A pattern recognition modeling approach based on the intelligent ensemble classifier: Application to identification and appraisal of water-flooded layers
Restricted accessResearch articleFirst published online August, 2019
A pattern recognition modeling approach based on the intelligent ensemble classifier: Application to identification and appraisal of water-flooded layers
Since the actual chromatogram data of the water-flooded layer have characteristics of multiple dimension, complexity and noise, it is difficult to accurately identify and appraise the water-flooded layer in the oil and gas reservoirs. Therefore, this article proposes a recognition modeling approach based on the intelligent ensemble classifier, integrated model-free Bayesian classifier, the AdaBoost algorithm and the support vector machine algorithm. The effective chromatogram characteristic information can be obtained using the curve fitting method. In order to transform the sparse classification problem into a general classification problem, the synthetic minority over-sampling technique algorithm is used to process an unbalanced training sample as a general training sample. Moreover, the model-free Bayesian classifier, AdaBoost and support vector machine algorithms are used as the base classifiers to train the ensemble classification model. Compared to the traditional single classification approach, the robustness and the effectiveness of the ensemble classifier model are validated through the standard data source from the UCI (University of California at Irvine) repository. Finally, the proposed model is applied in the identification and appraisal of the water-flooded layers in a complex oil and gas recognition system. The chromatogram characteristic information and the prediction results are obtained to provide more reliable water-flooded layer information, guide the process of reservoir exploration and improve the oil development efficiency.
ChengzaoJYongfengZXiaZ.Prospects of and challenges to natural gas industry development in China. Nat Gas Ind B2014; 1(1): 1–13.
2.
ZhangMLGuoFLinJH.The application of dynamic development data in low-permeability reservoir water flooded layer identification. Appl Mech Mater2015; 733: 148–151.
3.
ZhangSZCaiMWangC.Identification research about low permeable water flooded layer in west of daqing. Adv Mater Res2012; 347–353: 694–698.
4.
Hernandez-TorresJVillamizarGASalgar-ChaparroSJet al. Prokaryotic community characterization in a mesothermic and water-flooded oil reservoir in Colombia. Geomicrobiol J2015; 33(2): 110–117.
5.
ZhangFSheYChaiLet al. Microbial diversity in long-term water-flooded oil reservoirs with different in situ temperatures in China. Sci Rep2012; 2: 760.
6.
AleardiM.Seismic velocity estimation from well log data with genetic algorithms in comparison to neural networks and multilinear approaches. J Appl Geophys2015; 117: 13–22.
7.
LuoJZhouWSuZet al. Comparison of fully-porous beads and cored beads in size exclusion chromatography for protein purification. Chem Eng Sci2013; 102: 99–105.
8.
CaiJLiCTangXet al. Experimental study of water wetting in oil–water two phase flow: horizontal flow of model oil. Chem Eng Sci2012; 73: 334–344.
9.
ShiWZhangCYuanSet al. A crossplot for mud logging interpretation of unconventional gas shale reservoirs and its application. Open Petrol Eng J2015; 8(1): 265–271.
10.
YuanJDengJLuoYet al. The research on borehole stability in depleted reservoir and caprock: using the geophysics logging data. Sci World J2013; 2013: 965754.
11.
FarrellKMHarrisWBMallinsonDJet al. Graphic logging for interpreting process-generated stratigraphic sequences and aquifer/reservoir potential: with analog shelf to shoreface examples from the Atlantic Coastal Plain province, U.S.A. J Sediment Res2013; 83(8): 723–745.
12.
JanaSOjhaMSainK.Gas hydrate saturation from heterogeneous model constructed from well log in Krishna–Godavari Basin, Eastern Indian Offshore. Geophys J Int2015; 203(1): 246–256.
13.
ShenQJiangBCocquempotV.Fuzzy logic system-based adaptive fault-tolerant control for near-space vehicle attitude dynamics with actuator faults. IEEE T Fuzzy Syst2013; 21(2): 289–300.
14.
KrishnakumariAElayaperumalASaravananMet al. Fault diagnostics of spur gear using decision tree and fuzzy classifier. Int J Adv Manuf Techn2017; 89(9–12): 3487–3494.
15.
LiCH.Adaptive recurrent Chebyshev neural network control for permanent magnet synchronous motor servo-drive electric scooter. Proc IMechE, Part I: J Systems and Control Engineering2014; 228(9): 699–714.
16.
HesarmaskanKHEbrahimHA.A novel modeling, simulation and optimization approach of crude oil cold stripping process. Chin Petrol Process Petrochem Technol2013; 15(1): 78–84.
17.
LiuCHsaioWLeeCet al. Semi-supervised text classification with Universum learning. IEEE T Syst Man Cyb2016; 46(2): 462–473.
WeinbergSAWatsonJSRamseyGHet al. X-ray motion picture techniques employed in medical diagnosis and research. J Soc Motion Pic T1952; 59(4): 300–308.
20.
ZhangFHongLIShaoCet al. Application of artificial neural network pattern recognition technology to the study of well-logging sedimentology. Petrol Explor Dev2003; 30(3): 121–123.
