Fatigue Life Estimation of High Strength 2090-T83 Aluminum Alloy under Pure Torsion Loading Using Various Machine Learning Techniques

The ongoing effort to create methods for detecting and quantifying fatigue damage is motivated by the high levels of uncertainty in present fatigue-life prediction approaches and the frequently catastrophic nature of fatigue failure.The fatigue life of high strength aluminum alloy 2090-T83 is predicted in this study using a variety of artificial intelligence and machine learning techniques for constant amplitude and negative stress ratios(R?1).Artificial neural networks(ANN),adaptive neuro-fuzzy inference systems(ANFIS),support-vector machines(SVM),a random forest model(RF),and an extreme-gradient tree-boosting model(XGB)are trained using numerical and experimental input data obtained from fatigue tests based on a relatively low number of stress measurements.In particular,the coefficients of the traditional force law formula are found using relevant numerical methods.It is shown that,in comparison to traditional approaches,the neural network and neuro-fuzzy models produce better results,with the neural network models trained using the boosting iterations technique providing the best performances.Building strong models from weak models,XGB helps to predict fatigue life by reducing model partiality and variation in supervised learning.Fuzzy neural models can be used to predict the fatigue life of alloys more accurately than neural networks and traditional methods.

Machine learning-based real-time visible fatigue crack growth detection

Many large-scale and complex structural components are applied in the aeronautics and automobile industries.However,the repeated alternating or cyclic loads in service tend to cause unexpected fatigue fractures.Therefore,developing real-time and visible monitoring methods for fatigue crack initiation and propagation is critically important for structural safety.This paper proposes a machine learning-based fatigue crack growth detection method that combines computer vision and machine learning.In our model,computer vision is used for data creation,and the machine learning model is used for crack detection.Then computer vision is used for marking and analyzing the crack growth path and length.We apply seven models for the crack classification and find that the decision tree is the best model in this research.The experimental results prove the effectiveness of our method,and the crack length measurement accuracy achieved is 0.6 mm.Furthermore,the slight machine learning models help us realize real-time and visible fatigue crack detection.

Effect of Machined Surface Integrity on Fatigue Performance of Metal Workpiece:A Review

Fatigue performance is a serious concern for mechanical components subject to cyclical stresses,particularly where safety is paramount.The fatigue performance of components relies closely on their surface integrity because the fatigue cracks generally initiate from free surfaces.This paper reviewed the published data,which addressed the effects of machined surface integrity on the fatigue performance of metal workpieces.Limitations in existing studies and the future directions in anti-fatigue manufacturing field were proposed.The remarkable surface topography(e.g.,low roughness and few local defects and inclusions)and large compressive residual stress are beneficial to fatigue performance.However,the indicators that describe the effects of surface topography and residual stress accurately need further study and exploration.The effect of residual stress relaxation under cycle loadings needs to be precisely modeled precisely.The effect of work hardening on fatigue performance had two aspects.Work hardening could increase the material yield strength,thereby delaying crack nucleation.However,increased brittleness could accel-erate crack propagation.Thus,finding the effective control mechanism and method of work hardening is urgently needed to enhance the fatigue performance of machined components.The machining-induced metallurgical structure changes,such as white layer,grain refinement,dislocation,and martensitic transformation affect the fatigue performance of a workpiece significantly.However,the unified and exact conclusion needs to be investigated deeply.Finally,different surface integrity factors had complicated reciprocal effects on fatigue performance.As such,studying the comprehensive influence of surface integrity further and establishing the reliable prediction model of workpiece fatigue performance are meaningful for improving reliability of components and reducing test cost.

