A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems Article Swipe
Battery safety is paramount for electric vehicles. Early fault diagnosis remains a challenge due to the subtle nature of anomalies and the interference of dynamic operating noise. Existing data-driven methods often suffer from "physical blindness" leading to missed detections or false alarms. To address this, we propose a Physics-Aware Attention LSTM Autoencoder (PA-ALSTM-AE). This novel framework explicitly integrates battery aging laws (mileage) into the deep learning pipeline through a multi-stage fusion mechanism. Specifically, an adaptive physical feature construction module selects mileage-sensitive features, and a physics-guided latent fusion module dynamically calibrates the memory cells of the LSTM based on the aging state. Extensive experiments on the large-scale Vloong real-world dataset demonstrate that the proposed method significantly outperforms state-of-the-art baselines. Notably, it improves the recall rate of early faults by over 3 times while maintaining high precision, offering a robust solution for industrial battery management systems.
Related Topics
Concepts
Autoencoder
Battery (electricity)
Computer science
Artificial intelligence
Deep learning
Fault (geology)
Pipeline (software)
Fault detection and isolation
Feature (linguistics)
Feature learning
Machine learning
Interference (communication)
Recall
Artificial neural network
Long short term memory
SPARK (programming language)
Pattern recognition (psychology)
Supervised learning
Deep belief network
Real-time computing
Engineering
Feature extraction
Constant false alarm rate
Metadata
- Type
- preprint
- Landing Page
- https://doi.org/10.48550/arxiv.2512.06809
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W7110836710
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W7110836710Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2512.06809Digital Object Identifier
- Title
-
A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery SystemsWork title
- Type
-
preprintOpenAlex work type
- Publication year
-
2025Year of publication
- Publication date
-
2025-12-07Full publication date if available
- Authors
-
Yang jiongList of authors in order
- Landing page
-
https://doi.org/10.48550/arxiv.2512.06809Publisher landing page
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://doi.org/10.48550/arxiv.2512.06809Direct OA link when available
- Concepts
-
Autoencoder, Battery (electricity), Computer science, Artificial intelligence, Deep learning, Fault (geology), Pipeline (software), Fault detection and isolation, Feature (linguistics), Feature learning, Machine learning, Interference (communication), Recall, Artificial neural network, Long short term memory, SPARK (programming language), Pattern recognition (psychology), Supervised learning, Deep belief network, Real-time computing, Engineering, Feature extraction, Constant false alarm rateTop concepts (fields/topics) attached by OpenAlex
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W7110836710 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2512.06809 |
| ids.doi | https://doi.org/10.48550/arxiv.2512.06809 |
| ids.openalex | https://openalex.org/W7110836710 |
| fwci | |
| type | preprint |
| title | A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| concepts[0].id | https://openalex.org/C101738243 |
| concepts[0].level | 3 |
| concepts[0].score | 0.7978463172912598 |
| concepts[0].wikidata | https://www.wikidata.org/wiki/Q786435 |
| concepts[0].display_name | Autoencoder |
| concepts[1].id | https://openalex.org/C555008776 |
| concepts[1].level | 3 |
| concepts[1].score | 0.6520313620567322 |
| concepts[1].wikidata | https://www.wikidata.org/wiki/Q267298 |
| concepts[1].display_name | Battery (electricity) |
| concepts[2].id | https://openalex.org/C41008148 |
| concepts[2].level | 0 |
| concepts[2].score | 0.6452690958976746 |
| concepts[2].wikidata | https://www.wikidata.org/wiki/Q21198 |
| concepts[2].display_name | Computer science |
| concepts[3].id | https://openalex.org/C154945302 |
| concepts[3].level | 1 |
| concepts[3].score | 0.6128807067871094 |
| concepts[3].wikidata | https://www.wikidata.org/wiki/Q11660 |
| concepts[3].display_name | Artificial intelligence |
