... by visual inspection of the shale shakers, is to evaluate the solids return in the shale shakers. Hole cleaning and wellbore instability issues, among other events can be detected. ( Grossi, 2020 ). upstream oil & gas machine learning neural network experiment accuracy deep learning...

...), denotes the change of events that are not explained by the principal components model. It is a measure of the difference, or residual, between a sample and its projection on the model. upstream oil & gas drilling fluids and materials brazil government algorithm deep learning expert system...

.... The same process is repeated for each of the wells as they are in turn defined as a subject well. Results show that the framework can infer and generate logs such as GR logs in real time. neural network drilling operation deep learning norway government well logging drilling measurement...

... the first outcomes of that application in real-time decision-making. brazil government model directional drilling structural geology neural network upstream oil & gas drilling operation deep learning europe government norway government sand control dataset rock formation consolidation...

... signs of poor hole cleaning. These techniques are not limited to downlinking or heave detection, and can be applied more generally to scenarios with complex periodic signals. deep learning machine learning neural network united states government artificial intelligence international drilling...

... Abstract There is considerable value in automatically quantifying cutter damage from drill bit pictures. Current approaches do not classify cutter damage by type, i.e., broken, chipped, lost, etc. We, therefore, present a computer vision model using deep learning neural networks to automate...

... in advance, giving the driller opportunity to take preventive actions to avoid a potential stuck pipe. drilling fluid management & disposal deep learning ecd measurement ecd downhole ecd dataset well control neural network calculation incident application downhole equivalent circulating...

... variation upstream oil & gas stressful situation accuracy skin tissue deep learning emission model detection consumer health neural network radiation heart rate blood vessel stress level variability experiment participant test subject indicator operator thermal camera operation...

... method derived from real-time data from mud logger and the image recognition method based on deep learning of the video image from surveillance cameras. This paper will present the system's architecture, algorithms, and functions in detail and will conclude with a typical application case which...

... Analysis The drilling operations have procedures, tools, and cutting-edge sensors that produce large amount of data. That output data can be integrated methodically to artificial intelligence (AI) models. The nature of the data along with its considerable size allows deep learning models to be built...

... energy to the bit for rock destruction, without exciting the system into stick/slip. Results presented are developed for these approaches that have been applied to data collected over the last decade from different wellsites. drilling equipment markovrnn artificial intelligence deep learning...

... learning and deep learning models. Stuck incidents are some of the most difficult and challenging situations. The proposed method uses a two-step model and available historical data from prior drilling operations to predict the occurrence of such an incident well in advance so that it can be avoided...

..., although difficult to interpret accurately. This paper presents a novel deep learning methodology using mechanical drilling parameters for lithology classification. A cascade of multilayered perceptrons (MLPs) are trained on historical data from wells on a field operated by Equinor. Rather than an end...

...-based, stochastic decision-making algorithm. To start, neural networks and deep learning models were trained using time-series drilling data. From there, physics-based equations that model the pressure required to break the mud's gel strength as well as the flow of non-Newtonian fluids through...

... to capture temporal information. The initial results demonstrate this pipeline to be effective in detecting rig states using computer vision analytics. drilling equipment annotation pipeline artificial intelligence deep learning neural network upstream oil & gas petrobras rig state video...

... the technical details to develop a real-time deep learning model to detect and estimate the duration of downlinking sequences of Rotary Steerable Systems (RSS) based on a single measurement (standpipe pressure, SPP). Further analytics are derived based on the downlink recognition results together with other...

... detection algorithm Drilling Conference algorithm washout event hydraulic coefficient machine learning deep learning washout detection model parameter international association of drilling contractors reliable solution society of petroleum engineers physics model Introduction...

... network change point detection pressure drop machine learning Upstream Oil & Gas variation deep learning flow rate operation pump pressure threshold algorithm drilling operation data frequency pressure anomaly washout drilling equipment detection remote monitoring center false...

... Abstract A real-time deep learning model is proposed to analyze the volume of cuttings from a shaker on an offshore drilling rig. The model is able to extract features and perform real-time classification in relatively good accuracy compared to the traditional video analytics method, which...

... learning Upstream Oil & Gas accuracy neural network fc component simulated time series simulator deep neural network approach latent space deep learning drilling time series training data long short-term memory automation system dataset realistic curve pattern convolutional layer time...