scholarly journals High precision implicit function learning for forecasting supercapacitor state of health based on Gaussian process regression

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Jiahao Ren ◽  
Junfei Cai ◽  
Jinjin Li
Keyword(s):  
Gaussian Process ◽  
High Precision ◽  
Gaussian Process Regression ◽  
Prediction Errors ◽  
Implicit Function ◽  
State Of Health ◽  
Energy Storage Devices ◽  
Function Learning ◽  
Data Set ◽  
Covariance Functions

AbstractState of health (SOH) prediction of supercapacitors aims to provide reliable lifetime control and avoid system failure. Gaussian process regression (GPR) has emerged for SOH prediction because of its capability of capturing nonlinear relationships between features, and tracking SOH attenuations effectively. However, traditional GPR methods based on explicit functions require multiple screenings of optimal mean and covariance functions, which results in data scarcity and increased time consumption. In this study, we propose a GPR-implicit function learning, which is a prior knowledge algorithm for calculating mean and covariance functions from a preliminary data set instead of screening. After introducing the implicit function, the average root mean square error (Average RMSE) is 0.0056 F and the average mean absolute percent error (Average MAPE) is 0.6%, where only the first 5% of the data are trained to predict the remaining 95% of the cycles, thereby decreasing the error by more than three times than previous studies. Furthermore, less cycles (i.e., 1%) are trained while still obtaining low prediction errors (i.e., Average RMSE is 0.0094 F and Average MAPE is 1.01%). This work highlights the strength of GPR-implicit function model for SOH prediction of energy storage devices with high precision and limited property data.

Exchange Spin Coupling from Gaussian Process Regression

2020 ◽  
Author(s):  
Marc Philipp Bahlke ◽  
Natnael Mogos ◽  
Jonny Proppe ◽  
Carmen Herrmann
Keyword(s):  
Machine Learning ◽  
Gaussian Process ◽  
Gaussian Process Regression ◽  
Molecular Magnets ◽  
Molecular Structures ◽  
Spin Coupling ◽  
Structure Property ◽  
Data Set ◽  
Uncertainty Estimates

Heisenberg exchange spin coupling between metal centers is essential for describing and understanding the electronic structure of many molecular catalysts, metalloenzymes, and molecular magnets for potential application in information technology. We explore the machine-learnability of exchange spin coupling, which has not been studied yet. We employ Gaussian process regression since it can potentially deal with small training sets (as likely associated with the rather complex molecular structures required for exploring spin coupling) and since it provides uncertainty estimates (“error bars”) along with predicted values. We compare a range of descriptors and kernels for 257 small dicopper complexes and find that a simple descriptor based on chemical intuition, consisting only of copper-bridge angles and copper-copper distances, clearly outperforms several more sophisticated descriptors when it comes to extrapolating towards larger experimentally relevant complexes. Exchange spin coupling is similarly easy to learn as the polarizability, while learning dipole moments is much harder. The strength of the sophisticated descriptors lies in their ability to linearize structure-property relationships, to the point that a simple linear ridge regression performs just as well as the kernel-based machine-learning model for our small dicopper data set. The superior extrapolation performance of the simple descriptor is unique to exchange spin coupling, reinforcing the crucial role of choosing a suitable descriptor, and highlighting the interesting question of the role of chemical intuition vs. systematic or automated selection of features for machine learning in chemistry and material science.

