Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “FORECASTING MODEL”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,477 records · Page 82
All sourcesNASA NTRSDOE OSTI
DOE OSTI2026

Predicting initial trans-membrane pressure across cycles in the ultrafiltration process using random forest

With growing freshwater scarcity, direct potable reuse (DPR) systems that reclaim wastewater for drinking are becoming increasingly important for sustainable water supply. Reliable operation requires minimizing downtime in ultrafiltration (UF) units, where membrane fouling leads to elevated trans-membrane pressure (TMP). This study develops data-driven regression models based on random forest (RF) and autoregressive (AR) approaches to forecast the initial TMP at the start of each UF filtration cycle in a pilot-scale DPR system. The RF model consistently outperforms baseline methods, including historical mean, last observation carried forward, and AR models, across multiple forecast horizons, achieving the lowest root mean square error. To evaluate how different classes of process variables contribute to TMP dynamics over time, we examine the feature importance of independent input variables across multiple forecast horizons. This analysis provides insight into the temporal relevance of operational and sensor-derived features, guiding control and monitoring strategies. Additionally, the impact of hyperparameter tuning on TMP prediction performance is assessed for both direct and recursive RF modelling approaches. The proposed RF framework establishes a robust foundation for predictive monitoring and real-time optimization of UF operations, supporting sustainable and reliable water reuse.

direct potable reuse↗
DOE OSTI2022

Important powertrain dynamics for developing models for control of connected and automated electrified vehicles

Connected and Automated Vehicles (CAV) technology presents significant opportunities for energy saving in the transportation sector. CAV technology forecasts vehicle and powertrain power needs under various terrain, ambient, and traffic conditions. Integration of the CAV technology in Hybrid Electric Vehicles (HEVs) provides the opportunity for optimal vehicle operation. Indeed, Hybrid Electric Vehicle powertrains present high degrees of flexibility and possibility for choosing optimum powertrain modes based on the predicted traction power needs. In modeling complex CAV powertrain dynamics, the modeler needs to consider short-time scale powertrain dynamics, such as engine transients, and hysteresis of mode-switching for a multi-mode HEV. Therefore, the powertrain dynamics essential for developing powertrain controllers for a class of connected HEVs is presented. To this end, control-oriented powertrain dynamic models for a test vehicle consisting of full electric, hybrid, and conventional engine operating modes are developed. The resulting powertrain model can forecast vehicle traction torque and energy consumption for the specified prediction horizon of the test vehicle. The model considers different operating modes and associated energy penalty terms for mode switching. Thus, the vehicle controller can determine the optimum powertrain mode, torque, and speed for forecasted vehicle operation via utilizing connectivity data. The powertrain model is validated against the experimental data and shows prediction error of less than 5% for predicting vehicle energy consumption. The model is used to create energy penalty maps that can be used for CAV control, for example fuel penalty map for engine torque changes (10–40 Nm) at each engine speed. The results of model-based optimization show optimum switching delays ranging from 0.4 to 1.4 s to avoid hysteresis in mode switching.

Engineering↗
DOE OSTI2018

Generic HLW Repository In Bedded Salt In Germany: Emplacement Technologies and Repository Designs - 18288

In Germany, a new site selection act for a repository for HLW and SNF entered into force in July 2013 and was amended in spring 2017 [1]. It stipulates that the safety of repository systems for heat-generating radioactive waste and spent nuclear fuel in different host rock formations be compared. This requires that generic repository concepts and adequate safety- and safety demonstration concepts for all potential host rock formations in Germany (salt, clay and crystalline rock) exist. For several decades, development of disposal concepts and safety analyses for a repository in a salt dome was prioritized while repository concepts for clay and crystalline rock have been taken into account for two decades only. So far, bedded salt formations have not been the subject of comparative investigations. Thus, in summer 2015, the Federal Ministry for Economic Affairs and Energy (BMWi) launched the R and D project KOSINA to develop repository designs and carry out safety analyses for different emplacement alternatives in a generic bedded salt formation and a generic salt pillow. KOSINA is an acronym for 'Concept development for a generic repository for heat-generating waste in bedded salt formations in Germany as well as development and testing of a safety and demonstration concept'. Together with its partners BGR, GRS, and IfG, DBE Technology GmbH has successfully carried out an almost three years lasting scientific programme, which will be concluded in April 2018. The core areas of the programme are the development of generic geologic models, including derivation of model parameters, the development of a safety and safety demonstration concept, the development of technical repository designs for four different emplacement alternatives, the analysis of geomechanical integrity, the evaluation of operational safety as well as the analysis of radiological consequences. An interim report, which compiles the basic data of the waste inventory, the repository design requirements, the data basis for geologic model developments, and the outline of a safety and safety demonstration concept, was already published in February 2016. The main achievements of the R and D project KOSINA are the development of four different repository designs, two per each generic geologic model (flat-bedded salt, salt pillow) based on thermomechanical calculations. This includes the implementation of a safety concept that provides containment of the radioactive materials with regard to the technical designs of waste packages, transport and emplacement technologies, and backfilling and sealing concepts. Furthermore, the integrity of the geologic barriers could be demonstrated for all four repository designs, and the long-term predictions showed no radiological releases during the demonstration period of one million years. (authors)

