SEARCH · Engineering Papers

Results for “induction”

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.

SourceResearch connectionFrom yearThrough year

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

At least 127 records · Page 7

All sources NASA NTRS DOE OSTI

DOE OSTI2024

Fourier Analysis and Design of a Shielded 120kW Inductive Wireless System

High-power inductive wireless power transfer (WPT) systems for EVs are designed to meet specifications such as stray field, power level, efficiency, misalignment tolerance, and ground clearance. These metrics are all heavily influenced by the coil geometry. Herein this paper proposes a coil design method based on the Fourier Analysis Method (FAM) which is an analytical method for directly designing coil geometries to meet stray field and power level requirements through an optimization of Fourier basis function coefficients. In this work, two 120 kW WPT proof-of-concept demonstrators with low stray field and high efficiency are built from FAM optimization results to validate the models and show the impact of the FAM design process. Experimental validation of the Gen. 2 demonstrator at 120 kW output power resulted in a measured DC/DC efficiency of 97.2% at alignment with a 125 mm airgap. At the 120 kW test point, the stray fields 80 cm away from the center of the airgap between the coil assemblies were 3.4 µT(rms) on the X-axis and 3.5 µT(rms) on the Y-axis, much lower than the 27 µT(rms) ICNIRP limit.

42 ENGINEERING↗

DOE OSTI2025

Characterization of Impedance and Stability for Doubly-Fed Induction Generator Based on Voltage-Modulated Direct Power Control

Voltage-modulated direct power control (VM-DPC) applied to the doubly-fed induction generator (DFIG) offers superior steady-state and transient performance but remains underexplored for suppressing wideband oscillations. Here, this article proposes a comprehensive impedance for the VM-DPC-based DFIG, analyzing its impedance characteristics and stability mechanisms compared with the DFIG based on vector-oriented control (VOC). The unified power transfer function is defined for DFIGs employing VM-DPC or VOC to ensure consistent comparison benchmarks. The comprehensive impedance of VM-DPC-based DFIG, incorporating mechanical and grid-side converter (GSC) dynamics, is derived using complex vector modeling in the αβ -frame. Furthermore, the influence of VM-DPC parameters and grid strength on the stability of grid-connected DFIG systems is assessed through eigenvalue trajectory analysis. Impedance analysis reveals the significant contributions of mechanical and GSC dynamics to DFIG impedance, as well as the narrower frequency range of negative resistance in the VM-DPC-based DFIG compared to the VOC-based DFIG. Stability analysis identifies the VM-DPC parameters of the rotor-side converter as dominant factors affecting system stability and confirms that the VM-DPC-based DFIG achieves better stability under weak grid conditions than its VOC-based counterpart. These findings are validated through simulations and experiments.

42 ENGINEERING↗

DOE OSTI2020

High-Efficiency Inductive Output Tubes Using a Third Harmonic Drive on the Grid

In this article, we discuss the use of a third harmonic component to the drive voltage on the grid of an inductive output tube (IOT). High-efficiency IOTs are typically characterized by efficiencies up to 70%–75%. However, the achievement of efficiencies greater than 80% would substantially reduce the operating costs of next-generation accelerators. In order to achieve this goal, we consider the addition of a third harmonic component to the drive signal on the grid of an IOT. The use of a third harmonic drive component in IOT guns has been considered in order to apply such a gun as the injector of radio frequency linear accelerators (RF linacs). Furthermore, we consider that the IOT will be used to provide the rf power to drive RF linacs and apply the third harmonic with the intention of increasing the efficiency of the RF output of the IOT. We consider a model IOT with a 700-MHz resonant cavity and using an annular beam with a voltage of 30 kV, an average current of 6.67 A yielding a perveance of about 1.3 μP. We simulate this IOT using the NEMESIS simulation code which has been successfully validated by comparison with the K5H90W-2 IOT developed by Communications and Power Industries. It is found that the effect of the third harmonic on the efficiency is greatest when the phase of the third harmonic is shifted by radians with respect to the fundamental drive signal and with third harmonic powers greater than about 50% that of the fundamental drive power. For the present example, we show that efficiencies approaching 86% are possible by this means.

