Predicting future capacities and remaining useful life (RUL) with uncertainty quantification is a key but challenging issue in the applications of battery health diagnosis and management. This paper applies advanced machine-learning techniques to achieve effective future capacities and RUL prediction for lithium-ion batteries with reliable uncertainty management. To be specific, after using the empirical mode decomposition (EMD) method, the original battery capacity data is decomposed into some intrinsic mode functions (IMFs) and a residual. Then the long short term memory (LSTM) sub-model is applied to estimate the residual while the gaussian process regression (GPR) sub-model is utilized to fit the IMFs with the uncertainty level. Consequently, both the long-term dependence of capacity and uncertainty quantification caused by the capacity regenerations can be captured directly and simultaneously. Experimental aging data from different batteries are deployed to evaluate the performance of proposed LSTM+GPR model in comparison with the solo GPR, solo LSTM, GPR+EMD and LSTM+EMD models. Illustrative results demonstrate the combined LSTM+GPR model outperforms other counterparts and is capable of achieving accurate results for both 1-step and multi-step ahead capacity predictions. Even predicting the RUL at the early battery cycle stage, the proposed data-driven approach still presents good adaptability and reliable uncertainty quantification for battery health diagnosis.
In conventional equalizers, the facts of bulky size and high cost are widespread. Particularly, the zero switching loss and zero-voltage gap (ZVG) between cells are difficult to implement due to the high-frequency hard switching and the voltage drop across power devices. To overcome these difficulties, a direct cell-to-cell battery equalizer based on quasi-resonant LC converter (QRLCC) and boost DC-DC converter (BDDC) is proposed. The QRLCC is employed to gain zero-current switching (ZCS), leading to a reduction of power losses. The BDDC is employed to enhance the equalization voltage gap for large balancing current and ZVG between cells. Moreover, through controlling the duty cycle of the BDDC, the topology can online adaptively regulate the equalization current according to the voltage difference, which not only effectively prevents over-equalization but also abridges the overall balancing time. Instead of a dedicated equalizer for each cell, only one balancing converter is employed and shared by all cells, reducing the size and implementation cost. Simulation and experimental results show the proposed scheme exhibits outstanding balancing performance, and the energy conversion efficiency is higher than 98%. The validity of the proposed equalizer is further verified by a quantitative and systematic comparison with the existing active balancing methods.
This paper presents a fault detection method for short circuits based on the correlation coefficient of voltage curves. The proposed method utilizes the direct voltage measurements from the battery cells, and does not require any additional hardware or effort in modeling during fault detection. Moreover, the inherent mathematical properties of the correlation coefficient ensure the robustness of this method as the battery pack ages or is imbalanced in real applications. In order to apply this method online, the recursive moving window correlation coefficient calculation is adopted to maintain the detection sensitivity to faults during operation. An additive square wave is designed to prevent false positive detections when the batteries are at rest. The fault isolation can be achieved by identifying the overlapped cell in the correlation coefficients with fault flags. Simulation and experimental results validated the feasibility and demonstrated the advantages of this method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.