Lithium-ion battery state of charge estimation method based on fusion of deep belief network and Kalman filter
A deep belief network and Kalman filter technology, applied in the measurement of electricity, measurement devices, measurement of electrical variables, etc., can solve the problems of low SOC estimation accuracy and model parameter identification of lithium-ion batteries
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0048] combine Figure 4 This embodiment will be specifically described with Table 1. In this embodiment, four sets of sample data sets of the NASA PCoE random working condition data set are selected to estimate the state of charge of the battery.
[0049] Step 1: Extract the voltage, current, temperature and SOC data of the battery from the battery test data, and normalize the extracted data to [0, 1] to obtain a normalized data set.
[0050] Step 2: Divide the normalized data set into the No. 1 input vector X at time k according to the following formula k (1) , the second input vector X k (2) and the output vector Y k ; The number one input vector X at the time k k (1) , the second input vector X k (2) and the output vector Y k The expressions of are as follows:
[0051] x k (1) =[v k ,...,v k-m ,i k ,...,i k-n ,t k ,...,t k-p ],
[0052] x k (2) =[v k ,...,v k-m ,i k ,...,i k-n ,t k ,...,t k-p ,SOC k-1 ],
[0053] Y k =[SOC k ],
[0054] Amo...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