43 PARTICLE ACCELERATORS↗

DOE OSTI2024

Preliminary Design of Ironless Linear Induction Motors for ITER MSE Shutter Actuators

In this article, the shutters need to be closed or opened during the operation and calibration period time for the fusion diagnostic systems, such as the International Thermonuclear Experimental Reactor (ITER) motional stark effect (MSE). Standard electric motors and actuators will not work in a strong magnetic field environment due to the presence of the magnetic field of fusion reactors. The innovative linear induction motor (LIM) with an ironless feature overcomes this kind of challenge and can be used for any application that requires controlled motion with a large stroke in the magnetic field environment. It consists of a high-electrical conductivity plate like copper and three-phase motor windings with nonferrous or stainless-steel stators. The conductor plate attached with the shutter is simply driven by the underneath three-phase linear windings to achieve linear motion. The motor drive can be controlled remotely by a controller using the electrical connection, so no sensitive electronic components are located in the harsh environment where the motor itself is located. The design requirements and test facility have been described. Several 3-D transient Maxwell electromagnetic (EM) models with different locations of three-phase linear motor windings and shutter stators have been analyzed and evolved to meet any applications allowed in the harsh environment inside the vacuum vessel of fusion reactors. The preliminary design results are presented in this article.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2024

Fourier Analysis and Loss Modeling for Inductive Wireless Electric Vehicle Charging with Reduced Stray Field

With the growth of electric vehicle (EV) popularity, different charging options to increase user convenience and reduce charging times are being considered and researched. Among these, inductive wireless power transfer (WPT) systems for EVs are being designed to meet specifications such as stray field, power level, efficiency, misalignment tolerance, and ground clearance, which are all heavily influenced by the coil geometry. The proposed Fourier Analysis Method (FAM) is an analytical method to directly design coil geometries to meet stray field and power level requirements through an optimization of Fourier basis function coefficients. The outputs of the optimization are complex, planar coil geometries that meet the power level and stray field constraints with minimized loss factors. Contours of these potentials determine the coil conductor paths and loss models predict the system efficiency and performance over misalignment. The Fourier representation of the geometry is used to conveniently calculate the coupling over misalignment, external proximity effect loss, and ferrite loss. A 6.6 kW prototype WPT system with low stray field and high efficiency is built from the optimization results to validate the models and showcase the usefulness of the FAM design approach.

33 ADVANCED PROPULSION SYSTEMS↗

DOE OSTI2022

Absolute measurement of vacuum ultraviolet photon flux in an inductively coupled plasma using a Au thin film

A new method for absolute measurement of the vacuum ultraviolet (VUV) photon flux at the edge of a plasma is described. The light produced by the plasma was allowed to strike a negatively biased, gold-coated copper substrate remote from the plasma. The resulting photoelectron emission current was measured, and the absolute photon flux was then found from the known photoelectron yield of Au. The method was used to quantify the amount of VUV light produced by an Ar/He inductively coupled plasma (ICP). Strong emissions at 104.82 and 106.67 nm, corresponding to the 1s 2 and 1s 4 resonant states of Ar, were observed. The maximum, integrated VUV photon flux measured at the remote location was 3.2 × 10 13 photons/cm 2 s. This was estimated to correspond to a flux of 5 × 10 15 photons/cm 2 s at the edge of the ICP, in the range of reported values under similar conditions.

70 PLASMA PHYSICS AND FUSION TECHNOLOGY↗

DOE OSTI2020

Trace Elemental Analysis of Bulk Thorium Using an Automated Separation–Inductively Coupled Plasma Optical Emission Spectroscopy Methodology

Presented here is a novel automated method for determining the trace element composition of bulk thorium by inductively coupled plasma–optical emission spectroscopy (ICP-OES). ICP-OES is a universal approach for measuring the trace elemental impurities present in actinide-rich materials; however, due to the emission rich spectrum of the actinide, a separation from the trace elements is warranted for spectrochemical analysis. Here, AG MP-1 ion exchange resin was utilized for retention of the Th matrix, while allowing the trace element impurities to be separated prior to subsequent analysis using ICP-OES. After demonstrating the separation on traditional gravity-driven columns, the methodology was transitioned to an automated platform for comparison. This automated platform utilizes syringe-driven sample and solvent flow and can collect the trace element and thorium fractions in separate locations. Finally, while reducing the sample size (500 µL, 1.5 mg of Th), maintaining the overall separation efficiency (recoveries >95%), and illustrating the sample throughput ability (n = 10+), this automated methodology could be readily adopted to nuclear facilities in which the determination of trace elemental impurities in Th samples is warranted.

