Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “error performance”

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 1,063 records · Page 59
All sourcesNASA NTRSDOE OSTI
DOE OSTI2023

The miniJPAS survey quasar selection – II. Machine learning classification with photometric measurements and uncertainties

Astrophysical surveys rely heavily on the classification of sources as stars, galaxies, or quasars from multiband photometry. Surveys in narrow-band filters allow for greater discriminatory power, but the variety of different types and redshifts of the objects present a challenge to standard template-based methods. In this work, which is part of a larger effort that aims at building a catalogue of quasars from the miniJPAS survey, we present a machine learning-based method that employs convolutional neural networks (CNNs) to classify point-like sources including the information in the measurement errors. We validate our methods using data from the miniJPAS survey, a proof-of-concept project of the Javalambre Physics of the Accelerating Universe Astrophysical Survey (J-PAS) collaboration covering ∼1 deg 2 of the northern sky using the 56 narrow-band filters of the J-PAS survey. Due to the scarcity of real data, we trained our algorithms using mocks that were purpose-built to reproduce the distributions of different types of objects that we expect to find in the miniJPAS survey, as well as the properties of the real observations in terms of signal and noise. We compare the performance of the CNNs with other well-established machine learning classification methods based on decision trees, finding that the CNNs improve the classification when the measurement errors are provided as inputs. The predicted distribution of objects in miniJPAS is consistent with the putative luminosity functions of stars, quasars, and unresolved galaxies. Our results are a proof of concept for the idea that the J-PAS survey will be able to detect unprecedented numbers of quasars with high confidence.

79 ASTRONOMY AND ASTROPHYSICS↗
DOE OSTI2025

A dynamic 2D Borehole Thermal Energy Storage (BTES) model for enhanced computational efficiency

Progressing toward a future increasingly reliant on renewable energy sources, the development of effective, durable energy storage solutions becomes essential to balance supply and demand fluctuations. Borehole Thermal Energy Storage (BTES) is a long-duration thermal energy storage technology that captures excess heat generated from renewable energy sources and stores it underground for later use, enabling the efficient utilization of sustainable energy. This approach is particularly valuable in district energy networks when integrated with Ground Source Heat Pumps (GSHP) to provide stable heating and cooling. However, traditional three-dimensional (3D) numerical models of BTES systems demand extensive computational resources, limiting their practicality for real-time and large-scale applications. This study introduces a novel two-dimensional (2D) modeling approach that reduces computational costs while maintaining high accuracy. By employing a radial ring-based discretization method, the model simulates heat injection, retention, and retrieval dynamics over seasonal cycles. A new thermal-mass weighted-average temperature parameter is introduced to evaluate the performance of BTES systems. Model validation against FEFLOW simulations demonstrates a 17-fold improvement in computational speed compared to traditional Computational Fluid Dynamics (CFD) models while achieving a mean absolute percentage error (MAPE) of 2 % during charging and 4 % during discharging. Additionally, a trade-off analysis between computational efficiency and accuracy is conducted, ensuring the model's applicability for real-world scenarios. The findings of this research contribute to the development of computationally efficient BTES models, facilitating better optimization, control, and integration into renewable energy systems. This work provides a foundation for further studies in techno-economic analysis, multi-year performance evaluation, and real-time operational strategies for BTES applications, supporting a more sustainable energy future.

2D modeling↗
DOE OSTI2022

A hybrid adaptive multiresolution approach for the efficient simulation of reactive flows

Computational studies that use block-structured adaptive mesh refinement (AMR) approaches suffer from unnecessarily high mesh resolution in regions adjacent to important solution features. This deficiency limits the performance of AMR codes. In this work a novel hybrid adaptive multiresolution (HAMR) approach to AMR-based calculations is introduced to address this issue. The multiresolution (MR) smoothness indicators are used to identify regions of smoothness on the mesh where the computational cost of individual physics solvers may be decreased by replacing direct calculations with interpolation. We suggest an approach to balance the errors due to the adaptive discretization and the interpolation of physics quantities such that the overall accuracy of the HAMR solution is consistent with that of the MR-driven AMR solution. The performance of the HAMR scheme is evaluated for a range of test problems, from pure hydrodynamics to turbulent combustion.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2026

