Online estimation of SOH for lithium-ion battery based on SSA-Elman neural network

Abstract

The estimation of state of health (SOH) of a lithium-ion battery (LIB) is of great significance to system safety and economic development. This paper proposes a SOH estimation method based on the SSA-Elman model for the first time. To improve the correlation rates between features and battery capacity, a method combining median absolute deviation filtering and Savitzky–Golay filtering is proposed to process the data. Based on the aging characteristics of the LIB, five features with correlation rates above 0.99 after data processing are then proposed. Addressing the defects of the Elman model, the sparrow search algorithm (SSA) is used to optimize the network parameters. In addition, a data incremental update mechanism is added to improve the generalization of the SSA-Elman model. Finally, the performance of the proposed model is verified based on NASA dataset, and the outputs of the Elman, LSTM and SSA-Elman models are compared. The results show that the proposed method can accurately estimate the SOH, with the root mean square error (RMSE) being as low as 0.0024 and the mean absolute percentage error (MAPE) being as low as 0.25%. In addition, RMSE does not exceed 0.0224 and MAPE does not exceed 2.21% in high temperature and low temperature verifications.

Self-Powered Electronic Skin for Remote Human–Machine Synchronization

“…With the development of economy, science, and technology, today’s society has entered a highly developed intelligent era. − In the process of the new technological revolution, signal sensing is a key link and an important technical element. − As an important information acquisition tool, sensors play a very important role in signal transmission in different sensing fields. − In real life, sensors with various functions are similar to various organs of the human body and they are all indispensable parts for sensing external stimuli. − At present, the research of robot is a very important field in the intelligent era and numerous research groups have done a lot of research on robot’s autonomous behavior, remote observation, and interaction ability in special environment. − In order to perceive the behavior state in different working conditions, it is necessary to improve the sensing ability of the robot to adapt to the signal perception in more complex environments. − …”

200 MPa cold isostatic pressing creates surface-microcracks in a Zn foil for scalable and long-life zinc anodes

“…10 Therefore, how to solve the problem of zinc dendrite growth is an important challenge. 11 In order to solve this challenge of obtaining highperformance zinc anodes, the research procedure mainly involves the following ways to improve the performance of zinc anodes, (i) covering the zinc surface with a protective layer, [12][13][14] (ii) adjusting the structure of the electrolyte, [15][16][17] and (iii) changing the metal structure of the zinc anode. [18][19][20] Recently, it has been reported that creating a copper-zinc alloy material on the zinc surface inhibits the electrochemical corrosion of aqueous zinc metal and improves the cycle performance.…”

Inhibition of Structural Transformation and Surface Lattice Oxygen Activity for Excellent Stability Li-Rich Mn-Based Layered Oxides

“…The rise of electric vehicles around the world is driving the search for batteries with low cost and high energy density. − In existing commercial lithium-ion batteries, the anode has made great progress, while the main bottleneck at present is the mismatched and insufficient capacity of the cathode . Li-rich Mn-based layered oxides (LLOs) are considered one of the most promising cathode materials because their capacity exceeds 250 mA h/g. , The redox reaction of transition metal ions (TM n + /TM ( n +1)+ ) and anions (O 2– /O 2 ) is the primary reason for LLOs’ remarkable capacity.…”