基于k-NN算法的钢板性能预测模型的建立与应用

Establishment and Application of Prediction Model of Steel Plate Performance Based on k-NN Algorithm

为准确预测钢板性能,利用影响中厚板性能的因素(化学成分、压缩率、开轧温度、冷却时间、冷却速度等)作为特征向量,将屈服强度、抗拉强度、延伸率等作为输出变量,构建了基于k-NN算法的中厚板性能k-NN预测模型。利用福建三钢中厚板数据库资料,采用该模型探索大数据挖掘技术在中厚板生产中性能预测领域的应用。

In order to accurately predict the performance of steel plate,the yield strength,tensile strength and elongation are taken as the output variables by using the factors which affect the properties of medium and heavy plate(chemical composition,compression ratio,starting temperature,cooling time,cooling speed,etc.)as the eigenvector,a k-NN prediction model for plate performance based on k-NN algorithm was established.By using the statistic material of medium and heavy palte of Fujian steel,this model is used to explore the application of big data mining technology in the production of medium and heavy plate.