Wind turbine prognostics

Last updated
Early small scale onshore Wind Turbines Barn wind turbines 0504.jpg
Early small scale onshore Wind Turbines

The growing demand for renewable energy has resulted in global adoption and rapid expansion of wind turbine technology. Wind Turbines are typically designed to reach a 20-year life, [1] however, due to the complex loading and environment in which they operate wind turbines rarely operate to that age without significant repairs and extensive maintenance during that period. [2] In order to improve the management of wind farms there is an increasing move towards preventative maintenance as opposed to scheduled and reactive maintenance to reduce downtime and lost production. This is achieved through the use of prognostic monitoring/management systems.

Contents

Typical Wind Turbine architecture consists of a variety of complex systems such as multi stage planetary gear boxes, hydraulic systems and a variety of other electro-mechanical drives. Due to the scale of some mechanical systems and the remoteness of some sites, wind turbine repairs can be prohibitively expensive and difficult to co-ordinate resulting in long periods of downtime and lost production.

As typical wind turbine capacity is expected to reach over 15MW is coming years [3] combined with the inaccessibility of Offshore wind farms, the use prognostic method is expected to become even more prevalent within the industry.

Modern Large Scale Offshore Wind Farm Barrow Offshore wind turbines NR.jpg
Modern Large Scale Offshore Wind Farm

Wind Turbine prognostics is also referred to as Asset Health Management, Condition Monitoring or Condition Management.

History

Early small-scale wind turbines were relatively simple and typically fitted with minimal instrumentation required to control the turbine. There was little design focus on ensuring long-term operation for the relatively infantile technology. The main faults resulting in turbine downtime are typically drive train or pitch system related. [4]

Wind Turbine Gearbox Replacement Gearbox , Rotor Shaft and Disk Brake Assembly for Turbine No 3 - geograph.org.uk - 758164.jpg
Wind Turbine Gearbox Replacement

There has been rapid development of wind turbine technology. As turbines have grown in capacity, complexity and cost, there have been significant improvements in the sophistication of instrumentation installed on wind turbines which has enabled more effective prognostic systems on newer wind turbines. In response, there has been a growing trend of retro-fitting similar systems on existing wind turbines in order to manage aging assets effectively.

Prognostic methods that enable preventative maintenance have been common place in some industries for decades such as Aerospace and other industrial applications. As the cost of repairing wind turbines has increased as designs have grown more complex it is expected that the Wind Turbine industry will adopt a number of prognostic methods and economic models from these industries such a power-by-the-hour approach to ensure availability. [5]

Failure Modes

Turbine failures, particularly mechanical failures, cause significant downtime for repairs. Additionally, turbines are most often built in remote areas or offshore locations, where maintenance is a logistical and financial challenge. Analysis and mitigation of turbine failure is essential to improve the cost and reliability of wind energy. [6] The components responsible for the most downtime per repair are typically the turbine blades and components of the drivetrain. [7]

Turbine Blades

Wind turbine blades withstand consistently high centripetal loads throughout their life and must endure high exposure to their surroundings. Rotor blades can experience surface weathering at the leading and trailing edges due to windborne dust and debris, which deteriorates the blade material and affects the turbine’s efficiency. [8] While detrimental if left unchecked, this deterioration is also easy to monitor and repair before serious damage is incurred. More damaging are interior structural cracks caused by invisible defects in the material which propagate under high stresses, and connection faults at the root which can cause blade separation. [9] The blades are also susceptible to lightning damage, which is particularly harmful for blades made of carbon-fiber reinforced polymer, due to the mechanical stresses caused by inductive heating from eddy currents. [10]

Drivetrain

Tasked with converting the low-speed rotation of the massive blades into rotation in the thousands of rpm, the drivetrain of a wind turbine experiences some of the most extreme loads of any component, most notably in the bearings, which support the mechanical load of the system. The primary cause of roller bearing failure in turbines is the high contact stress involved, manifesting as abrasive wear, micro pitting, scuffing, and macropitting issues. Wind turbines also experience widely varying operating conditions like dynamic wind load, varying speed, and impact, which can push bearings beyond their limits, accelerating their failure. [11] Wind turbine bearings also frequently exhibit white etching cracks, a kind of localized damage to the ferrite microstructure of steel. The exact cause of this process is unknown, but it is responsible for a large portion of drivetrain bearing failures. [12]

Data Capture

The methods for wind turbine prognostics can broadly be grouped into two categories:

Most wind turbines are fitted with a range of instrumentation by the manufacturer. However this is typically limited to parameters required for turbine operation, environmental conditions and drivetrain temperatures. [13] This SCADA based turbine prognostics approach is the most economical approach for more rudimentary wind turbine designs.