47 OTHER INSTRUMENTATION↗

DOE OSTI2025

Assessment of Low-Level Pu Isotope Ratio Measurements Using Multicollector Inductively Coupled Plasma Mass Spectrometry (MC-ICP-MS/MS) Equipped with a Pre-Mass Filter

We present an initial investigation into the performance of a multicollector inductively coupled plasmamass spectrometer equipped with a pre-mass filter (Neoma MC-ICP-MS/MS) for making plutonium (Pu) isotope ratio measurements on solutions containing low level (i.e., pg mL –1 ) Pu concentrations. This assessment was achieved by comparison of the 240 Pu/ 239 Pu, 241 Pu/ 239 Pu, and 242 Pu/ 239 Pu ratios attained over a one month period on the MC-ICP-MS/MS with the long-term (∼1 year) performance observed on the predecessor MC-ICP-MS (Neptune Plus) instrument each equipped with an equipped with an APEXΩ desolvating nebulizer for repeated measurements of certified reference materials from New Brunswick Program Office (NBL PO) CRM 136a and CRM 137. The MC-ICP-MS/MS performance of repeated measurement of CRM 136a (n = 20) resulted in mean values of 240 Pu/ 239 Pu = 0.1448 ± 0.0006, 241 Pu/ 239 Pu = 0.00371 ± 0.00006, and 242 Pu/ 239 Pu = 0.00682 ± 0.00006 (k = 2). The CRM 137 (n = 20), analyzed during the same analytical sessions, produced mean values for 240 Pu/ 239 Pu = 0.2414 ± 0.0006, 241 Pu/ 239 Pu = 0.00464 ± 0.00007, and 242 Pu/ 239 Pu = 0.0157 ± 0.0001 (k = 2). These results closely align with the certificate values for CRM 136a and CRM 137 and are within the k = 2 envelopes defined by the long-term performance of the traditional MC-ICP-MS approach (Neptune Plus). Examination of the performance of the various Pu isotope ratios as a function of total Pu content revealed accurate results (<3% relative difference, or RD) above ∼50 fg total Pu. The results presented here demonstrate the capability of the MC-ICP-MS/MS making accurate and precise low level Pu isotopic measurements. While the intent of this work was not to investigate the functionality of the collision cell, the pre-mass filter was employed. Future studies are warranted to investigate the entire capability of the MC-ICP-MS/MS collision cell and pre-cell mass filter optimization for performing low level Pu isotope measurements, even in mixed matrix samples.

CRM↗

DOE OSTI2022

Data for Increased bundle sheath leakiness of CO2 during photosynthetic induction shows a lack of coordination between the C4 and C3 cycles

We developed a new application of isotopic gas exchange which couples a tunable diode laser absorption spectroscope (TDL) with a leaf gas exchange system, analyzing leakiness through induction of C4 photosynthesis on dark to high-light transitions. The youngest fully expanded leaf was measured on 40-45 day-old maize(B73) and sorghum (Tx430). Detail definition of each variable in raw Li-6400XT and Li-6800 (in "Original_data_AND_Data_processing_code.zip") is summarized in: https://www.licor.com/env/support/LI-6800/topics/symbols.html#const

bundle sheath leakage↗

DOE OSTI2026

Electromagnetic Induction (EMI) Data, 2024, Trail Creek, Colorado

This dataset contains Electromagnetic Induction (EMI) data collected at Trail Creek, Colorado, in 2024. EMI surveys were conducted to investigate the spatial distribution of electrical conductivity in the subsurface, providing insights into soil moisture and subsurface geological features. The surveys were performed along multiple transects to capture variations in conductivity influenced by changes in soil composition, moisture content, and underlying geological structures. This dataset complements other geophysical data collected in the region, including Electrical Resistivity Tomography (ERT) and Terrestrial LiDAR Scanning (TLS), providing a detailed understanding of the subsurface and its impact on surface vegetation and hydrological processes. The data are valuable for environmental geophysics, ecological research, and hydrological modeling in mountainous ecosystems. The files include: - data.zip: the raw EMI data (.csv) - inversion.zip: the inverted resistivity model (.csv and .kml) - kriging.zip: the kriging resistivity model (.csv, .tif, .kmz) - flmd.csv: file level metadata file describing all files within this dataset - dd.csv: data dictionary file describing the column headers within CSV files This work was supported by the Watershed Function Science Focus Area at Lawrence Berkeley National Laboratory funded by the US Department of Energy, Office of Science, Biological and Environmental Research under Contract No. DE-AC02-05CH11231.

