# Battery_State_of_Charge_Estimation_Device
<h3>Introduction</h3>
<br>This is a deep learning approach to estimate State-of-Charge of 18650 Li-Ion batteries in real-time with high accuracy.</br>
<br>The dataset, used can be found here, [Dataset](https://data.mendeley.com/datasets/cp3473x7xv/1).
<br>Clone this repo into your working directory and execute the **training_code.m** file to train an artifical neural network.
<br>You can change the network hyper-parameters to improve training results.
<br>Once the training is complete, you can export the model into various formats as per your use case through builtin matlab commands. In this case, it has been exported as a Tensorflow model and later converted to TFLite format to be deployed on Hardware.
<br>Matlab Code files have been written in Matlab 2020b and all python files have been verified to work in Python 3.9
<br>The Schematic and board files for the PCB HAT designed for Raspberry Pi can be found in the [PCB](https://github.com/SIDDHARTH-S-001/Battery_State_of_Charge_Estimation_Device/tree/main/PCB) folder. These were designed in [Eagle](https://www.autodesk.com/products/eagle/overview?term=1-YEAR&tab=subscription) 9.6.2
<h3>Components</h3>
<br>1) Raspberry Pi 4</br>
<br>2) 3Ah 18650 Li-Ion cell</br>
<br>3) 0-25V Generic Voltage sensor</br>
<br>4) 0-30A ACS712 Current Sensor</br>
<br>5) DHT11 Temperature Humidity Sensor</br>
<br>6) ADS1115 / MCP3208 (ADC)</br>
蓄电池充电状态估计装置matlab代码.zip （85个子文件） 
蓄电池充电状态估计装置matlab代码 
soc_model.tflite 21KB data_convert.m 2KB soc_ann.mat 15KB PSO_based_tuning.m 6KB PCB Schematic_09.job 55KB Schematic.s#6 48KB Schematic_11.job 54KB Schematic_07.job 54KB Schematic.s#1 48KB Schematic_13.job 55KB Schematic_00.job 78KB Schematic_17.job 55KB Schematic_03.job 54KB Schematic_02.job 54KB Schematic.s#4 49KB Schematic_06.job 54KB Schematic_18.job 55KB Schematic.s#3 48KB Schematic_19.job 55KB Schematic.brd 40KB Schematic_16.job 56KB Schematic_01.job 54KB Schematic_05.job 54KB Schematic_10.job 55KB Schematic_04.job 54KB Schematic.pro 1KB Schematic_08.job 56KB Schematic_20.job 55KB Schematic_14.job 55KB Schematic.b## 50KB Schematic_21.job 55KB Schematic_15.job 56KB Schematic.s#5 48KB Schematic.sch 50KB Schematic.s#2 48KB Schematic_12.job 55KB new_ann __init__.py 3KB weights.h5 87KB
README.txt 1KB model.py 1KB __pycache__ model.cpython-39.pyc 1KB __init__.cpython-39.pyc 2KB pso_new.m 4KB ann_model __init__.py 3KB weights.h5 87KB README.txt 1KB model.py 1KB testing.ipynb 6KB __pycache__ model.cpython-39.pyc 1KB __init__.cpython-39.pyc 2KB README.md 1KB Battery_State_of_Charge_Estimation_Device-main Codes 
25-10-0.01-0.99-10-percentage.png 23KB 5-10-15-0.01-0.9999.png 97KB 15-25-10-0.01-0.5-1000-3000 Epochs RMSE 1.02 percentage_6.png 54KB ArchitectureF2.png 1.15MB Architecture.png 2.75MB 25-10-0.01-0.99-10.png 107KB 10-25-0.01-0.999-10.png 99KB 15-30-10-0.01-0.1-150-percentage.png 24KB 15-25-10-0.01-0.5-1000-3000 Epochs RMSE 1.02 percentage_6.eps 421KB
15-25-10-0.01-0.5-1000-3000 Epochs RMSE 1.02 percentage_3.jpg 79KB 10-25-5.png 102KB ArchitectureF.png 1.15MB Dataset LGHG2@n10C_to_25degC Train TRAIN_LGHG2@n10degC_to_25degC_Norm_5Inputs.mat 16.82MB Test 02_TEST_LGHG2@0degC_Norm_(05_Inputs).mat 1.22MB 01_TEST_LGHG2@n10degC_Norm_(05_Inputs).mat 1.13MB 04_TEST_LGHG2@25degC_Norm_(05_Inputs).mat 1.4MB 03_TEST_LGHG2@10degC_Norm_(05_Inputs).mat 1.28MB Other_Files data_t.txt 23MB TRAIN_LGHG2@0degC_Norm_5Inputs.mat 4.47MB TRAIN_LGHG2@25degC_Norm_5Inputs.mat 4.45MB TRAIN_LGHG2@10degC_Norm_5Inputs.mat 3.93MB TRAIN_LGHG2@n10degC_Norm_5Inputs.mat 3.96MB LGHG2_Min_Max_25degC_to_n10degC.mat 274B TRAIN_LGHG2@n10degC_to_25degC_Norm_5Inputs_TwoCharges.mat 8.08MB TRAIN_LGHG2@n10degC_to_25degC_Norm_5Inputs_OneCharge.mat 7.91MB Validation 01_TEST_LGHG2@n10degC_Norm_(05_Inputs).mat 1.13MB 15-25-10-0.01-0.5-1000-3000 Epochs RMSE 1.02 percentage_2.jpg 79KB 15-25-10-0.01-0.5-1000-3000 Epochs RMSE 1.02 percentage.png 96KB 15-25-10-0.01-0.5-1000-3000 Epochs RMSE 1.02 percentage_5.eps 19KB 15-30-10-0.01-0.1-150.png 87KB 15-25-10-0.01-0.5-1000-3000 Epochs RMSE 1.02 percentage_5.png 20KB
15-25-10-0.01-0.5-1000-3000 Epochs RMSE 1.02 percentage_4.pdf 91KB 5-10-5.png 104KB training_code.m 4KB资源评论
matlab科研助手
- 粉丝: 3w+
- 资源: 5961
下载权益
C知道特权
VIP文章
课程特权
VIP享7折，此内容立减5.97元 开通VIP
最新资源
资源上传下载、课程学习等过程中有任何疑问或建议，欢迎提出宝贵意见哦~我们会及时处理！
点击此处反馈