Design of a Cantilever - Type Rotating Bending Fatigue Testing Machine

This research is centered on the design of a low–cost cantilever loading rotating bending fatigue testing machine using locally sourced materials. The design principle was based on the adaptation of the technical theory of bending of elastic beams. Design drawings were produced and components/materials selections were based on functionality, durability, cost and local availability. The major parts of the machine: the machine main frame, the rotating shaft, the bearing and the bearing housing, the specimen clamping system, pulleys, speed counter, electric motor, and dead weights;were fabricated and then assembled following the design specifications. The machine performance was evaluated using test specimens which were machined in conformity with standard procedures. It was observed that the machine has the potentials of generating reliable bending stress – number of cycles data;and the cost of design (171,000 Naira) was lower in comparison to that of rotating bending machines from abroad. Also the machine has the advantages of ease of operation and maintenance, and is safe for use.

Estimation of Fatigue Strength of Reinforced Complete Upper Denture Using a Newly Designed Testing Machine: A Laboratory Research Project

In the present study, an aero pneumatic fatigue testing machine for complete dentures was designed, fabricated, and tested for the evaluation of the fatigue life of reinforced complete upper denture (CUD). On completion and testing, it was observed that the machine has the potential of generating reliable number of cyclic data. The machine’s performance was evaluated using test specimens of identical CUDs that were machined in conformity with standard procedures. The fatigue machine compressed the lower dental arch over the upper denture-specimen in centric occlusion, in the same way that the two masticatory muscles pull the lower jaw over the upper jaw during chewing. The incorporation of glass fibres into the CUD using a sandwich technique quadruples the lifespan of the denture (P = 0.004). The low standard deviation, along with the low coefficient of variation (CV) of the group of unreinforced dentures shows the repeatability of the results and the reliability of the machine. The high standard deviation and coefficient of variation of reinforced dentures was expected, since a high variation of results is usually recorded in fibre reinforcement cases. This research confirmed the view that the crack during denture fracture initiates in the anterior palatal area and propagates to the posterior.

Detection and Recuperation of Mental Fatigue

Mental fatigue is a complex state that results from prolonged cognitive activity. Symptoms of mental fatigue can include change in mood, motivation, and temporary deterioration of various cognitive functions involved in goal-directed behavior. Extensive research has been done to develop methods for recognizing physiological and psychophysiological signs of mental fatigue. This has allowed the development of many AI-based models to classify different levels of fatigue, using data extracted from eye-tracking device, EEG, or ECG. In this paper, we present an experimental protocol which aims to both generate/measure mental fatigue and provide effective strategies for recuperation via VR sessions paired with EEG and eye tracking devices. This paper first provides a comprehensive state-of-the-art of mental fatigue predictive factors, measurement methods, and recuperation strategies. Then the paper presents an experimental protocol resulting from the state-of-the-art to 1) generate and measure mental fatigue and 2) evaluate the effectiveness of virtual therapy for fatigue recuperation, using a virtual reality (VR) simulated environment. In our work, we successfully generated mental fatigue through completion of cognitive tasks in a virtual simulated environment. Participants showed significant decline in pupil diameter and theta/alpha score during the various cognitive tasks. We trained an RBF SVM classifier from Electroencephalogram (EEG) data classifying mental fatigue with 95% accuracy on the test set. Finally, our results show that the time allocated for virtual therapy did not improve pupil diameter in post-relaxation period. Further research on the impact of relaxation therapy on relaxation therapy should allocate time closer to the standard recovery time of 60 min.

Recent Advances in Fatigue Detection Algorithm Based on EEG

Fatigue is a state commonly caused by overworked,which seriously affects daily work and life.How to detect mental fatigue has always been a hot spot for researchers to explore.Electroencephalogram(EEG)is considered one of the most accurate and objective indicators.This article investigated the devel-opment of classification algorithms applied in EEG-based fatigue detection in recent years.According to the different source of the data,we can divide these classification algorithms into two categories,intra-subject(within the same sub-ject)and cross-subject(across different subjects).In most studies,traditional machine learning algorithms with artificial feature extraction methods were com-monly used for fatigue detection as intra-subject algorithms.Besides,deep learn-ing algorithms have been applied to fatigue detection and could achieve effective result based on large-scale dataset.However,it is difficult to perform long-term calibration training on the subjects in practical applications.With the lack of large samples,transfer learning algorithms as a cross-subject algorithm could promote the practical application of fatigue detection methods.We found that the research based on deep learning and transfer learning has gradually increased in recent years.But as afield with increasing requirements,researchers still need to con-tinue to explore efficient decoding algorithms,design effective experimental para-digms,and collect and accumulate valid standard data,to achieve fast and accurate fatigue detection methods or systems to further widely apply.

