|Theme||Visible||Selectable||Appearance||Zoom Range (now: 0)|
In recent times, several machine learning algorithms have been utilized to analyze massive amount of data and provide fast and effective smart solution. To monitor the saturation over time, reservoir saturation tool is run in each well to provide the cased hole saturations. A single well may have as many has 15-20 runs over time which provides an estimate of present saturation, depletion across reservoirs or any other changes in saturation profile to EOR system in place and its impact. This paper demonstrates the idea of the use of machine learning algorithm to perform a time lapse saturation analysis and present a saturation forecast based on class-based machine learning combined with the time series modelling using multiple time lapse runs in a single well for a field. The first step involves using an unsupervised class-based machine learning model that classifies the input petrophysical data into set of classes with distinct similarity. The next step of the workflow involves using time series modeling on each of the obtained classes. Different methods were studied and eventually "Prophet" was used for time series modeling to forecast saturation over time. A way forward and game changer is propagating the classes to multiple wells with multi runs and predict the changes in saturation and pressure for a formation across a field to make holistic interpretation. Reversing the time series modeling can also provide an estimate of OH conditions and original hydrocarbon in place. The use of CBML and time series modelling for petrophysical saturation evaluation will open new doors to understanding of fields already under production and introduce smart decision-making capabilities. The idea presented in this paper can be implemented in different fields across the globe with different formation settings and EOR system in place and can be further advanced in terms of providing deep insight and interpretation like forecasting the change in reservoir pressure.
Cementing forms an essential part of well construction as it supports the casing and provides hydraulic sealing. Wireline (WL) sonic tools have been providing the cement evaluation (CBL/VDL) for more than 50 years. Quantitative cement evaluation is becoming increasingly important in the industry to verify well integrity and zonal isolation. There has been a growing interest in providing cement bond quality quantitatively with LWD sonic tools owing to its plethora of benefits over wireline logging, such as rig time saving, tool conveyance, less tool eccentering effect and timelapse evaluation. However, there is also an LWD specific challenge that has for long hindered the ability to measure quantitative bond index i.e. drill collar contamination which limits the range of cement bond evaluation with the conventional amplitude-based approach. Deriving a characteristic correlation of attenuation measurement against the bond index was one of the key components to overcoming the limitation of amplitude-based. A new hybrid processing approach combining amplitude and attenuation was established for full-range cement bond evaluation. Schlumberger's LWD multipole sonic Cement Evaluation Service delivers the industry's first quantitative bond index answer product on LWD platform. The quantitative bond index becomes even more critical in offshore and deepwater markets.
This paper discusses, in brief, the technology and associated challenges in delivering industry's first quantitative bond index and showcases the result for one of the deepwater well. A subsequent comparison of LWD multipole sonic cement evaluation results with conventional WL CBL-VDL further corroborates the reliability of the result. The performance of the industry's first LWD bond index derived using LWD multipole sonic from around the globe has demonstrated that it can be expected to show abundant success in expanding the LWD utilization globally
Saumya, Sachit (Schlumberger) | Sarkar, Sujit Kumar (Schlumberger) | Singh, Juli (Schlumberger) | Kumar, Ajit (Schlumberger) | Agarwal, Gaurav (Schlumberger) | Khambra, Isha (Schlumberger) | Vij, Jitesh (Schlumberger) | Das, Bhaswati (Schlumberger) | Shedde, Preetika (Schlumberger) | Majumdar, Chandan (Schlumberger) | Pabla, S (ONGC)
Drilling is carried out in the very early stage of the well and it is critical for ensuring smooth execution of every aspect of well construction such as faster drilling, better hole cleaning, superior logging, running casing efficiently, maintaining wellbore integrity and achieving economic production. This paper will demonstrate the significance of best drilling practices to achieve good wellbore geometry, which has a profound effect on total well construction and production time and cost and sometimes even determine the success of the well.
Poor wellbore geometry, because of improper choice of drilling system i.e. mud motor or rotatory steerable, is generally related to the washed out and/or spiraled wellbore. Washed out hole is recognized by using calipers, however, the hole spiraling is difficult to detect at the early stage of the well. In spiraled holes, it becomes virtually impossible to get a good cementing job done. The poor cementing conditions behind the casing are identified using ultra-sonic images or high amplitudes values of CBL/VDL. These channels behind casing are, a clear threat to production and life cycle of the well. It is widely assumed that the squeeze jobs are an option to improve cement behind casing, however, it does not hold true in case of a spiral borehole. This paper compares the wells, drilled with different drilling system and their impact on the wellbore geometry. It also exhibits the aftermath effects on wellbore construction, well integrity and production.
Since its arrival in 1989, logging while drilling (LWD) technology has become an integral part of the industry. The possibility of real-time measurements, saving rig time, with the significant advantage of logging in better-shaped and less invaded boreholes, is the major advantage of LWD technology. Although LWD tools are developed with the aim to deliver results like those from wireline tools, the need to withstand harsh drilling conditions manifests as starkly different tool designs, thus precluding the acquisition of certain types of measurements or lowering the precision or accuracy of others.
Despite the significant advances that have been made in LWD technology, there is significant room to fully use its potential for advanced workflows. Because a significant amount of evaluation done in the industry today still uses conventional logs, it can be reasonably assumed that the capability and versatility of LWD tools is not always realized. The paper seeks to explain the value of LWD tools by systematically enlisting all relevant technology and discussing its current scope, limitations, and untapped potential.
Sarkar, Sujit (Schlumberger) | Majumdar, Chandan (Schlumberger) | Das, Ritwika (Schlumberger) | Srivastava, Chandramani (Schlumberger) | Vij, Jitesh (Schlumberger) | Hussain, Syed Aaquib (Schlumberger) | Joshi, Kireet (Schlumberger) | Saumya, Sachit (Schlumberger)
Borehole sonic measurements are acquired while drilling, on e-line and through the bit using various configuration of transmitters and receivers. The waveforms recorded at receivers from different sources can be analysed distinctly in a slowness frequency dispersion plot for verification of slowness accuracy. Proper dispersion analysis and interpretation requires consideration of many factors such as measurement physics, logging conditions, formation type and knowledge and experience.
The frequency-dispersion plots have proven to be the most robust and reliable method to quality check the data for both dispersive and non-dispersive waves. The other frequently used methods, for example, coherence plot, slowness frequency analysis (SFA) can be considered as complementary. Results from various environments such as borehole washout/rugosity, near wellbore alteration and damage, slow formation, anisotropy, eccentricity effects, and cased hole are captured and analysed. The uncertainty in measured slowness can be introduced by acquisition method, borehole/formation condition and processing parameters. Moreover, this is further propagated to various sonic based solutions. It is an attempt to understand the uncertainty of the available sonic logging technologies from a single reference point i.e. frequency-dispersion plot, instead of going into the details of acquisition and cumbersome processing complexities. In addition to that, the compilation of a wide range of examples from the different borehole and lithologic environment may serve as a standard reference and ready reckoner to demystify the sonic uncertainties in complex logging environments.