WO2011143531A2 - Turbine-to-turbine prognostics technique for wind farms - Google Patents
Turbine-to-turbine prognostics technique for wind farms Download PDFInfo
- Publication number
- WO2011143531A2 WO2011143531A2 PCT/US2011/036402 US2011036402W WO2011143531A2 WO 2011143531 A2 WO2011143531 A2 WO 2011143531A2 US 2011036402 W US2011036402 W US 2011036402W WO 2011143531 A2 WO2011143531 A2 WO 2011143531A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- wind turbines
- wind turbine
- wind
- performance metrics
- component
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 71
- 230000007613 environmental effect Effects 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 7
- 230000036541 health Effects 0.000 claims description 20
- 238000012423 maintenance Methods 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 239000000203 mixture Substances 0.000 claims description 13
- 230000002596 correlated effect Effects 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 7
- 230000007547 defect Effects 0.000 claims description 4
- 238000010248 power generation Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 claims description 2
- 238000007477 logistic regression Methods 0.000 claims description 2
- 238000000691 measurement method Methods 0.000 claims description 2
- 238000003909 pattern recognition Methods 0.000 claims description 2
- 238000000513 principal component analysis Methods 0.000 claims description 2
- 230000000306 recurrent effect Effects 0.000 claims description 2
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 239000013598 vector Substances 0.000 description 20
- 210000002569 neuron Anatomy 0.000 description 18
- 230000015556 catabolic process Effects 0.000 description 12
- 238000006731 degradation reaction Methods 0.000 description 12
- 238000009826 distribution Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 7
- 230000008439 repair process Effects 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 238000013459 approach Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 239000000306 component Substances 0.000 description 2
- 230000000875 corresponding effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000004615 ingredient Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 238000005096 rolling process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 241000932075 Priacanthus hamrur Species 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000004931 aggregating effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000000135 prohibitive effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 229910000679 solder Inorganic materials 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000009897 systematic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/80—Diagnostics
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F05—INDEXING SCHEMES RELATING TO ENGINES OR PUMPS IN VARIOUS SUBCLASSES OF CLASSES F01-F04
- F05B—INDEXING SCHEME RELATING TO WIND, SPRING, WEIGHT, INERTIA OR LIKE MOTORS, TO MACHINES OR ENGINES FOR LIQUIDS COVERED BY SUBCLASSES F03B, F03D AND F03G
- F05B2260/00—Function
- F05B2260/82—Forecasts
- F05B2260/821—Parameter estimation or prediction
Definitions
- the present disclosure is generally directed to systems for managing maintenance of wind turbine farms.
- Wind turbines are used nearly continuously to generate energy by harnessing the wind. Often times, wind turbines are placed in remote locations and typically operate without intervention from local personnel. Additionally, because wind turbines are often subjected to varied and dynamic environmental conditions (e.g., varied wind speeds, temperature, moisture, etc.), the components of the wind turbines are subject to a high amount of wear, which may not be easily monitored.
- a method for predicting an end of life of a wind turbine component wherein a processor transforms electronic data into a prognostic evaluation including receiving environmental conditions indicative of natural surroundings of wind turbines within a wind turbine farm and receiving component performance metrics indicative of an operation of wind turbines within a wind turbine farm. The method further includes distributing the wind turbines into peer-clusters such that the wind turbines within each of the peer-clusters have similar environmental conditions, and identifying a low performing wind turbine and a remaining portion of wind turbines within one of the peer-clusters based upon a predicted performance model.
- the method further includes processing the component performance metrics of the low performing wind turbine and the remaining portion of wind turbines to extract fault condition indicators that correlate the component performance metrics to failure modes, identifying a critical component of the low performing wind turbine by contrasting the fault condition indicators of the low performing wind turbine with the remaining portion, and predicting the end of life of the critical component of the low performing wind turbine based upon the component performance metrics of the remaining portion of wind turbines.
- a system for predicting an end of life of a wind turbine component including a processor for executing machine readable instructions electronically coupled to an electronic memory for storing the machine readable instructions, a wind turbine farm comprising wind turbines for generating energy from wind, environmental sensors located proximate to each of the wind turbines for detecting environmental conditions surrounding the wind turbines, and performance sensors located proximate to each of the wind turbines for detecting performance metrics correlated with the wind turbines.
- the processor is supplied with data from the environmental sensors and the performance sensors and executes the machine readable instructions to distribute the wind turbines into peer-clusters according to similarities in the environmental conditions and distinguish a low performing wind turbine from a remaining portion of the wind turbines within one of the peer-clusters based upon the performance metrics.
- the wind turbine farm further includes gearbox sensors located proximate to each of the gearboxes for detecting gearbox performance metrics correlated with the wind turbines and a processor for executing machine readable instructions.
- the processor is supplied with data from the environmental sensors, the performance sensors, and the gearbox sensors and executes the machine readable instructions to distribute the wind turbines into peer-clusters according to similarities in the environmental conditions, distinguish a low performing wind turbine from a remaining portion of the wind turbines within one of the peer-clusters based upon the performance metrics, and predict an end of life of the gearbox from the low performing wind turbine according to differences in the gearbox performance metrics.
- FIG. 1 depicts a schematic representation of a wind turbine farm according to one or more embodiments shown and described herein;
- FIG. 2 depicts a schematic representation of a wind turbine according to one or more embodiments shown and described herein;
- FIG. 3 depicts a schematic cross-sectional representation of a wind turbine according to one or more embodiments shown and described herein;
- FIG. 4 depicts a schematic representation of a wind turbine farm according to one or more embodiments shown and described herein;
- FIG. 5 depicts a schematic representation of a method for evaluating wind turbine performance according to one or more embodiments shown and described herein;
- FIG. 6 depicts a schematic representation of the method for evaluating wind turbine performance according to FIG. 5;
- FIG. 7 depicts a schematic representation of the method for evaluating wind turbine performance according to FIG. 5.
- FIG. 8 depicts a schematic representation of the method for evaluating wind turbine performance according to FIG. 5.
- Embodiments of the present disclosure are directed to methods and systems for predicting an end of life of a wind turbine component.
- the methods analyze data provided by sensors located at the wind turbines or which sense data indicative of wind turbines.
- Raw input data from the sensors may be introduced to a supervisory control and data acquisition (SCADA) of a wind turbine.
- SCADA supervisory control and data acquisition
- the SCADA then may output the sensor data for external monitoring.
- the wind turbines may be arranged into peer- clusters based on the environmental conditions in which each of the wind turbines are operating.
- the low performing wind turbines within the peer-clusters are identified, and sensors monitoring the components of the wind turbines are analyzed to identify the critical components to which poor performance can be attributed.
- An estimation of expected life of the critical components may be made based on a physics-based model of an individual wind turbine.
- the methods of the present disclosure allow for the identification of critical components that are operating below optimal performance and a prediction of the end of life of those critical components, while not requiring development of a physics-based model to evaluate the entirety of the wind turbine farm.
- the system 100 may include an electronic control unit 108 that monitors and/or controls operation of at least one wind turbine 210 arranged in a wind turbine farm 200.
- the electronic control unit 108 comprises a processor 110 for executing machine readable instructions and is electrically coupled to an electronic memory 120 for storing machine readable instructions.
- the electronic control unit 108 is in electrical communication with the processor 110 and the electronic memory 120.
- the processor 110 may be an integrated circuit, a microchip, a computer, or any other computing device capable of executing machine readable instructions.
- the electronic memory 120 may be RAM, ROM, a flash memory, a hard drive, or any device capable of storing machine readable instructions.
- the processor 110 and the electronic memory 120 may be integral with the electronic control unit 108.
- the electronic control unit 108, the processor 110, and the electronic memory 120 may be discrete components in electrical communication with one another without departing from the scope of the present disclosure.
- the phrase "in electrical communication” means that the components are capable of transmitting electrical or electromagnetic signals with one another via a conductive medium such as for example, terminal blocks, posts, solder joints, integrated circuit traces, wires, and the like.
- the processor 110 and/or the electronic memory 120 may be electronically coupled to a plurality of sensors originating from wind turbines 210.
- Each of the wind turbines 210 are provided with environmental sensors 220, performance sensors 230, and component sensors 240 arranged along the wind turbines 210 or in close proximity to the wind turbines 210.
- the environmental sensors 220, the performance sensors 230, and the component sensors 240 are generally used in regular operation of the wind turbines 210, and input signals to a SCADA 300.
- the SCADA 300 monitors and controls the wind turbines 210 during operation.
- the SCADA 300 may include control logic that allows the SCADA 300 to adjust the wind turbine 210 to manage power generation of the wind turbines 210 at various environmental conditions.
- data may be collected by the SCADA 300 and sent to an offline computer or a networked computer for processing according to the techniques described in the present disclosure.
- the wind turbines 210 themselves may generally include a plurality of blades 213 having an airfoil shape.
- the blades 213 are mounted within a hub 214, which rotates about a nacelle 215.
- the nacelle 215 may rotate to position the blades 213 such that the blades 213 face towards the direction of wind (i.e., yaw the position of the blades 213).
- the blades 213 may include a feathering mechanism that changes the angle of pitch of the blades 213 relative to the direction of wind. The pitch of the blades 213 may be controlled to maximize power extraction by the blades 213 from the wind.
- the pitch of the blades 213 may be moved away from an angle that maximizes power extraction in cases of high wind speeds to protect the various components of the wind turbine 210.
- Orientation of the nacelle 215 and the pitch of the blades 213 may be controlled by the SCADA 300.
- the blades 213 and the hub 214 is coupled to a generator 221, located within the nacelle 215.
- the generator 221 includes a rotor element and a stator element (not shown). Rotation of the rotor element within the stator element of the generator 221 creates electrical energy.
- the hub 214 may be coupled to the generator 221 through a gearbox 218.
- the gearbox 218 may include a gear set that has gears with mating gear teeth. The gear set may increase the speed of rotation of the rotor element within the stator element, as compared to the speed of rotation of the blades 213 and the hub 214.
- the gearbox 218 may be coupled to the generator 221 through an intermediate shaft 219.
