ESS BATTERY STATE DIAGNOSIS AND LIFESPAN PREDICTION DEVICE AND METHOD

• Main Authors: CHONG, Byong Chol, JUNG, Tae Ho, OH, Sang Yeop
• Format: Patent
• Language: English; French; Korean
• Published: 04.03.2021
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; MEASURING; MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES; PHYSICS; TESTING

The purpose of the present embodiment is to provide a battery state diagnosis and lifespan prediction device and method, capable of helping in the stable operation of an energy storage system (ESS) by carrying out state diagnosis and lifespan prediction of a battery contained in the ESS by using a diagnosis prediction model on the basis of data on the state of the battery. Here, the diagnosis prediction model is implemented by a deep learning-based neural network, and parameters of the diagnosis prediction model are updated using parameters received from a server. La présente invention a pour objet, selon le mode de réalisation, de fournir un dispositif et un procédé de prédiction de durée de vie et de diagnostic d'état de batterie, qui peuvent aider à l'opération stable d'un système de stockage d'énergie (ESS) en effectuant un diagnostic d'état et une prédiction de durée de vie d'une batterie contenue dans le système ESS en utilisant un modèle de prédiction de diagnostic sur la base de données sur l'état de la batterie. Ici, le modèle de prédiction de diagnostic est mis en œuvre par un réseau neuronal basé sur un apprentissage profond et des paramètres du modèle de prédiction de diagnostic sont mis à jour à l'aide de paramètres reçus d'un serveur. 본 실시예는, ESS(Energy Storage System)에 포함된 배터리의 상태에 대한 데이터를 기반으로 진단예측 모델을 이용하여 배터리의 상태진단 및 수명예측을 수행함으로써 ESS의 안정적인 동작에 도움을 줄 수 있는 배터리 상태진단 및 수명예측을 위한 장치와 방법을 제공하는 데 목적이 있다. 여기서, 진단예측 모델은 딥러닝 기반의 신경망으로 구현되며, 서버로부터 전달받은 파라미터를 이용하여 진단예측 모델의 파라미터가 업데이트된다.