Giter Club home page Giter Club logo

nasa's Introduction

NASA 锂电池数据集,基于 Python 的锂电池寿命预测(Remaining Useful Life,RUL)& (End Of Life,EOL)

主要库版本:

  • pytorch >=1.6.0

预测结果

关于代码的说明:

最近经常收到有同学问代码中一些问题,现汇总如下:

(1) build_sequences(text, window_size) 函数生成的预测数据为什么是序列不是下一个点?

序列[1, 2, 3, 4, 5], build_sequences 函数生成的 x=[[1, 2, 3], [2, 3, 4]], y=[[2, 3, 4], [3, 4, 5]]的目的有两个:

一种是用序列预测序列,即 x=[1, 2, 3] 预测 y=[2, 3, 4],x=[2, 3, 4] 预测 y=[3, 4, 5];

一种是用序列预测下一个点,即 x=[1, 2, 3] 预测 y=[4],x=[2, 3, 4] 预测 y=[5];

本次实验中,我采用后者。所以,代码中,我训练的时候最后是取了train_y的最后一列:

y = np.reshape(train_y[:,-1]/Rated_Capacity,(-1,1)).astype(np.float32)

版本更新:

  • 2024年5月12日,修改部分代码以及添加预测图像

  • 2022年2月24日,修改部分变量名字

  • 2022年2月6日,解决错误“Tensor for argument #2 ‘mat1’ is on CPU, but expected it to be on GPU (while checking arguments for addmm)”

  • 2021年12月1日, 添加数据读取模块

    如果原始数据集无法成功读取,可以直接选择加载我已经提取出来的数据:NASA.npy

    Battery = np.load('NASA.npy', allow_pickle=True)

    Battery = Battery.item()

有任何问题,欢迎留言!

Homepage: http://zhouxiuze.com

个人博客: http://snailwish.com

个人邮箱: [email protected]

更多内容

  1. NASA 锂电池数据集,基于 Python 的锂电池寿命预测: https://snailwish.com/395/

  2. NASA 锂电池数据集,基于 python 的 MLP 锂电池寿命预测: https://snailwish.com/427/

  3. 马里兰大学锂电池数据集 CALCE,基于 Python 的锂电池寿命预测: https://snailwish.com/437/

  4. NASA 和 CALCE 锂电池数据集,基于 Pytorch 的 RNN、LSTM、GRU 寿命预测: https://snailwish.com/497/

  5. 基于 Pytorch 的 Transformer 锂电池寿命预测: https://snailwish.com/555/

参考文献

@article{chen2022transformer,
  title={Transformer network for remaining useful life prediction of lithium-ion batteries},
  author={Chen, Daoquan and Hong, Weicong and Zhou, Xiuze},
  journal={Ieee Access},
  volume={10},
  pages={19621--19628},
  year={2022},
  publisher={IEEE}
}

PDF download

nasa's People

Contributors

xiuzezhou avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

nasa's Issues

关于输入rnn中的数据shape的问题

输入rnn的数据shape为[batch_size, seq_len, input_size],而对train的reshape操作为[-1, 1, feature_size],令build_sequences函数输出的电池容量序列被归为了input_size,而seq_len变为了1。
请问此处的reshape是否应改为[-1, seq_len, 1]?

关于score均值的计算

我发现您的代码在tain函数中score计算时,只有epoch为99,199等数的时候[re, mae, rmse]这3个数字才会更新,但是函数中对每个epoch都保存了score = [re, mae, rmse],这样是不是有问题

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.