Papers

DecayFormer:混合状态空间-注意力架构用于电池衰退轨迹预测

A Hybrid State Space-Attention Architecture for Forecasting the Trajectories of Battery Degradation

Why we picked it

电池研发最耗时间的就是老化测试,这篇论文用状态空间加注意力的紧凑模型,从最初几十个循环就能预测整条衰退曲线。Li-ion 的 MAPE 只有 2.25%,而且所有数据集共用一套配置不调参,比那种靠大规模模型和逐折调优的方法实用得多。做电池管理或能源方向研发的值得看看代码实现思路。

DecayFormer 是一种紧凑型混合架构,结合状态空间模型与注意力机制,用于电池早期寿命衰退轨迹预测,目标是从最初充放电循环预测电池全生命周期的 SOH 轨迹,可将电池评估时间从数月缩短到数天。

Body

架构上,DecayFormer 采用循环级的选择性递归(每通道仅一个标量状态),配合以递归状态为查询的注意力机制,并引入 SOC 区间统计和一条主曲线头,同时估计标量寿命和以归一化寿命参数化的单调不增 SOH 曲线。

在 BatteryLife 基准的全部 22 个老化条件独占折上测试,所有折共用一个固定配置、单次运行、不做折级调参。结果显示 DecayFormer 在 Li-ion 上平均测试 MAPE 为 2.25%、CALB 上为 2.76%、Na-ion 上为 0.95%、Zn-ion 上为 7.19%。相比依赖模型扩展、LLM 衍生老化条件嵌入和大量折级超参调优的现有 SOTA 方法,该工作说明紧凑序列模型也能在多种电池化学体系上实现准确早期预测。

Original · arXiv cs.AI

A Hybrid State Space-Attention Architecture for Forecasting the Trajectories of Battery Degradation

Early-life battery degradation trajectory forecasting aims to predict a battery cell's full state-of-health (SOH) trajectory from its initial charge-discharge cycles, potentially reducing cell qualification and evaluation time from months to days. Despite recent advances, accurate forecasting remains challenging for emerging battery chemistries, data-scarce domains, and cells exhibiting degradation behaviors beyond those observed during training. Existing state-of-the-art approaches increasingly rely on model scaling, large language model-derived aging-condition embeddings, and extensive fold-specific hyperparameter tuning, raising concerns about computational efficiency, reproducibility, and generalization. This work introduces DecayFormer, a compact hybrid state-space and attention architecture designed for early-life degradation trajectory forecasting. DecayFormer combines cycle-level selective recurrence, using a single scalar state per channel, with an attention mechanism queried by the recurrent state. It further incorporates state-of-charge (SOC) interval statistics and a master curve head that jointly estimates a scalar lifetime and a monotonically non-increasing SOH profile parameterized by normalized lifetime. We evaluate DecayFormer on the BatteryLife benchmark using all 22 aging-condition-exclusive folds, with a single run per fold and one fixed configuration across all folds, without fold-specific tuning. DecayFormer achieves mean test MAPE values of 2.25% on Li-ion, 2.76% on CALB, 0.95% on Na-ion, and 7.19% on Zn-ion. These results demonstrate the potential of compact sequence models to deliver accurate early-life degradation forecasts across diverse battery chemistries and aging conditions, without relying on extensive model scaling or per-fold optimization.

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include DecayFormer, BatteryLife, state space models.

Source attribution: curated from arXiv cs.AI (@Shrey Patel, Bhargav Srinivas Rao, Samet Ayhan).