Research Article

SOM Neural Network Fault Diagnosis Method of Polymerization Kettle Equipment Optimized by Improved PSO Algorithm

Table 3

Number of winning neurons corresponding to fault class of SOM neural network.

TypeNumber of winning neurons

I55626364697172737479810000000
II1231019222830383942465000000
III789161718262730314041424348585967
IV62324303139404147485658656667000