12 MANAGEMENT OF RADIOACTIVE AND NON-RADIOACTIVE W↗
DOE OSTI2017

On the Bayesian calibration of computer model mixtures through experimental data, and the design of predictive models

For many real systems, several computer models may exist with different physics and predictive abilities. To achieve more accurate simulations/predictions, it is desirable for these models to be properly combined and calibrated. Here, we propose the Bayesian calibration of computer model mixture method which relies on the idea of representing the real system output as a mixture of the available computer model outputs with unknown input dependent weight functions. The method builds a fully Bayesian predictive model as an emulator for the real system output by combining, weighting, and calibrating the available models in the Bayesian framework. Moreover, it fits a mixture of calibrated computer models that can be used by the domain scientist as a mean to combine the available computer models, in a flexible and principled manner, and perform reliable simulations. It can address realistic cases where one model may be more accurate than the others at different input values because the mixture weights, indicating the contribution of each model, are functions of the input. Inference on the calibration parameters can consider multiple computer models associated with different physics. The method does not require knowledge of the fidelity order of the models. We provide a technique able to mitigate the computational overhead due to the consideration of multiple computer models that is suitable to the mixture model framework. We implement the proposed method in a real-world application involving the Weather Research and Forecasting large-scale climate model.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2023

Machine Learning for Daily Forecasts of Arctic Sea Ice Motion: An Attribution Assessment of Model Predictive Skill

Physics-based simulations of Arctic sea ice are highly complex, involving transport between different phases, length scales, and time scales. Resultantly, numerical simulations of sea ice dynamics have a high computational cost and model uncertainty. We employ data-driven machine learning (ML) to make predictions of sea ice motion. The ML models are built to predict present-day sea ice velocity given present-day wind velocity and previous-day sea ice concentration and velocity. Models are trained using reanalysis winds and satellite-derived sea ice properties. We compare the predictions of three different models: persistence (PS), linear regression (LR), and a convolutional neural network (CNN). We quantify the spatiotemporal variability of the correlation between observations and the statistical model predictions. Additionally, we analyze model performance in comparison to variability in properties related to ice motion (wind velocity, ice velocity, ice concentration, distance from coast, bathymetric depth) to understand the processes related to decreases in model performance. Results indicate that a CNN makes skillful predictions of daily sea ice velocity with a correlation up to 0.81 between predicted and observed sea ice velocity, while the LR and PS implementations exhibit correlations of 0.78 and 0.69, respectively. The correlation varies spatially and seasonally: lower values occur in shallow coastal regions and during times of minimum sea ice extent. LR parameter analysis indicates that wind velocity plays the largest role in predicting sea ice velocity on 1-day time scales, particularly in the central Arctic. Regions where wind velocity has the largest LR parameter are regions where the CNN has higher predictive skill than the LR.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

PFLOTRAN-SIP: A PFLOTRAN Module for Simulating Spectral-Induced Polarization of Electrical Impedance Data