| concepts[4].id | https://openalex.org/C108583219 |
| concepts[4].level | 2 |
| concepts[4].score | 0.6012080907821655 |
| concepts[4].wikidata | https://www.wikidata.org/wiki/Q197536 |
| concepts[4].display_name | Deep learning |
| concepts[5].id | https://openalex.org/C175551986 |
| concepts[5].level | 2 |
| concepts[5].score | 0.5555345416069031 |
| concepts[5].wikidata | https://www.wikidata.org/wiki/Q47089 |
| concepts[5].display_name | Fault (geology) |
| concepts[6].id | https://openalex.org/C43521106 |
| concepts[6].level | 2 |
| concepts[6].score | 0.4647577702999115 |
| concepts[6].wikidata | https://www.wikidata.org/wiki/Q2165493 |
| concepts[6].display_name | Pipeline (software) |
| concepts[7].id | https://openalex.org/C152745839 |
| concepts[7].level | 3 |
| concepts[7].score | 0.4356308877468109 |
| concepts[7].wikidata | https://www.wikidata.org/wiki/Q5438153 |
| concepts[7].display_name | Fault detection and isolation |
| concepts[8].id | https://openalex.org/C2776401178 |
| concepts[8].level | 2 |
| concepts[8].score | 0.43427568674087524 |
| concepts[8].wikidata | https://www.wikidata.org/wiki/Q12050496 |
| concepts[8].display_name | Feature (linguistics) |
| concepts[9].id | https://openalex.org/C59404180 |
| concepts[9].level | 2 |
| concepts[9].score | 0.40680527687072754 |
| concepts[9].wikidata | https://www.wikidata.org/wiki/Q17013334 |
| concepts[9].display_name | Feature learning |
| concepts[10].id | https://openalex.org/C119857082 |
| concepts[10].level | 1 |
| concepts[10].score | 0.36352357268333435 |
| concepts[10].wikidata | https://www.wikidata.org/wiki/Q2539 |
| concepts[10].display_name | Machine learning |
| concepts[11].id | https://openalex.org/C32022120 |
| concepts[11].level | 3 |
| concepts[11].score | 0.3559771776199341 |
| concepts[11].wikidata | https://www.wikidata.org/wiki/Q797225 |
| concepts[11].display_name | Interference (communication) |
| concepts[12].id | https://openalex.org/C100660578 |
| concepts[12].level | 2 |
| concepts[12].score | 0.341387540102005 |
| concepts[12].wikidata | https://www.wikidata.org/wiki/Q18733 |
| concepts[12].display_name | Recall |
| concepts[13].id | https://openalex.org/C50644808 |
| concepts[13].level | 2 |
| concepts[13].score | 0.3385034501552582 |
| concepts[13].wikidata | https://www.wikidata.org/wiki/Q192776 |
| concepts[13].display_name | Artificial neural network |
| concepts[14].id | https://openalex.org/C133488467 |
| concepts[14].level | 4 |
| concepts[14].score | 0.33613988757133484 |
| concepts[14].wikidata | https://www.wikidata.org/wiki/Q6673524 |
| concepts[14].display_name | Long short term memory |
| concepts[15].id | https://openalex.org/C2781215313 |
| concepts[15].level | 2 |
| concepts[15].score | 0.3261670470237732 |
| concepts[15].wikidata | https://www.wikidata.org/wiki/Q3493345 |
| concepts[15].display_name | SPARK (programming language) |
| concepts[16].id | https://openalex.org/C153180895 |
| concepts[16].level | 2 |
| concepts[16].score | 0.3206268548965454 |
| concepts[16].wikidata | https://www.wikidata.org/wiki/Q7148389 |
| concepts[16].display_name | Pattern recognition (psychology) |
| concepts[17].id | https://openalex.org/C136389625 |
| concepts[17].level | 3 |
| concepts[17].score | 0.2971177399158478 |
| concepts[17].wikidata | https://www.wikidata.org/wiki/Q334384 |
| concepts[17].display_name | Supervised learning |
| concepts[18].id | https://openalex.org/C97385483 |
| concepts[18].level | 3 |
| concepts[18].score | 0.29189053177833557 |
| concepts[18].wikidata | https://www.wikidata.org/wiki/Q16954980 |
| concepts[18].display_name | Deep belief network |
| concepts[19].id | https://openalex.org/C79403827 |
| concepts[19].level | 1 |
| concepts[19].score | 0.2900053560733795 |
| concepts[19].wikidata | https://www.wikidata.org/wiki/Q3988 |
| concepts[19].display_name | Real-time computing |
| concepts[20].id | https://openalex.org/C127413603 |
| concepts[20].level | 0 |
| concepts[20].score | 0.2861899137496948 |
| concepts[20].wikidata | https://www.wikidata.org/wiki/Q11023 |
| concepts[20].display_name | Engineering |
| concepts[21].id | https://openalex.org/C52622490 |
| concepts[21].level | 2 |
| concepts[21].score | 0.2769562602043152 |
| concepts[21].wikidata | https://www.wikidata.org/wiki/Q1026626 |