- the intermediate shaft transfers torque from the gearbox 218 to the generator 221, and may include torque transferring features, for example, a splined interface or a key and keyway interface.
- the hub 214 and therefore the blades 213, may extend away from the generator 221 and/or the gearbox 218 along a shaft 216.
- the shaft 216 be supported by one or more bearings 217 that allow rotation of the hub 214 and the generator 221 rotor element about the generator stator element, and/or maintain spacing of the rotor element and the stator element.
- the bearing 217 may be a rolling element bearing having an inner race, an outer race, and a plurality of rolling elements, for example balls, cylindrical rollers, tapered rollers, or spherical rollers, which are inserted between the inner race and the outer race.
- the environmental sensors 220 may measure characteristics of the environment surrounding the wind turbines 210, including, but not limited to, wind speed, wind direction, ambient temperature, barometric pressure, humidity, or a combination thereof.
- the performance sensors 230 may include sensors that measure the electrical power generated by the wind turbines 210.
- the component sensors 240 may measure status of the components of the wind turbines 210, and may include, but are not limited to, blade pitch measurement, blade yaw measurement, accelerometers, tachometers, thermocouples, oil pressure sensors, oil temperature sensors, or oil degradation sensor. Component sensors 240 that measure status of the components of the gearbox 218 may be classified as gearbox sensors.
- a plurality of wind turbines 210 may be arranged in geographic proximity to one another to form a wind turbine farm 200. By localizing a plurality of wind turbines 210 in one location, costs associated with infrastructure and maintenance may be controlled.
- the maximum power performance of a wind turbine 210 may be calculated using a procedure described in the International Electrotechnical Commission Standard 61400-12. Energy generation of the wind turbine 210 is measured across a series of wind speed bins. The realistic power expectation may be calculated using by evaluating the following formula: where R is the rotor radius of the wind turbine 210, p is the air density, V is the wind speed, and C p is the power coefficient, which is determined experimentally for each of the series of wind speed bins.
- the power generated by a wind turbine 210 may therefore be compared with the realistic power expectation formula to determine if the wind turbine 210 is performing according to the expectation, or if the wind turbine 210 is performing below expectation.
- the power coefficient, and therefore the realistic power expectation may vary due to a variety of causes, including age, condition, and manufacturing variations of the hardware components of the wind turbines 210. Therefore, accurate calculation of the realistic power expectation for any one wind turbine 210 may require direct measurement of the power coefficient, which may be impractical or cost prohibitive, particularly for wind turbines 210 that are currently operated in the field.
- a wind turbine 210 located in a higher-velocity wind stream may have a higher rate of rotation than a wind turbine 210 located in a lower- velocity wind stream.
- the wind turbine 210 located in a higher-velocity wind stream may have higher oil temperatures, higher slip ring temperatures, and larger vibration as measured at the bearings 217 and the gearbox 218, if any.
- a wind turbine 210 operates at a rotational speed that corresponds with one of the natural frequencies of one of the components of the wind turbine 210
- the vibration as measured at the bearings 217 and the gearbox 218, if any may be larger than the vibration if the same wind turbine 210 were operated at a speed other than a speed corresponding to one of the natural frequencies of one of the components of the wind turbine 210.
- direct comparison between two wind turbines 210 operating in different environmental conditions may not provide the desired results.
- Steps in the analysis of wind turbines 210 according to the methods and systems of the present disclosure are depicted in FIGS. 5-8.
- the wind turbines 210 may be distributed into peer-clusters 212 in the steps of peer clustering 510.
- the system 100 of the present disclosure processes input data from the SCADA 300 of the wind turbines 210 to first distribute the wind turbines 210 into peer-clusters 212, such that the wind turbines 210 within each of the peer-clusters 212 have similar environmental conditions.
- the peer-clusters 212 may include wind turbines 210 that are arranged geographically independent from one another. Further, as depicted in FIG. 4, the peer-clusters 212 may overlap one another, as the environmental conditions that some wind turbines 210 experience may fall within one or more peer- cluster 212.
- the environmental conditions surrounding the wind turbines 210 are measured in the step evaluating environmental conditions 512.
- Environmental conditions evaluated may include, but are not limited to, wind speed, wind direction, temperature, barometric pressure, humidity, or a combination thereof.
- the wind turbines 210 are distributed into peer-clusters 212 in the step of group wind turbines 514 based on similar data provided by the environmental sensors 220.
- Each of the wind turbines 210 within a given peer-cluster 212 are denoted for later analysis in the step identifying peer- clusters 516
- the performance of each of the wind turbines 210 within each peer-cluster 212 may be processed through a performance assessment through steps of selection of the best unit 540, i.e., identifying the best performing wind turbine 210 in any peer-cluster 212.
- the power output and wind speed (e.g., when measured along a power curve) of the wind turbines 210 within the peer-cluster 212 may be collected and compared in the step of evaluate peer-clusters 542.
- the wind turbine 210 having the highest performance value within the peer-cluster 212 (as identified in the step of calculate highest performing wind turbine 544) is selected as the baseline wind turbine 210, to which other wind turbines 210 within the peer-cluster 212 may be compared.
- the wind turbines 210 having the low performance values within the peer-cluster 212 e.g., the lowest performing wind turbine 210 or a selection of low performing wind turbines 210) may be identified as low performing wind turbines 210, and may be targeted for maintenance.
- Data from the component sensors 240 of the highest performing wind turbine 210 within the peer-cluster 212 may be placed into electronic memory 120 of the electronic control unit 108 in a step of storing baseline unit weights 546. This data from the component sensors 240 may be compared to other wind turbines 210 within the peer-cluster 212.
- Each wind turbine 210 within the peer-cluster 212 may be assigned a performance value that corresponds to a predicted performance model for the wind turbines 210.
- the performance value of the wind turbine 210 may be a comparison of the actual power generated by the wind turbine 210 to a realistic power expectation calculated using the realistic power expectation formula using the actual environmental data and a generic power coefficient.
- the signals output from the performance sensors 230 of the wind turbines 210 may be used to calculate a component performance metric.
- wind turbines 210 are compared to their peer-cluster 212 in the steps of peer-to-peer comparison 570.
- step of compare wind turbine component performance metrics 572 component performance metrics may be assigned to the components of the low performing wind turbines 210 based on data gathered from the component sensors 240. These component performance metrics may compare the data gathered from the component sensors 240 of the low performing wind turbines 210 to the data gathered from the component sensors 240 of the highest performing wind turbine 210 within the peer-cluster 212. Further, the comparison of the component performance metrics may allow the step of compute health estimate 574, which may provide an analytical tool to monitor and evaluate the energy generation performance of each of the wind turbines 210, and calculate a probability of defect of a component.
- the steps of peer-to-peer comparison 570 may allow for the implementation of an analytical tool that assists with scheduling of maintenance procedures.
- wind turbines 210 that require repair may be taken off line from generating power for an extended period of time, as the costs of performing the required repairs may exceed the revenue that may be generated had the wind turbine 210 been operating.
- the systems and methods of the current disclosure may include an algorithm that assists an operator with making a decision whether to initiate a repair and incur the associated costs, or if waiting to perform a repair operation would be more cost effective.
- Such an algorithm may predict a cost of not performing the maintenance procedure (i.e., lost revenue) and compare it with a predicted cost of performing the maintenance procedure. Additionally, if the operator of a wind turbine farm 200 elects to perform the maintenance procedure, the systems and methods of the current disclosure may be used to assist the operator with identifying wind turbines 210 that are likely to need maintenance in the future. Performing maintenance operations on multiple wind turbines 210 within a wind turbine farm 200 at the same time may reduce the overhead costs of operating the wind turbine farm 200.
- Data from the environmental sensors 220, the performance sensors 230, and the component sensors 240 may be processed by the electronic control unit 108 using a variety of commonly available methods.
- the signals from the sensors may be processed using a time domain analysis, a frequency domain analysis, a time-frequency analysis, a wavelet/wavelet packet analysis, a principal component analysis, and the like.
- the signals obtained from the sensors may be processed to form a performance prediction, a health assessment model, and a health diagnosis.
- a performance prediction may assign a value to each individual wind turbine 210 that represents the power generating capacity of the wind turbine 210 to the highest performing wind turbine 210.
- a performance prediction analysis may be conducted using, for example, an autoregressive moving average, an Elman recurrent neural network, fuzzy logic, a match matrix, and the like.
- a health assessment may assign a value to components of the wind turbine 210 that are measured by the component sensors 240. A low value assigned in the health assessment may indicate maintenance is due.
- a health assessment may be conducted using, for example, logistic regression, statistical pattern recognition, feature map pattern matching (for example, Self- Organizing map), a neural network, a Gaussian Mixture Model, and the like.
- a health diagnosis may evaluate the data provided by the component sensors 240 of a low performing wind turbine 210 to establish which of the components within the wind turbine 210 are responsible for the poor performance.
- a health diagnosis may be conducted using, for example, a support vector machine, a feature map pattern matching (for example, Self-Organized Maps), a Bayesian Belief Network (BBN), a Hidden Markov Model (HMM), and the like.
- Some or all of these analysis models may be commercially available, for example, in MATHWORKS MATLAB ® and associated Toolkits, or by any other analysis software.
- a SOM is a variant of a neural network technique, which are used to model complex relationships between inputs and outputs.
- neurons within the network represent known data points of known inputs and outputs. When a new data point becomes available, the new data point is placed "proximate" to the nearest neurons.
- Pre-existing nodes in the neural network may provide an estimation of the predicted output of a system based on a given input.
- the term "self-organizing” refers to the ability of the SOM to learn and organize information without being giving the corresponding class labels. SOM learns the nature of the input training data and organizes the neurons with similar feature values next to each other on the map.
- a best matching unit BMU
- the distance between the new input and the BMU may be used to assess the performance of the wind turbine 210.
- a large distance value means that the new input is highly dissimilar from the trained baseline; a small distance value indicates the new input is close or similar to the baseline.
- An input vector x of n dimension is defined as:
- the BMU is the neuron whose weight vector has the smallest distance measure from the input vector.
