A Bayesian nonparametric approach to modeling battery health
The batteries of many consumer products are both a substantial portion of the product's cost and commonly a first point of failure. Accurately predicting remaining battery life can lower costs by reducing unnecessary battery replacements. Unfortunately, battery dynamics are extremely complex, a...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
Institute of Electrical and Electronics Engineers (IEEE)
2013
|
| Online Access: | http://hdl.handle.net/1721.1/81281 https://orcid.org/0000-0002-8293-0492 |
| _version_ | 1811081669198741504 |
|---|---|
| author | Doshi-Velez, Finale P. Roy, Nicholas Joseph, Joshua Mason |
| author2 | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics |
| author_facet | Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Doshi-Velez, Finale P. Roy, Nicholas Joseph, Joshua Mason |
| author_sort | Doshi-Velez, Finale P. |
| collection | MIT |
| description | The batteries of many consumer products are both a substantial portion of the product's cost and commonly a first point of failure. Accurately predicting remaining battery life can lower costs by reducing unnecessary battery replacements. Unfortunately, battery dynamics are extremely complex, and we often lack the domain knowledge required to construct a model by hand. In this work, we take a data-driven approach and aim to learn a model of battery time-to-death from training data. Using a Dirichlet process prior over mixture weights, we learn an infinite mixture model for battery health. The Bayesian aspect of our model helps to avoid over-fitting while the nonparametric nature of the model allows the data to control the size of the model, preventing under-fitting. We demonstrate our model's effectiveness by making time-to-death predictions using real data from nickel-metal hydride battery packs. |
| first_indexed | 2024-09-23T11:50:31Z |
| format | Article |
| id | mit-1721.1/81281 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T11:50:31Z |
| publishDate | 2013 |
| publisher | Institute of Electrical and Electronics Engineers (IEEE) |
| record_format | dspace |
| spelling | mit-1721.1/812812022-10-01T06:21:42Z A Bayesian nonparametric approach to modeling battery health Doshi-Velez, Finale P. Roy, Nicholas Joseph, Joshua Mason Massachusetts Institute of Technology. Department of Aeronautics and Astronautics Joseph, Joshua Mason Doshi-Velez, Finale P. Roy, Nicholas The batteries of many consumer products are both a substantial portion of the product's cost and commonly a first point of failure. Accurately predicting remaining battery life can lower costs by reducing unnecessary battery replacements. Unfortunately, battery dynamics are extremely complex, and we often lack the domain knowledge required to construct a model by hand. In this work, we take a data-driven approach and aim to learn a model of battery time-to-death from training data. Using a Dirichlet process prior over mixture weights, we learn an infinite mixture model for battery health. The Bayesian aspect of our model helps to avoid over-fitting while the nonparametric nature of the model allows the data to control the size of the model, preventing under-fitting. We demonstrate our model's effectiveness by making time-to-death predictions using real data from nickel-metal hydride battery packs. United States. Army Research Office (Nostra Project STTR W911NF-08-C-0066) iRobot 2013-10-03T13:02:14Z 2013-10-03T13:02:14Z 2012-05 Article http://purl.org/eprint/type/ConferencePaper 978-1-4673-1405-3 978-1-4673-1403-9 978-1-4673-1578-4 978-1-4673-1404-6 http://hdl.handle.net/1721.1/81281 Joseph, Joshua, Finale Doshi-Velez, and Nicholas Roy. “A Bayesian nonparametric approach to modeling battery health.” In 2012 IEEE International Conference on Robotics and Automation, 1876-1882. Institute of Electrical and Electronics Engineers, 2012. https://orcid.org/0000-0002-8293-0492 en_US http://dx.doi.org/10.1109/ICRA.2012.6225178 Proceedings of the 2012 IEEE International Conference on Robotics and Automation Creative Commons Attribution-Noncommercial-Share Alike 3.0 http://creativecommons.org/licenses/by-nc-sa/3.0/ application/pdf Institute of Electrical and Electronics Engineers (IEEE) MIT web domain |
| spellingShingle | Doshi-Velez, Finale P. Roy, Nicholas Joseph, Joshua Mason A Bayesian nonparametric approach to modeling battery health |
| title | A Bayesian nonparametric approach to modeling battery health |
| title_full | A Bayesian nonparametric approach to modeling battery health |
| title_fullStr | A Bayesian nonparametric approach to modeling battery health |
| title_full_unstemmed | A Bayesian nonparametric approach to modeling battery health |
| title_short | A Bayesian nonparametric approach to modeling battery health |
| title_sort | bayesian nonparametric approach to modeling battery health |
| url | http://hdl.handle.net/1721.1/81281 https://orcid.org/0000-0002-8293-0492 |
| work_keys_str_mv | AT doshivelezfinalep abayesiannonparametricapproachtomodelingbatteryhealth AT roynicholas abayesiannonparametricapproachtomodelingbatteryhealth AT josephjoshuamason abayesiannonparametricapproachtomodelingbatteryhealth AT doshivelezfinalep bayesiannonparametricapproachtomodelingbatteryhealth AT roynicholas bayesiannonparametricapproachtomodelingbatteryhealth AT josephjoshuamason bayesiannonparametricapproachtomodelingbatteryhealth |