FEATURE SPONSOR
CONDITION MONITORING
FIGURE 5 - Order Spectrum of Wind Turbine Main Bearing Vibration Signal
FIGURE 4 -ANN methodology analysing temperature development in rear bearing of Direct Drive turbine
By acting on the early warning (3 months in this case 10th of October vs 27th of January) and issuing inspection of the bearing with corresponding action taken, it can avoid the bearing reaching a ‘non – repairable’ status. It is evident that such early detection methodology has clear advantages representing a potential for reduced maintenance cost and increased production.
FAULT DETECTION BY VIBRATION SENSOR In addition to temperature measurements, vibration sensors are an important mean to indicate faults of rotational machinery. One of the most common methods for analysing sound and vibration signals is Fast Fourier Transform (FFT) analysis which is suitable for machines with fixed rotational speed.
Most wind turbines are running with change of rotational speed because the wind speed changes. In this case, traditional FFT has problems to indicate the fault at specific frequencies. Order analysis techniques enable you to analyse sound and vibration signals when the rotational speed changes over time. An order is the normalisation of the rotational speed.
The first order is the rotational speed and order ‘n’ is ‘n’ times the rotational speed. Order components thus are the harmonics of the rotational speed. With order analysis, you can uncover information about harmonics buried in the FFT power spectrum due to changing rotational speed.
The order power spectrum plot shows clearly-defined peaks associated with different mechanical parts as seen in the Figure 5. The peak at the first order corresponds to the vibration caused by main shaft rotation. The peak at the third order corresponds to the vibration caused by the blades rotation. The peaks at BPFO=13.2x and its harmonics correspond a defect of the outer race of the main bearing in the same bearing as analysed in 3.1. It is clearly shown that the outer race of the main bearing is damaged.
www.windenergynetwork.co.uk 71 CONCLUSION
This article has briefly described the ANN technique applied for analysing temperature data and Order analyses for vibration sensor data applied on the same fault.
Both cases have shown examples of early fault identification for one of the main components of wind turbines, namely the bearings. Data is based on the existing SCADA data.
RESULTS
Results show that both methods can deal with amenity of SCADA data and give the operators of a wind farm very early warning to help make the right maintenance schedule and take the necessary actions in advance. In this way, the amenity of information presented to the operator is dramatically reduced without omitting useful information.
The maintenance and operation cost can be reduced by optimising the maintenance plan allocation of staff and preparation of tools in advance based on to the early warnings of imminent faults.
Kongsberg Click to view more info = Click to view video
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68 |
Page 69 |
Page 70 |
Page 71 |
Page 72 |
Page 73 |
Page 74 |
Page 75 |
Page 76 |
Page 77 |
Page 78 |
Page 79 |
Page 80 |
Page 81 |
Page 82 |
Page 83 |
Page 84 |
Page 85 |
Page 86 |
Page 87 |
Page 88 |
Page 89 |
Page 90 |
Page 91 |
Page 92 |
Page 93 |
Page 94 |
Page 95 |
Page 96 |
Page 97 |
Page 98 |
Page 99 |
Page 100