For more complex designs, with complex drivetrain and lubrication systems, a number of studies have demonstrated the value of Vibration monitoring and Oil monitoring prognostic systems. [14] These are now widely commercially available.

Traditional content management systems (CMS) typically rely on piezoelectric vibration sensors for gearbox monitoring tasks. While these sensors are capable of capturing adequate data, they fall short when it comes to detecting low-frequency phenomena, such as rotor imbalance. This is where Micro-Electro-Mechanical Systems (MEMS) sensors provide more detail, [15] as they have the ability to measure frequencies all the way down to 0 Hz (also referred to as DC offset). This capability enables these advanced sensors to identify critical frequencies related to the input shaft ('1P') and blade passing ('3P'), both of which often fall below 1 Hz and remain undetected by traditional CMS technologies.

Leveraging cutting-edge technology, this advanced monitoring solution excels in tracking vibration trends, including those caused by ice formation on turbine blades. When a rotor experiences imbalance, the system is designed to note any increase in the 1P rotor frequency. Mass imbalance can arise from a variety of issues, such as the non-uniform build-up of dirt or ice, presence of moisture, or damage. Additionally, aerodynamic imbalance may occur due to inaccuracies within individual blade profiles, physical damage, or errors in pitch calibration.

Data Analysis

Once data is collected by on board data acquisition systems, this is typically processed and communicated to ground based or cloud based data storage system.

Raw parameters and derived health indicators are typically trended over time. Due to the nature of drivetrain faults, these are typically analysed in the frequency domain in order to diagnose faults.

GHE can be generated from a wind turbine SCADA (Supervisory Control and Data Acquisition) system, by interpreting turbine performance as its capability to generate power under dynamic environmental conditions. Wind speed, wind direction, pitch angle and other parameters are first selected as input. Then two key parameters in characterizing wind power generation, wind speed and actual power output, collected while turbine is known to work under nominal healthy condition are used to establish a baseline model. When real-time data arrives, same parameters are used to model current performance. GHE is obtained by computing the distance between the new data and its baseline model.

By trending the GHE over time, performance prediction can be made when unit revenue will drop below a predetermined break-even threshold. Maintenance should be triggered and directed to components with low LDE values. LDE is computed based on measurements from condition monitoring system (CMS) and SCADA, and is used to locate and diagnose incipient failure at component level.

Machine learning is also used by collecting and analyzing massive amounts of data such as vibration, temperature, power and others from thousands of wind turbines several times per second to predict and prevent failures. [16]

See also

Related Research Articles

<span class="mw-page-title-main">Maintenance</span> Maintaining a device in working condition

The technical meaning of maintenance involves functional checks, servicing, repairing or replacing of necessary devices, equipment, machinery, building infrastructure and supporting utilities in industrial, business, and residential installations. Over time, this has come to include multiple wordings that describe various cost-effective practices to keep equipment operational; these activities occur either before or after a failure.

<span class="mw-page-title-main">FADEC</span> Computer used for engine control in aerospace engineering

A full authority digital enginecontrol (FADEC) is a system consisting of a digital computer, called an "electronic engine controller" (EEC) or "engine control unit" (ECU), and its related accessories that control all aspects of aircraft engine performance. FADECs have been produced for both piston engines and jet engines.

Prognostics is an engineering discipline focused on predicting the time at which a system or a component will no longer perform its intended function. This lack of performance is most often a failure beyond which the system can no longer be used to meet desired performance. The predicted time then becomes the remaining useful life (RUL), which is an important concept in decision making for contingency mitigation. Prognostics predicts the future performance of a component by assessing the extent of deviation or degradation of a system from its expected normal operating conditions. The science of prognostics is based on the analysis of failure modes, detection of early signs of wear and aging, and fault conditions. An effective prognostics solution is implemented when there is sound knowledge of the failure mechanisms that are likely to cause the degradations leading to eventual failures in the system. It is therefore necessary to have initial information on the possible failures in a product. Such knowledge is important to identify the system parameters that are to be monitored. Potential uses for prognostics is in condition-based maintenance. The discipline that links studies of failure mechanisms to system lifecycle management is often referred to as prognostics and health management (PHM), sometimes also system health management (SHM) or—in transportation applications—vehicle health management (VHM) or engine health management (EHM). Technical approaches to building models in prognostics can be categorized broadly into data-driven approaches, model-based approaches, and hybrid approaches.

Condition monitoring is the process of monitoring a parameter of condition in machinery, in order to identify a significant change which is indicative of a developing fault. It is a major component of predictive maintenance. The use of condition monitoring allows maintenance to be scheduled, or other actions to be taken to prevent consequential damages and avoid its consequences. Condition monitoring has a unique benefit in that conditions that would shorten normal lifespan can be addressed before they develop into a major failure. Condition monitoring techniques are normally used on rotating equipment, auxiliary systems and other machinery like belt-driven equipment,, while periodic inspection using non-destructive testing (NDT) techniques and fit for service (FFS) evaluation are used for static plant equipment such as steam boilers, piping and heat exchangers.

