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

Table 6

Comparison between actual values and predicted values of SOM neural network optimized by PSO algorithm.

Type	Number of winning neurons
1~18	46	17	73	23	36	49	60	60	78	75	13	27	48	8	1	58	67	3
Fault class	1	2	1	3	2	0	3	3	4	1	3	2	0	2	1	2	2	4
19~36	3	27	23	1	50	63	11	81	81	22	1	58	67	48	78	60	78	75
Fault class	4	2	3	1	0	3	1	3	3	4	1	2	2	0	4	3	4	1
37~54	13	27	60	64	10	32	49	13	2	31	78	26	43	54	18	80	22	11
Fault class	3	2	3	1	1	3	0	4	1	4	4	2	4	3	2	3	4	1
55~72	5	55	41	67	67	3	37	41	33	73	23	67	12	60	78	75	81	40
Fault class	0	1	3	2	2	4	1	3	0	1	3	2	4	3	4	1	3	0
73~80	62	70	18	78	8	62	18	1
Fault class	3	3	2	4	2	3	2	1