Water Droplet Erosion Life Prediction Method for Steam Turbine Blade Materials Based on Image Recognition and Machine Learning

2020 ◽  
Author(s):  
Zheyuan Zhang ◽  
Tianyuan Liu ◽  
Di Zhang ◽  
Yonghui Xie
Keyword(s):  
Machine Learning ◽  
Turbine Blade ◽  
Image Recognition ◽  
Water Droplet ◽  
Turbine Blades ◽  
Prediction Method ◽  
Remaining Useful Life ◽  
Feature Maps ◽  
Water Droplet Erosion ◽  
Data Processing Method

Abstract In this paper, a method for predicting remaining useful life (RUL) of turbine blade under water droplet erosion (WDE) based on image recognition and machine learning is presented. Using the experimental rig for testing the WDE characteristics of materials, the morphology pictures of specimen surface at different times in the process of WDE are collected. According to the data processing method of ASTM-G73 and the cumulative erosion-time curves, the WDE stages of materials is quantitatively divided and the WDE life coefficient (ζ) is defined. The life coefficient (ζ) could be used to calculate the RUL of turbine blades. One convolutional neural network model and three machine learning models are adopted to train and predict the image dataset. Then the training process and feature maps of the Resnet model are studied in detail. It is found that the highest prediction accuracy of the method proposed in this paper can be 0.949, which is considered acceptable to provide reference for turbine overhaul period and blade replacement time.

Water Droplet Erosion Life Prediction Method for Steam Turbine Blade Materials Based on Image Recognition and Machine Learning

2021 ◽  
Author(s):  
Zheyuan Zhang ◽  
Tianyuan Liu ◽  
Di Zhang ◽  
Yonghui Xie
Keyword(s):  
Machine Learning ◽  
Turbine Blade ◽  
Image Recognition ◽  
Water Droplet ◽  
Turbine Blades ◽  
Prediction Method ◽  
Remaining Useful Life ◽  
Feature Maps ◽  
Water Droplet Erosion ◽  
Data Processing Method

Abstract In this paper, a method for predicting remaining useful life (RUL) of turbine blade under water droplet erosion (WDE) based on image recognition and machine learning is presented. Using the experimental rig for testing the WDE characteristics of materials, the morphology pictures of specimen surface at different times in the process of WDE are collected. According to the data processing method of ASTM-G73 and the cumulative erosion-time curves, the WDE stages of materials is quantitatively divided and the WDE life coefficient (?) is defined. The life coefficient (?) could be used to calculate the RUL of turbine blades. One convolutional neural network model and three machine learning models are adopted to train and predict the image dataset. Then the training process and feature maps of the Resnet model are studied in detail. It is found that the highest prediction accuracy of the method proposed in this paper can be 0.949, which is considered acceptable to provide reference for turbine overhaul period and blade replacement time.

Water-droplet erosion behavior of high-velocity oxygen-fuel-sprayed coatings for steam turbine blades

2021 ◽  
Vol 0 (0) ◽  
Author(s):  
Dingjun Li ◽  
Peng Jiang ◽  
Fan Sun ◽  
Xiaohu Yuan ◽  
Jianpu Zhang ◽  
...  
Keyword(s):  
Steam Turbine ◽  
Water Droplet ◽  
Erosion Resistance ◽  
Turbine Blades ◽  
Impingement Angle ◽  
Erosion Behavior ◽  
Water Droplet Erosion ◽  
Steam Turbine Blades ◽  
Oxygen Fuel ◽  
Sprayed Coatings

