CONDITION MONITORING CM & PM
The system covers two separate functionalities for condition and performance monitoring.
1 An installation specific CMS for overview of the technical status 2 A benchmarking capability
The overall purpose of the system is to ensure optimal performance and to minimise downtime and operational costs. This shall be achieved by earlier and more secure detection of faults than by conventional systems CM & PM combined enables…
• Reduced number of unplanned stops • Reduced number of unplanned service interventions • Reduced HSE risk • Reduced time for localisation of faults • Repair before the fault develops into irreparable damage • Running at reduced loads until repair can be done • Reduction of consequential damages • Improved planning and scheduling of repair operations • Change from calendar based to Condition Based Maintenance • Extension of lifetime above rated based on technical condition
It is therefore important to select such measurement techniques that give an early but reliable detection with low risk of false alarms and to employ efficient signal processing algorithms for feature extraction and alarm qualification.
FIELD CASE STUDY - EARLY WARNING AND DETECTION OF FAULTS IN BEARINGS
Fault detection temperature sensors
In this case they applied an Artificial Neural Network (ANN) method including a model based tool by combining data from temperature sensors in the rear bearing of a direct drive wind turbine.
The standard temperature sensors showed the following temperature development in the bearing before the temperature alarm was reached and the turbine tripped:
FEATURE SPONSOR
FIGURE 2 - Performance Monitoring by the Wind Farm Management system
APPLIED METHODS FOR IMPROVED CM & PM A critical task in any CM system is to have as early warning as possible of imminent failures so that action can be taken before the failure develops into a critical fault. The detection of a non- conforming event is the starting point for isolation and diagnosis of the problem.
Much of the value of a CM system lies in the ability to give reliable estimates of remaining useful lifetime (RUL), which is the operating time between detection of the failure and the time when an unacceptable level of degradation is reached.
The RUL estimates can be based on statistics, but can be improved if we combine this with measurement methods that can be used to monitor indicators that reveal the gradual degradation. Different measurement techniques with different detection sensitivity can also be used in combination to assess the degradation level.
FIGURE 3 -Temperature developments in rear bearing of Direct Drive turbine
The first detection of a temperature increase was identified when the warning level of 50° C was reached on the 27th of December. The turbine tripped when the temperature reached 60° C on the 27th of January, it was restarted and it tripped again due to damages in the bearing.
By applying ANN methodology and designing a temperature development model for the rear bearing it was able to detect a significant change in the bearing status earlier than for conventional CM tools. As shown in Figure 4 measured the differential temperature between the actual temperature and the model based calculated temperature. In designing the temperature model it used the following input parameters; nacelle temperature, turbine speed, grid power and last time period temperature of the rear bearing.
70
www.windenergynetwork.co.uk
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