CMD Mini-Explorer↗

DOE OSTI2022

Time-Resolved Beam Position Measurements for the Scorpius Multipulse Linear Induction Accelerator

Beam position monitors (BPMs) provide time-resolved measurements of the current and centroid position of high-current electron beams in linear induction accelerators (LIAs). One of the types of detectors used in BPMs is the B-dot loop, which generates a signal from the EMF due to the time varying magnetic flux through the loop. If some of the boundaries of the loop are composed of thick metal walls with finite conductivity, the resulting signal must be corrected for the magnetic field diffusion into the metal. The theoretically predicted flux due to diffusion is in remarkable agreement with experimental measurements. Although accurate BPM measurements of beam current require correction of magnetic field diffusion, accurate measurement of beam position requires no correction. In this note, we present a theoretical derivation and the experimental validation of this result.

43 PARTICLE ACCELERATORS↗

DOE OSTI2025

HPC for Optimizing Process Parameters to Control Material Evolution in Seamless Induction Hardening of Wind Turbine Main Shaft Bearings

Work proposed in this project focused on understanding the effect of martensitic transformation in the steel on the potential for cracking during seamless induction hardening (SIH) as a function of process conditions to allow the process to optimally scale up. Large-scale, three-dimensional phase-field simulations of martensitic transformation were performed using MEUMAPPS-SS (Microstructure Evolution Using Massively Parallel Phase-field Simulations – Solid State) code developed at Oak Ridge National Laboratory. The simulations were guided by location-specific thermal history generated by experimental measurements of time-temperature history generated at The Timken Company. The simulations were able to capture the morphological evolution of the martensite variants in an Fe-1.0C-1.5Cr steel based on the Nishiyama-Wasserman (NW) orientation relationship. The simulations were also able to quantify the stress-state at the interface between impinging martensite variants. The simulations indicated that the magnitude of the various stress and strain components were dependent on the sizes of the impinging plates with a reduction in these quantities with reduced plate size in agreement with experimental findings. The results obtained from the simulations will be used to guide the optimization of the alloy thermal conditions to eliminate quench cracking during SIH of bearing steels.

99 GENERAL AND MISCELLANEOUS↗

DOE OSTI2021

Flow Redirection and Induction in Steady State (FLORIS) Wind Plant Power Production Data Sets

This dataset contains turbine- and plant-level power outputs for 252,500 cases of diverse wind plant layouts operating under a wide range of yawing and atmospheric conditions. The power outputs were computed using the Gaussian wake model in NREL's FLOw Redirection and Induction in Steady State (FLORIS) model, version 2.3.0. The 252,500 cases include 500 unique wind plants generated randomly by a specialized Plant Layout Generator (PLayGen) that samples randomized realizations of wind plant layouts from one of four canonical configurations: (i) cluster, (ii) single string, (iii) multiple string, (iv) parallel string. Other wind plant layout parameters were also randomly sampled, including the number of turbines (25-200) and the mean turbine spacing (3D-10D, where D denotes the turbine rotor diameter). For each layout, 500 different sets of atmospheric conditions were randomly sampled. These include wind speed in 0-25 m/s, wind direction in 0 deg.-360 deg., and turbulence intensity chosen from low (6%), medium (8%), and high (10%). For each atmospheric inflow scenario, the individual turbine yaw angles were randomly sampled from a one-sided truncated Gaussian on the interval 0 deg.-30 deg. oriented relative to wind inflow direction. This random data is supplemented with a collection of yaw-optimized samples where FLORIS was used to determine turbine yaw angles that maximize power production for the entire plant. To generate this data, a subset of cases were selected (50 atmospheric conditions from 50 layouts each for a total of additional 2,500 cases) for which FLORIS was re-run with wake steering control optimization. The IEA onshore reference turbine, which has a 130 m rotor diameter, a 110 m hub height, and a rated power capacity of 3.4 MW was used as the turbine for all simulations. The simulations were performed using NREL's Eagle high performance computing system in February 2021 as part of the Spatial Analysis for Wind Technology Development project funded by the U.S. Department of Energy Wind Energy Technologies Office. The data was collected, reformatted, and preprocessed for this OEDI submission in May 2023 under the Foundational AI for Wind Energy project funded by the U.S. Department of Energy Wind Energy Technologies Office. This dataset is intended to serve as a benchmark against which new artificial intelligence (AI) or machine learning (ML) tools may be tested. Baseline AI/ML methods for analyzing this dataset have been implemented, and a link to their repository containing those models has been provided. The .h5 data file structure can be found in the GitHub repository under explore_wind_plant_data_h5.ipynb.