Machine learning for predicting fatigue properties of additively manufactured materials

Fatigue properties of materials by Additive Manufacturing(AM) depend on many factors such as AM processing parameter, microstructure, residual stress, surface roughness, porosities, post-treatments, etc. Their evaluation inevitably requires these factors combined as many as possible, thus resulting in low efficiency and high cost. In recent years, their assessment by leveraging the power of Machine Learning(ML) has gained increasing attentions. A comprehensive overview on the state-of-the-art progress of applying ML strategies to predict fatigue properties of AM materials, as well as their dependence on AM processing and post-processing parameters such as laser power, scanning speed, layer height, hatch distance, built direction, post-heat temperature,etc., were presented. A few attempts in employing Feedforward Neural Network(FNN), Convolutional Neural Network(CNN), Adaptive Network-Based Fuzzy Inference System(ANFIS), Support Vector Machine(SVM) and Random Forest(RF) to predict fatigue life and RF to predict fatigue crack growth rate are summarized. The ML models for predicting AM materials' fatigue properties are found intrinsically similar to the commonly used ones, but are modified to involve AM features. Finally, an outlook for challenges(i.e., small dataset, multifarious features,overfitting, low interpretability, and unable extension from AM material data to structure life) and potential solutions for the ML prediction of AM materials' fatigue properties is provided.

Analytical Models of Concrete Fatigue:A State-of-the-Art Review

Fatigue failure phenomena of the concrete structures under long-term low amplitude loading have attractedmore attention.Some structures,such as wind power towers,offshore platforms,and high-speed railways,may resist millions of cycles loading during their intended lives.Over the past century,analytical methods for concrete fatigue are emerging.It is concluded that models for the concrete fatigue calculation can fall into four categories:the empirical model relying on fatigue tests,fatigue crack growth model in fracture mechanics,fatigue damage evolution model based on damage mechanics and advanced machine learning model.In this paper,a detailed review of fatigue computing methodology for concrete is presented,and the characteristics of different types of fatigue models have been stated and discussed.

Study of machining induced surface defects and its effect on fatigue performance of AZ91/15%SiCp metal matrix composite

The quality of surface generated in a peripheral milling of AZ91/SiCp/15%for varying machining conditions and its effect on the fatigue performance are investigated in this study.The machined surface quality was evaluated through roughness measurements and SEM micrographs of ine machined surface.Tensile iesis were pcifumicu io iiieasure the mechanical properties of the composite.Subsequently,fatigue life of milled specimens was measured through axial fatigue tests at four loading conditions.Optical and SEM/EDS micrographs of the fractured surface were studied to identify the crack initiation site and propagation mechanism.Specimens machined at a lower feed rate of 0.1 mm/rev was found to have excellent surface finish and consequently higher fatigue life.At 0.3 mm/rev,the presence of feed marks and other surface defects resulted in a drastic decrease in fatigue life.Five distinct regions were identified on the fractured surface,particle fracture along and perpendicular to the surface,voids in the matrix due to particle debonding and pull out and typical ductile failure of matrix with embedded SiC particles.

SEM in-situ investigation on fatigue cracking behavior of P/M Rene95 alloy with surface inclusions

The low-cycle fatigue behavior of powder metallurgy Rene95 alloy containing surface inclusions was investigated by in-situ observation with scanning electron microscopy （SEM）. The process of fatigue crack initiation and early stage of propagation behavior indicates that fatigue crack mainly occurs at the interface between the inclusion and the matrix. The effect of inclusion on the fatigue crack initiation and the early stage of crack growth was very obvious. The fatigue crack growth path in the matrix is similar to the shape of inclusion made on the basis of fatigue fracture image analysis. The empiric relation between the surface and inside crack growth length, near a surface inclusion, can be expressed. Therefore, the fatigue crack growth rate or life of P/M Rene95 alloy including the inclusions can be evaluated on the basis of the measurable surface crack length parameter. In addition, the effect of two inclusions on the fatigue crack initiation behavior was investigated by the in-situ observation with SEM.

