Every year, the complexity of horizontal wells grows, and matrix stimulation of these wells is key for maintaining production levels and improving the draw-down from producing formations. In the subject field, many wells are drilled as mega-reach with measured total depths up to 33,000 ft. The mega-reach represents a significant challenge for coiled tubing to reach the total depth (TD) and perform well interventions such as stimulation and logging. Coiled tubing (CT) may lock up before TD, and it can be challenging to understand the root cause. One difficulty is differentiating between lockups due to the well conditions and bottom-hole assembly (BHA) malfunctions. Electric submersible pump (ESP) completions contain bypass assemblies that impose an additional challenge introducing a restriction in tubing internal diameters. The restriction is less than 2.50" in the completion, increasing to 8-1/2" for the open hole, extending for at least 5,000 ft laterally in the producing formation. With the large variation in internal diameter (ID), the hydraulic tractor option is excluded from the mega-reach aid list, though it has proven reliable in extending the reach of CT for 6-1/8" openhole sizes in the same field. Therefore, the challenge here is to derive the maximum output possible from fluidic oscillation vibratory tools to achieve forces close enough to tractor forces and ultimately accomplishing the intervention objective. A combination of mechanical and chemical solutions was the designated approach to tackle the challenge. After reviewing all the possible solutions, tractors were excluded due to the extreme expansion ratio needed resulting in lower pulling forces. A fluidic oscillation tool inducing axial vibration of an absolute magnitude exceeding 1,600 lbf was yard tested and deployed as a solution in combination with a selection of friction and drag reducers. This paper will illustrate the reach challenges, analysis performed, and show how we could utilize the latest developments in fluidic oscillation vibratory tools. It will also include downhole real-time data acquisition assisting the understanding of lockup occurrence, as well as quantifying the improvements in the pre-job tubing force model simulation.

With the evolving sensor technologies and advances in integrated solutions, routine surveys and interventions in oil and gas fields are going through a major revamp. The most recent developments in autonomous and untethered devices set a new paradigm shift in such crucial and frequent well operations. In this paper, field implementation and deployment of the novel Sensor-Ball technology is discussed to highlight success, challenges and lessons learned. Sensor-Ball is a small device, almost a tennis-ball size that enables autonomous and untethered logging of pressure, temperature, and tri-axial magnetic field amplitude. This intelligent device is self-powered using a battery pack with a battery life that suffices logging a dozen wells in a raw including logging time and data transfer time. The internal memory is designed for large and high definition data rates for high resolution and extended recording. Sensor-Ball is encapsulated in a ruggedized housing that can withstand downhole conditions as the device travels on a free-fall down to the programmed depth, as well as while floating back to the surface. This housing is light enough to enable efficient and flawless return of the Sensor-Ball exclusively under bouncy effect once the attached weight is dropped off. For the deployment of this innovative technology, new procedures and guidelines are developed to ensure successful journey of the Sensor-Ball. Despite the failsafe features, prejob plan, and risk assessment procedures complement this user-friendly technology and make it reliable, efficient, and easy to use. The results of the field trial of Sensor-Ball in water supply wells revealed a superior data quality of both log-down and log-up. In fact, during the mission time of three hours only, thousands of feet of high-resolution data were collected. This operation would have taken double the time and a much more wellsite footprint, in addition to increased HSE risk, if a standard wireline/slickline unit was mobilized for this routine operation. Sensor-Ball is a reliable and more advanced alternative to traditional well surveillance methods considering the operational efficiency and comparison with benchmark data. In fact, the footprint, cost and time savings are substantial, especially in an offshore environment where barges are mobilized and operations depend on weather conditions. This technology is a major breakthrough in the surveillance and logging world as it enables a fully autonomous and untethered acquisition of high-resolution data. Sensor-Ball offered more with less and will ultimately replace traditional surveillance and intervention methods.

The stimulation of multilateral wells with Coiled Tubing (CT) has always imposed significant challenges to the oilfield. Starting with lateral's access, extended reach coverage, and finishing off with an adequate stimulation fluid placement to ensure treating all targeted zones. This paper presents an engineering approach that enables access to a multilateral open-hole completion and evaluates fluid placement using the Distributed Temperature Sensing (DTS). The through-tubing multilateral access tool has been designed and deployed on a CT string, including a hybrid fiber optic and an electric cable connected to an intelligent Bottom-Hole Assembly (BHA) with multiple downhole sensors. The casing windows or open-hole junctions can be located with a precise real-time measurement of the differential pressure drop across the two downhole bottom-hole pressure sensors inside and outside the intelligent BHA. Moreover, the casing shoe and windows access will be immediately confirmed with the real-time Casing Collar Locator (CCL) signal loss. In contrast, the junction's access can be established just after a few tens of running footage thanks to the real-time inclination measurement from the accelerometer sub added to the BHA for the first time. The identification of access into the mother-bore was intuitively identified with the immediate loss of CCL signal at a depth of the casing shoe. The window localization was confirmed with a low drop in the downhole differential pressure at the intelligent bottom-hole assembly, which was not noticed at the surface. The deviation survey measured by the accelerometer sub showed a matching signature with the drilling deviation survey for both; the mother-bore and the lateral, which were successfully treated. Acquired DTS profile logs showed thought-provoking outputs. After applying the advanced interpretation algorithms, communication between the lateral and various heterogeneities in the formation was detected. The CT intelligent BHA deployment enabled the real-time downhole measurement of pressure drop, CCL, and inclination, allowing a quick confirmation of each lateral with confidence. It supersedes the previously used techniques by eliminating all limitations related to pressure monitoring at the surface and the requirement to tag different measured depths for each lateral. Various conclusions were driven, which allowed re-building operational procedures to improve the matrix stimulation treatments in offset wells. Several domains were integrated to create a fit-for-purpose solution for a complex operation. Joint efforts including stratigraphy, fluids science, and well intervention technologies could yield a proven algorithm to be applied.

Stabilization time is an essential key for pressure measurement accuracy. Obtaining representative pressure points in build-up tests for pressure-sensitive reservoirs is driven by optimizing stabilization time. An artificial intelligence technique was used in the study for testing pressure-sensitive reservoirs using measuring gauges. The stabilization time function of reservoir characteristics is generally calculated using the diffusivity equation where rock and fluid properties are honored. The artificial neural network (ANN) technique will be used to predict the stabilization time and optimize it using readily available and known inputs or parameters. The values obtained from the formula known as the diffusion formula and the ANN technique are then compared against the actual values measured from pressure gauges in the reservoirs. The optimization of the number of datasets required to be fed to the network to allow for coverage over the whole range is essential as opposed to the clustering of the datasets. A total of about 3000 pressure derivative samples from the wells were used in the testing, training, and validation of the ANN. The datasets are optimized by dividing them into three fractional parts, and the number optimized through monitoring the ANN performance. The optimization of the stabilization time is essential and leads to the improvement of the ANN learning process. The sensitivity analysis proves that the use of the formula and ANN technique, compared to actual datasets, is better since, in the formula and ANN technique, the time was optimized with an average absolute relative error of 3.67%. The results are near the same, especially when the ANN technique undergoes testing using known and easily available parameters. Time optimization is essential since discreet points or datasets in the ANN technique and formula would not work, allowing ANN to work in situations of optimization. The study was expected to provide additional data and information, considering that stabilization time is essential in obtaining the pressure map representation. ANN is a superior technique and, through its superiority, allows for proper optimization of time as a parameter. Thus it can predict reservoir log data almost accurately. The method used in the study shows the importance of optimizing pressure stabilization time through reduction. The study results can, therefore, be applied in reservoir testing to achieve optimal results.