Abstract The water-droplet erosion of low-pressure steam turbine blades under wet steam environments can alter the vibration characteristics of the blade, and lead to its premature failure. Using high-velocity oxygen-fuel (HVOF) sprayed water-droplet erosion resistant coating is beneficial in preventing the erosion failure, while the erosion behavior of such coatings is still not revealed so far. Here, we examined the water-droplet erosion resistance of Cr3C2–25NiCr and WC–10Co–4Cr HVOF sprayed coatings using a pulsed water jet device with different impingement angles. Combined with microscopic characterization, indentation, and adhesion tests, we found that: (1) both of the coatings exhibited a similar three-stage erosion behavior, from the formation of discrete erosion surface cavities and continuous grooves to the broadening and deepening of the groove, (2) the erosion rate accelerates with the increasing impingement angle of the water jet; besides, the impingement angle had a nonlinear effect on the cumulative mass loss, and 30° sample exhibited the smallest mass loss per unit area (3) an improvement in the interfacial adhesion strength, fracture toughness, and hardness of the coating enhanced the water-droplet erosion resistance. These results provide guidance pertaining to the engineering application of water erosion protective coatings on steam turbine blades.

scholarly journals Fuzzy Multi-SVR Learning Model for Reliability-Based Design Optimization of Turbine Blades

Materials ◽  
2019 ◽  
Vol 12 (15) ◽  
pp. 2341 ◽  
Author(s):  
Chun-Yi Zhang ◽  
Ze Wang ◽  
Cheng-Wei Fei ◽  
Zhe-Shan Yuan ◽  
Jing-Shan Wei ◽  
...  
Keyword(s):  
Machine Learning ◽  
Response Surface ◽  
Turbine Blade ◽  
Response Surface Method ◽  
Fuzzy Theory ◽  
Turbine Blades ◽  
Learning Method ◽  
Reliability Based Design Optimization ◽  
Reliability Based Design ◽  
Surface Method

The effectiveness of a model is the key factor of influencing the reliability-based design optimization (RBDO) of multi-failure turbine blades in the power system. A machine learning-based RBDO approach, called fuzzy multi-SVR learning method, was proposed by absorbing the strengths of fuzzy theory, support vector machine of regression (SVR), and multi-response surface method. The model of fuzzy multi-SVR learning method was established by adopting artificial bee colony algorithm to optimize the parameters of SVR models and considering the fuzziness of constraints based on fuzzy theory, in respect of the basic thought of multi-response surface method. The RBDO model and procedure with fuzzy multi-SVR learning method were then resolved and designed by multi-objective genetic algorithm. Lastly, the fuzzy RBDO of a turbine blade with multi-failure modes was performed regarding the design parameters of rotor speed, temperature, and aerodynamic pressure, and the design objectives of blade stress, strain, and deformation, and the fuzzy constraints of reliability degree and boundary conditions, as well. It is revealed (1) the stress and deformation of turbine blade are reduced by 92.38 MPa and 0.09838 mm, respectively. (2) The comprehensive reliability degree of the blade was improved by 3.45% from 95.4% to 98.85%. (3) It is verified that the fuzzy multi-SVR learning method is workable for the fuzzy RBDO of complex structures just like a multi-failure blade with high modeling precision, as well as high optimization, efficiency, and accuracy. The efforts of this study open a new research way, i.e., machine learning-based RBDO, for the RBDO of multi-failure structures, which expands the application of machine learning methods, and enriches the mechanical reliability design method and theory as well.

scholarly journals Coating Life Prediction for Combustion Turbine Blades

1998 ◽  
Author(s):  
Kwai S. Chan ◽  
N. Sastry Cheruvu ◽  
Gerald R. Leverant
Keyword(s):  
Experimental Data ◽  
Turbine Blade ◽  
Cycle Time ◽  
Life Prediction ◽  
Aluminide Coating ◽  
Turbine Blades ◽  
Prediction Method ◽  
Remaining Life ◽  
Degradation Mechanisms ◽  
Useful Life

