Research Article

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

Table 5

Diagnosis results of the test data under 300–1000 W/m2 irradiation and PV module surface temperatures between 31 and 40°C.

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

110.60.550.580.290.190.230.240.10.2PF1PF1
210.60.660.610.230.230.20.280.220.23PF1PF1
30.50.970.590.650.310.210.220.230.230.2PF2PF2
40.50.990.60.50.250.270.20.250.140.19PF2PF2
50.50.6610.550.140.180.20.650.180.14PF3PF3
60.440.6610.420.0900.050.580.090.1PF3PF3
70.50.610.7610.160.230.140.250.570.52PF4PF4
80.870.840.830.990.50.590.460.470.630.53PF4PF4
90.160.20.110.1210.190.230.470.330.27PF5PF5
100.160.20.220.1510.230.20.580.510.23PF5PF5
110.330.240.140.190.3110.220.230.230.46PF6PF6
120.160.220.180.140.2510.20.360.140.45PF6PF6
130.160.190.220.180.140.4210.180.180.14PF7PF7
140.090.220.130.180.130.4110.080.110.08PF7PF7
150.140.320.510.170.580.120.1410.60.11PF8PF8
160.50.580.660.550.090.510.4610.010.43PF8PF8
17000.10.540.2500.390.2310.51PF9PF9
180.160.20.220.530.50.230.410.5810.71PF9PF9
190.160.240.140.530.530.520.340.230.651PF10PF10
200.160.220.180.640.250.590.20.250.741PF10PF10