In-Situ Test on Fatigue Characteristics of Top-Mounted Dividable Pile-Board Subgrade for High-Speed Railway

To simulate the fatigue characteristics of the pile-board structure under long-term dynamic load, using the in-situ dynamic testing system DTS-1, the forced vibration loading was repeated one million times at different cross-sections of the pile-board structure for high-speed railway. The dynamic deformation, permanent deformation and dynamic stress of main reinforcements were measured. The test results show that the dynamic responses of the pile-board structure almost did not vary with the forced vibration times under the simulated trainload. After one million times of forced vibration, the permanent deformations of the midspan section of intermediate span and midspan section of side span were 0.7 mm and 0. 6 mm, respectively, and there was no accumulative plastic deformation at the bearing section of intermediate span.

Data-driven approach to predict the fatigue properties of ferrous metal materials using the cGAN and machine-learning algorithms

The stress-life curve(S–N)and low-cycle strain-life curve(E–N)are the two primary representations used to characterize the fatigue behavior of a material.These material fatigue curves are essential for structural fatigue analysis.However,conducting material fatigue tests is expensive and time-intensive.To address the challenge of data limitations on ferrous metal materials,we propose a novel method that utilizes the Random Forest Algorithm and transfer learning to predict the S–N and E–N curves of ferrous materials.In addition,a data-augmentation framework is introduced using a conditional generative adversarial network(cGAN)to overcome data deficiencies.By incorporating the cGAN-generated data,the accuracy(R2)of the Random Forest Algorithm-trained model is improved by 0.3–0.6.It is proven that the cGAN can significantly enhance the prediction accuracy of the machine-learning model and balance the cost of obtaining fatigue data from the experiment.

IN-SITU OBSERVATION OF THERMAL FATIGUE CRACK GROWTH IN STEEL 3Cr2W8V

The growing process of thermal fatigue cracking,in steel 3Cr2WSV was observed under desk SEM fitted with sell-made minisized device for thermal faligue test.Before the growing of thermal fatigue crack,the main crack tip reveals to blunt firstly,and some holes and uncontinuous microcraeks occur in front of it.The growth is developed by bridging of main crack together with holes and microcracks.

SEM in-situ Fatigue Observation on Crack Initiation and Growth from Inclusion in P/M Rene95 Superalloy

A special designed experiment was conducted for observing crack initiation and growth in P/M Rene95 superalloy under tension-tension loading by self-made SEM in-situ fatigue loading stag. Several alumina inclusion particles exposed at the specimen surface were observed carefully. During fatigue test inclusions led to cracks initiation. The cracks can be formed by two mechanisms. Generally, the cracks nucleated at the interface between inclusion and matrix. Sometimes, cracks were also formed inside the inclusion. As the increase of cycles, some cracks at the interface between inclusion and matrix broadened and propagated along the direction about 45 degrees to the loading axis. On the other hand, the cracks inside the inclusion propagated in the inclusion and towards matrix.

Development of an In-Situ Laser Machining System Using a Three-Dimensional Galvanometer Scanner

In this study, a three-dimensional (3D) in-situ laser machining system integrating laser measurement and machining was built using a 3D galvanometer scanner equipped with a side-axis industrial camera. A line structured light measurement model based on a galvanometer scanner was proposed to obtain the 3D information of the workpiece. A height calibration method was proposed to further ensure measurement accuracy, so as to achieve accurate laser focusing. In-situ machining software was developed to realize time-saving and labor-saving 3D laser processing. The feasibility and practicability of this in-situ laser machining system were verified using specific cases. In comparison with the conventional line structured light measurement method, the proposed methods do not require light plane calibration, and do not need additional motion axes for 3D reconstruction;thus they provide technical and cost advantages. The insitu laser machining system realizes a simple operation process by integrating measurement and machining,which greatly reduces labor and time costs.

