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

Table 4

Comparison between actual values and predicted values of SOM neural network.

Type	Number of winning neurons
1~18	79	24	81	48	50	41	16	42	6	79	17	22	24	19	73	1	39	65
Fault class	1	4	1	0	2	0	3	0	4	1	3	2	4	2	1	2	2	4
19~36	24	1	48	73	22	17	64	9	9	47	73	3	1	50	6	42	6	79
Fault class	4	2	0	1	2	3	1	3	3	4	1	2	2	2	4	0	4	1
37~54	58	22	42	72	73	40	22	30	74	39	24	10	23	8	1	18	47	55
Fault class	0	2	0	1	1	0	2	0	1	0	4	2	4	3	2	3	4	1
55~72	67	63	18	42	1	65	69	9	22	81	48	50	23	59	6	79	9	31
Fault class	0	1	3	0	2	4	1	3	2	1	0	2	4	3	4	1	3	0
73~80	27	26	1	24	19	27	1	73
Fault class	3	3	2	4	2	3	2	1