Although visual data analytics using image processing is one of the most growing research areas today and is largely applied in many fields, it is not fully utilized in the petroleum industry. This study is inspired by medical image segmentation in detecting tumor cells. This paper uses a supervised Machine Learning technique through video analytics to identify bit dullness that can be used in the drilling industry in place of the subjective screening approach. The evaluation of bit performance can be affected by subjective evaluation of the degree of dullness. The present approach of using video analytics is able to grade bit dullness to avoid user subjectivity. The approach involves the use of datasets in good quantity and quality by separating them into training datasets, testing datasets, and validation datasets. Due to the large datasets, Google Collaboratory was used as it provides access to its Graphic Processing Unit (GPU) online for the processing of the bit datasets. The processing time and resource consumption are minimized using Google GPU. Using the Google GPU resources, the procedure is automated without any installation. After the bit is pulled out and cleaned, a video is taken around and up and down in 360°. Further, it is compared against the green bit. By this approach, multiple video datasets are not required. The algorithm was validated with new sets of bit videos and the results were satisfactory. The identification of the dullness or otherwise of each screened bit is done with the aid of a bounding box with a stamp of a level of confidence (range 0.5–1) and the algorithm assigns for its decision on the identified or screened object. This method is also able to screen multiple bits stored in a single place. In an event where several drill bits are to be screened, manual grading will be a huge task and will require a lot of resources. This model and algorithm will take a few minutes to screen and provide grading for several bits while videos are passed through the algorithm. It has also been found that the grading with the video was much better than the single image as the contextual information extracted are much higher at the level of the entire video, per segment, per shot, and per frame. Also, methodology is made robust so that the video model test starts successfully without error. The time penalty for the processing is fast and it took less time for a single video screening. The work developed here is probably the first to handle the dull bit grading using video analytics. With more of these datasets available, the future automation of the IADC bit characterization will soon evolve into an automated process.

Accurate prediction of gas critical rate is critical to the successful management of gas wells. This paper covers the prediction of gas critical rate and presents limitations of old models with gas condensate wells with water-cut reversal. Comparison of prediction methods or models with this new method will be explained using field data of condensate wells. The effect and relation of water-cut with critical gas rate determination will be presented and the best method that universally meets changing conditions of the well will be tested with field data. Any method that must be acceptable must meet the dynamics of the well. No static model can predict accurately a dynamic well and reservoir performance. The old models of critical gas rate prediction show a static outlook, probably see the beginning of the well-life and cannot predict correctly when the fluid phases change in gravity. The late life prediction of the well performance is much more critical than the early life when the well has sufficient energy. The production envelope is more critical at depletion than at when the reservoir energy just kick. Therefore, any model prediction must be dynamic. The results from the old models show that they fail the dynamic test of the well performance. This limitation makes those model unusable in a late life of the well when water cut increases. This study has revealed a method or a model for critical rate prediction that is accurate throughout the life of the well. The effect of water cut reversal is well tracked with this new model whereas the static nature of other models predicts a wrong minimum rate at a liquid load up rate. The field data reveals that the dynamic nature of well and reservoir performance can only be understood dynamically.

