Failure Prediction Modeling of Lithium Ion Battery toward Distributed Parameter Estimation

Lithium ion battery has typical character of distributed parameter system, and can be described precisely by partial differential equations and multi-physics theory because lithium ion battery is a complicated electrochemical energy storage system. A novel failure prediction modeling method of lithium ion battery based on distributed parameter estimation and single particle model is proposed in this work. Lithium ion concentration in the anode of lithium ion battery is an unmeasurable distributed variable. Failure prediction system can estimate lithium ion concentration online, track the failure residual which is the difference between the estimated value and the ideal value. The precaution signal will be triggered when the failure residual is beyond the predefined failure precaution threshold, and the failure countdown prediction module will be activated. The remaining time of the severe failure threshold can be estimated by the failure countdown prediction module according to the changing rate of the failure residual. A simulation example verifies that lithium ion concentration in the anode of lithium ion battery can be estimated exactly and effectively by the failure prediction model. The precaution signal can be triggered reliably, and the remaining time of the severe failure can be forecasted accurately by the failure countdown prediction module.

Voltage imbalance mitigation in an active distribution network using decentralized current control

Voltage imbalance(VI)is caused by the difference in connected single-phase load or generation in a low voltage distribution network(DN).VI increase in a smart distribution grid is due to the current practice of increasing single-phase distributed generators such as photovoltaic(PV)systems.This paper proposes a decentralized control method to mitigate VI using distributed batteries included in smart grid interfaced residential PV systems.To mitigate VI using the batteries in this way,five challenges must be overcome,i.e.,equalizing all battery stress currents within the DN,mitigating VI in abnormal conditions such as signal loss among bus controllers,being immune from the distorted feedback measurements,minimizing the steady-state error at different loads,and overcoming the insufficient number or capacity of the distributed batteries at the same bus.Three fuzzy logic controllers(FLC)are proposed at each bus to overcome these five tasks based on a decentralized control scheme.The proposed decentralized control based on FLC is compared with centralized control based on a PI controller.The proposed control method is tested and verified using simulations in the MATLAB/Simulink software,and the results validate the ability of the scheme to alleviate VI on a smart distribution network under both normal and abnormal conditions.