Advanced monopole and dipole sonic log data processing – part 1: real-time

Geophysics ◽  
2020 ◽  
pp. 1-91
Author(s):  
Ruijia Wang ◽  
Brian Hornby ◽  
Kristoffer Walker ◽  
Chung Chang ◽  
Gary Kainer ◽  
...  
Keyword(s):  
Data Processing ◽  
Real Time ◽  
Shear Wave ◽  
Time Window ◽  
Human Interaction ◽  
Data Driven ◽  
Flexural Wave ◽  
Frequency Domain Method ◽  
Rock Formation ◽  
Sonic Logging

Real-time open hole wireline sonic logging data processing becomes a nontrivial task to accurately, automatically and efficiently evaluate both the compressional and shear slowness of a borehole rock formation when human interaction is not possible and signal processing time is limited to elapsed time between different transmitter firings. To address real-time sonic data processing challenges, we present self-adaptive, data-driven methods to accurately measure formation compressional and shear wave slowness from both monopole and dipole waveforms in all types of formations. These new real-time processing techniques take advantage of the fact that advanced wireline sonic logging tools have wide frequency responses and little to no detectable tool body arrivals. These technology improvements provide an opportunity to implement a first-motion-detection technique that detects the onset of compressional waves in the monopole array waveforms. The knowledge of compressional arrival time and corresponding slowness are then used to project an appropriate slowness-time window in order to identify the monopole refracted shear wave and its slowness based on the range of possible Vp/Vs for earth rock formation. To process the borehole dipole flexural waves, we provide a new, data-driven frequency domain method that enables the evaluation of the full flexural-wave dispersion response and its corresponding low-frequency shear slowness asymptote. Field data processing results show that our methods provide high-quality compressional slowness (DTC) and shear slowness(DTS) measurements that are not affected by other borehole modes or dispersion complications in all formation types.

Automating the audience commodity: The unacknowledged ancestry of programmatic advertising

2019 ◽  
Vol 21 (11-12) ◽  
pp. 2366-2385 ◽  
Author(s):  
Lee McGuigan
Keyword(s):  
Information Technology ◽  
Data Processing ◽  
Real Time ◽  
Mathematical Optimization ◽  
Leading Edge ◽  
Digital Data ◽  
Data Driven ◽  
Commercial Media ◽  
History Of ◽  
History Of Information

Programmatic advertising describes techniques for automating and optimizing transactions in the audience marketplace. Facilitating real-time bidding for audience impressions and personalized targeting, programmatic technologies are at the leading edge of digital, data-driven advertising. But almost no research considers programmatic advertising within a general history of information technology in commercial media industries. The computerization of advertising and media buying remains curiously unexamined. Using archival sources, this study situates programmatic advertising within a longer trajectory, focusing on the incorporation of electronic data processing into the spot television business, starting in the 1950s. The article makes three contributions: it illustrates that (1) demands for information, data processing, and rapid communications have long been central to advertising and media buying; (2) automation “ad tech” developed gradually through efforts to coordinate and accelerate transactions; and (3) the use of computers to increase efficiency and approach mathematical optimization reformatted calculative resources for media and marketing decisions.

Advanced real-time sonic logging data processing

2016 ◽  
Author(s):  
Ruijia Wang ◽  
Chung Chang ◽  
Gary Kainer ◽  
John Granville ◽  
Kristoffer Walker ◽  
...  
Keyword(s):  
Data Processing ◽  
Real Time ◽  
Sonic Logging

Automatic Identification of Rock Formation Type While Drilling Using Machine Learning Based Data-Driven Models

2021 ◽  
Author(s):  
Enrique Z. Losoya ◽  
Narendra Vishnumolakala ◽  
Samuel F. Noynaert ◽  
Zenon Medina-Cetina ◽  
Satish Bukkapatnam ◽  
...  
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Real Time ◽  
Prediction Accuracy ◽  
Classification Model ◽  
Data Driven ◽  
Classification Algorithms ◽  
Rock Formation ◽  
Mechanical Specific Energy ◽  
Formation Type

Abstract The objective of this study is to present a novel rock formation identification model using a data-driven modeling approach. This study explores the use of real-time drilling data to train and validate a classification model to improve the efficiency of the drilling process by reducing Mechanical Specific Energy (MSE). In this study, we demonstrate the feasibility of a layer-based determination and change detection of properties of rock formation currently being drilled as accurately and fast as possible. Data for this study was collected from a custom-built lab-scale drilling rig equipped with multiple sensors. The experiment was conducted by drilling through an arrangement of different rock formations of varying rock strength properties. Data was recorded and stored at a frequency of 2 kHz, then filtered, processed, and downsampled to extract relevant features. This dataset was used to train an Artificial Neural Network and other machine learning classification algorithms. Feature selection was made first with ten most notable features found by Random Forest, and the second set with derived measurements and down-sampled dynamic features from the sensors. The classification analysis was divided into two steps: the best predictors/features extraction and classification model building. The models were trained using multiple classification algorithms, namely logistic regression, linear discriminant analysis (LDA), Support Vector Machines (SVM), Random Forest (RF), and Artificial Neural Networks (ANN). It was found that random forest and ANN performed the best with prediction accuracy of 99.48% and 99.58%, respectively, for the data set with ten most prominent features. The high prediction rate accuracy for the most prominent predictors suggests that if the high-frequency data can be processed in real-time, predicting what formation we are drilling in is possible to achieve in near real-time. This can lead to significant savings for drilling companies as optimal drilling parameters can be computed, and in turn, optimized Mechanical Specific Energy can be obtained in real-time. Since the rock formation identification is time-consuming, we also describe here an alternative approach using slightly less accurate but equally powerful dynamic predictors. In this case, we show that our dynamic predictor models with RF and ANN yielded prediction accuracy of 96.30% and 95.61%, respectively. Both the prominent feature and dynamic predictor approaches are described in detail in this paper. Our results suggest that accurately predicting rock formation type in real-time while drilling is very much feasible with lesser computational cost and complexity. This study provides the building blocks for the development of a completely autonomous downhole device and Electronic Device Recorders (EDR) that reduces the need for highly sophisticated sensors or data transmission processes downhole.

