scholarly journals Neural Network Optimization Algorithms to Predict Wind Turbine Blade Fatigue Life under Variable Hygrothermal Conditions

Eng ◽  
2021 ◽  
Vol 2 (3) ◽  
pp. 278-295
Author(s):  
Khaled Ziane ◽  
Adrian Ilinca ◽  
Sasan Sattarpanah Karganroudi ◽  
Mariya Dimitrova
Keyword(s):  
Neural Network ◽  
Fatigue Life ◽  
Wind Turbine ◽  
Turbine Blades ◽  
Cuckoo Search ◽  
Resin Matrix ◽  
Accuracy Evaluation ◽  
Vinyl Esters ◽  
Wind Turbine Blades ◽  
Air Temperatures

Moisture and temperature are the most important environmental factors that affect the degradation of wind turbine blades, and their influence must be considered in the design process. They will first affect the resin matrix and then, possibly, the interface with the fibers. This work is the first to use a series of metaheuristic approaches to analyze the most recent experimental results database and to identify which resins are the most robust to moisture/temperature in terms of fatigue life. Four types of resin are compared, representing the most common types used for wind turbine blades manufacturing. Thermoset polymer resins, including polyesters and vinyl esters, were machined as coupons and tested for the fatigue in air temperatures of 20 °C and 50 °C under “dry” and “wet” conditions. The experimental fatigue data available from Sandia National Laboratories (SNL) for wind turbine-related materials have been used to build, train, and validate an artificial neural network (ANN) to predict fatigue life under different environmental conditions. The performances of three algorithms (Backpropagation BP, Particle Swarm Optimization PSO, and Cuckoo Search CS) are compared for adjusting the synaptic weights of the ANN and evaluating the efficiency in predicting the fatigue life of the materials studied, under the conditions mentioned above. For accuracy evaluation, the mean square error (MSE) is used as an objective function to be optimized by the three algorithms.

scholarly journals A cuckoo search based neural network to predict fatigue life in rotor blade composites

2020 ◽  
Vol 14 (1) ◽  
pp. 6430-6442
Author(s):  
Khaled Ziane ◽  
Adrian Ilinca ◽  
Abdullah Khan ◽  
Soraya Zebirate
Keyword(s):  
Neural Network ◽  
Fatigue Life ◽  
Wind Turbine ◽  
Composite Laminates ◽  
Turbine Blades ◽  
Cuckoo Search ◽  
Wind Turbine Blades ◽  
Target Values ◽  
Predicted Values ◽  
The Cost

In modern wind turbine blades industry, fiber-reinforced composites are mostly used for their good mechanical characteristics: high stiffness, low density and long fatigue life. Wind turbine blades are constructed in different structural elements from a variety of composite laminates, often including Unidirectional (UD) material in spars and multiple forms of Multidirectional (MD) in skins and webs.  The purpose of this paper is to identify materials that have appropriate fiber orientations to improve fatigue life. By using Cuckoo Search-based Neural Network (CSNN), we have developed a model to predict fatigue life under tension-tension charges for five composite materials, with different fiber stacking sequences embedded in three types of resin matrices (epoxy, polyester and vinylester), which are all appropriate for the design of wind turbine blades. In the CSNN approach used in this work, the cost function was assessed using the Mean Square Error (MSE) computed as the squared difference between the predicted values and the target values for a number of training set samples, obtained from an experimental fatigue database. The results illustrate that the CSNN can provide accurate fatigue life prediction for different MD/UD composite laminates, under different angles of fiber orientation.

Effects of shallow angle on static strength and fatigue life of multi-directional laminates for wind turbine blades

2016 ◽  
Vol 51 (18) ◽  
pp. 2549-2563 ◽  
Author(s):  
Sung Kyu Ha ◽  
Alvaro Gorostidi Martinez de Lece ◽  
Carlos Donazar Moriones ◽  
Carlos Alberto Cimini Junior ◽  
Chengzhu Jin
Keyword(s):  
Fatigue Life ◽  
Wind Turbine ◽  
Turbine Blades ◽  
Failure Criteria ◽  
Static Strength ◽  
Experimental Results ◽  
Multiscale Approach ◽  
Wind Turbine Blades ◽  
Static Tests ◽  
Angle Effect