Thorium Monosilicide, ThSi: An Experimental and Theoretical Study

The present theoretical and experimental combination study investigates the ThSi molecule in detail. Computationally, we utilized high-level multireference and coupled-cluster levels of theory conjoined with large correlation consistent basis sets to study a series of electronic and spin–orbit states of ThSi. Here, we report potential energy curves (PECs), electron configurations at equilibrium distances, spectroscopic constants, energetics, and spin–orbit coupling effects for 16 electronic states of ThSi. The studied 16 electronic states are arranged tightly within 0.9 eV, highlighting the complexity of the electronic spectrum of ThSi. The ground electronic state of ThSi is a single-reference 1 1 Σ + state that derives from the 1σ 2 2σ 2 1π 4 electronic configuration. The Ω = 0 + spin–orbit ground state of ThSi is composed of 1 1 Σ + (47%) and 13Π (44%) electronic states. Our measured bond energy (D0) of ThSi, obtained using resonant two-photon ionization (R2PI) spectroscopy is 3.146(4) eV, where the assigned error limit is given in parentheses in units of the last quoted digits. The computed D0 of ThSi (Ω = 0 + ) at the CBS-C-CCSD(T)-δT(Q)-δDK-δSO level (3.181 eV) is in good agreement with the experimental value. Our derived enthalpy of formation for ThSi, Δ f H 0K o (ThSi(g)), is 971.8(6.0) kJ/mol. Finally, we have performed density functional theory (DFT) calculations for ThSi(1 1 Σ + ) using 16 exchange correlation functionals that span multiple rungs of “Jacob’s ladder” of density functional approximation (DFA) to assess the DFT errors on D 0 , r e , and ω e of ThSi with respect to experimental and ab initio coupled-cluster values.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2022

Development of Short-Term Forecasting Models Using Plant Asset Data and Feature Selection

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This paper focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 +- 0.014, 0.0026 +- 0, and 0.063 +- 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2022

Analytics-at-scale of Sensor Data for Digital Monitoring in Nuclear Plants (3 rd Annual Report)

Nuclear power plants collect and store large volumes of heterogeneous data from various components and systems. With recent advances in machine learning (ML) techniques, these data can be leveraged to develop diagnostic and short-term forecasting models to better predict future equipment condition. Maintenance operations can then be planned in advance whenever degraded performance is predicted, thus resulting in fewer unplanned outages and the optimization of maintenance activities. This enables lower maintenance costs and improves the overall economics of nuclear power. This report primarily focuses on developing a short-term forecasting process that leverages a feature selection process to distill large volumes of heterogeneous data and predict specific equipment parameters. A variety of feature selection methods, including Shapley Additive Explanations (SHAP) and variance inflation factor (VIF), were used to select the optimal features as inputs for three ML methods: long short-term memory (LSTM) networks, support vector regression (SVR), and random forest (RF). Each combination of model and input features was used to predict a pump bearing temperature both 1 and 24 hours in advance, based on actual plant system data. The optimal inputs for the LSTM and SVR were selected using the SHAP values, while the optimal input for the RF consisted solely of the response variable itself. Each model produced similar 1-hour-ahead predictions, with root mean square errors (RMSEs) of roughly 0.006. For the 24-hour-ahead predictions, differences could be seen between LSTM, SVR, and RF, as reflected by model performances of 0.036 ± 0.014, 0.0026 ± 0, and 0.063 ± 0.004 RMSE, respectively. As big data and continuous online monitoring become more widely available, the proposed feature selection process can be used for many applications beyond the prediction of process parameters within nuclear infrastructure. This report summarizes the Fiscal Year 2021 research progress encompassing the (1) data cleaning and feature selection necessary for ML applications; (2) development of short-term forecasting models to predict future plant process parameters for both single and multiple time steps ahead; and (3) validation of the feature selection methods and short-term forecasting models given new data from different systems.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗
DOE OSTI2023