| concepts[21].display_name | Feature extraction |
| concepts[22].id | https://openalex.org/C77052588 |
| concepts[22].level | 2 |
| concepts[22].score | 0.2728074789047241 |
| concepts[22].wikidata | https://www.wikidata.org/wiki/Q644307 |
| concepts[22].display_name | Constant false alarm rate |
| keywords[0].id | https://openalex.org/keywords/autoencoder |
| keywords[0].score | 0.7978463172912598 |
| keywords[0].display_name | Autoencoder |
| keywords[1].id | https://openalex.org/keywords/battery |
| keywords[1].score | 0.6520313620567322 |
| keywords[1].display_name | Battery (electricity) |
| keywords[2].id | https://openalex.org/keywords/deep-learning |
| keywords[2].score | 0.6012080907821655 |
| keywords[2].display_name | Deep learning |
| keywords[3].id | https://openalex.org/keywords/fault |
| keywords[3].score | 0.5555345416069031 |
| keywords[3].display_name | Fault (geology) |
| keywords[4].id | https://openalex.org/keywords/pipeline |
| keywords[4].score | 0.4647577702999115 |
| keywords[4].display_name | Pipeline (software) |
| keywords[5].id | https://openalex.org/keywords/fault-detection-and-isolation |
| keywords[5].score | 0.4356308877468109 |
| keywords[5].display_name | Fault detection and isolation |
| keywords[6].id | https://openalex.org/keywords/feature |
| keywords[6].score | 0.43427568674087524 |
| keywords[6].display_name | Feature (linguistics) |
| keywords[7].id | https://openalex.org/keywords/feature-learning |
| keywords[7].score | 0.40680527687072754 |
| keywords[7].display_name | Feature learning |
| language | |
| locations[0].id | doi:10.48550/arxiv.2512.06809 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | |
| locations[0].pdf_url | |
| locations[0].version | |
| locations[0].raw_type | article |
| locations[0].license_id | |
| locations[0].is_accepted | False |
| locations[0].is_published | |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | https://doi.org/10.48550/arxiv.2512.06809 |
| indexed_in | datacite |
| authorships[0].author.id | https://openalex.org/A2348492767 |
| authorships[0].author.orcid | |
| authorships[0].author.display_name | Yang jiong |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Yang, Jiong |
| authorships[0].is_corresponding | True |
| has_content.pdf | False |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://doi.org/10.48550/arxiv.2512.06809 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-12-10T00:00:00 |
| display_name | A Physics-Aware Attention LSTM Autoencoder for Early Fault Diagnosis of Battery Systems |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-12-10T02:49:46.989445 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 1 |
| best_oa_location.id | doi:10.48550/arxiv.2512.06809 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | |
| best_oa_location.pdf_url | |
| best_oa_location.version | |
| best_oa_location.raw_type | article |
| best_oa_location.license_id | |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | https://doi.org/10.48550/arxiv.2512.06809 |
| primary_location.id | doi:10.48550/arxiv.2512.06809 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | |
| primary_location.pdf_url | |
| primary_location.version | |
| primary_location.raw_type | article |
| primary_location.license_id | |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | https://doi.org/10.48550/arxiv.2512.06809 |
| publication_date | 2025-12-07 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.3 | 129 |
| abstract_inverted_index.a | 11, 47, 68, 83, 136 |
| abstract_inverted_index.To | 42 |
| abstract_inverted_index.an | 73 |
| abstract_inverted_index.by | 127 |
| abstract_inverted_index.is | 2 |
| abstract_inverted_index.it | 119 |
| abstract_inverted_index.of | 18, 23, 93, 124 |
| abstract_inverted_index.on | 97, 103 |
| abstract_inverted_index.or | 39 |
| abstract_inverted_index.to | 14, 36 |
| abstract_inverted_index.we | 45 |
| abstract_inverted_index.and | 20, 82 |
| abstract_inverted_index.due | 13 |
| abstract_inverted_index.for | 4, 139 |
| abstract_inverted_index.the | 15, 21, 63, 90, 94, 98, 104, 111, 121 |
| abstract_inverted_index.LSTM | 50, 95 |
| abstract_inverted_index.This | 53 |
| abstract_inverted_index.deep | 64 |
| abstract_inverted_index.from | 32 |
| abstract_inverted_index.high | 133 |