Blade pitch or simply pitch refers to the angle of a blade in a fluid. The term has applications in aeronautics, shipping, and other fields.

<span class="mw-page-title-main">Predictive maintenance</span> Method to predict when equipment should be maintained

Predictive maintenance techniques are designed to help determine the condition of in-service equipment in order to estimate when maintenance should be performed. This approach claims more cost savings over routine or time-based preventive maintenance, because tasks are performed only when warranted. Thus, it is regarded as condition-based maintenance carried out as suggested by estimations of the degradation state of an item.

Machine to machine (M2M) is direct communication between devices using any communications channel, including wired and wireless. Machine to machine communication can include industrial instrumentation, enabling a sensor or meter to communicate the information it records to application software that can use it. Such communication was originally accomplished by having a remote network of machines relay information back to a central hub for analysis, which would then be rerouted into a system like a personal computer.

<span class="mw-page-title-main">Balancing machine</span> Measuring tool used for balancing rotating machine parts

A balancing machine is a measuring tool used for balancing rotating machine parts such as rotors for electric motors, fans, turbines, disc brakes, disc drives, propellers and pumps. The machine usually consists of two rigid pedestals, with suspension and bearings on top supporting a mounting platform. The unit under test is bolted to the platform and is rotated either with a belt-, air-, or end-drive. As the part is rotated, the vibration in the suspension is detected with sensors and that information is used to determine the amount of unbalance in the part. Along with phase information, the machine can determine how much and where to add or remove weights to balance the part.

Rotordynamics is a specialized branch of applied mechanics concerned with the behavior and diagnosis of rotating structures. It is commonly used to analyze the behavior of structures ranging from jet engines and steam turbines to auto engines and computer disk storage. At its most basic level, rotor dynamics is concerned with one or more mechanical structures (rotors) supported by bearings and influenced by internal phenomena that rotate around a single axis. The supporting structure is called a stator. As the speed of rotation increases the amplitude of vibration often passes through a maximum that is called a critical speed. This amplitude is commonly excited by imbalance of the rotating structure; everyday examples include engine balance and tire balance. If the amplitude of vibration at these critical speeds is excessive, then catastrophic failure occurs. In addition to this, turbomachinery often develop instabilities which are related to the internal makeup of turbomachinery, and which must be corrected. This is the chief concern of engineers who design large rotors.

<span class="mw-page-title-main">Modal analysis</span> Study of vibration properties of systems

Modal analysis is the study of the dynamic properties of systems in the frequency domain. It consists of mechanically exciting a studied component in such a way to target the modeshapes of the structure, and recording the vibration data with a network of sensors. Examples would include measuring the vibration of a car's body when it is attached to a shaker, or the noise pattern in a room when excited by a loudspeaker.

A blade inspection method is the practice of monitoring the condition of a blade, such as a helicopter's rotor blade, for deterioration or damage. A common area of focus in the aviation industry has been the detection of cracking, which is commonly associated with fatigue. Automated blade condition monitoring technology has been developed for helicopters and has seen widespread adoption. The technique is routinely mandated by airworthiness authorities for engine inspections. Another commercial sector where such monitoring has become important is electricity generation, particularly on wind farms.

The term downtime is used to refer to periods when a system is unavailable. The unavailability is the proportion of a time-span that a system is unavailable or offline. This is usually a result of the system failing to function because of an unplanned event, or because of routine maintenance.

<span class="mw-page-title-main">Wind turbine design</span> Process of defining the form of wind turbine systems

Wind turbine design is the process of defining the form and configuration of a wind turbine to extract energy from the wind. An installation consists of the systems needed to capture the wind's energy, point the turbine into the wind, convert mechanical rotation into electrical power, and other systems to start, stop, and control the turbine.

Specialized wind energy software applications aid in the development and operation of wind farms.

ATA 100 contains the reference to the ATA numbering system which is a common referencing standard for commercial aircraft documentation. This commonality permits greater ease of learning and understanding for pilots, aircraft maintenance technicians, and engineers alike. The standard numbering system was published by the Air Transport Association on June 1, 1956. While the ATA 100 numbering system has been superseded, it continued to be widely used until it went out of date in 2015, especially in documentation for general aviation aircraft, on aircraft Fault Messages and the electronic and printed manuals.

Pipeline leak detection is used to determine if a leak has occurred in systems which contain liquids and gases. Methods of detection include hydrostatic testing, tracer-gas leak testing, infrared, laser technology, and acoustic or sonar technologies. Some technologies are used only during initial pipeline installation and commissioning, while other technologies can be used for continuous monitoring during service.

