Incorporating a proactive maintenance strategy is essential to cut down O&M costs and downtime. An effective approach is condition-based monitoring of components to predict failures and identify abnormal behaviour.
By Sabari Ram Subbaraman, Data and Operational Analytics Engineer, DNV GL – Energy
The rate of decarbonisation worldwide is expected to rise rapidly in the next few years, due to actions to climate change and global policy shifts. The role of wind power in the energy transition is undeniable, and DNV GL’s Energy Transition Outlook 2019 forecasts over a 15-fold escalation in wind-powered generation from 1.1 PWh in 2018 to 17 PWh in 2050.
However, migitating climate change is not as easy as just plugging wind generation sources into the grid. Wind turbines contain rotating machinery and equipment that are susceptible to failures and routine maintenance during their lifetime. Research from Wood Mackenzie shows global onshore wind operations and maintenance (O&M) costs will reach nearly $15 billion in 2019, of which $8.5 billion will be spent on unplanned repairs and corrective maintenance caused by component failures. Failure statistics from major reliability studies suggest that drivetrain components such as gearboxs and generators have large downtime per failure and cost implications. From DNV GL’s experience, common gearbox failures include bearing, gear and lubricant failures while common generator failures include stator, rotor and bearing failures. Deterioration of components occur due to loading during high wind speeds, start-up, grid connection, emergency stops, shutdowns and other transient load events.
Incorporating a proactive maintenance strategy is essential to cut down O&M costs and downtime. An effective approach is condition-based monitoring of components to predict failures and identify abnormal behaviour. Due to increasing importance for detecting incipient failures, many monitoring systems and approaches are being developed. The approaches are broadly divided into diagnostic and prognostic, with the implementation of prognostics relatively new in the wind industry. Generally, diagnostics deals with the detection of anomalies, identification of the component affected and extent of the fault while prognostics refer to the estimation of time to failure, remaining useful life and future failure modes.
Examples of commonly used condition monitoring systems (CMS) are supervisory control and data acquisition (SCADA) based CMS and specialised CMS. SCADA receives data feed on temperature parameters (bearings, gear oil, generator, etc), turbine operational parameters (yaw angle, pitch, etc), tower/drivetrain acceleration and status codes while specialised CMS incorporate additional hardware components to detect vibrations, acoustic emissions and particle measurements of drivetrain components. Market estimates price specialised vibration CMS at around $7,000-9,000 per turbine excluding the annual costs associated with maintenance, monitoring and software. This could be an expensive investment for a large windfarm stakeholder.
Due to lower costs and existing installations, SCADA based condition monitoring is widely used in the industry. Raw SCADA data is not very successful in detecting incipient faults due to the varying operational and environmental conditions stressed on the turbine. Additionally, the 10-minute granularity of SCADA might miss important transient events. To overcome this, multiple SCADA based data models are being researched and deployed using commercial softwares. For example, some of the traditional techniques involve models using wind speed/power binned values and parameter correlations. Furthermore, machine mearning (ML) based models such as polynomial regression and artificial neural networks (ANN) are used for identifying the normal behaviour of a turbine, and detecting any abnormal behaviour. ANNs can identify complex relationships between input and output variables, and are now being widely used in other areas of wind such as forecasting and control. Other ML approaches explored in this domain include models based on random forest and ANN based adaptive neuro fuzzy inference system (ANFIS) and self-organising maps (SOM).
Although ML models are now becoming easier to implement, more failure cases from a range of wind farms and manufacturers, and research/evaluation in combination with domain and analytical expertise are essential for demonstrating the success of a model. Also, data models have limited physical understanding. In contrast, physics-based damage models represent the failure with physical significance when applied to condition monitoring. Hybrid models that incorporate data models with underlying physical understanding can be effective in predicting failures.
In addition to detecting anomalies, it is important to develop tools and processes keeping in mind the failure modes. In doing so, the industry is faced with the challenges of determining thresholds and detection methods, preventing false positives and negatives, sparse expertise in both domain and digital, data availability, fusion and standardisation, developing models for different failure modes and updating the algorithm after on-site maintenance.
In conclusion, integrating multiple CMS, historical failure patterns, parameter relationships, alarm logs, operations records can help arrive at a quick prediction and provide actionable insights for a proactive maintenance strategy. Also, the integration of planning and forecasting tools can help refine the O&M process and feed valuable information back to the chain. From DNV GL’s experience, incorporating a proactive maintenance strategy has helped predict generator bearing failures well in advance and prevented a potential downtime of 500 hours and estimated revenue loss of $28,000. From an asset monitoring standpoint, it is important for an analyst to use all the resources available for a comprehensive review of the turbine’s performance. This is essential due to the complexity of failure modes and component behaviour. Therefore, in this time where the world is adopting various renewable energy generation sources, including wind, continuous monitoring and analysis is required for preventing unplanned failures and optimising the value of assets.