In this study, the authors investigated a fully data-driven approach using artificial neural networks (ANNs) for real-time virtual flowmetering and back-allocation in production wells. The authors present a new data-driven approach to estimate the injection rate in all noninstrumented wells in a large waterflooding operation accurately.
In this study, the authors investigated a fully data-driven approach using artificial neural networks (ANNs) for real-time virtual flowmetering and back-allocation in production wells. Australian technology developer MezurX is touting its newly introduced flow, density, and mud monitoring system as a significantly better alternative to the widely used Coriolis meter. Technology developers are working on a new ultrasonic flowmeter for drilling fluids aimed at obtaining better measurements than current systems with far fewer disruptions to rig systems.
Total plans to start a digital factory to tap artificial intelligence in a bid to save hundreds of millions of dollars on exploration and production projects, according to an executive. Behavior-based safety is not a new concept nor is it new at Murphy Oil. But when Murphy launched its Safety Observation Program as a digital tool, it revitalized the way the culture of safety spread throughout the company. New funding for a chatbot technology, or smart assistant, represents the latest development in the Norwegian operator’s drive toward digitalization. Rapid advances in deep learning continue to demonstrate the significance of end-to-end training with no a priori knowledge.
Ashtead Technology has acquired Louisiana-based subsea equipment rental and cutting services specialist, Aqua-Tech Solutions, as part of the company’s international growth plans in the US. High-fidelity 3D engineering simulations are valuable in making decisions, but they can be cost-prohibitive and require significant amounts of time to execute. The integration of deep-learning neural networks with computational fluid dynamics may help accelerate the simulation process. The chemical reactions creating buildups of scale that can clog a well can be replicated in a chemical lab, but researchers are finding many more variables on the surfaces of pipes that need to be considered. The web-based interactive tool provides users specialized “ocean neighborhood analyses,” including maps and graphics by analyzing more than 100 ocean datasets instantaneously. BP and partners have sanctioned the Azeri Central East project, the next stage of development of the giant Azeri-Chirag-Deepwater Gunashli oilfield complex in the Azerbaijan sector of the Caspian Sea. The pipeline system will have the initial capacity to deliver 150,000 B/D of crude oil to multiple delivery points, accessing local refineries and connecting to several downstream pipelines.
AGI stands for artificial general intelligence, a hypothetical computer program that can perform intellectual tasks as well as, or better than, a human. AGI will make today’s most advanced AIs look like pocket calculators. In collaboration with Stanford University and Brown University, Google explores how existing knowledge in an organization can be used as noisier, higher-level supervision—or, as it is often termed, weak supervision—to quickly label large training data sets. Robots have been a part of industrial production for decades, but the interface between humans and robots has changed as automation technologies increased in complexity, scope, and scale. Once a novelty, collaborative robots are projected to become a significant element of the automation landscape.
Alkinani, Husam H. (Missouri University of Science and Technology) | Al-Hameedi, Abo Taleb T. (Missouri University of Science and Technology) | Dunn-Norman, Shari (Missouri University of Science and Technology) | Alkhamis, Mohammed M. (Missouri University of Science and Technology) | Mutar, Rusul A. (Ministry of Communications and Technology)
Lost circulation is a complicated problem to be predicted with conventional statistical tools. As the drilling environment is getting more complicated nowadays, more advanced techniques such as artificial neural networks (ANNs) are required to help to estimate mud losses prior to drilling. The aim of this work is to estimate mud losses for induced fractures formations prior to drilling to assist the drilling personnel in preparing remedies for this problem prior to entering the losses zone. Once the severity of losses is known, the key drilling parameters can be adjusted to avoid or at least mitigate losses as a proactive approach.
