0.845, and SE = 0.900. Besides, the ANN model with architecture I(6)‐HL(3)‐O(1) was built from the descriptors of the MLR model with excellent results as R2train = 0.958, Q2CV = 0.966, and Q2test = 0.980. Also, the models were externally validated on the other experimental dataset. Consequently, the resulting QSPR models could be applied to develop new complexes for chemically related fields.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Constructing Qsprmlr Modelsmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Design, virtual screening and in silico QSPR modeling for the development of new thiosemicarbazone‐based complexes

Quang,

Chau,

Hoa

et al. 2023

Vietnam Journal of Chemistry

View full text Add to dashboard Cite

show abstract

“…Increasing the ROP has been the main target of drilling in the O-G industry [31]. Excessive increases in the ROP can cause problems such as stuck pipes, poor hole cleaning, and drill bit tooth wear [26] in addition to drilling vibrations and fast drill bit warming [32,33].…”

Section: Introductionmentioning

confidence: 99%

Analysis and Multi-Objective Optimization of the Rate of Penetration and Mechanical Specific Energy: A Case Study Applied to a Carbonate Hard Rock Reservoir Based on a Drill Rate Test Using Play-Back Methodology

Mantegazini,

Nascimento,

Dornelas

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

Until early 2006, in Brazil, the focus used to be on oil and gas exploration/exploitation of post-salt carbonates. This changed when the industry announced the existence of large fields in pre-salt layers across the South Atlantic Ocean from nearshore zones up to almost 350 [km] from the shore. With the discovery of pre-salt hydrocarbons reservoirs, new challenges appeared. One of the main challenges is the necessity to optimize the drilling processes due to their high operational costs. Drilling costs are considerably high, which leads the oil and gas industry to search for innovative and entrepreneurial methods. The coupling of the mechanical specific energy (MSE) and the rate of penetration (ROP) is a method that allows for the identification of ideal conditions to efficiently enhance the drilling process. In addition, the performance of the drilling process can be estimated through pre-operational tests, which consist in continuously testing the applied drilling mechanic parameters, such as the weight-on-bit (WOB) and drill string rotary speed (RPM), looking for optimum sets that would ultimately provide the most desirable ROP. Thus, the goal of this research was to analyze field data from pre-salt layer operations, using a multi-objective optimization based on the play-back methodology for pre-operational drilling tests, through the ideal combination of the highest ROP and the lowest MSE. The results showed that the new concept of pre-operational tests based on the MSE proved to be effective in the drilling process optimization. The combination of the highest ROP and the lowest MSE allows for a high-performance drilling process. For WOB intervals of 5 and 7 [klb], a good fit of the parameters was obtained. Through the parameters obtained from pre-operational tests, the eventual cost-saving and time-saving values could be estimated, respectively, ranging from USD 1,056,180 to 1,151,898 and 19.50 to 21.27 [h], respectively. In addition, the results of this research can be applied to the exploration of other natural resources, such as natural hydrogen and geothermal sources.

show abstract

Automated neural network optimization for data-driven predictive models: an application to ROP in drilling

Khebouri,

Rechak,

Boulham

et al. 2024

Soft Comput

View full text Add to dashboard Cite

Half a century experience in rate of penetration management: Application of machine learning methods and optimization algorithms - A review

Cited by 30 publications

References 72 publications

Design, virtual screening and in silico QSPR modeling for the development of new thiosemicarbazone‐based complexes

Design, virtual screening and in silico QSPR modeling for the development of new thiosemicarbazone‐based complexes

Analysis and Multi-Objective Optimization of the Rate of Penetration and Mechanical Specific Energy: A Case Study Applied to a Carbonate Hard Rock Reservoir Based on a Drill Rate Test Using Play-Back Methodology

Automated neural network optimization for data-driven predictive models: an application to ROP in drilling

Contact Info

Product

Resources

About