English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Electrochemical batteries are ubiquitous devices in our society. When theyare employed in mission-critical applications, the ability to precisely predictthe end of discharge under highly variable environmental and operatingconditions is of paramount importance in order to support operationaldecision-making. While there are accurate predictive models of the processesunderlying the charge and discharge phases of batteries, the modelling ofageing and its effect on performance remains poorly understood. Such a lack ofunderstanding often leads to inaccurate models or the need for time-consumingcalibration procedures whenever the battery ages or its conditions changesignificantly. This represents a major obstacle to the real-world deployment ofefficient and robust battery management systems. In this paper, we propose forthe first time an approach that can predict the voltage discharge curve forbatteries of any degradation level without the need for calibration. Inparticular, we introduce Dynaformer, a novel Transformer-based deep learningarchitecture which is able to simultaneously infer the ageing state from alimited number of voltage/current samples and predict the full voltagedischarge curve for real batteries with high precision. Our experiments showthat the trained model is effective for input current profiles of differentcomplexities and is robust to a wide range of degradation levels. In additionto evaluating the performance of the proposed framework on simulated data, wedemonstrate that a minimal amount of fine-tuning allows the model to bridge thesimulation-to-real gap between simulations and real data collected from a setof batteries. The proposed methodology enables the utilization ofbattery-powered systems until the end of discharge in a controlled andpredictable way, thereby significantly prolonging the operating cycles andreducing costs.

Dynaformer: A Deep Learning Model for Ageing-aware Battery Discharge Prediction