Article Promoting charging safety of electric bicycles via machine learning

The worldwide penetration of electric bicycles has caused numerous charging ac-cidents; however, online diagnosing charging faults remains challenging because of non-standard chargers, non-uniform communication manners and inaccessible battery inner status. The development of Internet of Things enables to acquire the input current information of chargers in the cloud platform, thereby supply-ing an alternative perspective to excavate underlying charge abnormalities. Through analyzing 181,282 charge records collected from the power-grid side, we establish an update-to-date deep neural network algorithm, which can auto-matically capture these charge feature variables, determine their dependencies and identify abnormal charge behaviors. Based on the only input current se-quences, the algorithm can effectively diagnose the charging fault with the average accuracy of 85%, efficiently ensuring the charging safety of more than 20 million E-bicycles after substantial validations. Besides, this diagnosis frame-work can be extended to the real-time charge safety detection of electric vehicles and other similar

Automated summary

The widespread use of electric bicycles has led to numerous charging accidents. However, diagnosing charging faults online is challenging due to the lack of standard chargers, inconsistent communication methods, and limited access to battery status. The development of the Internet of Things allows for the collection of charger input current information on a cloud platform, providing an alternative approach to identify underlying charging abnormalities. By analyzing 181,282 charge records, a deep neural network algorithm has been developed to automatically capture charge feature variables, determine their dependencies, and identify abnormal charge behaviors. With an average accuracy of 85%, the algorithm effectively diagnoses charging faults, ensuring the safety of over 20 million E-bicycles after extensive validation. Furthermore, this diagnostic framework can be extended to real-time charge safety detection for electric vehicles and similar vehicles.