APPLICATION OF LWD ACOUSTIC DISPERSIVE DATA PROCESSING FOR HIGH-QUALITY SHEAR SLOWNESS LOGS IN SLOW FORMATIONS

2021 ◽  
Author(s):  
Ruijia Wang ◽  
◽  
Jiajun Zhao ◽  
Taher Kortam ◽  
◽  
...  
Keyword(s):  
Data Processing ◽  
Shear Wave ◽  
Dispersion Model ◽  
Cutoff Frequency ◽  
Data Driven ◽  
Dispersion Correction ◽  
Flexural Waves ◽  
Differential Phase ◽  
Slowness Vector ◽  
Density Map

For conventional acoustic monopole sources in a logging-while-drilling (LWD) or wireline environment, shear slowness logs can be hard to obtain, particularly in slow formations where direct refracted shear-wave arrivals are often absent. For LWD dipole sources, formation flexural waves are often coupled with the lowest order of tool flexural waves, so the flexural mode does not approach shear wave slowness at low frequencies. A dispersion correction is required to extract shear slowness from LWD dipole data. Instead, a quadrupole firing, which generates screw waves, is considered the best LWD excitation mode for shear measurement. A fundamental feature of screw waves in an LWD environment is that their non-leaky cutoff frequency slowness is the formation shear slowness. However, slowness data near the cutoff frequency of LWD screw waves are often influenced by noise or the presence of other modes because of low excitation amplitude. To overcome these LWD data processing challenges, we propose a data-driven processing method that uses all useful dispersion responses of existing modes in the frequency domain. The process first generates a differential phase frequency-slowness coherence map and extracts the slowness dispersion vs. frequency. Then, it computes the slowness density log, referring to the intensity of the dispersion response along the slowness axis. Next, an edge-detection method is applied to capture the edge of the first peak associated with shear slowness on the slowness density map. To refine the shear slowness answer, this initial estimate of shear slowness serves as the input to another algorithm that minimizes the misfit between the screw slowness vector and a simplified screw dispersion model. The simplified screw dispersion model consists of a pre-computed base library of theoretical screw dispersion curves and two data-driven parameters. The two data-driven parameters are used by the measured data to stretch the base dispersion model in the frequency and slowness axes, respectively, to account for errors generated by alteration, anisotropy, or other parameters not included in the forward modeling. The method can also be applied to flexural waves, where the initial guess of shear slowness is picked from the slowness density map of flexural waves after dispersion-correction processing. This paper shows a case study of borehole flexural and screw waves processing in soft formations. A modified differential-phase frequency-semblance (MDPFS) approach is applied to extract the mode waves' full-frequency dispersion response from measured waveforms. The data-driven shear slowness processing is applied to the dispersion response. Both dipole flexural waves and quadrupole screw waves are processed. A combination of slowness density log from the flexural or screw wave slowness and the dispersion-corrected slowness is used as a QC metric of the final estimated shear. Results show that flexural and screw dispersions are well measured by the LWD sonic tool, even if the shear slowness is as large as 500 s/ft. Shear slowness extracted from flexural waves and screw waves match well with each other and with wireline shear slowness logs, demonstrating that the processing is reliable and robust.

scholarly journals Data-Driven Dispatching Rules Mining and Real-Time Decision-Making Methodology in Intelligent Manufacturing Shop Floor with Uncertainty

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4836
Author(s):  
Liping Zhang ◽  
Yifan Hu ◽  
Qiuhua Tang ◽  
Jie Li ◽  
Zhixiong Li
Keyword(s):  
Decision Making ◽  
Data Base ◽  
Real Time ◽  
Manufacturing Industry ◽  
Job Shop ◽  
Data Driven ◽  
Dispatching Rules ◽  
Shop Floor ◽  
Production Data ◽  
Online Decision Making

In modern manufacturing industry, the methods supporting real-time decision-making are the urgent requirement to response the uncertainty and complexity in intelligent production process. In this paper, a novel closed-loop scheduling framework is proposed to achieve real-time decision making by calling the appropriate data-driven dispatching rules at each rescheduling point. This framework contains four parts: offline training, online decision-making, data base and rules base. In the offline training part, the potential and appropriate dispatching rules with managers’ expectations are explored successfully by an improved gene expression program (IGEP) from the historical production data, not just the available or predictable information of the shop floor. In the online decision-making part, the intelligent shop floor will implement the scheduling scheme which is scheduled by the appropriate dispatching rules from rules base and store the production data into the data base. This approach is evaluated in a scenario of the intelligent job shop with random jobs arrival. Numerical experiments demonstrate that the proposed method outperformed the existing well-known single and combination dispatching rules or the discovered dispatching rules via metaheuristic algorithm in term of makespan, total flow time and tardiness.

Sign in / Sign up

Export Citation Format

Share Document