A life prediction method for combustion turbine blade coatings has been developed by modeling coating degradation mechanisms including oxidation, spallation, and aluminum loss due to inward diffusion. Using this model, the influence of cycle time on coating life is predicted for GTD-111 coated with an MCrAlY, PtAl, or aluminide coating. The results are used to construct a coating life diagram that depicts failure and safe regions for the coating in a log-log plot of number of startup cycles versus cycle time. The regime where failure by oxidation, spallation, and inward diffusion dominates is identified and delineated from that dominated by oxidation and inward diffusion only. A procedure for predicting the remaining life of a coating is developed. The utility of the coating life diagram for predicting the failure and useful life of MCrAlY, aluminide, or PtAl coatings on the GTD-111 substrate is illustrated and compared against experimental data.

scholarly journals Water Droplet Erosion of Wind Turbine Blades: Mechanics, Testing, Modeling and Future Perspectives

Materials ◽  
2019 ◽  
Vol 13 (1) ◽  
pp. 157 ◽  
Author(s):  
Mohamed Elhadi Ibrahim ◽  
Mamoun Medraj
Keyword(s):  
Wind Turbine ◽  
Water Droplet ◽  
Prediction Models ◽  
Experimental Testing ◽  
Turbine Blades ◽  
Leading Edge ◽  
Droplet Impact ◽  
Wind Turbine Blades ◽  
Water Droplet Erosion ◽  
Erosion Prediction

The problem of erosion due to water droplet impact has been a major concern for several industries for a very long time and it keeps reinventing itself wherever a component rotates or moves at high speed in a hydrometer environment. Recently, and as larger wind turbine blades are used, erosion of the leading edge due to rain droplets impact has become a serious issue. Leading-edge erosion causes a significant loss in aerodynamics efficiency of turbine blades leading to a considerable reduction in annual energy production. This paper reviews the topic of water droplet impact erosion as it emerges in wind turbine blades. A brief background on water droplet erosion and its industrial applications is first presented. Leading-edge erosion of wind turbine is briefly described in terms of materials involved and erosion conditions encountered in the blade. Emphases are then placed on the status quo of understanding the mechanics of water droplet erosion, experimental testing, and erosion prediction models. The main conclusions of this review are as follow. So far, experimental testing efforts have led to establishing a useful but incomplete understanding of the water droplet erosion phenomenon, the effect of different erosion parameters, and a general ranking of materials based on their ability to resist erosion. Techniques for experimentally measuring an objective erosion resistance (or erosion strength) of materials have, however, not yet been developed. In terms of modelling, speculations about the physical processes underlying water droplet erosion and consequently treating the problem from first principles have never reached a state of maturity. Efforts have, therefore, focused on formulating erosion prediction equations depending on a statistical analysis of large erosion tests data and often with a combination of presumed erosion mechanisms such as fatigue. Such prediction models have not reached the stage of generalization. Experimental testing and erosion prediction efforts need to be improved such that a coherent water droplet erosion theory can be established. The need for standardized testing and data representation practices as well as correlations between test data and real in-service erosion also remains urgent.

scholarly journals Experimental Research on Water Droplet Erosion Resistance Characteristics of Turbine Blade Substrate and Strengthened Layers Materials

Materials ◽  
2020 ◽  
Vol 13 (19) ◽  
pp. 4286
Author(s):  
Juan Di ◽  
Shunsen Wang ◽  
Xiaojiang Yan ◽  
Xihang Jiang ◽  
Jinyi Lian ◽  
...  
Keyword(s):  
Solid Solution ◽  
Steam Turbine ◽  
Turbine Blade ◽  
Laser Cladding ◽  
Water Droplet ◽  
Positive Contribution ◽  
Water Droplet Erosion ◽  
Stellite Alloy ◽  
New Findings ◽  
Starting Point