Adaptive estimation of quantum observables

The accurate estimation of quantum observables is a critical task in science. With progress on the hardware, measuring a quantum system will become increasingly demanding, particularly for variational protocols that require extensive sampling. Here, we introduce a measurement scheme that adaptively modifies the estimator based on previously obtained data. Our algorithm, which we call AEQuO, continuously monitors both the estimated average and the associated error of the considered observable, and determines the next measurement step based on this information. We allow both for overlap and non-bitwise commutation relations in the subsets of Pauli operators that are simultaneously probed, thereby maximizing the amount of gathered information. AEQuO comes in two variants: a greedy bucket-filling algorithm with good performance for small problem instances, and a machine learning-based algorithm with more favorable scaling for larger instances. The measurement configuration determined by these subroutines is further post-processed in order to lower the error on the estimator. We test our protocol on chemistry Hamiltonians, for which AEQuO provides error estimates that improve on all state-of-the-art methods based on various grouping techniques or randomized measurements, thus greatly lowering the toll of measurements in current and future quantum applications.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2023

In-situ thermophysical measurement of flowing molten chloride salt using modulated photothermal radiometry

Molten salts are leading candidates for high-temperature heat transfer fluids (HTFs) for thermal energy storage and conversion systems in concentrated solar power (CSP) and nuclear energy power plants. The ability to probe molten salt thermal transport properties in both stationary and flowing status is important for the evaluation of their heat transfer performance under realistic operational conditions, including the temperature range and potential degradation due to corrosion and contamination. However, accurate thermal transport properties are usually challenging to obtain even for stagnant molten salts due to different sources of errors from convection, radiation, and corrosion, let alone at flowing status. To the best of authors’ knowledge, there is no available in-situ technique for measuring flowing molten salt thermal conductivity. Here, we report the first in-situ flowing molten salt thermal conductivity measurement using modulated photothermal radiometry (MPR). We could successfully perform the first in-situ thermal conductivity measurement of flowing molten NaCl-KCl-MgCl 2 in the typical operating temperature (520 and 580 °C) with flow velocities ranging from around 0.3 to 1.0 m s -1 . The relative change of the molten salt thermal conductivity was measured. Gnielinski’s correlation was also used to estimate the heat transfer coefficient h of the flowing NaCl-KCl-MgCl 2 in the given experimental condition. Furthermore, the work showed the potential of the MPR technique serving as an in-situ diagnostics tool to evaluate the heat transfer performance of flowing molten salts and other high-temperature HTFs.

14 SOLAR ENERGY↗
DOE OSTI2021

Measuring a Low Horizontal Hydraulic Gradient in a High Transmissivity Aquifer

Abstract High transmissivity aquifers typically have low hydraulic gradients (i.e., a flat water table). Measuring low gradients using water levels can be problematic because measurement error may be greater than the true difference in water levels (i.e., a low signal‐to‐noise ratio). In this study, the feasibility of measuring a hydraulic gradient in the range of 10 −6 to 10 −5 m/m was demonstrated. The study was performed at a site where the depth to water from land surface ranged from 40.1 to 94.2 m and the aquifer transmissivity was estimated at 41,300 m 2 /d (hydraulic conductivity of 18,800 m/d). The goals of the study were to reduce measurement error as much as practicable and assess the importance of factors affecting water level measurement accuracy. Well verticality was the largest source of error (0.000 to 0.168 m; median of 0.014 m), and geodetic survey of casing elevations was the next most important source of error (0.002 to 0.013 m; median of 0.005 m). Variability due to barometric pressure fluctuations was not an important factor at the site. Hydraulic heads were measured to an accuracy of ±0.0065 m, and the average hydraulic gradient was estimated to be 8.0 × 10 −6 (±0.9 × 10 −6 ) m/m. The improvement in accuracy allowed for two reversals in the groundwater flow direction to be identified, after which the gradient averaged 2.5 × 10 −5 (±0.4 × 10 −5 ) m/m. This study showed it is possible to sufficiently control sources of error to measure hydraulic gradients in the 10 −6 to 10 −5 m/m range.

