实验目的

实验装置

【部分】实验原理

【部分】实验数据记录及处理

借助Python

插个题外话，如果数据比较多的话

pip install numpy
pip install matplotlib
pip install pandas

import numpy as np
import matplotlib as plt
import pandas as pd

import numpy as np

#均值
np.mean(nums)
#中位数
np.median(nums)

借助MATLAB

如果你的数据量不够的话，可以用神经网络来预测一下
以下是我之前的一个项目的，改一改变量就行

quantity=[33.00 ,33.23 ,33.90 ,35.01 ,36.55 ,38.53 ,40.92 ,43.73 ,46.94 ,50.56 ,54.57 ,58.98 ,63.76 ,68.92 ,74.45 ,80.35 ,86.60 ,93.20 ,100.15 ,107.44 ,115.06 ,123.00 ,136.78 ,159.08 ,185.65 ,212.24 ,234.61 ,248.50 ,254.50 ,274.40 ,297.08 ,320.13 ,344.17 ,369.84 ,397.76 ,428.56 ,462.87 ,501.30 ,544.50 ,615.18 ,683.60 ,722.58 ,757.27 ,788.14 ,815.64 ,840.23 ,862.36 ,882.48 ,901.06 ,918.55 ,935.40 ,951.22 ,965.47 ,978.38 ,990.18 ,1001.10 ,1011.29 ,1020.70 ,1029.23 ,1036.80]; 
%forest stockpile 
%%% Training BP neural networks with known data 
x=year; 
y=quantity; 
net=newff(x,y,2); %Generate a BP network with one neuron for both input and output, and 2 neurons for the hidden layer. 
net.trainParam.epochs = 1000; % Number of training sessions, this file is set to 1000 (the maximum number of training sessions). 
net.trainParam.goal = 0.1; % Minimum error of the training target, this file is set to 0.1. 
net.trainParam.lr = 0.01; % Learning rate, this file is set to 0.01. 
net=train(net,x,y); %Training Network 
%%%forecasting their quantities for 1962-2021 
quantity_pre=sim(net,year); 
plot(year,quantity,'*b','MarkerSize',8);hold on 
plot(year,quantity_pre,'or','MarkerSize',8);hold on 
plot(year,quantity,'b','LineWidth',2);hold on 
plot(year,quantity_pre,'r','LineWidth',2);grid on 
legend('Real Data','Theoretical Data') 
xlabel('year') 
ylabel('quantity') 
title('BP neural network forecasting curve') 
%%%projected numbers between 2021-2049. 
Year_pre=2021:2049; 
quantity_pre_BP=sim(net,Year_pre)% Pass parameters to the Simulink model in the m-file and run the model to get the result data of the model run. 

【部分】实验分析与讨论

【部分】本次实验的心得及建议

参考文献

【更多内容】

备用2（b站）

原版【全文】文件在这里【详细】

>>>我在这里<<<