Research Article

Applying a Cerebellar Model Articulation Controller Neural Network to a Photovoltaic Power Generation System Fault Diagnosis

Table 7

Diagnosis results of the test data under 300–1000 W/m2 irradiation and PV module surface temperatures between 51 and 60°C.

Test no.Output weight for various fault types Known fault type Diagnosed results
PF1PF2PF3PF4PF5PF6PF7PF8PF9PF10

110.660.620.670.340.280.230.260.20.28PF1PF1
210.640.650.660.340.370.20.320.220.26PF1PF1
30.510.670.660.240.240.320.220.250.22PF2PF2
40.510.60.60.280.260.220.240.220.27PF2PF2
50.610.660.990.660.250.280.230.710.280.22PF3PF3
60.50.8910.660.190.140.140.680.150.08PF3PF3
70.50.630.6210.220.350.150.440.660.64PF4PF4
80.410.580.5710.170.550.310.370.660.68PF4PF4
90.160.220.190.110.280.230.440.440.28PF5PF5
100.160.320.230.190.980.370.20.520.40.26PF5PF5
110.330.240.190.220.2410.320.430.250.58PF6PF6
120.150.220.180.170.2810.220.350.220.59PF6PF6
130.120.190.190.220.250.5610.280.280.22PF7PF7
140.120.220.120.220.190.3710.190.150.08PF7PF7
150.120.280.520.110.60.180.1510.480.15PF8PF8
160.020.260.550.190.840.40.1210.530.15PF8PF8
170000.520.200.180.1710.56PF9PF9
180.160.20.230.520.610.370.20.5510.81PF9PF9
190.160.420.190.550.380.590.320.220.71PF10PF10
200.150.220.180.570.280.540.220.240.721PF10PF10