McDonald, John P.↗
DOE OSTI2020

Blood flow imaging by optimal matching of computational fluid dynamics to 4D-flow data

Three-dimensional, time-resolved blood flow measurement (4D-flow) is a powerful research and clinical tool, but improved resolution and scan times are needed. Therefore, this study aims to (1) present a postprocessing framework for optimization-driven simulation-based flow imaging, called 4D-flow High-resolution Imaging with a priori Knowledge Incorporating the Navier-Stokes equations and the discontinuous Galerkin method (4D-flow HIKING), (2) investigate the framework in synthetic tests, (3) perform phantom validation using laser particle imaging velocimetry, and (4) demonstrate the use of the framework in vivo. An optimizing computational fluid dynamics solver including adjoint-based optimization was developed to fit computational fluid dynamics solutions to 4D-flow data. Synthetic tests were performed in 2D, and phantom validation was performed with pulsatile flow. Reference velocity data were acquired using particle imaging velocimetry, and 4D-flow data were acquired at 1.5 T. In vivo testing was performed on intracranial arteries in a healthy volunteer at 7 T, with 2D flow as the reference. Results Synthetic tests showed low error (0.4%-0.7%). Phantom validation showed improved agreement with laser particle imaging velocimetry compared with input 4D-flow in the horizontal (mean -0.05 vs -1.11 cm/s, P < .001; SD 1.86 vs 4.26 cm/s, P < .001) and vertical directions (mean 0.05 vs -0.04 cm/s, P = .29; SD 1.36 vs 3.95 cm/s, P < .001). In vivo data show a reduction in flow rate error from 14% to 3.5%. Phantom and in vivo results from 4D-flow HIKING show promise for future applications with higher resolution, shorter scan times, and accurate quantification of physiological parameters.

4D-flow MRI↗
DOE OSTI2021

A software environment for effective reliability management for pulsed power design

The reliable design of magnetically insulated transmission lines (MITLs) for very high current pulsed power machines must be accomplished in the future by utilizing a variety of sophisticated modeling tools. The complexity of the models required is high and the number of sub-models and approximations large. The potential for significant analyst error using a single tool is large, with possible reliability issues associated with the plasma modeling tools themselves or the chosen approach by the analyst to solve a given problem. Here, we report on a software infrastructure design that provides a workable framework for building self-consistent models and constraining feedback to limit analyst error. The framework and associated tools aid the development of physical intuition, the development of increasingly sophisticated models, and the comparison of performance results. The work lays the computational foundation for designing state-of-the-art pulsed-power experiments. The design and useful features of this environment are described. We discuss the utility of the Git source code management system and a GitLab interface for use in project management that extends beyond software development tasks.

42 ENGINEERING↗
DOE OSTI2021

Quantification of manganese for ChemCam Mars and laboratory spectra using a multivariate model

In this work, we report a new calibration model for manganese using the laser-induced breakdown spectroscopy instrument that is part of the ChemCam instrument suite onboard the NASA Curiosity rover. The model has been trained using an expanded set of 523 manganese-bearing rock, mineral, metal ore, and synthetic standards. The optimal calibration model uses the Partial Least Squares (PLS) and Least Absolute Shrinkage and Selection Operator (LASSO) multivariate techniques, with a novel “double blending” technique. We determined the detection limit for manganese is 82 ppm using a method blank procedure and is possibly as low as 27 ppm based on visual inspection of the spectra. Based on a representative test set consisting of measurements on 93 standards, the double blended multivariate model shows a Root Mean Squared Error of Prediction (RMSEP) accuracy of 1.39 wt% MnO for the full blended model. Employing a local RMSEP estimate where the model performance is evaluated based on nearby test samples, the accuracy is 0.03 wt% at the quantification limit (0.05 wt% MnO), 0.4 wt% accuracy at 1.0 wt% MnO, and 4.4 wt% accuracy at 100 wt% MnO. Precision is estimated using the standard deviation of the test set measurements, and is ±0.01 wt% MnO at the quantification limit, ±0.09 wt% MnO at 1.0 wt% MnO, and ± 2.1 wt% MnO at 100 wt% MnO (all 1 standard deviation). This new calibration is important for understanding the variation of manganese in the bedrock with the Curiosity rover on Mars, which provides insight into past redox conditions on Mars.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2026