WangYPedramM.Model-free reinforcement learning and Bayesian classification in system-level power management. IEEE T Comput2016; 65(12): 3713–3726.
23.
Martin-DiazIMorinigo-SoteloDDuque-PerezOet al. Early fault detection in induction motors using Adaboost with imbalanced small data and optimized sampling. IEEE T Ind Appl2017; 53: 3066–3075.
24.
YinSOuyangPDaiXet al. An Adaboost-based face detection system using parallel configurable architecture with optimized computation. IEEE Syst J2015; 11: 260–271.
25.
PaulSMagdon-IsmailMDrineasP.Feature selection for linear SVM with provable guarantees. Pattern Recogn2016; 60: 205–214.
26.
FattahiMAbediniHBaghbanAet al. Application of LS-SVM strategy to estimate H2S loading capacity in different ionic liquids and alkanolamines. Petrol Sci Technol2017; 35(11): 1117–1123.
27.
MondalDChakrabortyAKoleDKet al. Detection and classification technique of yellow vein mosaic virus disease in okra leaf images using leaf vein extraction and Naive Bayesian classifier. In 2015 International Conference onSoft Computing Techniques and Implementations (ICSCTI). Faridabad, India, 2016June, pp. 166–171. IEEE.
28.
WangXHeYWangDD.Non-Naive Bayesian classifiers for classification problems with continuous attributes. IEEE T Syst Man Cyb2014; 44(1): 21–39.
29.
ZhangHLiuGChowTWet al. Textual and visual content-based anti-phishing: a Bayesian approach. IEEE T Neural Networ2011; 22(10): 1532–1546.
30.
FreundYIyerRSchapireREet al. An efficient boosting algorithm for combining preferences. J Mach Learn Res2003; 933–969.
31.
ChenTGuestrinC.Xgboost: a scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining, New York, USA, 2016, August, pp. 785–794: ACM.
32.
MaJLiZTWangBB.Application of singular spectrum analysis to the noise reduction of intrusion detection alarms. J Comput2011; 6(8): 1715–1722.
RiondatoMUpfalE.VC-dimension and Rademacher averages: from statistical learning theory to sampling algorithms. In Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, USA, 2015, August, pp. 2321–2322. ACM.
35.
SwaminathanAJoachimsT.Batch learning from logged bandit feedback through counterfactual risk minimization. J Mach Learn Res2015; 16(1): 1731–1755.
36.
Cárdenas-GalloISarmientoCAMoralesGAet al. An ensemble classifier to predict track geometry degradation. Reliab Eng Syst Safe2017; 161: 53–60.
37.
CogranneRFridrichJ.Modeling and extending the ensemble classifier for steganalysis of digital images using hypothesis testing theory. IEEE T Inf Foren Sec2015; 10(12): 2627–2642.
38.
RahmanATasnimS.Ensemble classifiers and their applications: a review. Int J Comput Trend Technol2014; 10(1): 31–35.
39.
AbawajyJKelarevAVChowdhuryM.Large iterative multitier ensemble classifiers for security of big data. IEEE T Emerg Topic Comput2014; 2(3): 352–363.
40.
HallackLNSzkloASJúniorAOPet al. Curve-fitting variants to model Brazil’s crude oil offshore post-salt production. J Petrol Sci Eng2017; 159: 230–243.
41.
KhanukaevaDYFilippovAN.Statistical processing of ultrafiltration membrane pore size distribution determined by atomic force microscopy. Petrol Chem2015; 55(10): 909–917.
42.
AgnihotriSPWaghmareLM.Iterative algorithm and curve fitting technique for tuning with time delay system PID controller. J Intell Fuzzy Syst2015; 29(4): 1527–1537.
43.
BlagusRLusaL.Smote for high-dimensional class-imbalanced data. BMC Bioinform2013; 14(1): 106.
44.
SheridanRP.Time-split cross-validation as a method for estimating the goodness of prospective prediction. J Chem Inform Model2013; 53(4): 783–790.
45.
HeLHuDWanMet al. Common Bayesian network for classification of EEG-based multiclass motor imagery BCI. IEEE T Syst Man Cy S2017; 46(6): 843–854.
46.
HassanatABAbbadiMAAltarawnehGAet al. Solving the problem of the K parameter in the KNN classifier using an ensemble learning approach. Comput Sci2014; 12(8): 33–39.
47.
SharmaSAgrawalJSharmaS.Classification through machine learning technique: C4.5 algorithm based on various entropies. Int J Comput Appl2013; 82(16): 28–32.
48.
MasonJPKirkIWindsorCGet al. A novel algorithm for chromatogram matching in qualitative analysis. J Sep Sci2015; 15(8): 539–547.
49.
AlmarshedAHartALeekeGAet al. Effectiveness of different transition metal dispersed catalysts for in situ heavy oil upgrading. Ind Eng Chem Res2015; 54(43): 10645–10655.
50.
RouchesEDignacMFZhouSet al. Pyrolysis-GC–MS to assess the fungal pretreatment efficiency for wheat straw anaerobic digestion. J Anal Appl Pyrol2017; 123: 409–418.