Human-knowledge-augmented Gaussian Process Regression for State-of-Health Prediction of Lithium-ion Batteries with Charging Curves

2021 ◽  
pp. 1-10
Author(s):  
Quan Zhou ◽  
Chongming Wang ◽  
Zeyu Sun ◽  
Ji Li ◽  
Huw Williams ◽  
...  
Keyword(s):  
Gaussian Process ◽  
Lithium Ion Batteries ◽  
Gaussian Process Regression ◽  
Lithium Ion ◽  
Learning Performance ◽  
Transport Systems ◽  
State Of Health ◽  
Human Knowledge ◽  
Voltage Profile ◽  
Inference System

Abstract Lithium-ion batteries have been widely used in renewable energy storage and electrified transport systems, and State-of-Health (SoH) prediction is critical for safe and reliable operation of the lithium-ion batteries. Following the standard routine which predicts battery SoH based on charging curves, a human-knowledge-augmented Gaussian process regression (HAGPR) model is newly proposed for SoH prediction by incorporating two promising artificial intelligence techniques, i.e., the Gaussian process regression (GPR) and the adaptive neural fuzzy inference system (ANFIS). Based on human knowledge on voltage profile during battery degradation, a ANFIS is developed for feature extraction that helps improve machine learning performance and reduce the need of physical testing. Then, the ANFIS is integrated with a GPR model to enable SoH prediction with the extracted feature from battery aging test data. With a conventional GPR model as the baseline, a comparison study is conducted to demonstrate the advantage and robustness of the proposed HAGPR model. It indicates that the proposed HAGPR model can reduce at least 12% root mean square error with 31.8% less battery aging testing compared to the GPR model.

scholarly journals An Imbalanced Data Handling Framework for Industrial Big Data Using a Gaussian Process Regression-Based Generative Adversarial Network

Symmetry ◽  
2020 ◽  
Vol 12 (4) ◽  
pp. 669 ◽  
Author(s):  
Eunseo Oh ◽  
Hyunsoo Lee
Keyword(s):  
Big Data ◽  
Gaussian Process ◽  
Missing Values ◽  
Gaussian Process Regression ◽  
Estimation Methods ◽  
Data Handling ◽  
Generative Adversarial Network ◽  
Data Set ◽  
Adversarial Network ◽  
Industrial Big Data

The developments in the fields of industrial Internet of Things (IIoT) and big data technologies have made it possible to collect a lot of meaningful industrial process and quality-based data. The gathered data are analyzed using contemporary statistical methods and machine learning techniques. Then, the extracted knowledge can be used for predictive maintenance or prognostic health management. However, it is difficult to gather complete data due to several issues in IIoT, such as devices breaking down, running out of battery, or undergoing scheduled maintenance. Data with missing values are often ignored, as they may contain insufficient information from which to draw conclusions. In order to overcome these issues, we propose a novel, effective missing data handling mechanism for the concepts of symmetry principles. While other existing methods only attempt to estimate missing parts, the proposed method generates a whole set of data set using Gaussian process regression and a generative adversarial network. In order to prove the effectiveness of the proposed framework, we examine a real-world, industrial case involving an air pressure system (APS), where we use the proposed method to make quality predictions and compare the results with existing state-of-the-art estimation methods.

Dealing with Observation Outages within Navigation Data using Gaussian Process Regression

2014 ◽  
Vol 67 (4) ◽  
pp. 603-615 ◽  
Author(s):  
Hongmei Chen ◽  
Xianghong Cheng ◽  
Haipeng Wang ◽  
Xu Han
Keyword(s):  
Kalman Filter ◽  
Theoretical Analysis ◽  
Gaussian Process ◽  
Inertial Navigation System ◽  
Dynamic Models ◽  
Gaussian Process Regression ◽  
Parametric Model ◽  
Integrated Navigation ◽  
Data Set ◽  
Navigation Data

Gaussian process regression (GPR) is used in a Spare-grid Quadrature Kalman filter (SGQKF) for Strap-down Inertial Navigation System (SINS)/odometer integrated navigation to bridge uncertain observation outages and maintain an estimate of the evolving SINS biases. The SGQKF uses nonlinearized dynamic models with complex stochastic nonlinearities so the performance degrades significantly during observation outages owing to the uncertainties and noise. The GPR calculates the residual output after factoring in the contributions of the parametric model that is used as a nonlinear SINS error predictor integrated into the SGQKF. The sensor measurements and SINS output deviations from the odometer are collected in a data set during observation availability. The GPR is then applied to predict SINS deviations from the odometer and then the predicted SINS deviations are fed to the SGQKF as an actual update to estimate all SINS biases during observation outages. We demonstrate our method's effectiveness in bridging uncertain observation outages in simulations and in real road tests. The results agree with the theoretical analysis, which demonstrate that SGQKF using GPR can maintain an estimate of the evolving SINS biases during signal outages.

