Collaborative and privacy-preserving retired battery sorting for profitable direct recycling via federated machine learning

Shengyu Tao; Haizhou Liu; Chongbo Sun; Haocheng Ji; Guanjun Ji; Zhiyuan Han; Runhua Gao; Jun Ma; Ruifei Ma; Yuou Chen; Shiyi Fu; Yu Wang; Yaojie Sun; Yu Rong; Xuan Zhang; Guangmin Zhou; Hongbin Sun

doi:10.1038/s41467-023-43883-y

Collaborative and privacy-preserving retired battery sorting for profitable direct recycling via federated machine learning

Nat Commun. 2023 Dec 5;14(1):8032. doi: 10.1038/s41467-023-43883-y.

Authors

Shengyu Tao^#¹, Haizhou Liu^#¹, Chongbo Sun^#¹, Haocheng Ji¹, Guanjun Ji¹, Zhiyuan Han¹, Runhua Gao¹, Jun Ma¹, Ruifei Ma¹, Yuou Chen¹, Shiyi Fu², Yu Wang², Yaojie Sun², Yu Rong³, Xuan Zhang⁴, Guangmin Zhou⁵, Hongbin Sun^{6

7

8}

Affiliations

¹ Tsinghua-Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China.
² School of Information Science and Technology, Fudan University, Shanghai, China.
³ Tencent AI Lab, Tencent, Shenzhen, China.
⁴ Tsinghua-Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China. xuanzhang@sz.tsinghua.edu.cn.
⁵ Tsinghua-Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China. guangminzhou@sz.tsinghua.edu.cn.
⁶ Tsinghua-Berkeley Shenzhen Institute, Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China. shb@tsinghua.edu.cn.
⁷ Department of Electrical Engineering, Tsinghua University, Beijing, China. shb@tsinghua.edu.cn.
⁸ College of Electrical and Power Engineering, Taiyuan University of Technology, Taiyuan, China. shb@tsinghua.edu.cn.

^# Contributed equally.

Abstract

Unsorted retired batteries with varied cathode materials hinder the adoption of direct recycling due to their cathode-specific nature. The surge in retired batteries necessitates precise sorting for effective direct recycling, but challenges arise from varying operational histories, diverse manufacturers, and data privacy concerns of recycling collaborators (data owners). Here we show, from a unique dataset of 130 lithium-ion batteries spanning 5 cathode materials and 7 manufacturers, a federated machine learning approach can classify these retired batteries without relying on past operational data, safeguarding the data privacy of recycling collaborators. By utilizing the features extracted from the end-of-life charge-discharge cycle, our model exhibits 1% and 3% cathode sorting errors under homogeneous and heterogeneous battery recycling settings respectively, attributed to our innovative Wasserstein-distance voting strategy. Economically, the proposed method underscores the value of precise battery sorting for a prosperous and sustainable recycling industry. This study heralds a new paradigm of using privacy-sensitive data from diverse sources, facilitating collaborative and privacy-respecting decision-making for distributed systems.