Unified Evaluation Framework for Stochastic Algorithms Applied to Remaining Useful Life Prognosis Problems
A unified evaluation framework for stochastic tools is developed in this paper. Firstly, we provide a set of already existing quantitative and qualitative metrics that rate the relevant aspects of the performance of a stochastic prognosis algorithm. Secondly, we provide innovative guidelines to dete...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Batteries |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-0105/7/2/35 |
| _version_ | 1797532763616706560 |
|---|---|
| author | Mikel Arrinda Mikel Oyarbide Haritz Macicior Eñaut Muxika |
| author_facet | Mikel Arrinda Mikel Oyarbide Haritz Macicior Eñaut Muxika |
| author_sort | Mikel Arrinda |
| collection | DOAJ |
| description | A unified evaluation framework for stochastic tools is developed in this paper. Firstly, we provide a set of already existing quantitative and qualitative metrics that rate the relevant aspects of the performance of a stochastic prognosis algorithm. Secondly, we provide innovative guidelines to detect and minimize the effect of side aspects that interact on the algorithms’ performance. Those aspects are related with the input uncertainty (the uncertainty on the data and the prior knowledge), the parametrization method and the uncertainty propagation method. The proposed evaluation framework is contextualized on a Lithium-ion battery Remaining Useful Life prognosis problem. As an example, a Particle Filter is evaluated. On this example, two different data sets taken from NCA aged batteries and two semi-empirical aging models available in the literature fed up the Particle Filter under evaluation. The obtained results show that the proposed framework gives enough details to take decisions about the viability of the chosen algorithm. |
| first_indexed | 2024-03-10T11:04:56Z |
| format | Article |
| id | doaj.art-eb7b9c97ecbb404c91005154c80f458c |
| institution | Directory Open Access Journal |
| issn | 2313-0105 |
| language | English |
| last_indexed | 2024-03-10T11:04:56Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Batteries |
| spelling | doaj.art-eb7b9c97ecbb404c91005154c80f458c2023-11-21T21:16:52ZengMDPI AGBatteries2313-01052021-05-01723510.3390/batteries7020035Unified Evaluation Framework for Stochastic Algorithms Applied to Remaining Useful Life Prognosis ProblemsMikel Arrinda0Mikel Oyarbide1Haritz Macicior2Eñaut Muxika3CIDETEC, Basque Research and Technology Alliance (BRTA), Po. Miramón 196, 20014 Donostia-San Sebastián, SpainCIDETEC, Basque Research and Technology Alliance (BRTA), Po. Miramón 196, 20014 Donostia-San Sebastián, SpainCIDETEC, Basque Research and Technology Alliance (BRTA), Po. Miramón 196, 20014 Donostia-San Sebastián, SpainElectronics and Computing Department, Mondragon Unibertsitatea, Arrasate, 20500 Gipuzkoa, SpainA unified evaluation framework for stochastic tools is developed in this paper. Firstly, we provide a set of already existing quantitative and qualitative metrics that rate the relevant aspects of the performance of a stochastic prognosis algorithm. Secondly, we provide innovative guidelines to detect and minimize the effect of side aspects that interact on the algorithms’ performance. Those aspects are related with the input uncertainty (the uncertainty on the data and the prior knowledge), the parametrization method and the uncertainty propagation method. The proposed evaluation framework is contextualized on a Lithium-ion battery Remaining Useful Life prognosis problem. As an example, a Particle Filter is evaluated. On this example, two different data sets taken from NCA aged batteries and two semi-empirical aging models available in the literature fed up the Particle Filter under evaluation. The obtained results show that the proposed framework gives enough details to take decisions about the viability of the chosen algorithm.https://www.mdpi.com/2313-0105/7/2/35prognosisstochastic algorithmparticle filterevaluation metricuncertainty propagation |
| spellingShingle | Mikel Arrinda Mikel Oyarbide Haritz Macicior Eñaut Muxika Unified Evaluation Framework for Stochastic Algorithms Applied to Remaining Useful Life Prognosis Problems Batteries prognosis stochastic algorithm particle filter evaluation metric uncertainty propagation |
| title | Unified Evaluation Framework for Stochastic Algorithms Applied to Remaining Useful Life Prognosis Problems |
| title_full | Unified Evaluation Framework for Stochastic Algorithms Applied to Remaining Useful Life Prognosis Problems |
| title_fullStr | Unified Evaluation Framework for Stochastic Algorithms Applied to Remaining Useful Life Prognosis Problems |
| title_full_unstemmed | Unified Evaluation Framework for Stochastic Algorithms Applied to Remaining Useful Life Prognosis Problems |
| title_short | Unified Evaluation Framework for Stochastic Algorithms Applied to Remaining Useful Life Prognosis Problems |
| title_sort | unified evaluation framework for stochastic algorithms applied to remaining useful life prognosis problems |
| topic | prognosis stochastic algorithm particle filter evaluation metric uncertainty propagation |
| url | https://www.mdpi.com/2313-0105/7/2/35 |
| work_keys_str_mv | AT mikelarrinda unifiedevaluationframeworkforstochasticalgorithmsappliedtoremainingusefullifeprognosisproblems AT mikeloyarbide unifiedevaluationframeworkforstochasticalgorithmsappliedtoremainingusefullifeprognosisproblems AT haritzmacicior unifiedevaluationframeworkforstochasticalgorithmsappliedtoremainingusefullifeprognosisproblems AT enautmuxika unifiedevaluationframeworkforstochasticalgorithmsappliedtoremainingusefullifeprognosisproblems |