论文信息 - Wavelet neural network based battery state-of-charge estimation for portable electronics applications

Wavelet neural network based battery state-of-charge estimation for portable electronics applications

A wavelet neural network-based battery state-of-charge estimator is designed and validated. It possess the following advantages: high accuracy with a limited error of /spl plusmn/3%, easy to implement by using minimized network with only one node, and low cost since no current measurement is required and only battery voltage is measured.

[1] Mohammad Bagher Menhaj,et al. Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[2] Chenghui Cai,et al. State-of-charge (SOC) estimation of high power Ni-MH rechargeable battery with artificial neural network , 2002, Proceedings of the 9th International Conference on Neural Information Processing, 2002. ICONIP '02..

[3] S. Mallat. Multiresolution approximations and wavelet orthonormal bases of L^2(R) , 1989 .

[4] Ss Grewal,et al. A novel technique for modelling the state of charge of lithium ion batteries using artificial neural networks , 2001 .

[5] T. Yamazaki,et al. Estimation of the residual capacity of sealed lead-acid batteries by neural network , 1998, INTELEC - Twentieth International Telecommunications Energy Conference (Cat. No.98CH36263).

[6] F. Huet. A review of impedance measurements for determination of the state-of-charge or state-of-health of secondary batteries , 1998 .

[7] Adnan H. Anbuky,et al. VRLA battery state-of-charge estimation in telecommunication power systems , 2000, IEEE Trans. Ind. Electron..

[8] Qinghua Zhang,et al. Wavelet networks , 1992, IEEE Trans. Neural Networks.