Spectral induced polarization (SIP) is a non-intrusive geophysical method that collects chargeability information (the ability of a material to retain charge) in the time domain or its phase shift in the frequency domain. Although SIP is a temporal method, it cannot measure the dynamics of flow and solute/species transport in the subsurface over long times (i.e., 10–100 s of years). Data collected with the SIP technique need to be coupled with fluid flow and reactive-transport models in order to capture long-term dynamics. To address this challenge, PFLOTRAN-SIP was built to couple SIP data to fluid flow and solute transport processes. Specifically, this framework couples the subsurface flow and transport simulator PFLOTRAN and geoelectrical simulator E4D without sacrificing computational performance. PFLOTRAN solves the coupled flow and solute-transport process models in order to estimate solute concentrations, which were used in Archie’s model to compute bulk electrical conductivities at near-zero frequency. These bulk electrical conductivities were modified while using the Cole–Cole model to account for frequency dependence. Using the estimated frequency-dependent bulk conductivities, E4D simulated the real and complex electrical potential signals for selected frequencies for SIP. These frequency-dependent bulk conductivities contain information that is relevant to geochemical changes in the system. This study demonstrated that the PFLOTRAN-SIP framework is able to detect the presence of a tracer in the subsurface. SIP offers a significant benefit over ERT in the form of greater information content. It provided multiple datasets at different frequencies that better constrained the tracer distribution in the subsurface. Consequently, this framework allows for practitioners of environmental hydrogeophysics and biogeophysics to monitor the subsurface with improved resolution.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2020

Post-Calibration Uncertainty Analysis for Travel Times at a Naval Weapons Industrial Reserve Plant

The Naval Weapons Industrial Reserve Plant (NWIRP) in McGregor, Texas began manufacturing explosives in 1980 and several hazardous chemicals were discovered in lakes and streams surrounding the site in 1998. Contaminants traveled to local lakes and streams much faster than initially predicted. This research estimated contaminant travel times and identified locations where monitoring wells should be installed to yield the greatest reductions in uncertainties in travel-time predictions. To this end, groundwater and particle-tracking models for NWIRP site were built to predict hydraulic heads and contaminant travel times. Next, parameter (hydraulic conductivities) uncertainties, parameter identifiabilities, observation (hydraulic heads) worth, and predictive (contaminant travel times) uncertainties were quantified. Parameter uncertainties were reduced by up to 92%; a total of 19 of 158 parameters were at least moderately identifiable; travel-time uncertainties were reduced up to 92%. Additionally, travel-time predictions and post-calibration parameter distributions were generated using the null-space Monte Carlo (NSMC) technique. NSMC predicted that conservative tracers exited the flow system within a year, which matches with field data. Finally, an observations-worth analysis found that additional 11 more measurements would reduce travel-time uncertainties by factors from 1.04 to 4.3 over existing data if monitoring wells were installed at the suggested locations.

45 MILITARY TECHNOLOGY, WEAPONRY, AND NATIONAL DEF↗
DOE OSTI2016

Comparison of Measured and Numerically Simulated Turbulence Statistics in a Convective Boundary Layer Over Complex Terrain

High resolution numerical simulation can provide insight into important physical processes that occur within the planetary boundary layer (PBL). The present work employs large eddy simulation (LES) nested within the Weather Forecasting and Research (WRF) framework to simulate real conditions in the convective PBL over an area of complex terrain. A multiple nesting approach has been used to downsize the grid spacing size from 12.15 km (mesoscale) to 0.03 km (LES). To minimize artifacts in theWRF-LES solutions resulting from using an inappropriate grid spacing on the WRF-Meso domain, a careful selection of grid spacing has been conducted. The WRF-LES results have been evaluated with in situ and remote sensing observations collected during the US Department of Energy supported Columbia BasinWind Energy Study (CBWES). The comparison for the first and second order moments, turbulence spectrum, and probability density function (pdf) of wind speed show good agreement between the simulation and data. Furthermore, the WRF-LES variables show a great deal of variability in space and time caused by the complex topography in the LES domain. The WRF-LES results show that the flow structures, such as roll vortices and convective cells, over the domain vary depending on both the spatial location and time of the day. In addition to basic studies related to boundary-layer meteorology, results from these simulations can be used in other applications, such as studying the wind energy resources.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2022

MSASGCN : Multi-Head Self-Attention Spatiotemporal Graph Convolutional Network for Traffic Flow Forecasting

Traffic flow forecasting is an essential task of an intelligent transportation system (ITS), closely related to intelligent transportation management and resource scheduling. Dynamic spatial-temporal dependencies in traffic data make traffic flow forecasting to be a challenging task. Most existing research cannot model dynamic spatial and temporal correlations to achieve well-forecasting performance. The multi-head self-attention mechanism is a valuable method to capture dynamic spatial-temporal correlations, and combining it with graph convolutional networks is a promising solution. Therefore, we propose a multi-head self-attention spatiotemporal graph convolutional network (MSASGCN) model. It can effectively capture local correlations and potential global correlations of spatial structures, can handle dynamic evolution of the road network, and, in the time dimension, can effectively capture dynamic temporal correlations. Experiments on two real datasets verify the stability of our proposed model, obtaining a better prediction performance than the baseline algorithms. The correlation metrics get significantly reduced compared with traditional time series prediction methods and deep learning methods without using graph neural networks, according to MAE and RMSE results. Compared with advanced traffic flow forecasting methods, our model also has a performance improvement and a more stable prediction performance. We also discuss some problems and challenges in traffic forecasting.

