Update README.md

README.md

@@ -2,7 +2,7 @@
 Retired batteries have been presenting a severe sustainability challenge worldwide. One promising sustainable solution is reuse and recycling, but state of health (SOH) information for residual value evaluation retrieved from charge-discharge approaches are still time-consuming and energy-intensive. Developing a data-driven, rapid, and sustainable SOH estimation method for reuse and recycling decision-making is crucial. Here we open-source the collected PulseBat dataset for pulse voltage response generation of retired batteries across random retirement conditions, i.e., state of charge (SOC) conditions, facilitating downstream SOH estimation tasks. The PulseBat dataset was collected from diversified cathode material types, historical usages, physical formats and capacity designs to deliberately introduce data heterogeneities, which is a common challenge in retired battery reuse and recycling scenarios. Xiamen Lijing New Energy Technology Co., Ltd., (Xiamen Lijing) collected the dataset. The collaboration team at Tsinghua Berkeley Shenzhen Institute (TBSI) processed this dataset. AI and battery community will find the PulseBat dataset useful for SOH estimation of retired batteries under transfer learning, continual learning, and generative learning settings.
 
 # 1. Publication
-[Generative-learning-assisted Rapid State-of-Health Estimation for Sustainable Battery Recycling with Random Retirement Conditions](To be published)
+[Generative-learning-assisted Rapid State-of-health Estimation for Sustainable Battery Recycling with Random Retirement Conditions](Under Consideration)
 # 2. Description
 ## 2.1. Overview
 Retired batteries exhibit considerable heterogeneities in cathode material types, historical usages, physical formats and capacity designs. We physically tested 464 retired lithium-ion batteries, covering 3 cathode types, 6 historical usages, 3 physical formats, and 6 capacity designs.