AI↗

DOE OSTI2021

Data-Driven Adaptive Damping Controller for Wind Power Plants with Doubly-Fed Induction Generators: Preprint

This paper presents an adaptive damping controller for wind power plants in which the turbines are equipped with doubly-fed induction generators. The controller is designed to respond to an input control signal that is triggered according to the system operating conditions. A processing unit continuously estimates the electromechanical modes of oscillation based on real-time streaming data acquired from a phasor measurement unit that is strategically positioned on the grid. The decision to trigger (or not trigger) the control signal is automatic, based on the relative damping of the dominant mode. The modes are estimated using the dynamic mode decomposition algorithm with time-delay embedding. Numerical simulations performed on the two-area system demonstrate that the proposed controller enhances the rotor angle stability for both small-signal and large disturbances, and is adaptive to changing grid conditions.

61 RADIATION PROTECTION AND DOSIMETRY↗

DOE OSTI2023

Induction and Stabilization of Columnar Mesophases in Fluorinated Polycyclic Aromatic Hydrocarbons by Arene‐Perfluoroarene Interactions

Abstract The straightforward synthesis of several Fluorinated Polycyclic Aromatic Hydrocarbons by the efficient, transition‐metal‐free, arene fluorine nucleophilic substitution reaction is described, and the full investigation of their liquid crystalline and optical properties reported. The key precursors for this study, i. e. 2,2’‐dilithio‐4,4′,5,5′‐tetraalkoxy‐1,1’‐biphenyl derivatives, were obtained in two steps from the highly selective Scholl oxidative homo‐coupling of 3,4‐dialkoxy‐1‐bromobenzene, followed by quantitative double‐lithiation. In situ room temperature nucleophilic annulation with either perfluorobenzene or perfluoronaphthalene leads to 1,2,3,4‐tetrafluoro‐6,7,10,11‐tetraalkxoytriphenylenes and 9,10,11,12,13,14‐hexafluoro‐2,3,6,7‐tetraalkoxybenzo[f]tetraphenes, respectively, in good yields. Exploiting the same strategy, subsequent double annulations resulted in the formation of 9,18‐difluoro‐2,3,6,7,11,12,15,16‐octa(alkoxy)tribenzo[f,k,m]tetraphenes and 9,10,19,20‐tetrafluoro‐2,3,6,7,12,13,16,17‐octakis(hexyloxy)tetrabenzo[a,c,j,l]tetracenes, respectively. Despite the presence of only four alkoxy chains, the polar “Janus” mesogens display a columnar hexagonal mesophase over broad temperature ranges, with higher mesophase stability than the archetypical 2,3,6,7,10,11‐hexa(alkoxy)triphenylenes and their hydrogenated counterparts. The improvement or induction of mesomorphism is attributed to efficient antiparallel face‐to‐face π‐stacking driven by the establishment of non‐covalent perfluoroarene‐arene intermolecular interactions. The larger lipophilic discotic π‐extended compounds also exhibit columnar mesomorphism, over similar temperature ranges and stability than their hydrogenated homologs. Finally, these fluorinated molecules form stringy gels in various solvents, and show interesting solvatochromic emission properties in solution as well as strong emission in thin films and gels.

Chemistry↗

DOE OSTI2026

Simultaneous Determination of Halogens and Metals in Waste Plastic Pyrolysis Oil by Inductively Coupled Plasma Mass Spectrometry

A major barrier to integrating pyrolysis-derived oil into conventional refinery technology is the presence of impurities, particularly halogens and metals, that can deactivate catalysts. This study presents a novel, cost-effective approach for the simultaneous analysis of a subset of halogens, metals, nonmetals, and metalloids in complex, industrially relevant distilled pyrolysis oil samples, this was previously achievable only through multiple techniques. Excellent results were obtained using a widely accessible inductively coupled plasma mass spectrometry (ICP-MS) method with helium gas mode and standard laboratory consumables, enabling high-throughput analysis and efficient evaluation of adsorbent performance. Sample preparation is straightforward, requiring only dilution in a compatible matrix, and provides accurate and precise quantification, with 75%–137% spike recovery for Be, Ti, V, Cr, Fe, Ni, Co, Cu, As, Se, Mo, Cd, Sb, Tl, and Pb, and 62%–65% spike recovery for Cl and 109%–133% spike recovery for Br. Additionally, an enhanced version of the method using ICP-MS/MS and hydrogen gas is described, which has higher accuracy with 69%–112% spike recovery for Be, B, Ti, V, Fe, Co, Ni, Cu, As, Se, Mo, Cd, Sb, Tl, and Pb, with 85%–102% spike recovery for Cl and 63%–93% spike recovery for Br. Helium mode detection limits for industrially relevant elements (V, Fe, Ni, Cu, As, and Pb) are less than 1.7 µg/kg, and less than 0.2 mg/kg for Br and Cl. Furthermore, this methodology facilitates rapid systematic evaluation of adsorption capacities of materials under time-on-stream conditions and supports robust comparisons across diverse operating environments.