Deep-water Riser Fatigue Monitoring Systems Based on Acoustic Telemetry

Marine risers play a key role in the deep and ultra-deep water oil and gas production. The vortex-induced vibration （VIV） of marine risers constitutes an important problem in deep water oil exploration and production. VIV will result in high rates of structural failure of marine riser due to fatigue damage accumulation and diminishes the riser fatigue life. In-service monitoring or full scale testing is essential to improve our understanding of V1V response and enhance our ability to predict fatigue damage. One ma- rine riser fatigue acoustic telemetry scheme is proposed and an engineering prototype machine has been developed to monitor deep and ultra-deep water risers＇ fatigue and failure that can diminish the riser fatigue life and lead to economic losses and eco-catastrophe. Many breakthroughs and innovation have been achieved in the process of developing an engineering prototype machine. Sea trials were done on the 6th generation deep-water drilling platform HYSY-981 in the South China Sea. The inclination monitoring results show that the marine riser fatigue acoustic telemetry scheme is feasible and reliable and the engineering prototype machine meets the design criterion and can match the requirements of deep and ultra-deep water riser fatigue monitoring. The rich experience and field data gained in the sea trial which provide much technical support for optimization in the engineering prototype machine in the future.

Color space lip segmentation for drivers＇ fatigue detection

to the chroma distribution diversity （CDD） between lip color and skin color, the lip color area is segmented by the back propagation neural network （BPNN） with three typical color features. Isolated noisy points of the lip color area in binary image are eliminated by a proposed re- gion connecting algorithm. An improved integral projection algorithm is presented to locate the lip boundary. Whether a driver is fatigued is recognized by the ratio of the frame number of the images with mouth opening continuously to the total image frame number in every 20s. The experiments show that the proposed algorithm provides higher correct rate and reliability for fatigue driving detec- tion, and is superior to the single color feature-based method in the lip color segmention. Besides, it improves obviously the accuracy and speed of the lip boundary location compared with the traditional integral projection algrothm.

SIMULATION OF COMPLEX THERMOMECHANICAL FATIGUE

Two different types of experimental techniques to perform non-isothermal, uniax-ial and biaxial fatigue tests were described. A new miniaturised electrothermal-mechanical test rig was presented and discussed. It enables testing of small specimens under complex thermomechanical loading conditions. In order to cope with the simulation of well defined biaxial proportional and non-proportional loadings with in-phase and out-of-phase superposition of thermal loads a cruciform biaxial fatigue testing machine has been developed. Special design features of both machines, and the specimens tested, as well as typical test results were discussed.

Fatigue Life Prediction of Gray Cast Iron for Cylinder Head Based on Microstructure and Machine Learning

Conventional fatigue tests on complex components are difficult to sample,time-consuming and expensive.To avoid such problems,several popular machine learning(ML)algorithms were used and compared to predict fatigue life of gray cast iron(GCI)with the complex microstructures.The feature analysis shows that the fatigue life of GCI is mainly influenced by the external environment such as the stress amplitude,and the internal microstructure parameters such as the percentage of graphite,graphite length,stress concentration factor at the graphite tip,matrix microhardness and Brinell hardness.For simplicity,collected datasets with some of the above features were used to train ML models including back-propagation neural network(BPNN),random forest(RF)and eXtreme gradient boosting(XGBoost).The comparison results suggest that the three models could predict the fatigue lives of GCI,while the implemented RF algorithm is the best performing model.Moreover,the S–N curves fitted by the Basquin relation in the predicted data have a mean relative error of 15%compared to the measured data.The results have demonstrated the advantages of ML,which provides a generic way to predict the fatigue life of GCI for reducing time and cost.