Lost circulation data were extracted from over 1500 wells drilled worldwide. The data were divided into three sets; training, validation, and testing datasets. 60% of the data are used for training, 20% for validation, and 20% for testing. Any ANN consists of the following layers, the input layer, hidden layer(s), and the output layer. A determination of the optimum number of hidden layers and the number of neurons in each hidden layer is required to have the best estimation, this is done using the mean square of error (MSE). A supervised ANNs was created for induced fractures formations. A decision was made to have one hidden layer in the network with ten neurons in the hidden layer. Since there are many training algorithms to choose from, it was necessary to choose the best algorithm for this specific data set. Ten different training algorithms were tested, the Levenberg-Marquardt (LM) algorithm was chosen since it gave the lowest MSE and it had the highest R-squared. The final results showed that the supervised ANN has the ability to predict lost circulation with an overall R-squared of 0.925 for induced fractures formations. This is a very good estimation that will help the drilling personnel prepare remedies before entering the losses zone as well as adjusting the key drilling parameters to avoid or at least mitigate losses as a proactive approach. This ANN can be used globally for any induced fractures formations that are suffering from the lost circulation problem to estimate mud losses.
As the demand for energy increases, the drilling process is becoming more challenging. Thus, more advanced tools such as ANNs are required to better tackle these problems. The ANN built in this paper can be adapted to commercial software that predicts lost circulation for any induced fractures formations globally.
Computer vision (CV) techniques were applied to X-ray computed tomographic (CT) images of reservoir cores to evaluate their potential for rapidly identifying fractures and other lithologic/geologic characteristics. The analyses utilized feature-labeled CT cross sectional images, themselves distributed submillimeter voxels of density- and atomic number-sensitive CT Numbers, as inputs to a Fully Convolutional Neural Network (FCN) for semantic segmentation of reservoir core features. In FCN, an image is interrogated using a series of sliding windows at various scales to create weighted filters to reduce error between classes in training images. These networks of filter layers were used to assign probabilities of classes, which were upscaled back to the original image dimensions resulting in probabilistic class assignments onto each pixel. FCN model accuracy, defined by its ability to replicate manually-assigned labels in the raw (unannotated) training image stack, was at least 80% and generally improved with the size of the training set. Once the labels were assigned, the underlying feature frequency, orientation, and size were measured in 3D volume reconstructions using algorithms modified from standard image analysis software. This method allowed users to endow a classification model with subject matter knowledge for further, autonomous label prediction. Thus, while initial image annotation was labor intensive, subsequent images were rapidly classified once the model was built. The classified labels were analyzed for abundance, orientation, and size of fractures were calculated to characterize spatial information of these features. FCN combined with fracture labeling improved knowledge capture and automation of fracture identification. Models trained by high quality 3D datasets can greatly reduce the time needed to describe subsequent core. The method demonstrated is not limited to fractures, other lithologic/geologic features could be trained using the same method, which may result in additional efficiencies.
Vertical Interference tests (VIT) are used to determine the hydraulic connectivity between the formation sand intervals. This paper showcases an innovative workflow of using the petrophysical log attributes to characterize a heterogeneous reservoir sand by making use of ANN (Artificial Neural Net) and SMLP (Stratigraphic Modified Lorentz) based rock typing techniques as well as image based advanced sand layer computation techniques.
Vertical interference test is either performed using a wireline formation testing tool with multiple flow probes deployed in a vertical sequence at desired depth points on the borehole wall or using a drill stem test configuration. Based on the test design, flow rates are changed using downhole pumps, which induces pressure transients in the formation. The measured pressure response is then compared with a numerical model to derive the reservoir parameters such as vertical permeability, hydraulic connectivity etc. The conventional way of model generation is to consider a section of reservoir sand as homogenous, which generally leads to over estimation or underestimation of vertical permeabilities. The technique proposed in this paper utilizes advanced logs such as image logs; magnetic resonance logs, water saturation and other advanced lithology logs to obey heterogeneity in the reservoir model by utilizing ANN/SMLP based rock-typing techniques. These rock types would be helpful in making a multi layer formation model for the VIT modeling and regression approach. The vertical interference test model is then used to determine the vertical permeability values for each of the individual rock types. The paper displays the workflow to utilize the rock type based layered formation model in vertical interference test modeling for a channel sand scenario.