Cao, Yang↗
DOE OSTI2018

Modeling India’s Coal Production with a Negatively Skewed Curve-Fitting Model

India’s coal demand is forecast to increase at a rapid pace in the future due to the country’s economic and population growth. Analyzing the scope for future production of India’s domestic coal resources, therefore, plays a vital role in the country’s development of sound energy policies. This paper presents a quantitative scenario analysis of India’s potential future coal production by using a negatively skewed curve-fitting model and a range of estimates of the country’s ultimately recoverable resources (URR) of coal. The results show that the resource base is sufficient for India’s coal production to keep increasing over the next few decades, to reach between 2400 and 3200 Mt/y at 2050, depending on the assumed value of URR. A further analysis shows that the high end of this range, which corresponds to our ‘GSI’ scenario, can be considered as the probable upper-bound to India’s domestic coal production. Comparison of production based on the ‘GSI’ scenario with India’s predicted demand shows that the domestic production of coal will be insufficient to meet the country’s rising coal demand, with the gap between demand and production increasing from its current value of about 268 Mt/y to reach 300 Mt/y in 2035, and 700 Mt/y by 2050. This increasing gap will be challenging for the energy security of India.

29 ENERGY PLANNING, POLICY, AND ECONOMY↗
DOE OSTI2022

Machine learning for postprocessing ensemble streamflow forecasts

Skillful streamflow forecasts can inform decisions in various areas of water policy and management. We integrate numerical weather prediction ensembles, distributed hydrological model, and machine learning to generate ensemble streamflow forecasts at medium-range lead times (1–7 days). We demonstrate the application of machine learning as postprocessor for improving the quality of ensemble streamflow forecasts. Our results show that the machine learning postprocessor can improve streamflow forecasts relative to low-complexity forecasts (e.g., climatological and temporal persistence) as well as standalone hydrometeorological modeling and neural network. The relative gain in forecast skill from postprocessor is generally higher at medium-range timescales compared to shorter lead times; high flows compared to low–moderate flows, and the warm season compared to the cool ones. Overall, our results highlight the benefits of machine learning in many aspects for improving both the skill and reliability of streamflow forecasts.

54 ENVIRONMENTAL SCIENCES↗
DOE OSTI2017

Hardening of DOE UQ Codes for Ultra-Deep Proactive Geosteering in Oilfield Service

The primary objective of this project was to harden the DOE uncertainty quantification (UQ) code to solve the inverse problem for the geosteering service in the oilfield drilling and exploration. The primary focus is to verify the feasibility of using QUESO to solve geosteering inverse problems through statistical inversion. QUESO is a software library developed by QUEST, a DOE's Scientific Discovery through Advanced Computing (SciDAC) institute. In the process of drilling a borehole, geosteering is the act of adjusting the well trajectory on the fly to reach the geological targets or to keep the wellbore within desired formation. Geosteering inversion is to infer underground formation structure using measurements such as azimuthal resistivity logging data. The geosteering process relies on the real-time reconstruction of the subsurface earth model, and a robust and efficient inversion algorithm is always necessary to satisfy the job requirement. The new generation of azimuthal resistivity geosteering tool is capable of detecting multiple formation boundaries 20-100 ft away, and the corresponding geosteering inversion problem can be very challenging as many parameters need to be inverted within such a large depth of investigation. The success of the project will support US energy security by helping to advance subsurface modeling and characterization technologies in oilfield applications. An effective subsurface inversion algorithm and the implementation as a software package will promote the usage of ultra-deep azimuthal resistivity measurements, which can help well placement in complicated underground environments, reduce costs and risks of drilling, and increase oil and gas production. It will help medium and small size independent service companies and tool manufactures to enter the more advanced and lucrative directional drilling area. In addition, by hardening the QUESO code and building a transparent interface for easy manipulation of the QUESO functions, we provide a user-friendly tool for a larger scientific and industry communities that rely heavily on modeling and simulation tools for forecasting, parameter studies, design, and decision making. These are all activities that can strongly benefit from meaningful representations of modeling uncertainty supported by our product.