Many-Body Benchmark of Electronic Charge and Spin Densities for Li 1–x NiO 2

Accurate benchmarks are particularly important for highly correlated oxides as mean-field approximations often fail to describe the subtle balance of charge transfer and magnetism in these materials with an accuracy comparable to experimental needs. Here we present accurate diffusion Monte Carlo (DMC) results of the electronic charge and spin densities for the tunable highly correlated oxide Li 1–x NiO 2 for x = 0, 1/2, and 1. To enable quantitative comparisons, we introduce a robust density-partitioning scheme, extending Voronoi analysis to assign atomic charges from spatially noisy DMC densities. We then benchmark common approximations used in density functional theory (DFT). Comparison against DMC shows that r 2 SCAN delivers the most balanced performance across charge, spin, and radial density descriptors, nearly reproducing DMC results for LiNiO 2 and apical Ni sites in Li 0.5 NiO 2 . Hybrid functionals (PBE0, SCAN0) perform unexpectedly poorly, and PBE + U + V yields inconsistent trends between charge and spin densities. Therefore, the r 2 SCAN functional minimizes errors relative to DMC while capturing the variable valence of the Ni ion and also retaining the computational efficiency of DFT for large-scale simulations of the tunable structural and electronic phases of Li1−xNiO2. Our study highlights the importance of accurate benchmarking of the fundamental quantities involved in DFT to select appropriate DFT approximations in order to advance the predictive modeling of charge-transfer-driven phenomena in correlated electron systems.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2020

Machine Learning-Based Upscaling of Finite-Size Molecular Dynamics Diffusion Simulations for Binary Fluids

Molecular diffusion coefficients calculated using molecular dynamics (MD) simulations suffer from finite-size (i.e., finite box size and finite particle number) effects. Results from finite-sized MD simulations can be upscaled to infinite simulation size by applying a correction factor. For self-diffusion of single-component fluids, this correction has been well-studied by many researchers including Yeh and Hummer (YH); for binary fluid mixtures, a modified YH correction was recently proposed for correcting MD-predicted Maxwell–Stephan (MS) diffusion rates. In this study we use both empirical and machine learning methods to identify improvements to the finite-size correction factors for both self-diffusion and MS diffusion of binary Lennard-Jones (LJ) fluid mixtures. Using artificial neural networks (ANNs), the error in the corrected LJ fluid diffusion is reduced by an order of magnitude versus existing YH corrections, and the ANN models perform well for mixtures with large dissimilarities in size and interaction energies where the YH correction proves insufficient.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2021

A machine learning approach for efficient multi-dimensional integration

Many physics problems involve integration in multi-dimensional space whose analytic solution is not available. The integrals can be evaluated using numerical integration methods, but it requires a large computational cost in some cases, so an efficient algorithm plays an important role in solving the physics problems. We propose a novel numerical multi-dimensional integration algorithm using machine learning (ML). After training a ML regression model to mimic a target integrand, the regression model is used to evaluate an approximation of the integral. Then, the difference between the approximation and the true answer is calculated to correct the bias in the approximation of the integral induced by ML prediction errors. Because of the bias correction, the final estimate of the integral is unbiased and has a statistically correct error estimation. Three ML models of multi-layer perceptron, gradient boosting decision tree, and Gaussian process regression algorithms are investigated. The performance of the proposed algorithm is demonstrated on six different families of integrands that typically appear in physics problems at various dimensions and integrand difficulties. The results show that, for the same total number of integrand evaluations, the new algorithm provides integral estimates with more than an order of magnitude smaller uncertainties than those of the VEGAS algorithm in most of the test cases.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗
DOE OSTI2021

