Research Article

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

Table 11

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

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

10.830.660.620.680.340.280.230.260.430.54PF1PF1
20.830.430.420.47000000PF1PF1
30.660.830.670.660.340.240.320.220.250.22PF2PF2
40.50.890.60.60.40.260.220.240.220.27PF2PF2
50.490.470.560.440.3100.110.1700PF3PF3
60.50.660.870.660.40.390.140.490.150.08PF3PF3
70.370.480.470.6600.4600.250.240.24PF4PF4
80.410.580.570.80.170.770.310.370.390.41PF4PF4
900000.4400.2000PF5PF5
100.530.640.650.660.830.370.2320.220.26PF5PF5
11000.120.1200.640420.190.45PF6PF6
120.150.220.180.170.540.820.220.240.220.59PF6PF6
13000000.280.5000PF7PF7
14000000.370.59000PF7PF7
150.50.630.470.560.220.270.150.850.120.15PF8PF8
160.380.640.470.410.270.140.090.8700.05PF8PF8
170000.130.20.180.380.170.460.28PF9PF9
180.160.430.230.190.450.450.550.410.750.26PF9PF9
1900.170.120.220.140.5700.420.330.64PF10PF10
200000.390.2200.250.290.430.75PF10PF10