The effects of the shallow angle on the static strength and the fatigue life of the multi-directional glass fiber-reinforced plastics for wind turbine blades were presented based on experimental results and predictions. The static tests and the tension–tension fatigue tests under cyclic fatigue loads with a stress ratio of 0.1 were performed on bi-axial (BX, [±θ]), tri-axial 1 (TA, [0/±θ2]), and tri-axial 2 (TX, [02/±θ]) laminates with ply angles θ of 25°, 35°, and 45°. A multiscale approach was applied to predict the static tensile and compressive strengths and the S–N curves of BX, TA, and TX laminates based on the constituents: fiber, matrix, and interface. Three ply-based failure criteria (Hashin, Puck, and Tsai–Wu) were also employed to predict the static strength and compare with the experimental results. The predictions and the experimental results show that the tensile strength increases as θ becomes shallower, while laminates with a shallow ply angle of 35° showed similar or even lower compressive strengths, especially for TA and TX laminates. The laminate fatigue life increases as θ becomes shallower. The shallow angle effect on strength and fatigue life is greater for BX than TA and TX laminates since the ply angle θ plays a more important role in BX. By using the multiscale approach, the shallow angle effect on the laminate static and fatigue behaviors were also explained based on the ply stresses as well as the constitutive micro stresses.

scholarly journals The Effect of Ply Waviness for the Fatigue Life of Composite Wind Turbine Blades

2013 ◽  
pp. 1195-1199
Author(s):  
U.I.K. Galappaaththi ◽  
Anthony Pickett ◽  
Milos Draskovic ◽  
Mark Capellaro ◽  
A.M. De Silva
Keyword(s):  
Fatigue Life ◽  
Wind Turbine ◽  
Turbine Blades ◽  
Wind Turbine Blades

scholarly journals PSO-BP Neural Network-Based Strain Prediction of Wind Turbine Blades

Materials ◽  
2019 ◽  
Vol 12 (12) ◽  
pp. 1889 ◽  
Author(s):  
Xin Liu ◽  
Zheng Liu ◽  
Zhongwei Liang ◽  
Shun-Peng Zhu ◽  
José A. F. O. Correia ◽  
...  
Keyword(s):  
Neural Network ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Turbine Blades ◽  
Full Scale ◽  
Wind Turbine Blade ◽  
Blade Design ◽  
Wind Turbine Blades ◽  
Static Testing ◽  
Bpnn Model

The full-scale static testing of wind turbine blades is an effective means to verify the accuracy and rationality of the blade design, and it is an indispensable part in the blade certification process. In the full-scale static experiments, the strain of the wind turbine blade is related to the applied loads, loading positions, stiffness, deflection, and other factors. At present, researches focus on the analysis of blade failure causes, blade load-bearing capacity, and parameter measurement methods in addition to the correlation analysis between the strain and the applied loads primarily. However, they neglect the loading positions and blade displacements. The correlation among the strain and applied loads, loading positions, displacements, etc. is nonlinear; besides that, the number of design variables is numerous, and thus the calculation and prediction of the blade strain are quite complicated and difficult using traditional numerical methods. Moreover, in full-scale static testing, the number of measuring points and strain gauges are limited, so the test data have insufficient significance to the calibration of the blade design. This paper has performed a study on the new strain prediction method by introducing intelligent algorithms. Back propagation neural network (BPNN) improved by Particle Swarm Optimization (PSO) has significant advantages in dealing with non-linear fitting and multi-input parameters. Models based on BPNN improved by PSO (PSO-BPNN) have better robustness and accuracy. Based on the advantages of the neural network in dealing with complex problems, a strain-predictive PSO-BPNN model for full-scale static experiment of a certain wind turbine blade was established. In addition, the strain values for the unmeasured points were predicted. The accuracy of the PSO-BPNN prediction model was verified by comparing with the BPNN model and the simulation test. Both the applicability and usability of strain-predictive neural network models were verified by comparing the prediction results with simulation outcomes. The comparison results show that PSO-BPNN can be utilized to predict the strain of unmeasured points of wind turbine blades during static testing, and this provides more data for characteristic structural parameters calculation.

Sign in / Sign up

Export Citation Format

Share Document