| abstract_inverted_index.into | 62 |
| abstract_inverted_index.laws | 60 |
| abstract_inverted_index.over | 128 |
| abstract_inverted_index.rate | 123 |
| abstract_inverted_index.that | 110 |
| abstract_inverted_index.Early | 7 |
| abstract_inverted_index.aging | 59, 99 |
| abstract_inverted_index.based | 96 |
| abstract_inverted_index.cells | 92 |
| abstract_inverted_index.early | 125 |
| abstract_inverted_index.false | 40 |
| abstract_inverted_index.fault | 8 |
| abstract_inverted_index.novel | 54 |
| abstract_inverted_index.often | 30 |
| abstract_inverted_index.this, | 44 |
| abstract_inverted_index.times | 130 |
| abstract_inverted_index.while | 131 |
| abstract_inverted_index.Vloong | 106 |
| abstract_inverted_index.faults | 126 |
| abstract_inverted_index.fusion | 70, 86 |
| abstract_inverted_index.latent | 85 |
| abstract_inverted_index.memory | 91 |
| abstract_inverted_index.method | 113 |
| abstract_inverted_index.missed | 37 |
| abstract_inverted_index.module | 78, 87 |
| abstract_inverted_index.nature | 17 |
| abstract_inverted_index.noise. | 26 |
| abstract_inverted_index.recall | 122 |
| abstract_inverted_index.robust | 137 |
| abstract_inverted_index.safety | 1 |
| abstract_inverted_index.state. | 100 |
| abstract_inverted_index.subtle | 16 |
| abstract_inverted_index.suffer | 31 |
| abstract_inverted_index.Battery | 0 |
| abstract_inverted_index.address | 43 |
| abstract_inverted_index.alarms. | 41 |
| abstract_inverted_index.battery | 58, 141 |
| abstract_inverted_index.dataset | 108 |
| abstract_inverted_index.dynamic | 24 |
| abstract_inverted_index.feature | 76 |
| abstract_inverted_index.leading | 35 |
| abstract_inverted_index.methods | 29 |
| abstract_inverted_index.propose | 46 |
| abstract_inverted_index.remains | 10 |
| abstract_inverted_index.selects | 79 |
| abstract_inverted_index.through | 67 |
| abstract_inverted_index.Existing | 27 |
| abstract_inverted_index.Notably, | 118 |
| abstract_inverted_index.adaptive | 74 |
| abstract_inverted_index.electric | 5 |
| abstract_inverted_index.improves | 120 |
| abstract_inverted_index.learning | 65 |
| abstract_inverted_index.offering | 135 |
| abstract_inverted_index.physical | 75 |
| abstract_inverted_index.pipeline | 66 |
| abstract_inverted_index.proposed | 112 |
| abstract_inverted_index.solution | 138 |
| abstract_inverted_index.systems. | 143 |
| abstract_inverted_index."physical | 33 |
| abstract_inverted_index.(mileage) | 61 |
| abstract_inverted_index.Attention | 49 |
| abstract_inverted_index.Extensive | 101 |
| abstract_inverted_index.anomalies | 19 |
| abstract_inverted_index.challenge | 12 |
| abstract_inverted_index.diagnosis | 9 |
| abstract_inverted_index.features, | 81 |
| abstract_inverted_index.framework | 55 |
| abstract_inverted_index.operating | 25 |
| abstract_inverted_index.paramount | 3 |
| abstract_inverted_index.vehicles. | 6 |
| abstract_inverted_index.baselines. | 117 |
| abstract_inverted_index.blindness" | 34 |
| abstract_inverted_index.calibrates | 89 |
| abstract_inverted_index.detections | 38 |
| abstract_inverted_index.explicitly | 56 |
| abstract_inverted_index.industrial | 140 |
| abstract_inverted_index.integrates | 57 |
| abstract_inverted_index.management | 142 |
| abstract_inverted_index.mechanism. | 71 |
| abstract_inverted_index.precision, | 134 |
| abstract_inverted_index.real-world | 107 |
| abstract_inverted_index.Autoencoder | 51 |
| abstract_inverted_index.data-driven | 28 |
| abstract_inverted_index.demonstrate | 109 |
| abstract_inverted_index.dynamically | 88 |
| abstract_inverted_index.experiments | 102 |
| abstract_inverted_index.large-scale | 105 |
| abstract_inverted_index.maintaining | 132 |
| abstract_inverted_index.multi-stage | 69 |
| abstract_inverted_index.outperforms | 115 |
| abstract_inverted_index.construction | 77 |
| abstract_inverted_index.interference | 22 |
| abstract_inverted_index.Physics-Aware | 48 |
| abstract_inverted_index.Specifically, | 72 |
| abstract_inverted_index.significantly | 114 |
| abstract_inverted_index.(PA-ALSTM-AE). | 52 |
| abstract_inverted_index.physics-guided | 84 |
| abstract_inverted_index.state-of-the-art | 116 |
| abstract_inverted_index.mileage-sensitive | 80 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 1 |
| citation_normalized_percentile |