Lazarcik, James [University of Wisconsin-Madison, ↗

DOE OSTI2024

A preliminary investigation into the feasibility of laser ablation U–Pb isotope ratio measurement via all‐faraday cup detection with 10 11 ‐ and 10 13 ‐Ω amplifiers on the Neoma multicollector‐inductively coupled plasma‐mass spectrometer

Rationale Signal detection for uranium–lead (U–Pb) dating of zircon is typically performed via ion counters. Here, we develop a preliminary understanding of the strengths and limitations of faraday‐cup‐based detection. Methods A suite of zircon reference materials and the NIST‐610 glass were sampled using laser ablation followed by U–Pb isotope ratio measurement on a Neoma multicollector‐inductively coupled plasma‐mass spectrometer. Results We were able to produce geologically accurate 207 Pb/ 206 Pb, 206 Pb/ 238 U, and 207 Pb/ 235 U ratios for the NIST‐610 glass and the zircon standards, with ages ranging from ~2.5 Ga to ~337 Ma (TanBrown A, Oracle, 91550, Mud Tank, Temora, and Plešovice). Two of the younger zircon standards examined (94‐35, ~55.6 Ma, and Fish Canyon, 28.6 Ma) yielded accurate 206 Pb/ 238 U but not 207 Pb/ 235 U or 207 Pb/ 206 Pb ratios, whereas the youngest zircon standard (Penglai, ~4.4 Ma) failed for all three ratios of interest. The accuracy and precision of the all‐faraday method are directly tied to signal intensity, with reliable data capable of being produced even when both isotopes in a ratio have signals below ~0.001 V (equivalent to ~62 500 cps on an ion counter). Conclusion The all‐faraday cup multicollection method provides sufficient sensitivity to obtain geologically meaningful U–Pb data, with possible advantages being that laser pit depth‐dependent changes in the observed interelemental fractionation behavior may be easier to correct using a static collector configuration compared to when the ion beam is swept across a single detector while also removing the need for an interdetector‐type calibration. Further work is needed to refine the all‐faraday cup method (e.g., application of background subtraction and common Pb corrections, outlier removal, and interelement as well as down‐hole fractionation corrections), but our initial results demonstrate that the faraday detector method has sufficient sensitivity to warrant further study.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

DOE OSTI2021

Energy and Emission Prediction for Mixed-Vehicle Transit Fleets Using Multi-task and Inductive Transfer Learning

Public transit agencies are focused on making their fixed-line bus systems more energy efficient by introducing electric (EV) and hybrid (HV) vehicles to their fleets. However, because of the high upfront cost of these vehicles, most agencies are tasked with managing a mixed-fleet of internal combustion vehicles (ICEVs), EVs, and HVs. In managing mixed-fleets, agencies require accurate predictions of energy use for optimizing the assignment of vehicles to transit routes, scheduling charging, and ensuring that emission standards are met. The current state-of-the-art is to develop separate neural network models to predict energy consumption for each vehicle class. Although different vehicle classes’ energy consumption depends on a varied set of covariates, we hypothesize that there are broader generalizable patterns that govern energy consumption and emissions. In this paper, we seek to extract these patterns to aid learning to address two problems faced by transit agencies. First, in the case of a transit agency which operates many ICEVs, HVs, and EVs, we use multi-task learning (MTL) to improve accuracy of forecasting energy consumption. Second, in the case where there is a significant variation in vehicles in each category, we use inductive transfer learning (ITL) to improve predictive accuracy for vehicle class models with insufficient data. As this work is to be deployed by our partner agency, we also provide an online pipeline for joining the various sensor streams for fixed-line transit energy prediction. Here, we find that our approach outperforms vehicle-specific baselines in both the MTL and ITL settings.

97 MATHEMATICS AND COMPUTING↗