将concrete_data.mat文件导入到MATLAB中，其中attributes为影响混凝土抗压强度的7个输入变量，strength为混凝土的抗压强度，即输出变量；
将整个数据集中的103个样本随机划分为训练集与测试集，其中训练集包含80个样本，测试集包含23个样本；
将训练集与测试集数据进行归一化；
建立BP神经网络，并训练；
利用训练好的BP神经网络对测试集中的23个样本的抗压强度进行预测；
输出结果并绘图（真实值与预测值对比图）(The concrete_data.mat file is imported into MATLAB, where attributes is the 7 input variable affecting the compressive strength of concrete, and strength is the compressive strength of concrete, that is, the output variable;
The 103 samples in the whole dataset are randomly divided into training set and test set, in which the training set contains 80 samples, and the test set contains 23 samples;
The training set is normalized to the test set data;
The BP neural network is established and trained;
The trained BP neural network is used to predict the compressive strength of 23 samples in the test set;
Output results and plot (true values versus predicted values))