Color Recurrence Plots for Bearing Fault Diagnosis.

This paper presents bearing fault diagnosis using the image classification of different fault patterns. Feature extraction for image classification is carried out using a novel approach of Color recurrence plots, which is presented for the first time. Color recurrence plots are created using non-linear embedding of the vibration signals into delay coordinate space with variable time lags. Deep learning-based image classification is then performed by building the database of the extracted features of the bearing vibration signals in the form of Color recurrence plots. A Series of computational experiments are performed to compare the accuracy of bearing fault classification using Color recurrence plots. The standard bearing vibration dataset of Case Western Reserve University is used for those purposes. The paper demonstrates the efficacy and the accuracy of a new and unique approach of scalar time series extraction into two-dimensional Color recurrence plots for bearing fault diagnosis.

Automatic Detection of Cracks on Concrete Surfaces in the Presence of Shadows.

Deep learning-based methods, especially convolutional neural networks, have been developed to automatically process the images of concrete surfaces for crack identification tasks. Although deep learning-based methods claim very high accuracy, they often ignore the complexity of the image collection process. Real-world images are often impacted by complex illumination conditions, shadows, the randomness of crack shapes and sizes, blemishes, and concrete spall. Published literature and available shadow databases are oriented towards images taken in laboratory conditions. In this paper, we explore the complexity of image classification for concrete crack detection in the presence of demanding illumination conditions. Challenges associated with the application of deep learning-based methods for detecting concrete cracks in the presence of shadows are elaborated on in this paper. Novel shadow augmentation techniques are developed to increase the accuracy of automatic detection of concrete cracks.

Estimation of Local Equilibrium Model Parameters for Simulation of the Laboratory Foam-Enhanced Oil Recovery Process Using a Commercial Reservoir Simulator.

An accurate determination of the foam simulation parameters is crucial in modeling foam flow in porous media. In this paper, we present an integrated workflow to obtain the parameters in the local equilibrium foam model by history matching a series of laboratory experiments performed at reservoir conditions (131 F and 1500 psi) on Estaillades limestone using a commercial reservoir simulator. The gas-water and water-oil relative permeability curves were first validated after history matching with the unsteady-state flooding experiments. The modeling parameters for foam generation and foam dry-out effect were obtained by history matching with the gas/surfactant coinjection experiments at varying foam quality and injection rates. Moreover, the modeling parameters for the destabilizing effect of oil on foam and foam shear thinning effect were derived after history matching with the foam-enhanced oil recovery process and oil fractional flow experiments in the laboratory. In practice, the calculated results reproduce the experimental outputs reasonably well. Furthermore, sensitivity analysis of foam modeling parameters is investigated to determine the most dominating parameters for accurate simulation of foam-enhanced oil recovery process in porous media. In this work, an efficient parameter estimation approach is developed from reliable foam flooding experimental data, which may be further applied to field-scale simulation. Moreover, the simulation approach can also be utilized to facilitate our interpretation of complex lab foam flooding results.

Improved Oil Recovery in Carbonates by Ultralow Concentration of Functional Molecules in Injection Water through an Increase in Interfacial Viscoelasticity.

Injection of sea water is the most common practice to displace oil in porous media in subsurface formations. In numerous studies, conventional surfactants at concentrations in a range of one weight percent have been proposed to be added to the injected water to improve oil recovery. Surfactants accumulate at the oil-water interface and may reduce the interfacial tension by three orders of magnitude or more, resulting in higher oil recovery. Recently, we have proposed the addition of ultralow concentration of a non-ionic surfactant to the injected water to increase interface viscoelasticity as a new process. The increase in interface viscoelasticity increases oil recovery from porous media. This alternative approach requires only a concentration of 100 ppm (two orders less than the conventional improved oil recovery) and therefore is potentially a much more efficient process. In this work, we present a comprehensive report of the process in an intermediate-wet carbonate rock. There is very little adsorption of the functional molecules to the rock surface. Because the critical micelle concentration is low (around 30 ppm), most of the molecules move to the fluid-fluid interface to form molecular structures, which give rise to an increase in interface elasticity. We also demonstrate that interface elasticity has a non-monotonic behavior with the salt concentration of injected brine, and an optimum salinity exists for maximum oil recovery.