This study is to determine the effective use of localized reservoir pressure of each well drainage area in a multi-well reservoir system model to determine optimum fracturing design for production improvement. A static bottom-hole pressure (BHP) survey may present different values for each well draining from the same reservoir but these different pressure values have not been incorporated into determining the performance of each individual well based on the pressure as seen by each well, rather an indeterminate average reservoir pressure is used. Fracturing as a concept of increasing reservoir permeability will further expose the well to reservoir pressure as seen by the individual well than the assumed single-value reservoir-wide pressure. This is so except when the fracture half-length is equal to the drainage length of the reservoir, connecting the whole reservoir to justify the single reservoir pressure effect if it is a single-well reservoir system. In reality, many reservoirs are multi-well reservoir systems and this simplified assumption may pose some drawbacks. The damaged wellbore area may truly be more exposed to the localized reservoir pressure as seen by the well than the apparent reservoir single value pressure assumed to determine drawdown and damage. In a multi-well reservoir system with each well-drainage area subjected to different reservoir pressures than the single reservoir pressure, fracturing and stimulation candidates screening may not present the actual effect of each well-drainage area static reservoir pressure. This paper is to present a new model that incorporates the average reservoir pressure for whole reservoir system and the reservoir pressure as seen by individual wells in the determination of the drawdown and damage. The knowledge of the different pressures in different well locations in the reservoir system will be utilized to present a linear flow model in well fracturing to enhance better well performance. With this new model, the actual and more realistic damage estimation and ways to achieve a linear flow for optimum performance through fracturing will be better understood. The effect of other flowing wells on the skin of the candidate well will enhance a better planning than is done now because the existing formulations are done with a single-well reservoir system in mind; no account for contributing skin of other flowing wells in the industry applied model approaches.

Accurate prediction of gas critical rate is critical to the successful management of gas wells. This paper covers the prediction of gas critical rate and presents limitations of old models with gas condensate wells with water-cut reversal. Comparison of prediction methods or models with this new method will be explained using field data of condensate wells. The effect and relation of water-cut with critical gas rate determination will be presented and the best method that universally meets changing conditions of the well will be tested with field data. Any method that must be acceptable must meet the dynamics of the well. No static model can predict accurately a dynamic well and reservoir performance. The old models of critical gas rate prediction show a static outlook, probably see the beginning of the well-life and cannot predict correctly when the fluid phases change in gravity. The late life prediction of the well performance is much more critical than the early life when the well has sufficient energy. The production envelope is more critical at depletion than at when the reservoir energy just kick. Therefore, any model prediction must be dynamic. The results from the old models show that they fail the dynamic test of the well performance. This limitation makes those model unusable in a late life of the well when water cut increases. This study has revealed a method or a model for critical rate prediction that is accurate throughout the life of the well. The effect of water cut reversal is well tracked with this new model whereas the static nature of other models predicts a wrong minimum rate at a liquid load up rate. The field data reveals that the dynamic nature of well and reservoir performance can only be understood dynamically.

Condensate reservoirs are mostly pressure sensitive and keeping the pressure above the dew point pressure in the reservoir is critical to avoid condensate banking in the reservoir. If it occurs, production is highly inhibited and the well may ultimately quit on production under liquid loading. Fluid ratios are important in the management of condensate wells and most critical is the Gas Liquid Ratio (GLR). There is a certain GLR that below it, there will be a liquid loading in the wellbore that could quit the well. Each fluid rate goes with a GLR and the point where there is a reversal of the GLR or CGR trends may present a case of loading scenario and that is taken as the determination reference point. When a condensate well shows an improvement of water cut as the choke bean size is reduced does not necessarily signify a healthy situation and neither a one-point higher water cut with increase in choke bean size mean a water coning situation. When a liquid loading well is beaned up, there is early signs of water coning in the production data but this is just a wellbore production and the BS&W improves as the production rate is further increased. Further investigation is necessary to separate the challenge of water conning from the challenge of too low Gas rate which causes the loading of the liquids in the wellbore. That is the operating envelop to manage condensate well rates: rates too low with a possibility of a liquid loading and rates too high that depicts a case of water conning when water is close to the perforation. This band must be completely exploited to turn the production curve in the positive. This paper provides a strategy to recover a condensate well production with a challenge of liquid loading using a case study. The degree of the severity of the liquid loading can be represented using a power law model with the gradient being the level of severity of the loading. The production improvement is greater than nβ percent where n is the quadratic model number 2 and β is the product of the graphical and Lagrangian-Quadratic alpha parameters. The optimum rate can be determined using the Lagrange Multiplier optimization method to effectively extend the production life of the well.