- the simplest distance measure is the Euclidean distance.
- the square root of the inner product of x T ⁇ 5 can be used to measure the distance between x and ⁇ ).
- the distance of the neuron weight is within a range of the neighborhood function, the value of h. is 1, which means that the weight of the neuron is to be updated.
- the value of h. is 0, which means that the weight of the & ⁇ , ⁇ b
- a typical choice of the neighborhood function is a Gaussian function.
- the weight updating process is repeatedly carried out if a preset stop criterion, for example, a maximum number of iteration steps and threshold of the change of network error, is met.
- the distance between the input vector and the weight of the BMU in a trained SOM structure may be used as a performance indicator to quantitatively measure the degradation status.
- the distance between the input vector and the weight of the BMU is defined as minimum quantization error (MQE):
- MQE b - co BMU where x is the input vector andiller T is the weight vector of BMU.
- normal operating conditions of the wind turbine 210 may be used to train a SOM structure as a baseline. Data obtained later can be used as input to the trained SOM structure. With all of the MQE values, the deviation of the input vector from the baseline may be evaluated and used as the performance indicator. If the input vector is close to the baseline, the MQE value is small. Otherwise, a large MQE value indicates a large deviation from the baseline, which may mean a degradation or abnormal situation has happened. Using this method, the multi-dimensional feature space is converted to a distance measure value (MQE) indicating the degradation status.
- MQE distance measure value
- GMM Gaussian Mixture Model
- One method to estimate the parameters of a GMM is the expectation maximization (EM) algorithm. Determining the GMM starts with clustering; the k-mean method may be utilized to determine the center of each GMM component. The clusters, which are candidate mixtures, are then solved with their mixture weights, p . , and the distribution parameters ( ⁇ . , ⁇ . ) using the EM technique.
- EM expectation maximization
- the EM algorithm is a two-step approach: expectation and maximization.
- expectation step initial guesses for the parameters are made and then the "partial membership" of each data point in each of the clusters is calculated.
- maximization step the component weight and distribution parameters are iteratively computed until the model converges.
- BIC Bayesian Information Criterion
- AIC Akaike Information Criterion
- the appropriate distance measurement techniques may also be defined for two distributions.
- CV health confidence value
- L2 distance is a comparison (i.e., a distance) between the recent behavior distribution with a known normal behavior distribution
- the degree of similarity or the overlap between two Gaussian mixtures may be numerically obtained using L2 distance.
- the computed value is normalized between 0 and 1, where the lower CV represents a larger distance between the two distributions and lower health status, or a degraded equipment performance condition.
- an Artificial Neural Network also called parallel distribution processing systems
- Neural networks consist of simple neurons arranged in a structured and systematic manner. Each neuron is a processing unit that weights its inputs, sums the weighted inputs, adds a bias to the calculation, and processes the input in a transfer function.
- a neural network may consist of several neurons in one or more layers.
- a neural network can also be configured to me multi- input and/or multi- output.
- the weight matrix constructs a relationship between the input and output vectors.
- the process of finding the optimum values for the weight matrix is called the training phase, where the error function is minimized. Updating the weight values are based on the network feedback, i.e., the difference between the target and the network output.
- the feed-forward back- propagation neural network may be suited for this application. For example, a network having two layers where the first layer has ⁇ neurons and the second layer has N2 neurons, the weight matrix may be set up as an ⁇ ⁇ 2 matrix.
- the weight value for the ith input of the jth neuron ma then be updated according to:
- E(n) is the difference between the target and the network output for the nth input
- ⁇ is the learning rate, which controls the amount of change in the weights in each epoch, and is called the momentum constant, which may be set to avoid being trapped in local minima.
- degradation assessment may then be implemented by comparing the computed output with the actual measured equipment output. The difference between the two may be referred to as a "residue.”
- the residual values should be small, approaching 0. If the equipment performance begins to degrade, the residues may increase in magnitude. This is an indirect technique demonstrating how neural networks may be used in fault detection or health assessment if actual failure modes cannot be directly modeled due to a lack of data during the conditions.
- a method may be used to minimize erratic results due to only a localized portion of the regime support being affected by degradation. Instead of computing the health value for each sample, the data is segmented to an acceptable, discrete time period, the duration of which depends on the frequency with which the performance assessment results are to be evaluated. For each segment, the residues r are computed using a traditional approach, but the CV ⁇ is computed according to the following equation:
- the degradation of a wind turbine 210 and its components are indicated by the excess of certain features or combination of features over a prescribed threshold.
- Features may be extracted from sensor measurement and control signal.
- the change of a power output profile over a wind speed spectrum may indicate the power generation capability degradation of a wind turbine 210 as a whole.
- the increase of vibration level or temperature reading for a component for example the gearbox 218 or the hub support bearings 217, may imply that the component may be developing a mechanical defect.
- Each wind turbine 210 in the wind turbine farm 200 has three attached vectors: where O(r. j is the v-dimensional vector associated with the performance variable of the wind turbines 210; w(r. j is the ⁇ -dimensional vector associated with the different environmental conditions of the wind turbines 210; and E(r. j is the w-dimensional vector consisting of the features of the wind turbines 210 that are indicative of component performance degradation.
- Peer-clusters 212 may be formed by comparing the environmental condition described by for one of the
- the highest performing wind turbines 210 within a peer-cluster 212 are selected for establishing a baseline to which other wind turbines 210 within the peer-cluster 212 may be compared.
- the highest performing wind turbine 210 may represent the difference between actual power produced by the wind turbine 210 and the realistic power expectation based on the environmental conditions.
- the highest performing wind turbine 210 has the smallest performance variable stored in O(r. j. Therefore, the highest performing wind turbine 210 in each peer-cluster c r will be identifiable, and is denoted as r, concern r .
- the / h*,f f highest performance wind turbine 210 may be compared to other wind turbines 210 using a distance measure D, . .
- a normalized L2 distance metric may be used to bound I D e ⁇ , ⁇
- each peer-cluster c has a small subgroup of higher performing wind turbines 210 that may be used to create the peer-cluster baseline:
- Dynamic environmental conditions prevent the use of pre-constructed performance degradation assessment models.
- use of local modeling known as lazy or just-in-time learning, to utilize the most recent data provided by the SCADA 300 to create a degradation assessment model.
- Each peer-cluster c j. constructs its own model M f , which are a collection of individual models based on each peer-cluster baseline unit in c . , . , as identified above.
- the peer-cluster modules use features for training the vector indicative of performance degradation,
- the health value of each peer wind turbine 210, CV ⁇ j. is then computed by using a locally weighted averaging method using the similarity weights, ⁇ ⁇ , that were discussed above:
- the disclosed method aims to address wind turbine 210 condition monitoring when there are multiple environmental conditions.
- a multiple modeling approach may be used to decompose the component performance metric distribution into a mixture of Gaussians.
- q. represents the class weights of the training set for each baseline peer
- a represents the number of working regimes for that baseline peer
- the expression is a component probability distribution.
- M r may be generated for each r, . in each cluster c r :
- the health, V ⁇ j. may be estimated for each wind turbine 210 within the peer cluster by using a similar locally weighted averaging method that applies the similarity weight, ⁇ ⁇ , to individually computed health values when each baseline wind turbine 210 is compared to a peer wind turbine 210 using L2 distance between the
- turbine-to-turbine prognostics techniques as described hereinabove may allow for monitoring the performance and health of a wind turbine using data readily available from SCAD As that are on-board the wind turbines.
- the systems and methods described herein allow for wind turbines operating at similar environmental conditions at a wind farm to be compared with one another to determine if and when any of the wind turbines require maintenance.
- the improved ability to monitor performance of the wind turbines may decrease downtime, may target preventative maintenance to those wind turbines requiring repair, and may reduce the need for unnecessary repairs.
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Educational Administration (AREA)
- General Health & Medical Sciences (AREA)
- Wind Motors (AREA)
Abstract
Methods and systems for predicting an end of life of a wind turbine component including receiving environmental conditions indicative of natural surroundings of wind turbines within a wind turbine farm, receiving component performance metrics indicative of an operation of wind turbines within a wind turbine farm, and distributing the wind turbines into peer-clusters such that the wind turbines within each of the peer-clusters have similar environmental conditions. The methods and systems further include identifying a low performing wind turbine and a remaining portion of wind turbines within one of the peer-clusters based upon a predicted performance model, processing the component performance metrics of the low performing wind turbine, identifying a critical component of the low performing wind turbine and predicting the end of life of the critical component of the low performing wind turbine.
Description
TURBINE-TO-TURBINE PROGNOSTICS TECHNIQUE FOR WIND FARMS
The present application claims the benefit of U.S. Provisional Application Serial No. 61/334,302, titled "Turbine-to-Turbine Prognostic Technique for Wind Farms" filed May 13, 2010.
The present disclosure is generally directed to systems for managing maintenance of wind turbine farms.
Wind turbines are used nearly continuously to generate energy by harnessing the wind. Often times, wind turbines are placed in remote locations and typically operate without intervention from local personnel. Additionally, because wind turbines are often subjected to varied and dynamic environmental conditions (e.g., varied wind speeds, temperature, moisture, etc.), the components of the wind turbines are subject to a high amount of wear, which may not be easily monitored.
To ensure the reliability of wind turbines in a wind turbine farm and, therefore, to maintain a high availability rate of the turbines and low operational and maintenance costs, predictive maintenance techniques that monitor and evaluate the performance of wind turbines may be used to forecast the health of the wind turbines themselves. However, variable such as geographic position and hardware modifications may prevent the direct comparison of wind turbines at a wind turbine farm. Accordingly, alternative systems for managing maintenance of wind turbine farms may be desired.