The use of artificial lift equipment for oil production in onshore reservoirs is becoming increasingly more important to help sustain the production rates of declining oil fields. Oil field producers therefore depend on the efficient operation of the artificial lift equipped and it is becoming increasingly more important to ensure maximum uptime of the equipment for the continuous production of oil.
One of the widely used methods for artificial lift is using Electrical Submersible Pumps to produce high volumes from deep oil wells. The ESP is a very effective method of artificial lift due to its unique characteristic of having the complete pump assembly and electrical motor submersed directly in the well fluid. This however requires a complex technical design of the pump and electrical motor to ensure safe operation several thousand feed below surface. It is therefore necessary to implement systems that can monitor the pump operation and notify the operator of events that will result in failure of the equipment.
Typically, ESPs are connected to SCADA or other distributed control systems to provide supervisory and control functions for their effective operation as well as for operational visibility. Today, many diagnostic methods are available to determine the health and status of an ESP system by making use of that functionality in its automation system. However, while these methods can provide insightful analysis of problems, they usually require constant monitoring of a human operator who is able to react in time to alarm notifications or implement corrective action. The correct operation of the ESP largely depends on the decisions made by the ESP field operator and his ability to effectively control the ESP fleet based on his experience. The complexity of the operator’s task increases with the size of the of ESP fleet that the operator must manage at any given point in time.
But this situation is changing, with efforts being made to reduce the dependency on the human operator by implementing digital support systems. With recent advances in artificial intelligence (AI) combined with the new Internet of Things (IoT) technologies, it is possible to effectively use data-driven analytics fueled by large data sets to assist the operator with the task of operating ESP fleets. In particular, AI technology that involves deep learning and neural networks can be extremely effective in detecting abnormal behavior of complex physical systems such as ESPs, based on the data gathered from the system, providing decision support for remediating or managing the causative issues.
One of the primary advantages of using AI technology is its ability to detect abnormal behavior in complex systems. Such an AI system can be implemented to monitor ESP systems using the real-time process data from the Supervisory system and then using a neural network model identify abnormal ESP pump behavior. The paper discuss how such an AI based anomaly detection systems can be used in a extended form to implemented an autonomous surveillance system which can monitor and entire ESP fleet. The purpose of the autonomous surveillance system is to support the operator in his supervisory tasks by doing the selection and prioritization of ESP units that requires operator attention.
This paper is a continuation of an earlier paper which discussed the possibility to implement a predictive maintenance system for ESPs using AI. This paper further elaborates the implementation of an autonomous surveillance solution for ESP systems using the predictive maintenance solution and explain how it can be implemented using AI technology in combination with a cloud-based IoT platform.
In this work, we present the development of a compositional simulator accelerated by proxy flash calculation. We aim to speed up the compositional modeling of unconventional formations by stochastic training.
We first developed a standalone vapor-liquid flash calculation module with the consideration of capillary pressure and shift of critical properties induced by confinement. We then developed a fully connected network with 3 hidden layers using Keras. The network is trained with Adam optimizer. 250,000 samples are used as training data, while 50,000 samples are used as testing data. Based on the trained network, we developed a forward modeling (prediction) module in a compositional simulator. Therefore, during the simulation run, the phase behavior of the multicomponent system within each grid block at each iteration is obtained by simple interpolation from the forward module.
Our standalone flash calculation module matches molecular simulation results well. The accuracy of the trained network is up to 97%. With the implementation of the proxy flash calculation module, the CPU time is reduced by more than 30%. In the compositional simulator, less than 2% of CPU time is spent in the proxy flash calculation.
The novelty of this work lies in two aspects. We have incorporated the impacts of both capillary pressure and shift of critical properties in the flash calculation, which matches molecular simulation results well. We developed a proxy flash calculation module and implemented it in a compositional simulator to replace the traditional flash calculation module, speeding the simulation by 30%.