58 GEOSCIENCES↗
DOE OSTI2015

Tall Tower Wind Energy Monitoring and Numerical Model Validation in Northern Nevada

The main objectives of this project were to conduct a tall-tower and sodar field campaign in complex terrain, investigate wind properties relevant to wind energy assessment, and evaluate high-resolution models with fixed and adaptive grid structures. Two 60-m towers at Virginia Peak ridges near Washoe Valley, Nevada, were instrumented with cup and vane anemometers as well as sonic anemometers, and an acoustic sounder (hereafter sodar) was installed near one of the towers. The towers were located 2,700 m apart with a vertical distance of 140 m elevation between their bases. Each tower had a downhill exposure of rolling complex terrain, with the nearby valley floor 3,200 m to the west and 800 m below the summit. Cup anemometers were installed at both towers at 20, 40, and 60 m, wind vanes at 20 and 60 m, and sonic anemometers at 20 and 60 m. The sodar measurements were nominally provided every 10 m in vertical distance from 40 to 200 m with the quality of the data generally decreasing with height. Surface air temperature, atmospheric pressure, and radiation measurements were conducted at 1.5 m AGL at both of the towers. Although the plan was to conduct a 1-year period of data collection, we extended the period (October 5, 2012 through February 24, 2014) to cover for possible data loss from instrument or communication problems. We also present a preliminary analysis of the towers and sodar data, including a detailed inventory of available and missing data as well as outliers. The analysis additionally includes calculation of the Weibull parameters, turbulence intensity, and initial computation of wind power density at various heights.

17 WIND ENERGY↗
DOE OSTI2022

A deep learning-based direct forecasting of CO 2 plume migration

Accurate and timely forecasts of CO 2 plume evolution in geological reservoirs are crucial for CO 2 migration detection, leakage risk assessment, and operation decision support. Conventional forecasting usually adopts a two-step strategy, first calibrating reservoir model parameters against observations using iterative inverse modeling (or history matching) and then applying the calibrated model for predictions. This method impedes real-time forecasts due to the heavy computational demand in inverse modeling and may suffer from poor prediction accuracy because of the limited observation data. In this work, we propose a deep learning-based latent space mapping framework to forecast CO 2 plume migration directly by avoiding the inverse modeling. We first use the convolutional autoencoder to map the high-dimensional complex plume extents onto low-dimensional latent space. Next, we use neural networks to learn the relationship between the observation variables and the prediction latent variables. And then for given observation data, we infer the prediction values directly. This one-step direct forecasting is computationally efficient which requires a few number of parallelizable reservoir simulations and it can provide accurate predictions with limited observations by learning the observation-prediction relationship in the reduced dimension. Therefore, our proposed method enables an in-time forecast of dynamic CO 2 plume distributions. In this work, we demonstrate the effectiveness and accuracy of our method in predicting the CO 2 plume migration using four metrics such as plume area, centroid movement distance, and plume spreading in the primary and secondary directions. And the spatio-temporal evolution patterns of plume migration under diverse geological complexities are also accurately quantified.

15 GEOTHERMAL ENERGY↗
DOE OSTI2020

Future projections and uncertainty assessment of precipitation extremes in the Korean peninsula from the CMIP5 ensemble

Abstract Projections of changes in extreme climate are sometimes predicted by multimodel ensemble methods that combine forecasts from individual simulation models using weighted averaging. One method to assign weight to each model is the Bayesian model averaging (BMA) in which posterior probability is used. For the cases of extreme climate, the generalized extreme value distribution (GEVD) is typically used. We applied the approach of GEV‐embedded BMA to a series of 35 years of the annual maximum daily precipitation data (both historical data and data gathered from simulation experiments for future periods) over the Korean peninsula as simulated by the models in the Coupled Model Intercomparison Project Phase 5 (CMIP5). Simulation data under two Representative Concentration Pathway (RCP) scenarios, namely RCP4.5 and RCP8.5, were used. Observed data and 17 CMIP5 models for 12 gird cells in Korea have been examined to predict future changes in precipitation extremes. A simple regional frequency analysis of pooling observations from three stations in each cell was employed to reduce the estimation variance and local fluctuations. A bias correction technique using the regression‐type transfer function was applied to these simulation data. Return levels spanning over 20 and 50 years, as well as the return periods relative to the reference years (1971–2005), were estimated for two future periods, namely Period 1 (2021–2050) and Period 2 (2066–2095). From these analyses, relative increase observed in the spatially averaged 20‐year (50‐year) return level was approximately 23% (16%) and 45% (36%) in the RCP4.5 and RCP8.5 experiments, respectively, by the end of the 21st century. We concluded that extreme rainfalls will likely occur two times and four times more frequently in the RCP4.5 and RCP8.5 scenarios, respectively, as compared to in the reference years by the end of the 21st century.