scholarly journals Four-dimensional mesospheric and lower thermospheric wind fields using Gaussian process regression on multistatic specular meteor radar observations

2021 ◽  
Author(s):  
Ryan Volz ◽  
Jorge L. Chau ◽  
Philip J. Erickson ◽  
Juha P. Vierinen ◽  
J. Miguel Urco ◽  
...  
Keyword(s):  
Gaussian Process ◽  
Wind Velocity ◽  
Wind Field ◽  
Gaussian Process Regression ◽  
Small Scale ◽  
Model Parameters ◽  
Meteor Radar ◽  
Wind Fields ◽  
Data Set ◽  
Uncertainty Estimates

Abstract. Mesoscale dynamics in the mesosphere and lower thermosphere (MLT) region have been difficult to study from either ground- or satellite-based observations. For understanding of atmospheric coupling processes, important spatial scales at these altitudes range between tens to hundreds of kilometers in the horizontal plane. To date, this scale size is challenging observationally, and so structures are usually parameterized in global circulation models. The advent of multistatic specular meteor radar networks allows exploration of MLT mesocale dynamics on these scales using an increased number of detections and a diversity of viewing angles inherent to multistatic networks. In this work, we introduce a four dimensional wind field inversion method that makes use of Gaussian process regression (GPR), a non-parametric and Bayesian approach. The method takes measured projected wind velocities and prior distributions of the wind velocity as a function of space and time, specified by the user or estimated from the data, and produces posterior distributions for the wind velocity. Computation of the predictive posterior distribution is performed on sampled points of interest and is not necessarily regularly sampled. The main benefits of the GPR method include this non-gridded sampling, the built-in statistical uncertainty estimates, and the ability to horizontally-resolve winds on relatively small scales. The performance of the GPR implementation has been evaluated on Monte Carlo simulations with known distributions using the same spatial and temporal sampling as one day of real meteor measurements. Based on the simulation results we find that the GPR implementation is robust, providing wind fields that are statistically unbiased and with statistical variances that depend on the geometry and are proportional to the prior velocity variances. A conservative and fast approach can be straightforwardly implemented by employing overestimated prior variances and distances, while a more robust but computationally intensive approach can be implemented by employing training and fitting of model parameters. The latter GPR approach has been applied to a 24-hour data set and shown to compare well to previously used homogeneous and gradient methods. Small scale features have reasonably low statistical uncertainties, implying geophysical wind field horizontal structures as low as 20–50 km. We suggest that this GPR approach forms a suitable method for MLT regional and weather studies.

scholarly journals Searching for rewards in graph-structured spaces

2019 ◽  
Author(s):  
Eric Schulz ◽  
Charley M Wu
Keyword(s):  
Reinforcement Learning ◽  
Regression Model ◽  
Gaussian Process ◽  
Predictive Model ◽  
Human Behavior ◽  
Model Comparison ◽  
Gaussian Process Regression ◽  
Diffusion Kernel ◽  
Function Learning ◽  
Psychological Models

How do people generalize and explore structured spaces? We study human behavior on a multi-armed bandit task, where rewards are influenced by the connectivity structure of a graph. A detailed predictive model comparison shows that a Gaussian Process regression model using a diffusion kernel is able to best describe participant choices, and also predict judgments about expected reward and confidence. This model unifies psychological models of function learning with the Successor Representation used in reinforcement learning, thereby building a bridge between different models of generalization.

Sign in / Sign up

Export Citation Format

Share Document