Fault detection, isolation, and recovery (FDIR) is a subfield of control engineering which concerns itself with monitoring a system, identifying when a fault has occurred, and pinpointing the type of fault and its location. Two approaches can be distinguished: A direct pattern recognition of sensor readings that indicate a fault and an analysis of the discrepancy between the sensor readings and expected values, derived from some model. In the latter case, it is typical that a fault is said to be detected if the discrepancy or residual goes above a certain threshold. It is then the task of fault isolation to categorize the type of fault and its location in the machinery. Fault detection and isolation (FDI) techniques can be broadly classified into two categories. These include model-based FDI and signal processing based FDI.

Integrated vehicle health management (IVHM) or integrated system health management (ISHM) is the unified capability of systems to assess the current or future state of the member system health and integrate that picture of system health within a framework of available resources and operational demand.

An intelligent maintenance system (IMS) is a system that uses collected data from machinery in order to predict and prevent potential failures in them. The occurrence of failures in machinery can be costly and even catastrophic. In order to avoid failures, there needs to be a system which analyzes the behavior of the machine and provides alarms and instructions for preventive maintenance. Analyzing the behavior of the machines has become possible by means of advanced sensors, data collection systems, data storage/transfer capabilities and data analysis tools. These are the same set of tools developed for prognostics. The aggregation of data collection, storage, transformation, analysis and decision making for smart maintenance is called an intelligent maintenance system (IMS).

<span class="mw-page-title-main">Vertical-axis wind turbine</span> Type of wind turbine

A vertical-axis wind turbine (VAWT) is a type of wind turbine where the main rotor shaft is set transverse to the wind while the main components are located at the base of the turbine. This arrangement allows the generator and gearbox to be located close to the ground, facilitating service and repair. VAWTs do not need to be pointed into the wind, which removes the need for wind-sensing and orientation mechanisms. Major drawbacks for the early designs included the significant torque ripple during each revolution, and the large bending moments on the blades. Later designs addressed the torque ripple by sweeping the blades helically. Savonius vertical-axis wind turbines (VAWT) are not widespread, but their simplicity and better performance in disturbed flow-fields, compared to small horizontal-axis wind turbines (HAWT) make them a good alternative for distributed generation devices in an urban environment.

References

  1. "DNV certification guidelines". DNV GL. 2010.
  2. "Why wind-turbine gearboxes fail to hit the 20-year mark". Windpower Engineering & Development. Retrieved 2020-02-19.
  3. "Next-Generation Wind Technology". Energy.gov. Retrieved 2020-02-19.
  4. "Wind Turbine Failures Encyclopedia". ONYX Insight. Retrieved 2020-02-19.
  5. "Reducing complexity in Wind Turbine Maintenance". ONYX Insight. 2019-06-24.
  6. Yang, Wenxian (1 August 2012). "Wind turbine condition monitoring: technical and commercial challenges". Wind Energy. 17 (5): 673–693. doi:10.1002/we.1508.
  7. Liu, Huan (26 September 2024). "Wind turbine generator failure analysis and fault diagnosis: A review". IET Renewable Power Generation. 18 (15): 3127–3148. doi: 10.1049/rpg2.13104 .
  8. "Mitigating Risks of Wind Turbine Blade Failures: Matching Detection Methods to Failure Modes". 25 March 2024.
  9. "Defect Types and Mechanism of Wind Turbine Blades".
  10. Rachidi, Frahad (May 2008). "A Review of Current Issues in Lightning Protection of New-Generation Wind-Turbine Blades". IEEE Transactions on Industrial Electronics. 55 (5): 2489–2496. doi:10.1109/TIE.2007.896443.
  11. Greco, A. (11 February 2013). "Material wear and fatigue in wind turbine Systems". Wear. 302 (1–2): 1583–1591. doi:10.1016/j.wear.2013.01.060.
  12. "Premature bearing failures in wind gearboxes and white etching cracks (WEC)". Bearing-NEWS. 31 March 2013.
  13. ORE Catapult (UK). "Wind Turbine Condition Monitoring Methods" (PDF). ORE Catapult.
  14. García Márquez, Fausto Pedro; Tobias, Andrew Mark; Pinar Pérez, Jesús María; Papaelias, Mayorkinos (2012-10-01). "Condition monitoring of wind turbines: Techniques and methods". Renewable Energy. 46: 169–178. Bibcode:2012REne...46..169G. doi:10.1016/j.renene.2012.03.003. ISSN   0960-1481.
  15. "The unique advantages of ecoCMS – cutting edge sensor technology enabling real advances in condition monitoring". ONYX Insight. 2021-04-28. Retrieved 2024-08-13.
  16. "Neurale netværk kan forudsige, hvornår møllens tandhjul knækker". Version2/Ingeniøren . 2016-11-19. Retrieved 19 November 2016.