Lee, Youngsaeng↗
DOE OSTI2013

Lidar Investigation of Tropical Nocturnal Boundary Layer Aerosols and Cloud Macrophysics

Observational evidence of two-way association between nocturnal boundary layer aerosols and cloud macrophysical properties under different meteorological conditions is reported in this paper. The study has been conducted during 2008-09 employing a high space-time resolution polarimetric micro-pulse lidar over a tropical urban station in India. Firstly, the study highlights the crucial role of boundary layer aerosols and background meteorology on the formation and structure of low-level stratiform clouds in the backdrop of different atmospheric stability conditions. Turbulent mixing induced by the wind shear at the station, which is associated with a complex terrain, is found to play a pivotal role in the formation and structural evolution of nocturnal boundary layer clouds. Secondly, it is shown that the trapping of energy in the form of outgoing terrestrial radiation by the overlying low-level clouds can enhance the aerosol mixing height associated with the nocturnal boundary layer. To substantiate this, the long-wave heating associated with cloud capping has been quantitatively estimated in an indirect way by employing an Advanced Research Weather Research and Forecasting (WRF-ARW) model version 2.2 developed by National Center for Atmospheric Research (NCAR), Colorado, USA, and supplementary data sets; and differentiated against other heating mechanisms. The present investigation as well establishes the potential of lidar remote-sensing technique in exploring some of the intriguing aspects of the cloud-environment relationship.

aerosols↗
DOE OSTI2026

AGFormer: Adaptive Spatiotemporal graph informed transformer for multi-reservoir inflow forecasting

Accurate reservoir inflow forecasting is crucial for effective water resource management, yet most machine learning models focus on single-reservoir prediction and overlook spatial dependencies among hydrologically connected reservoirs. Here, we propose AGFormer (Adaptive Graph-Informed Transformer), an end-to-end framework that integrates adaptive graph learning with temporal sequence modeling for multi-reservoir inflow forecasting. A shared encoder and graph attention mechanism generate reservoir-specific embeddings, which are then processed by the Transformer-based encoder–decoder for multi-step inflow forecasting. We also introduce a pretraining paradigm to learn robust temporal embeddings from misaligned historical records. Evaluated on 30 reservoirs in the Upper Colorado River Basin, AGFormer achieves superior seven-day-ahead forecasts, with NSE > 0.75 for 20 reservoirs—outperforming Encoder–Decoder LSTM, GCN+LSTM, and Transformer baselines. Adaptive graph learning captures dynamic inter-reservoir dependencies, and feature attribution aligns with snowmelt-driven hydrology. Incorporating forecasted meteorological inputs further enhances accuracy, demonstrating AGFormer’s potential to support reservoir management under dynamic hydrological conditions.

Adaptive graph learning↗
DOE OSTI2023

Impurity gas monitoring using ultrasonic sensing and neural networks: forward and inverse problems

Ultrasonic sensing is a non-invasive technique for monitoring impurity gas composition in various industrial applications where safety and regulatory compliance are crucial. In this study, ultrasonic sensing and neural networks were used to analyze impurity gases (i.e., air and argon) in helium. An experimental platform was established to acquire ultrasonic data. In the forward problem, an artificial neural network (ANN) model was used to forecast the response and time-of-flight (TOF) based on the excitation, and argon and air concentrations. The inverse problem was solved using a convolutional neural network (CNN) to predict the argon and air concentrations given the ultrasonic response and excitation. The results showed that the ANN accurately predicted the ultrasonic response and the change in TOF with concentration. As the air concentration was increased from 0 to 9.8%, the TOF sensitivity to detect argon decreased by 39.8% and 16.1% from ANN and sound speed theory, respectively. The CNN demonstrated high accuracy in predicting concentrations for inputs in the testing dataset. The application of the trained CNN indicated that it over-predicts air concentration while under-predicting the argon concentration. To improve accuracy, the predicted air and argon concentrations should be corrected by -0.992% and 1.027% bias, respectively.

47 OTHER INSTRUMENTATION↗