In one embodiment, a method for predicting an end of life of a wind turbine component wherein a processor transforms electronic data into a prognostic evaluation including receiving environmental conditions indicative of natural surroundings of wind turbines within a wind turbine farm and receiving component performance metrics indicative of an operation of wind turbines within a wind turbine farm. The method further includes distributing the wind turbines into peer-clusters such that the wind turbines within each of the peer-clusters have similar environmental conditions, and identifying a low performing wind turbine and a remaining portion of wind turbines within one of the peer-clusters based upon a predicted performance model. The method further includes processing the component performance metrics of the low performing wind turbine and the remaining portion of wind turbines to extract fault condition
indicators that correlate the component performance metrics to failure modes, identifying a critical component of the low performing wind turbine by contrasting the fault condition indicators of the low performing wind turbine with the remaining portion, and predicting the end of life of the critical component of the low performing wind turbine based upon the component performance metrics of the remaining portion of wind turbines.
In another embodiment, a system for predicting an end of life of a wind turbine component including a processor for executing machine readable instructions electronically coupled to an electronic memory for storing the machine readable instructions, a wind turbine farm comprising wind turbines for generating energy from wind, environmental sensors located proximate to each of the wind turbines for detecting environmental conditions surrounding the wind turbines, and performance sensors located proximate to each of the wind turbines for detecting performance metrics correlated with the wind turbines. The processor is supplied with data from the environmental sensors and the performance sensors and executes the machine readable instructions to distribute the wind turbines into peer-clusters according to similarities in the environmental conditions and distinguish a low performing wind turbine from a remaining portion of the wind turbines within one of the peer-clusters based upon the performance metrics.
In yet another embodiment, a wind turbine farm that predicts an end of life of a wind turbine component includes a plurality of wind turbines, each wind turbine comprising a generator coupled to a blade by a gearbox for generating energy from wind, environmental sensors located proximate to each of the wind turbines for detecting environmental conditions surrounding the wind turbines, and performance sensors located proximate to each of the wind turbines for detecting performance metrics correlated with the wind turbines. The wind turbine farm further includes gearbox sensors located proximate to each of the gearboxes for detecting gearbox performance metrics correlated with the wind turbines and a processor for executing machine readable instructions. The processor is supplied with data from the environmental sensors, the performance sensors, and the gearbox sensors and executes the machine readable instructions to distribute the wind turbines into peer-clusters according to similarities in the environmental conditions, distinguish a low performing wind turbine from a
remaining portion of the wind turbines within one of the peer-clusters based upon the performance metrics, and predict an end of life of the gearbox from the low performing wind turbine according to differences in the gearbox performance metrics.
The following detailed description of specific embodiments of the present disclosure can be best understood when read in conjunction with the drawings enclosed herewith.
FIG. 1 depicts a schematic representation of a wind turbine farm according to one or more embodiments shown and described herein;
FIG. 2 depicts a schematic representation of a wind turbine according to one or more embodiments shown and described herein;
FIG. 3 depicts a schematic cross-sectional representation of a wind turbine according to one or more embodiments shown and described herein;
FIG. 4 depicts a schematic representation of a wind turbine farm according to one or more embodiments shown and described herein;
FIG. 5 depicts a schematic representation of a method for evaluating wind turbine performance according to one or more embodiments shown and described herein;
FIG. 6 depicts a schematic representation of the method for evaluating wind turbine performance according to FIG. 5;
FIG. 7 depicts a schematic representation of the method for evaluating wind turbine performance according to FIG. 5; and
FIG. 8 depicts a schematic representation of the method for evaluating wind turbine performance according to FIG. 5.
The embodiments set forth in the drawings are illustrative in nature and not intended to be limiting of the disclosure defined by the claims. Moreover, individual features of the drawings and disclosure will be more fully apparent and understood in view of the detailed description.
The following text sets forth a broad description of numerous different embodiments of the present disclosure. The description is to be construed as exemplary only and does not describe every possible embodiment since describing every possible embodiment would be impractical, if not impossible, and it will be understood that any feature, characteristic, component, composition, ingredient, product, step or methodology described herein can be deleted, combined with or substituted for, in whole
or part, any other feature, characteristic, component, composition, ingredient, product, step or methodology described herein. Numerous alternative embodiments could be implemented, using either current technology or technology developed after the filing date of this patent, which would still fall within the scope of the claims.
Embodiments of the present disclosure are directed to methods and systems for predicting an end of life of a wind turbine component. The methods analyze data provided by sensors located at the wind turbines or which sense data indicative of wind turbines. Raw input data from the sensors may be introduced to a supervisory control and data acquisition (SCADA) of a wind turbine. The SCADA then may output the sensor data for external monitoring. The wind turbines may be arranged into peer- clusters based on the environmental conditions in which each of the wind turbines are operating. The low performing wind turbines within the peer-clusters are identified, and sensors monitoring the components of the wind turbines are analyzed to identify the critical components to which poor performance can be attributed. An estimation of expected life of the critical components may be made based on a physics-based model of an individual wind turbine. The methods of the present disclosure allow for the identification of critical components that are operating below optimal performance and a prediction of the end of life of those critical components, while not requiring development of a physics-based model to evaluate the entirety of the wind turbine farm.
One embodiment of a system 100 for predicting the end of life of a wind turbine component is depicted in FIG. 1. The system 100 may include an electronic control unit 108 that monitors and/or controls operation of at least one wind turbine 210 arranged in a wind turbine farm 200. The electronic control unit 108 comprises a processor 110 for executing machine readable instructions and is electrically coupled to an electronic memory 120 for storing machine readable instructions. The electronic control unit 108 is in electrical communication with the processor 110 and the electronic memory 120. The processor 110 may be an integrated circuit, a microchip, a computer, or any other computing device capable of executing machine readable instructions. The electronic memory 120 may be RAM, ROM, a flash memory, a hard drive, or any device capable of storing machine readable instructions. In the embodiments described herein, the processor 110 and the electronic memory 120 may be integral with the electronic control unit 108. However, it is noted that the electronic control unit 108, the processor
110, and the electronic memory 120 may be discrete components in electrical communication with one another without departing from the scope of the present disclosure. As used herein, the phrase "in electrical communication" means that the components are capable of transmitting electrical or electromagnetic signals with one another via a conductive medium such as for example, terminal blocks, posts, solder joints, integrated circuit traces, wires, and the like.
The processor 110 and/or the electronic memory 120 may be electronically coupled to a plurality of sensors originating from wind turbines 210. Each of the wind turbines 210 are provided with environmental sensors 220, performance sensors 230, and component sensors 240 arranged along the wind turbines 210 or in close proximity to the wind turbines 210. The environmental sensors 220, the performance sensors 230, and the component sensors 240 are generally used in regular operation of the wind turbines 210, and input signals to a SCADA 300. The SCADA 300 monitors and controls the wind turbines 210 during operation. The SCADA 300 may include control logic that allows the SCADA 300 to adjust the wind turbine 210 to manage power generation of the wind turbines 210 at various environmental conditions. In an alternative or in addition, data may be collected by the SCADA 300 and sent to an offline computer or a networked computer for processing according to the techniques described in the present disclosure.
As depicted in FIG. 2, the wind turbines 210 themselves may generally include a plurality of blades 213 having an airfoil shape. In one embodiment, the blades 213 are mounted within a hub 214, which rotates about a nacelle 215. The nacelle 215 may rotate to position the blades 213 such that the blades 213 face towards the direction of wind (i.e., yaw the position of the blades 213). Additionally, the blades 213 may include a feathering mechanism that changes the angle of pitch of the blades 213 relative to the direction of wind. The pitch of the blades 213 may be controlled to maximize power extraction by the blades 213 from the wind. Additionally, the pitch of the blades 213 may be moved away from an angle that maximizes power extraction in cases of high wind speeds to protect the various components of the wind turbine 210. Orientation of the nacelle 215 and the pitch of the blades 213 may be controlled by the SCADA 300.
As schematically depicted in FIG. 3, the blades 213 and the hub 214 is coupled to a generator 221, located within the nacelle 215. The generator 221 includes a
rotor element and a stator element (not shown). Rotation of the rotor element within the stator element of the generator 221 creates electrical energy. The hub 214 may be coupled to the generator 221 through a gearbox 218. The gearbox 218 may include a gear set that has gears with mating gear teeth. The gear set may increase the speed of rotation of the rotor element within the stator element, as compared to the speed of rotation of the blades 213 and the hub 214. The gearbox 218 may be coupled to the generator 221 through an intermediate shaft 219. The intermediate shaft transfers torque from the gearbox 218 to the generator 221, and may include torque transferring features, for example, a splined interface or a key and keyway interface.
The hub 214, and therefore the blades 213, may extend away from the generator 221 and/or the gearbox 218 along a shaft 216. The shaft 216 be supported by one or more bearings 217 that allow rotation of the hub 214 and the generator 221 rotor element about the generator stator element, and/or maintain spacing of the rotor element and the stator element. The bearing 217 may be a rolling element bearing having an inner race, an outer race, and a plurality of rolling elements, for example balls, cylindrical rollers, tapered rollers, or spherical rollers, which are inserted between the inner race and the outer race.
The environmental sensors 220 may measure characteristics of the environment surrounding the wind turbines 210, including, but not limited to, wind speed, wind direction, ambient temperature, barometric pressure, humidity, or a combination thereof. The performance sensors 230 may include sensors that measure the electrical power generated by the wind turbines 210. The component sensors 240 may measure status of the components of the wind turbines 210, and may include, but are not limited to, blade pitch measurement, blade yaw measurement, accelerometers, tachometers, thermocouples, oil pressure sensors, oil temperature sensors, or oil degradation sensor. Component sensors 240 that measure status of the components of the gearbox 218 may be classified as gearbox sensors.
As depicted in FIG. 4, a plurality of wind turbines 210 may be arranged in geographic proximity to one another to form a wind turbine farm 200. By localizing a plurality of wind turbines 210 in one location, costs associated with infrastructure and maintenance may be controlled.