In this paper, the water droplet erosion (WDE) performance of typical martensitic precipitation substrate 0Cr17Ni4Cu4Nb in steam turbine final stage, laser solid solution strengthened sample, laser cladding sample and brazed stellite alloy samples have been studied based on a high-speed rotating waterjet test system. The WDE resistance of several materials from strong to weak is in sequence: Brazed stellite alloy > laser cladding sample > laser solid solution sample > martensitic substrate. Furthermore, the WDE resistance mechanism and the failure mode of brazed stellite alloy have been revealed. It is found that the hard carbide in the stellite alloy is the starting point of crack formation and propagation. Under the continuous droplet impact, cracks grow and connect into networks, resulting in the removal of carbide precipitates and WDE damage. It is proved that the properties of the Co-based material itself is the reason for its excellent WDE resistance. And the carbides have almost no positive contribution to its anti-erodibility. These new findings are of great significance to process methods and parameter selection of steam turbine blade materials and surface strengthened layers.

Coating Life Prediction for Combustion Turbine Blades

1999 ◽  
Vol 121 (3) ◽  
pp. 484-488 ◽  
Author(s):  
K. S. Chan ◽  
N. S. Cheruvu ◽  
G. R. Leverant
Keyword(s):  
Experimental Data ◽  
Turbine Blade ◽  
Cycle Time ◽  
Life Prediction ◽  
Aluminide Coating ◽  
Turbine Blades ◽  
Prediction Method ◽  
Remaining Life ◽  
Degradation Mechanisms ◽  
Useful Life

A life prediction method for combustion turbine blade coatings has been developed by modeling coating degradation mechanisms including oxidation, spallation, and aluminum loss due to inward diffusion. Using this model, the influence of cycle time on coating life is predicted for GTD-111 coated with an MCrAlY, PtAl, or aluminide coating. The results are used to construct a coating life diagram that depicts failure and safe regions for the coating in a log-log Plot of number of startup cycles versus cycle time. The regime where failure by oxidation, spallation, and inward diffusion dominates is identified and delineated from that dominated by oxidation and inward diffusion only. A procedure for predicting the remaining life of a coating is developed. The utility of the coating life diagram for predicting the failure and useful life of MCrAlY, aluminide, or PtAl coatings on the GTD-111 substrate is illustrated and compared against experimental data.

Development of Life Prediction Method of Turbine Blade Using the Theory of Critical Distance

2012 ◽  
Author(s):  
Tetsuya Nakahara ◽  
Yusuke Ueda ◽  
Hiroshi Nakamura
Keyword(s):  
Single Crystal ◽  
Turbine Blade ◽  
Contact Surface ◽  
Low Cycle Fatigue ◽  
Turbine Blades ◽  
Prediction Method ◽  
Critical Distance ◽  
Fatigue Tests ◽  
Evaluation Methodology ◽  
Element Analysis

Gas turbine blades mounted dovetail root are subjected to high centrifugal loads and gas forces. This situation causes low cycle fatigue (LCF). Recently, rotating speed and temperature of turbine rotor become higher in order to improve engine performance. To achieve this, it is required to evaluate accurate turbine blade’s LCF life of the contact surface between the blade dovetail root and the disk. However, the estimated blade lives using the peak stress calculated by finite element analysis (FEA) are much shorter than actual life because the stress at contact surface is excessively high. As a result, the blades are designed conservative and the blade’s weight tends to be heavy. Therefore, a more accurate evaluation methodology needs to be established. This study investigates the method to estimate the fatigue strength of dovetail using the theory of critical distance. The theory assumes that fatigue failures would occur due to the representative stress within a specific distance from stress concentration point. Fatigue tests and FEA for the turbine blade dovetail were conducted respectively in this research. The tests were carried out using single crystal nickel-based turbine blades at 600 °C and the fracture lives of dovetail were obtained. FEA was conducted to obtain the stress distributions at dovetail contact surface under testing condition. In this study, the critical distances of the single crystal nickel based alloy were obtained from the notched bar fatigue tests and FEA. Using these results and the theory of critical distance, fatigue lives of dovetail were obtained more accurately.

Sign in / Sign up

Export Citation Format

Share Document