Deep potential generation scheme and simulation protocol for the Li 10 GeP 2 S 12 -type superionic conductors

We report solid-state electrolyte materials with superior lithium ionic conductivities are vital to the next-generation Li-ion batteries. Molecular dynamics could provide atomic scale information to understand the diffusion process of Li-ion in these superionic conductor materials. Here, we implement the deep potential generator to set up an efficient protocol to automatically generate interatomic potentials for Li 10 GeP 2 S 12 -type solid-state electrolyte materials (Li 10 GeP 2 S 12 , Li 10 SiP 2 S 12 , and Li 10 SnP 2 S 12 ). The reliability and accuracy of the fast interatomic potentials are validated. With the potentials, we extend the simulation of the diffusion process to a wide temperature range (300 K–1000 K) and systems with large size (~1000 atoms). Important technical aspects such as the statistical error and size effect are carefully investigated, and benchmark tests including the effect of density functional, thermal expansion, and configurational disorder are performed. The computed data that consider these factors agree well with the experimental results, and we find that the three structures show different behaviors with respect to configurational disorder. Our work paves the way for further research on computation screening of solid-state electrolyte materials.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗
DOE OSTI2024

Optimal hybrid power plants for electric vehicle charging demand

Transmission constraints, increasing motivations to decarbonize, and concerns over peak electric vehicle (EV) load impacts on local grids have driven electric customers to consider behind-the-meter, hybrid power plant generation and storage at the distributed-grid level for EV charging. In this study, we develop capabilities to optimize hybrid power plant component capacities for EV charging. We then demonstrate these capabilities in a case study for Boulder, Colorado, using public EV charging data as well as wind and solar resource data. Our results show system designs that balance the cost of energy with load-meeting and peak shaving performance. Within the case study, systems designed for wind, solar photovoltaic (PV), and storage resulted in lower cost of energy than those optimized for PV and storage only. This indicates that in areas where wind resource exists, hybrid power plants that include wind, PV, and battery assets can better meet EV charging loads (including peak loads that are prone to overloading local grids) than PV and battery assets alone. Future work to address limitations in this paper include extending cost modeling to include performance losses (e.g., based on operations or weather) and charging station costs to estimate levelized cost of charging, and quantifying uncertainty and error in our aggregation methods for estimating EV charging loads at the hourly timescale.

14 SOLAR ENERGY↗
DOE OSTI2022

Waveform processing using neural network algorithms on the front-end electronics

In a multi-channel radiation detector readout system, waveform sampling, digitization, and raw data transmission to the data acquisition system constitute a conventional processing chain. The deposited energy on the sensor is estimated by extracting peak amplitudes, area under pulse envelopes from the raw data, and starting times of signals or time of arrivals. However, such quantities can be estimated using machine learning algorithms on the front-end Application-Specific Integrated Circuits (ASICs), often termed as “edge computing”. Edge computation offers enormous benefits, especially when the analytical forms are not fully known or the registered waveform suffers from noise and imperfections of practical implementations. In this work, we aim to predict peak amplitude from a single waveform snippet whose rising and falling edges containing only 3 to 4 samples. We thoroughly studied two well-accepted neural network algorithms, Multi-Layer Perceptron (MLP) and Convolutional Neural Network (CNN) by varying their model sizes. Further, to better fit front-end electronics, neural network model reduction techniques, such as network pruning methods and variable-bit quantization approaches, were also studied. By combining pruning and quantization, our best performing model has the size of 1.5 KB, reduced from 16.6 KB of its full model counterpart. It can reach mean absolute error of 0.034 comparing to that of a naive baseline of 0.135. Such parameter-efficient and predictive neural network models established feasibility and practicality of their deployment on front-end ASICs.

47 OTHER INSTRUMENTATION↗