The maximum power performance of a wind turbine 210 may be calculated using a procedure described in the International Electrotechnical Commission Standard 61400-12. Energy generation of the wind turbine 210 is measured across a series of wind speed bins. The realistic power expectation may be calculated using by evaluating the following formula:
where R is the rotor radius of the wind turbine 210, p is the air density, V is the wind speed, and Cp is the power coefficient, which is determined experimentally for each of the series of wind speed bins. The power generated by a wind turbine 210 may therefore be compared with the realistic power expectation formula to determine if the wind turbine 210 is performing according to the expectation, or if the wind turbine 210 is performing below expectation. However, the power coefficient, and therefore the realistic power expectation, may vary due to a variety of causes, including age, condition, and manufacturing variations of the hardware components of the wind turbines 210. Therefore, accurate calculation of the realistic power expectation for any one wind turbine 210 may require direct measurement of the power coefficient, which may be impractical or cost prohibitive, particularly for wind turbines 210 that are currently operated in the field.
Further, it may not be practical to compare wind turbines 210 that are operating at different environmental conditions. For example, a wind turbine 210 located in a higher-velocity wind stream may have a higher rate of rotation than a wind turbine 210 located in a lower- velocity wind stream. As such, the wind turbine 210 located in a higher-velocity wind stream may have higher oil temperatures, higher slip ring temperatures, and larger vibration as measured at the bearings 217 and the gearbox 218, if any. Additionally, if a wind turbine 210 operates at a rotational speed that corresponds with one of the natural frequencies of one of the components of the wind turbine 210, the vibration as measured at the bearings 217 and the gearbox 218, if any, may be larger than the vibration if the same wind turbine 210 were operated at a speed other than a speed corresponding to one of the natural frequencies of one of the
components of the wind turbine 210. Thus, direct comparison between two wind turbines 210 operating in different environmental conditions may not provide the desired results.
Steps in the analysis of wind turbines 210 according to the methods and systems of the present disclosure are depicted in FIGS. 5-8. First, the wind turbines 210 may be distributed into peer-clusters 212 in the steps of peer clustering 510. Referring again to FIG. 1 and 4, the system 100 of the present disclosure processes input data from the SCADA 300 of the wind turbines 210 to first distribute the wind turbines 210 into peer-clusters 212, such that the wind turbines 210 within each of the peer-clusters 212 have similar environmental conditions. The peer-clusters 212 may include wind turbines 210 that are arranged geographically independent from one another. Further, as depicted in FIG. 4, the peer-clusters 212 may overlap one another, as the environmental conditions that some wind turbines 210 experience may fall within one or more peer- cluster 212.
Referring again to FIGS. 5-8, to distribute the wind turbines 210 into peer- clusters 212, the environmental conditions surrounding the wind turbines 210 are measured in the step evaluating environmental conditions 512. Environmental conditions evaluated may include, but are not limited to, wind speed, wind direction, temperature, barometric pressure, humidity, or a combination thereof. The wind turbines 210 are distributed into peer-clusters 212 in the step of group wind turbines 514 based on similar data provided by the environmental sensors 220. Each of the wind turbines 210 within a given peer-cluster 212 are denoted for later analysis in the step identifying peer- clusters 516
With the wind turbines 210 distributed into peer-clusters 212, the performance of each of the wind turbines 210 within each peer-cluster 212 may be processed through a performance assessment through steps of selection of the best unit 540, i.e., identifying the best performing wind turbine 210 in any peer-cluster 212. The power output and wind speed (e.g., when measured along a power curve) of the wind turbines 210 within the peer-cluster 212 may be collected and compared in the step of evaluate peer-clusters 542. The wind turbine 210 having the highest performance value within the peer-cluster 212 (as identified in the step of calculate highest performing wind turbine 544) is selected as the baseline wind turbine 210, to which other wind turbines 210 within the
peer-cluster 212 may be compared. The wind turbines 210 having the low performance values within the peer-cluster 212 (e.g., the lowest performing wind turbine 210 or a selection of low performing wind turbines 210) may be identified as low performing wind turbines 210, and may be targeted for maintenance. Data from the component sensors 240 of the highest performing wind turbine 210 within the peer-cluster 212 may be placed into electronic memory 120 of the electronic control unit 108 in a step of storing baseline unit weights 546. This data from the component sensors 240 may be compared to other wind turbines 210 within the peer-cluster 212.
Each wind turbine 210 within the peer-cluster 212 may be assigned a performance value that corresponds to a predicted performance model for the wind turbines 210. The performance value of the wind turbine 210 may be a comparison of the actual power generated by the wind turbine 210 to a realistic power expectation calculated using the realistic power expectation formula using the actual environmental data and a generic power coefficient. Thus, the signals output from the performance sensors 230 of the wind turbines 210 may be used to calculate a component performance metric.
In order to determine which of the components of the wind turbines 210 may need to be replaced or repaired in a subsequent maintenance operation, wind turbines 210 are compared to their peer-cluster 212 in the steps of peer-to-peer comparison 570. In the step of compare wind turbine component performance metrics 572, component performance metrics may be assigned to the components of the low performing wind turbines 210 based on data gathered from the component sensors 240. These component performance metrics may compare the data gathered from the component sensors 240 of the low performing wind turbines 210 to the data gathered from the component sensors 240 of the highest performing wind turbine 210 within the peer-cluster 212. Further, the comparison of the component performance metrics may allow the step of compute health estimate 574, which may provide an analytical tool to monitor and evaluate the energy generation performance of each of the wind turbines 210, and calculate a probability of defect of a component.
The steps of peer-to-peer comparison 570 may allow for the implementation of an analytical tool that assists with scheduling of maintenance procedures. In current wind turbine farm 200 implementations, wind turbines 210 that require repair may be
taken off line from generating power for an extended period of time, as the costs of performing the required repairs may exceed the revenue that may be generated had the wind turbine 210 been operating. As wind turbine farms 200 are located in further remote areas, this may become increasingly common. Accordingly, the systems and methods of the current disclosure may include an algorithm that assists an operator with making a decision whether to initiate a repair and incur the associated costs, or if waiting to perform a repair operation would be more cost effective. Such an algorithm may predict a cost of not performing the maintenance procedure (i.e., lost revenue) and compare it with a predicted cost of performing the maintenance procedure. Additionally, if the operator of a wind turbine farm 200 elects to perform the maintenance procedure, the systems and methods of the current disclosure may be used to assist the operator with identifying wind turbines 210 that are likely to need maintenance in the future. Performing maintenance operations on multiple wind turbines 210 within a wind turbine farm 200 at the same time may reduce the overhead costs of operating the wind turbine farm 200.
Data from the environmental sensors 220, the performance sensors 230, and the component sensors 240 may be processed by the electronic control unit 108 using a variety of commonly available methods. The signals from the sensors may be processed using a time domain analysis, a frequency domain analysis, a time-frequency analysis, a wavelet/wavelet packet analysis, a principal component analysis, and the like. The signals obtained from the sensors may be processed to form a performance prediction, a health assessment model, and a health diagnosis.
A performance prediction may assign a value to each individual wind turbine 210 that represents the power generating capacity of the wind turbine 210 to the highest performing wind turbine 210. A performance prediction analysis may be conducted using, for example, an autoregressive moving average, an Elman recurrent neural network, fuzzy logic, a match matrix, and the like. A health assessment may assign a value to components of the wind turbine 210 that are measured by the component sensors 240. A low value assigned in the health assessment may indicate maintenance is due. A health assessment may be conducted using, for example, logistic regression, statistical pattern recognition, feature map pattern matching (for example, Self- Organizing map), a neural network, a Gaussian Mixture Model, and the like. A health
diagnosis may evaluate the data provided by the component sensors 240 of a low performing wind turbine 210 to establish which of the components within the wind turbine 210 are responsible for the poor performance. A health diagnosis may be conducted using, for example, a support vector machine, a feature map pattern matching (for example, Self-Organized Maps), a Bayesian Belief Network (BBN), a Hidden Markov Model (HMM), and the like. Some or all of these analysis models may be commercially available, for example, in MATHWORKS MATLAB ® and associated Toolkits, or by any other analysis software.
Examples of analysis models that may be used to process the performance assessment as discussed above, including the use of a Self-Organizing Map (SOM), a Gaussian Mixture Model (GMM), or a Neural Network, will now be discussed in greater detail below. A SOM is a variant of a neural network technique, which are used to model complex relationships between inputs and outputs. Generally, neurons within the network represent known data points of known inputs and outputs. When a new data point becomes available, the new data point is placed "proximate" to the nearest neurons. Pre-existing nodes in the neural network may provide an estimation of the predicted output of a system based on a given input.
The term "self-organizing" refers to the ability of the SOM to learn and organize information without being giving the corresponding class labels. SOM learns the nature of the input training data and organizes the neurons with similar feature values next to each other on the map. When an SOM structure is trained using baseline data, a best matching unit (BMU) is located in the map when a new input is presented. The distance between the new input and the BMU may be used to assess the performance of the wind turbine 210. A large distance value means that the new input is highly dissimilar from the trained baseline; a small distance value indicates the new input is close or similar to the baseline.
Each neuron i in the SOM having m total neurons, has a weight vector denoted by:
ωί = [ωα , ωί2 ,..., ωίηΥ ,i = l,2,.
The BMU is the neuron whose weight vector has the smallest distance measure from the input vector. The simplest distance measure is the Euclidean distance.
Hence, the square root of the inner product of x T <5 can be used to measure the distance between x and ύ). . The BMU of the input vector can be denoted as ω , which meets ι c the following criterion: x— 0)„ mi inn{ x - co^. for all i = l,2,.
where | is the operator for calculating the distance between the input vector and the neuron. At each step of the SOM training process, the weights of the BMU or neurons in a predefined scope around the input vector are updated by the following equation: ω,.(ί + 1) =a,(t) + a(t)hi (0 (t)(x - ω, (0) where O) . is the weight and t is the iteration step. (t) is called the learning rate, which is similar to other neural networks. The learning rate starts at a large value at the initialization phase of the training and can be modified linearly, exponentially, or inversely proportionally to t. h. is a predefined neighborhood function. Simply, if
' c
the distance of the neuron weight is within a range of the neighborhood function, the value of h. is 1, which means that the weight of the neuron is to be updated.
