For access to this article, please select a purchase option:
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Your recommendation has been sent to your librarian.
The fault of the battery affects the reliability of the power supply, thus threatened the safety of the battery energy storage system (BESS). A fault warning method based on the predicted battery resistance and its change rate is proposed. The causes of the resistance change of the battery are classified, and the influencing factors of battery internal resistance are quantified. The prediction model of the battery resistance is constructed by the long-and-short-time memory neural network (LSTM) with the inputs of the state, voltage, current, temperature of the battery. The signal of the fault warning is issued and the cause of the fault is determined with the predicted battery resistance and its change rate. The results of the experiment show that the error of the prediction method of the battery resistance is within 3%. The fault warning method is beneficial to the safe operation of the BESS.
Inspec keywords: lead acid batteries; recurrent neural nets; power engineering computing; reliability; battery storage plants; fault diagnosis
Subjects: Secondary cells; Power engineering computing; Other power stations and plants; Secondary cells; Neural nets; Reliability