Battery health prediction under generalized conditions using a Gaussian process transition model
Accurately predicting the future health of batteries is necessary to ensure reliable operation, minimise maintenance costs, and calculate the value of energy storage investments. The complex nature of degradation renders data-driven approaches a promising alternative to mechanistic modelling. This s...
| Main Authors: | , , |
|---|---|
| Format: | Working paper |
| Published: |
2018
|
| _version_ | 1797083082659987456 |
|---|---|
| author | Richardson, R Osborne, M Howey, D |
| author_facet | Richardson, R Osborne, M Howey, D |
| author_sort | Richardson, R |
| collection | OXFORD |
| description | Accurately predicting the future health of batteries is necessary to ensure reliable operation, minimise maintenance costs, and calculate the value of energy storage investments. The complex nature of degradation renders data-driven approaches a promising alternative to mechanistic modelling. This study predicts the changes in battery capacity over time using a Bayesian non-parametric approach based on Gaussian process regression. These changes can be integrated against an arbitrary input sequence to predict capacity fade in a variety of usage scenarios, forming a generalised health model. The approach naturally incorporates varying current, voltage and temperature inputs, crucial for enabling real world application. A key innovation is the feature selection step, where arbitrary length current, voltage and temperature measurement vectors are mapped to fixed size feature vectors, enabling them to be efficiently used as exogenous variables. The approach is demonstrated on the open-source NASA Randomised Battery Usage Dataset, with data of 26 cells aged under randomized operational conditions. Using half of the cells for training, and half for validation, the method is shown to accurately predict non-linear capacity fade, with a best case normalised root mean square error of 4.3%, including accurate estimation of prediction uncertainty. |
| first_indexed | 2024-03-07T01:36:56Z |
| format | Working paper |
| id | oxford-uuid:95842ed0-eb7c-4318-b9d9-393441b197fb |
| institution | University of Oxford |
| last_indexed | 2024-03-07T01:36:56Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | oxford-uuid:95842ed0-eb7c-4318-b9d9-393441b197fb2022-03-26T23:46:42ZBattery health prediction under generalized conditions using a Gaussian process transition modelWorking paperhttp://purl.org/coar/resource_type/c_8042uuid:95842ed0-eb7c-4318-b9d9-393441b197fbSymplectic Elements at Oxford2018Richardson, ROsborne, MHowey, DAccurately predicting the future health of batteries is necessary to ensure reliable operation, minimise maintenance costs, and calculate the value of energy storage investments. The complex nature of degradation renders data-driven approaches a promising alternative to mechanistic modelling. This study predicts the changes in battery capacity over time using a Bayesian non-parametric approach based on Gaussian process regression. These changes can be integrated against an arbitrary input sequence to predict capacity fade in a variety of usage scenarios, forming a generalised health model. The approach naturally incorporates varying current, voltage and temperature inputs, crucial for enabling real world application. A key innovation is the feature selection step, where arbitrary length current, voltage and temperature measurement vectors are mapped to fixed size feature vectors, enabling them to be efficiently used as exogenous variables. The approach is demonstrated on the open-source NASA Randomised Battery Usage Dataset, with data of 26 cells aged under randomized operational conditions. Using half of the cells for training, and half for validation, the method is shown to accurately predict non-linear capacity fade, with a best case normalised root mean square error of 4.3%, including accurate estimation of prediction uncertainty. |
| spellingShingle | Richardson, R Osborne, M Howey, D Battery health prediction under generalized conditions using a Gaussian process transition model |
| title | Battery health prediction under generalized conditions using a Gaussian
process transition model |
| title_full | Battery health prediction under generalized conditions using a Gaussian
process transition model |
| title_fullStr | Battery health prediction under generalized conditions using a Gaussian
process transition model |
| title_full_unstemmed | Battery health prediction under generalized conditions using a Gaussian
process transition model |
| title_short | Battery health prediction under generalized conditions using a Gaussian
process transition model |
| title_sort | battery health prediction under generalized conditions using a gaussian process transition model |
| work_keys_str_mv | AT richardsonr batteryhealthpredictionundergeneralizedconditionsusingagaussianprocesstransitionmodel AT osbornem batteryhealthpredictionundergeneralizedconditionsusingagaussianprocesstransitionmodel AT howeyd batteryhealthpredictionundergeneralizedconditionsusingagaussianprocesstransitionmodel |