' c
Otherwise, if the distance of the neuron weight is outside of the range of the neighborhood function, the value of h. is 0, which means that the weight of the & ι, ω b
c
neuron is not to be updated. In practice, a typical choice of the neighborhood function is a Gaussian function. The weight updating process is repeatedly carried out if a preset
stop criterion, for example, a maximum number of iteration steps and threshold of the change of network error, is met.
As discussed above, the distance between the input vector and the weight of the BMU in a trained SOM structure may be used as a performance indicator to quantitatively measure the degradation status. The distance between the input vector and the weight of the BMU is defined as minimum quantization error (MQE):
MQE = b - co BMU where x is the input vector and „T is the weight vector of BMU. Data collected in
BMU B
normal operating conditions of the wind turbine 210 may be used to train a SOM structure as a baseline. Data obtained later can be used as input to the trained SOM structure. With all of the MQE values, the deviation of the input vector from the baseline may be evaluated and used as the performance indicator. If the input vector is close to the baseline, the MQE value is small. Otherwise, a large MQE value indicates a large deviation from the baseline, which may mean a degradation or abnormal situation has happened. Using this method, the multi-dimensional feature space is converted to a distance measure value (MQE) indicating the degradation status.
Another model, a Gaussian Mixture Model (GMM) may be used to evaluate the performance of wind turbines 210 in a wind farm. GMM is a probabilistic method that is often used for clustering and density estimation purposes. As the wind turbine features are not normally distributed, traditional distance metrics may not be appropriate for use. GMM can be used to decompose a non-Gaussian feature set into a combination of normal functions.
Using the feature set described above in reference to the SOM method, a mixture model, H(x), with n components may be mathematically described as:
Gaussian distribution with mean vector u . and covariance matrix S. .
ι ι
One method to estimate the parameters of a GMM is the expectation maximization (EM) algorithm. Determining the GMM starts with clustering; the k-mean method may be utilized to determine the center of each GMM component. The clusters, which are candidate mixtures, are then solved with their mixture weights, p . , and the distribution parameters (μ. , δ. ) using the EM technique.
The EM algorithm is a two-step approach: expectation and maximization. In the expectation step, initial guesses for the parameters are made and then the "partial membership" of each data point in each of the clusters is calculated. In the maximization step, the component weight and distribution parameters are iteratively computed until the model converges. In each EM iteration, Bayesian Information Criterion (BIC) or the Akaike Information Criterion (AIC) is computed. The GMM object that optimizes either of the BIC or the AIC allows the analysis method to determine the optimal number of mixture components, n.
With GMM objects as inputs, which may essentially be distributions, the appropriate distance measurement techniques may also be defined for two distributions. To determine the health confidence value (CV), which is a comparison (i.e., a distance) between the recent behavior distribution with a known normal behavior distribution, L2 distance may be employed. The degree of similarity or the overlap between two Gaussian mixtures may be numerically obtained using L2 distance. The computed value is normalized between 0 and 1, where the lower CV represents a larger distance between the two distributions and lower health status, or a degraded equipment performance condition.
In yet another model, an Artificial Neural Network, also called parallel distribution processing systems, may be used. Neural networks consist of simple neurons arranged in a structured and systematic manner. Each neuron is a processing unit that weights its inputs, sums the weighted inputs, adds a bias to the calculation, and processes the input in a transfer function. A neural network may consist of several
neurons in one or more layers. A neural network can also be configured to me multi- input and/or multi- output.
In a network structure, the weight matrix constructs a relationship between the input and output vectors. The process of finding the optimum values for the weight matrix is called the training phase, where the error function is minimized. Updating the weight values are based on the network feedback, i.e., the difference between the target and the network output. Among several network designs, the feed-forward back- propagation neural network may be suited for this application. For example, a network having two layers where the first layer has Ν neurons and the second layer has N2 neurons, the weight matrix may be set up as an Ν χΝ2 matrix. The weight value for the ith input of the jth neuron ma then be updated according to:
Aw„ (n) = + ατΔνν,, (n - 1)
where E(n) is the difference between the target and the network output for the nth input, η is the learning rate, which controls the amount of change in the weights in each epoch, and is called the momentum constant, which may be set to avoid being trapped in local minima.
After successfully training the neural network with good condition data from the wind turbines 210, degradation assessment may then be implemented by comparing the computed output with the actual measured equipment output. The difference between the two may be referred to as a "residue." In theory, if the equipment being monitor is in a state of acceptable normal condition, the residual values should be small, approaching 0. If the equipment performance begins to degrade, the residues may increase in magnitude. This is an indirect technique demonstrating how neural networks may be used in fault detection or health assessment if actual failure modes cannot be directly modeled due to a lack of data during the conditions.
A method may be used to minimize erratic results due to only a localized portion of the regime support being affected by degradation. Instead of computing the
health value for each sample, the data is segmented to an acceptable, discrete time period, the duration of which depends on the frequency with which the performance assessment results are to be evaluated. For each segment, the residues r are computed using a traditional approach, but the CV^ is computed according to the following equation:
CV,. = °f r ≥ r,hres
# of samples in k segment
where is a constant determined empirically and k is the segment index.
The degradation of a wind turbine 210 and its components are indicated by the excess of certain features or combination of features over a prescribed threshold. Features may be extracted from sensor measurement and control signal. For example, the change of a power output profile over a wind speed spectrum may indicate the power generation capability degradation of a wind turbine 210 as a whole. Additionally, the increase of vibration level or temperature reading for a component, for example the gearbox 218 or the hub support bearings 217, may imply that the component may be developing a mechanical defect.
One embodiment of the method of predicting an end of life of a wind turbine component is presented below. As discussed above, distributing wind turbines 210 within a wind turbine farm 200 into peer-clusters 212 allows analysis of wind turbines 210 operating under similar environmental conditions. Consider a wind turbine farm 200 R = [Γ^ ,Γ^ ,. - . , Γ^ J where the wind turbine farm 200 includes Y number of wind turbines
210. Each wind turbine 210 in the wind turbine farm 200 has three attached vectors:
where O(r. j is the v-dimensional vector associated with the performance variable of the wind turbines 210; w(r. j is the ^-dimensional vector associated with the different environmental conditions of the wind turbines 210; and E(r. j is the w-dimensional vector consisting of the features of the wind turbines 210 that are indicative of component performance degradation.
Becausae the component performance metrics vary as the environmental conditions in which the wind turbines 210 operate change, the environmental condition parameters described by may be partitioned. For situations where the
environmental conditions are acceptably discrete and the number of operating conditions is known, clustering techniques such as k-means may be used. Peer-clusters 212 may be formed by comparing the environmental condition described by for one of the
wind turbines 210 to all of the peer wind turbines 210. A multivariate hypothesis testing process may be employed. This process is repeated until such time that all Y units belong to a cluster. Therefore the result of distributing wind turbines 210 into peer clusters is the structure C = [c1 , c_ ,..., c ] consisting of z clusters where each cluster c r = i r h = 1,2,..., p . e i and p . is the number of wind turbines 210 in the f h, f f peer-cluster 212. Note that ∑ P f = Y■ It is expected that p . > 1 for all z clusters.
f = l * *
After aggregating wind turbines 210 into peer-clusters 212, the highest performing wind turbines 210 within a peer-cluster 212 are selected for establishing a baseline to which other wind turbines 210 within the peer-cluster 212 may be compared.
In one example, the performance variable of a given wind turbine 210 given in j
may represent the difference between actual power produced by the wind turbine 210 and the realistic power expectation based on the environmental conditions. For such an example, the highest performing wind turbine 210 has the smallest performance variable stored in O(r. j. Therefore, the highest performing wind turbine 210 in each peer-cluster c r will be identifiable, and is denoted as r,„ r . Within each peer-cluster c r , the / h*,f f highest performance wind turbine 210 may be compared to other wind turbines 210 using a distance measure D, . . A normalized L2 distance metric may be used to bound I D e {θ,ΐ}
J
Therefore, after evaluating the threshold T beyond which the actual power produced by wind turbine 210 is causes the wind turbine 210 to be identified as a lower performin wind turbine 210, values greater than Tcan be set aside as weights ω f :
Thus, each peer-cluster c has a small subgroup of higher performing wind turbines 210 that may be used to create the peer-cluster baseline:
Cf,bl ~ irc, k = - - - i hf > r c Ξ C f hf ^ P f
Dynamic environmental conditions prevent the use of pre-constructed performance degradation assessment models. Thus, use of local modeling, known as lazy or just-in-time learning, to utilize the most recent data provided by the SCADA 300
to create a degradation assessment model. Each peer-cluster c j. constructs its own model M f , which are a collection of individual models based on each peer-cluster baseline unit in c . , . , as identified above. The peer-cluster modules use features for training the vector indicative of performance degradation,
J . The health value of each peer wind turbine 210, CV^ j. , is then computed by using a locally weighted averaging method using the similarity weights, ω ^ , that were discussed above:
c=l where CV, f is the health value of each peer wind turbine 210 computed by
n— c, j
comparing the component performance metric with each baseline peer, r . , in th subgroup c r , , :
The disclosed method aims to address wind turbine 210 condition monitoring when there are multiple environmental conditions. Thus, a multiple modeling approach may be used to decompose the component performance metric distribution into a mixture of Gaussians. Each peer-cluster c j. , therefore, is represented by a model M ^ ^ , which can be derived by:
M f ,tr {F{cfJU )) = M f jr-c )
)for c = 1,
i=l where q. represents the class weights of the training set for each baseline peer, a represents the number of working regimes for that baseline peer, and the expression is a component probability distribution. Each wind turbine 210 within the peer-cluster will undergo the same density estimation process. The model testing
M r , may be generated for each r, . in each cluster c r :
f, ts - h y h f
=1
Finally, the health, V^ j. , may be estimated for each wind turbine 210 within the peer cluster by using a similar locally weighted averaging method that applies the similarity weight, ω ^ , to individually computed health values when each baseline wind turbine 210 is compared to a peer wind turbine 210 using L2 distance between the
It should now be understood that turbine-to-turbine prognostics techniques as described hereinabove may allow for monitoring the performance and health of a wind turbine using data readily available from SCAD As that are on-board the wind turbines. The systems and methods described herein allow for wind turbines operating at similar environmental conditions at a wind farm to be compared with one another to determine if and when any of the wind turbines require maintenance. The improved ability to monitor performance of the wind turbines may decrease downtime, may target preventative maintenance to those wind turbines requiring repair, and may reduce the need for unnecessary repairs.
