Browsing by Author "Desai, Prathamesh S."

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Lifetime Prediction Using a Tribology-Aware, Deep Learning-Based Digital Twin of Ball Bearing-Like Tribosystems in Oil and Gas
    (MDPI, 2021) Desai, Prathamesh S.; Granja, Victoria; Higgs, C. Fred
    The recent decline in crude oil prices due to global competition and COVID-19-related demand issues has highlighted the need for the efficient operation of an oil and gas plant. One such avenue is accurate predictions about the remaining useful life (RUL) of components used in oil and gas plants. A tribosystem is comprised of the surfaces in relative motion and the lubricant between them. Lubricant oils play a significant role in keeping any tribosystem such as bearings and gears working smoothly over the lifetime of the oil and gas plant. The lubricant oil needs replenishment from time to time to avoid component breakdown due to the increased presence of wear debris and friction between the sliding surfaces of bearings and gears. Traditionally, this oil change is carried out at pre-determined times. This paper explored the possibilities of employing machine learning to predict early failure behavior in sensor-instrumented tribosystems. Specifically, deep learning and tribological data obtained from sensors deployed on the components can provide more accurate predictions about the RUL of the tribosystem. This automated maintenance can improve the overall efficiency of the component. The present study aimed to develop a deep learning-based digital twin for accurately predicting the RUL of a tribosystem comprised of a ball bearing-like test apparatus, a four-ball tester, and lubricant oil. A commercial lubricant used in the offshore oil and gas components was tested for its extreme pressure performance, and its welding load was measured using a four-ball tester. Three accelerated deterioration tests was carried out on the four-ball tester at a load below the welding load. Based on the wear scar measurements obtained from the experimental tests, the RUL data were used to train a multivariate convolutional neural network (CNN). The training accuracy of the model was above 99%, and the testing accuracy was above 95%. This work involved the model-free learning prediction of the remaining useful lifetime of ball bearing-type contacts as a function of key sensor input data (i.e., load, friction, temperature). This model can be deployed for in-field tribological machine elements to trigger automated maintenance without explicitly measuring the wear phenomenon.
  • Thumbnail Image
    Item
    News Sentiment Informed Time-series Analyzing AI (SITALA) to curb the spread of COVID-19 in Houston
    (Elsevier, 2021) Desai, Prathamesh S.
    Coronavirus disease (COVID-19) has evolved into a pandemic with many unknowns. Houston, located in the Harris County of Texas, is becoming the next hotspot of this pandemic. With a severe decline in international and inter-state travel, a model at the county level is needed as opposed to the state or country level. Existing approaches have a few drawbacks. Firstly, the data used is the number of COVID-19 positive cases instead of positivity. The former is a function of the number of tests carried out while the number of tests normalizes the latter. Positivity gives a better picture of the spread of this pandemic as, with time, more tests are being administered. Positivity under 5% has been desired for the reopening of businesses to almost 100% capacity. Secondly, the data used by models like SEIRD (Susceptible, Exposed, Infectious, Recovered, and Deceased) lacks information about the sentiment of people concerning coronavirus. Thirdly, models that make use of social media posts might have too much noise and misinformation. On the other hand, news sentiment can capture long-term effects of hidden variables like public policy, opinions of local doctors, and disobedience of state-wide mandates. The present study introduces a new artificial intelligence (i.e., AI) model, viz., Sentiment Informed Time-series Analyzing AI (SITALA), trained on COVID-19 test positivity data and news sentiment from over 2750 news articles for Harris county. The news sentiment was obtained using IBM Watson Discovery News. SITALA is inspired by Google-Wavenet architecture and makes use of TensorFlow. The mean absolute error for the training dataset of 66 consecutive days is 2.76, and that for the test dataset of 22 consecutive days is 9.6. A cone of uncertainty is provided within which future COVID-19 test positivity has been shown to fall with high accuracy. The model predictions fare better than a published Bayesian-based SEIRD model. The model forecasts that in order to curb the spread of coronavirus in Houston, a sustained negative news sentiment (e.g., death count for COVID-19 will grow at an alarming rate in Houston if mask orders are not followed) will be desirable. Public policymakers may use SITALA to set the tone of the local policies and mandates.
  • Thumbnail Image
    Item
    Spreading Process Maps for Powder-Bed Additive Manufacturing Derived from Physics Model-Based Machine Learning
    (MDPI, 2019) Desai, Prathamesh S.; Higgs, C. Fred III
    The powder bed additive manufacturing (AM) process is comprised of two repetitive steps—spreading of powder and selective fusing or binding the spread layer. The spreading step consists of a rolling and sliding spreader which imposes a shear flow and normal stress on an AM powder between itself and an additively manufactured substrate. Improper spreading can result in parts with a rough exterior and porous interior. Thus it is necessary to develop predictive capabilities for this spreading step. A rheometry-calibrated model based on the polydispersed discrete element method (DEM) and validated for single layer spreading was applied to study the relationship between spreader speeds and spread layer properties of an industrial grade Ti-6Al-4V powder. The spread layer properties used to quantify spreadability of the AM powder, i.e., the ease with which an AM powder spreads under a set of load conditions, include mass of powder retained in the sampling region after spreading, spread throughput, roughness of the spread layer and porosity of the spread layer. Since the physics-based DEM simulations are computationally expensive, physics model-based machine learning, in the form of a feed forward, back propagation neural network, was employed to interpolate between the highly nonlinear results obtained by running modest numbers of DEM simulations. The minimum accuracy of the trained neural network was 96%. A spreading process map was generated to concisely present the relationship between spreader speeds and spreadability parameters.