Having described the disclosure in detail and by reference to specific embodiments thereof, it will be apparent that modifications and variations are possible without departing from the scope of the disclosure defined in the appended claims. More specifically, although some aspects of the present disclosure are identified herein as preferred or particularly advantageous, it is contemplated that the present disclosure is not necessarily limited to these preferred aspects of the disclosure.
Claims
1. A method for predicting an end of life of a wind turbine component wherein a processor transforms electronic data into a prognostic evaluation, the method
comprising:
receiving environmental conditions indicative of natural surroundings of wind turbines within a wind turbine farm;
receiving component performance metrics indicative of an operation of wind turbines within a wind turbine farm;
distributing the wind turbines into peer-clusters such that the wind turbines within each of the peer-clusters have similar environmental conditions;
identifying a low performing wind turbine and a remaining portion of wind turbines within one of the peer-clusters based upon a predicted performance model;
processing the component performance metrics of the low performing wind turbine and the remaining portion of wind turbines to extract fault condition indicators that correlate the component performance metrics to failure modes;
identifying a critical component of the low performing wind turbine by
contrasting the fault condition indicators of the low performing wind turbine with the remaining portion; and
predicting the end of life of the critical component of the low performing wind turbine based upon the component performance metrics of the remaining portion of wind turbines.
2. The method of claim 1 further comprising building a health assessment model of the critical component, wherein the health assessment model is built with the component performance metrics of the remaining portion of wind turbines.
3. The method of claim 2, wherein the health assessment model comprises a logistic regression, a statistical pattern recognition, a feature map pattern matching, a neural network, a Gaussian mixture model, a support vector machine, a Bayesian belief network, a hidden Markov model, a self organizing map, or a combination thereof.
4. The method of claim 1 further comprising receiving performance metrics indicative of performance of the wind turbines, wherein the low performing wind turbine is identified by evaluating the performance metrics of the wind turbines in the peer- clusters against the predicted performance model.
5. The method of claim 1, wherein the performance metrics comprise a comparison of power generation and wind speed.
6. The method of claim 1 further comprising applying a distance measurement technique to determine a probability of defect.
7. The method of claim 1 further comprising scheduling a maintenance procedure when a predicted cost of not performing the maintenance procedure is greater than the predicted cost of performing the maintenance procedure.
8. The method of claim 1, wherein the end of life is predicted by an autoregressive moving average, a recurrent neural network, a fuzzy logic, a match matrix, or a combination thereof.
9. The method of claim 1, wherein the environmental conditions comprise wind speed, wind direction, temperature, barometric pressure, humidity, or a combination thereof.
10. The method of claim 1, wherein the wind turbines comprise a bearing, a blade, and a generator.
11. The method of claim 10, wherein the component performance metrics are correlated to the bearing.
12. The method of claim 10, wherein the component performance metrics are correlated to a pitch of the blade.
13. The method of claim 10, wherein the component performance metrics are correlated to a yaw of the blade.
14. The method of claim 10, wherein the component performance metrics are correlated to a power output by the generator.
15. A system for predicting an end of life of a wind turbine component, the system comprising:
a processor for executing machine readable instructions electronically coupled to an electronic memory for storing the machine readable instructions;
a wind turbine farm comprising wind turbines for generating energy from wind; environmental sensors located proximate to each of the wind turbines for detecting environmental conditions surrounding the wind turbines; and
performance sensors located proximate to each of the wind turbines for detecting performance metrics correlated with the wind turbines;
wherein the processor is supplied with data from the environmental sensors and the performance sensors and executes the machine readable instructions to:
distribute the wind turbines into peer-clusters according to similarities in the environmental conditions; and
distinguish a low performing wind turbine from a remaining portion of the wind turbines within one of the peer-clusters based upon the performance metrics.
16. The system of claim 15, wherein the processor further executes the machine readable instructions to predict an end of life of a wind turbine component from the low performing wind turbine according to differences in the component performance metrics.
17. The system of claim 15, wherein the environmental conditions and/or the performance metrics are processed by a time domain analysis, a frequency domain analysis, a time-frequency analysis, a wavelet/wavelet packet analysis, a principal component analysis, or a combination thereof.
18. The system of claim 15, wherein the component sensors are an accelerometer, a thermocouple, a tachometer, an oil pressure sensor, or an oil temperature sensor.
19. A wind turbine farm that predicts an end of life of a wind turbine component comprising:
a plurality of wind turbines, each wind turbine comprising a generator coupled to a blade by a gearbox for generating energy from wind;
environmental sensors located proximate to each of the wind turbines for detecting environmental conditions surrounding the wind turbines;
performance sensors located proximate to each of the wind turbines for detecting performance metrics correlated with the wind turbines;
gearbox sensors located proximate to each of the gearboxes for detecting gearbox performance metrics correlated with the wind turbines; and
a processor for executing machine readable instructions,
wherein the processor is supplied with data from the environmental sensors, the performance sensors, and the gearbox sensors and executes the machine readable instructions to:
distribute the wind turbines into peer-clusters according to similarities in the environmental conditions;
distinguish a low performing wind turbine from a remaining portion of the wind turbines within one of the peer-clusters based upon the performance metrics; and
predict an end of life of the gearbox from the low performing wind turbine according to differences in the gearbox performance metrics.
20. The wind turbine farm of claim 19 further comprising processing the gearbox performance metrics to extract fault condition indicators that correlate the gearbox performance metrics to failure modes.
21. The wind turbine farm of claim 20, wherein the failure modes are gear tooth breakage, hub rotating imbalance, bent shaft, bearing race defect, or bent key.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US13/674,200 US8924162B2 (en) | 2010-05-13 | 2012-11-12 | Turbine-to-turbine prognostics technique for wind farms |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US33430210P | 2010-05-13 | 2010-05-13 | |
US61/334,302 | 2010-05-13 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US13/674,200 Continuation US8924162B2 (en) | 2010-05-13 | 2012-11-12 | Turbine-to-turbine prognostics technique for wind farms |
Publications (2)
Publication Number | Publication Date |
---|---|
WO2011143531A2 true WO2011143531A2 (en) | 2011-11-17 |
WO2011143531A3 WO2011143531A3 (en) | 2012-04-05 |
Family
ID=44914995
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/US2011/036402 WO2011143531A2 (en) | 2010-05-13 | 2011-05-13 | Turbine-to-turbine prognostics technique for wind farms |
Country Status (1)
Country | Link |
---|---|
WO (1) | WO2011143531A2 (en) |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
GB2491983A (en) * | 2011-06-15 | 2012-12-19 | Romax Technology Ltd | Vibration Monitoring of a wind or hydro turbine |
EP2696251A2 (en) | 2012-08-07 | 2014-02-12 | Prüftechnik Dieter Busch AG | Method for monitoring rotating machines |
DE102013210090A1 (en) * | 2013-05-29 | 2014-12-04 | Senvion Se | Method for operating a wind energy plant park |
WO2015011301A1 (en) * | 2013-07-22 | 2015-01-29 | Nabla Wind Power, S.L. | Method for determining the life of components of a wind turbine or similar according to its location |
US20150039374A1 (en) * | 2013-08-02 | 2015-02-05 | International Business Machines Corporation | Planning periodic inspection of geo-distributed infrastructure systems |
CN104764603A (en) * | 2015-04-17 | 2015-07-08 | 上海电机学院 | Assessment method for wind power equipment trouble evolution degree affected by environmental factors |
EP2631472B1 (en) | 2012-02-21 | 2017-03-08 | Mitsubishi Heavy Industries, Ltd. | Method for operating wind farm and operation control system for wind farm |
WO2018053237A1 (en) * | 2016-09-16 | 2018-03-22 | General Electric Company | System and method for autonomous service operation validation |
EP3415753A3 (en) * | 2017-06-14 | 2018-12-26 | Mitsubishi Heavy Industries, Ltd. | Abnormality monitoring apparatus and abnormality monitoring method for wind farm |
CN109653961A (en) * | 2018-12-14 | 2019-04-19 | 三重能有限公司 | A kind of monitoring method and device of wind-driven generator |
US10671039B2 (en) | 2017-05-03 | 2020-06-02 | Uptake Technologies, Inc. | Computer system and method for predicting an abnormal event at a wind turbine in a cluster |
US10975846B2 (en) | 2015-07-29 | 2021-04-13 | General Electric Company | Method and system to optimize availability, transmission, and accuracy of wind power forecasts and schedules |
CN112926273A (en) * | 2021-04-13 | 2021-06-08 | 中国人民解放军火箭军工程大学 | Method for predicting residual life of multivariate degradation equipment |
CN113204847A (en) * | 2021-05-11 | 2021-08-03 | 三门核电有限公司 | Comparison method for nuclear turbine performance test |
EP3740675A4 (en) * | 2018-01-18 | 2021-08-18 | ABB Schweiz AG | Method, apparatus and system for wind converter management |
EP3805557A4 (en) * | 2018-05-31 | 2022-01-26 | Hitachi, Ltd. | Wind power generation system |
CN114829985A (en) * | 2019-12-26 | 2022-07-29 | 维斯塔斯风力系统集团公司 | Calculating the wind speed in the recurrence period |
CN115434878A (en) * | 2022-11-09 | 2022-12-06 | 东方电气风电股份有限公司 | Wind generating set temperature cluster control method, device, equipment and medium |
CN117117858A (en) * | 2023-10-18 | 2023-11-24 | 中国华能集团清洁能源技术研究院有限公司 | Wind turbine generator power prediction method, device and storage medium |
DE102011054115B4 (en) | 2010-09-30 | 2024-07-11 | General Electric Renovables España, S.L. | Systems and methods for identifying wind turbine performance inefficiency |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105041571B (en) * | 2015-08-20 | 2018-02-23 | 沈阳华创风能有限公司 | The intelligence control system and its control method of prediction of wind speed wind direction |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070140847A1 (en) * | 2003-11-14 | 2007-06-21 | Martinez De Lizarduy Romo Mari | Monitoring and data processing equipment for wind turbines and predictive maintenance system for wind power stations |
US20080140349A1 (en) * | 2006-12-08 | 2008-06-12 | General Electric Company | Method and system for estimating life of a gearbox |
US20090257873A1 (en) * | 2008-04-15 | 2009-10-15 | Per Egedal | Method and apparatus for prediction-based wind turbine control |
KR100954090B1 (en) * | 2009-10-27 | 2010-04-23 | 주식회사 위다스 | Health and usage monitoring system for wind turbine |
-
2011
- 2011-05-13 WO PCT/US2011/036402 patent/WO2011143531A2/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070140847A1 (en) * | 2003-11-14 | 2007-06-21 | Martinez De Lizarduy Romo Mari | Monitoring and data processing equipment for wind turbines and predictive maintenance system for wind power stations |
US20080140349A1 (en) * | 2006-12-08 | 2008-06-12 | General Electric Company | Method and system for estimating life of a gearbox |
US20090257873A1 (en) * | 2008-04-15 | 2009-10-15 | Per Egedal | Method and apparatus for prediction-based wind turbine control |
KR100954090B1 (en) * | 2009-10-27 | 2010-04-23 | 주식회사 위다스 | Health and usage monitoring system for wind turbine |
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
DE102011054115B4 (en) | 2010-09-30 | 2024-07-11 | General Electric Renovables España, S.L. | Systems and methods for identifying wind turbine performance inefficiency |
GB2491983A (en) * | 2011-06-15 | 2012-12-19 | Romax Technology Ltd | Vibration Monitoring of a wind or hydro turbine |
GB2491983B (en) * | 2011-06-15 | 2016-03-30 | Romax Technology Ltd | Vibration monitoring |
EP2631472B1 (en) | 2012-02-21 | 2017-03-08 | Mitsubishi Heavy Industries, Ltd. | Method for operating wind farm and operation control system for wind farm |
US9324037B2 (en) | 2012-08-07 | 2016-04-26 | Prüftechnik Dieter Busch AG | Method for monitoring of rotating machines |
EP2696251A2 (en) | 2012-08-07 | 2014-02-12 | Prüftechnik Dieter Busch AG | Method for monitoring rotating machines |
US20140046881A1 (en) * | 2012-08-07 | 2014-02-13 | Prüftechnik Ag | Method for monitoring of rotating machines |
EP2696251A3 (en) * | 2012-08-07 | 2014-02-26 | Prüftechnik Dieter Busch AG | Method for monitoring rotating machines |
DE102012015485A1 (en) | 2012-08-07 | 2014-05-15 | Prüftechnik Dieter Busch AG | Method for monitoring rotating machines |
DE102013210090A1 (en) * | 2013-05-29 | 2014-12-04 | Senvion Se | Method for operating a wind energy plant park |
EP3575985A1 (en) * | 2013-07-22 | 2019-12-04 | Nabla Wind Power, S.L. | Method for determining the life of components of a wind turbine or similar according to its location |
EP3026587A4 (en) * | 2013-07-22 | 2016-07-27 | Nabla Wind Power S L | Method for determining the life of components of a wind turbine or similar according to its location |
WO2015011301A1 (en) * | 2013-07-22 | 2015-01-29 | Nabla Wind Power, S.L. | Method for determining the life of components of a wind turbine or similar according to its location |
CN105492762A (en) * | 2013-07-22 | 2016-04-13 | 纳布拉风力有限公司 | Method for determining the life of components of a wind turbine or similar according to its location |
EP3575985B1 (en) | 2013-07-22 | 2020-11-25 | Nabla Wind Power, S.L. | Method for determining the life of components of a wind turbine or similar according to its location |
US20150039374A1 (en) * | 2013-08-02 | 2015-02-05 | International Business Machines Corporation | Planning periodic inspection of geo-distributed infrastructure systems |
CN104764603A (en) * | 2015-04-17 | 2015-07-08 | 上海电机学院 | Assessment method for wind power equipment trouble evolution degree affected by environmental factors |
US10975846B2 (en) | 2015-07-29 | 2021-04-13 | General Electric Company | Method and system to optimize availability, transmission, and accuracy of wind power forecasts and schedules |
WO2018053237A1 (en) * | 2016-09-16 | 2018-03-22 | General Electric Company | System and method for autonomous service operation validation |
US11315062B2 (en) | 2016-09-16 | 2022-04-26 | General Electric Company | System and method for autonomous service operation validation |
CN109690586A (en) * | 2016-09-16 | 2019-04-26 | 通用电气公司 | System and method for independently maintaining operation acknowledgement |
CN109690586B (en) * | 2016-09-16 | 2023-12-22 | 通用电气公司 | System and method for autonomous maintenance operation validation |
US10671039B2 (en) | 2017-05-03 | 2020-06-02 | Uptake Technologies, Inc. | Computer system and method for predicting an abnormal event at a wind turbine in a cluster |
US10844842B2 (en) | 2017-06-14 | 2020-11-24 | Mitsubishi Heavy Industries, Ltd. | Abnormality monitoring apparatus and abnormality monitoring method for wind farm |
EP3415753A3 (en) * | 2017-06-14 | 2018-12-26 | Mitsubishi Heavy Industries, Ltd. | Abnormality monitoring apparatus and abnormality monitoring method for wind farm |
EP3740675A4 (en) * | 2018-01-18 | 2021-08-18 | ABB Schweiz AG | Method, apparatus and system for wind converter management |
EP3805557A4 (en) * | 2018-05-31 | 2022-01-26 | Hitachi, Ltd. | Wind power generation system |
CN109653961A (en) * | 2018-12-14 | 2019-04-19 | 三重能有限公司 | A kind of monitoring method and device of wind-driven generator |
CN114829985A (en) * | 2019-12-26 | 2022-07-29 | 维斯塔斯风力系统集团公司 | Calculating the wind speed in the recurrence period |
CN114829985B (en) * | 2019-12-26 | 2024-04-30 | 维斯塔斯风力系统集团公司 | Method for calculating a recurring wind speed of a proposed wind turbine site, method for designing a wind turbine and method for constructing a wind turbine |
CN112926273A (en) * | 2021-04-13 | 2021-06-08 | 中国人民解放军火箭军工程大学 | Method for predicting residual life of multivariate degradation equipment |
CN112926273B (en) * | 2021-04-13 | 2023-04-18 | 中国人民解放军火箭军工程大学 | Method for predicting residual life of multivariate degradation equipment |
CN113204847A (en) * | 2021-05-11 | 2021-08-03 | 三门核电有限公司 | Comparison method for nuclear turbine performance test |
CN115434878B (en) * | 2022-11-09 | 2023-02-03 | 东方电气风电股份有限公司 | Wind generating set temperature cluster control method, device, equipment and medium |
CN115434878A (en) * | 2022-11-09 | 2022-12-06 | 东方电气风电股份有限公司 | Wind generating set temperature cluster control method, device, equipment and medium |
CN117117858A (en) * | 2023-10-18 | 2023-11-24 | 中国华能集团清洁能源技术研究院有限公司 | Wind turbine generator power prediction method, device and storage medium |
CN117117858B (en) * | 2023-10-18 | 2024-01-30 | 中国华能集团清洁能源技术研究院有限公司 | Wind turbine generator power prediction method, device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
WO2011143531A3 (en) | 2012-04-05 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US8924162B2 (en) | Turbine-to-turbine prognostics technique for wind farms | |
WO2011143531A2 (en) | Turbine-to-turbine prognostics technique for wind farms | |
Lapira et al. | Wind turbine performance assessment using multi-regime modeling approach | |
Zeng et al. | Gearbox oil temperature anomaly detection for wind turbine based on sparse Bayesian probability estimation | |
Dhiman et al. | Wind turbine gearbox anomaly detection based on adaptive threshold and twin support vector machines | |
Rezamand et al. | Critical wind turbine components prognostics: A comprehensive review | |
Lee et al. | Introduction to data-driven methodologies for prognostics and health management | |
Chatterjee et al. | Deep learning with knowledge transfer for explainable anomaly prediction in wind turbines | |
Yang et al. | An unsupervised spatiotemporal graphical modeling approach for wind turbine condition monitoring | |
Teng et al. | DNN‐based approach for fault detection in a direct drive wind turbine<? show [AQ ID= Q1]?> | |
US20110020122A1 (en) | Integrated condition based maintenance system for wind turbines | |
Niu et al. | Intelligent condition monitoring and prognostics system based on data-fusion strategy | |
Wang et al. | SCADA data based condition monitoring of wind turbines | |
Chen et al. | Automated on‐line fault prognosis for wind turbine pitch systems using supervisory control and data acquisition | |
Hu et al. | Dynamic degradation observer for bearing fault by MTS–SOM system | |
Vera-Tudela et al. | Analysing wind turbine fatigue load prediction: The impact of wind farm flow conditions | |
EP3380724B1 (en) | A method for monitoring and assessing power performance changes of a wind turbine | |
DK178607B1 (en) | Method and system for monitoring electric brushes | |
Kreutz et al. | Machine learning-based icing prediction on wind turbines | |
Yan et al. | A dynamic multi-scale Markov model based methodology for remaining life prediction | |
US11761427B2 (en) | Method and system for building prescriptive analytics to prevent wind turbine failures | |
Chen et al. | Anomaly detection and critical attributes identification for products with multiple operating conditions based on isolation forest | |
Wang et al. | Hybrid approach for remaining useful life prediction of ball bearings | |
Yu | A nonlinear probabilistic method and contribution analysis for machine condition monitoring | |
CN112733283A (en) | Wind turbine generator component fault prediction method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 11781335 Country of ref document: EP Kind code of ref document: A2 |
|
NENP | Non-entry into the national phase in: |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 11781335 Country of ref document: EP Kind code of ref document: A2 |