Fatigue behavior prediction and analysis of shot peened mild carbon steels

Maleki, Erfan; Ünal, Okan; Kashyzadeh, Kazem Reza

doi:10.1016/j.ijfatigue.2018.06.004

Cited by 103 publications

(28 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Reference [24] investigated plastic behavior and determined collapse load factors using an ANN. Reference [37] developed an ANN model to predict fatigue behavior. Reference [17] used an ANN and particle swarm optimization (PSO) to predict the factor of safety (FOS) of seismic activity in homogeneous slopes.…”

Section: Study Past Researches Using Articifical Intelligementioning

confidence: 99%

Active Probability Backpropagation Neural Network Model for Monthly Prediction of Probabilistic Seismic Hazard Analysis in Taiwan

Lin

Chiou

2019

IEEE Access

View full text Add to dashboard Cite

In this study, an active probability backpropagation neural network model (PBNNM) was built by training a backpropagation neural network (BPNN) to predict the probability distribution of the probabilistic seismic hazard analysis (PSHA) monthly. The four-layered BPNN framework was determined using training data that were obtained from an earthquake catalogue for the time period of 1990-2015 (Taiwan Standard Time, TST). The studied region was divided into 500 small grids, each 0.2 • × 0.2 • in size, which is approximately 20 × 20 km 2. Each grid was assigned a predicted earthquake occurrence probability for a month between 2015 and 2018 by the PBNNM. The PBNNM successfully predicted the Tainan earthquake (2 February 2016 TST) and Hualien earthquake (2 February 2018 TST) with probabilities of 94% and 95%, respectively. A quantitative analysis of the reliability of the PBNNM, the standard error of the mean (SEM), and the normalised mean square error (NMSE) were used as statistical approaches to evaluate predicted probability errors of the PBNNM. The SEM (1.79) and NMSE (1.45) of 2015 were the inside test and within the time period of the training data. The SEM (2.11) and NMSE (2.03) of 2016, the low SEM (2.17) of 2017, the NMSE (2.13) and SEM (2.17) of 2017, and the SEM (1.71) and NMSE (1.32) of 2018 were the outside tests and not within the time period of the training data. These low SEM and NMSE values confirmed the accuracy of the PBNNM. In addition, the PBNNM does not consider the prerequisite conditions of past studies (e.g., the return period and assumed probability density model). Therefore, the PBNNM can be commercialised with relatively low cost and minimal resources and equipment compared with the methods presented in previous studies; only earthquake catalogues would be necessary. INDEX TERMS Active probability backpropagation neural network model (PBNNM), probabilistic seismic hazard analysis (PSHA), standard error of the mean (SEM), normalized mean square error (NMSE).

show abstract

Section: Study Past Researches Using Articifical Intelligementioning

confidence: 99%

Active Probability Backpropagation Neural Network Model for Monthly Prediction of Probabilistic Seismic Hazard Analysis in Taiwan

Lin

Chiou

2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…To achieve the optimal structure of ANN with the least errors, there is no generally accepted rule. However, one among the difficult steps in ANN modeling is selecting the optimum neural network structure via trial and error [43]. Generally, this procedure is carried out by training different networks with different structures and comparing them to gain acceptable ranges of errors.…”

Section: Implementation Of Annmentioning

confidence: 99%

Parametric analysis of collapse load factor of planar frames

Maleki

Kashyzadeh

2019

SN Appl. Sci.

Self Cite

View full text Add to dashboard Cite

The plastic analysis and determining the collapse load factor (CLF) of frames have received much attention in all kinematical methods applied for designing these frames. CLF in frames depends on many effective parameters such as length of the bay, the height of story, loads, and plastic moments. As the number of these parameters increases, the analysis becomes more complex and time-consuming. In this regard, artificial neural networks (ANNs) have been found many applications in prediction and optimization of ill-defined problems. In the present paper, two planar frames were considered and analyzed as examples for modeling via ANN. In order to develop the ANNs, results of thirty samples were gathered from every two examples. Parameters including the length of the bay, the height of story, loads, and plastic moments were regarded as inputs and the CLF was considered as the output of the networks. After developing the networks, the model function was generated and the effects of the input parameters were investigated on the CLF of frames. The results showed tuning networks are finely and adjusting their parameters would lead to very good and acceptable results for the design of frames.

show abstract

“…Gao [12] said that after shot peening up to the residual stress level of -350 MPa, the specimens achieved 5 fold increase in fatigue life. Maleki [13] showed that, in case of residual stress equal to -650 MPa, in the AISI 1045specimens observed 10 times higher fatigue life. Similar observations were made by Hammond [14], Seddik [15] and Dongxing [16].…”

Section: Introductionmentioning

confidence: 97%

Assessment of the Impact of Shot Peening on the Fatigue Life of a Compressor Blade Subjected to Resonance Vibrations

Bednarz

Misiołek

2020

Preprint

View full text Add to dashboard Cite

The publication presents the assessment of the influence of surface treatment such as shot-peening on the fatigue life of a compressor blade exposed to resonant vibrations. As part of the work, a geometric model of the blade was developed and a numerical modal and fatigue analysis were performed. The fatigue analysis was based on the Manson-Coffin-Basquin and Ramberg-Osgood models. As part of the work, the influence of different values of residual stresses on the results of fatigue life was determined. Additionally, the location of the highest equivalent stresses was established. The obtained results of the numerical analyzes were compared with the results presented in the scientific literature. An additional aim of the study was to determine the size of the grains at various points of the blade as well as the thickness of the layer plasticized as a result of peening. The obtained results are presented in the form of tables and charts. The relationship between the location of the highest values of equivalent stresses and the thickness of the plasticized layer was determined. The explanation of the effect of shot peening on the increase in fatigue life of the blade was proposed.

show abstract

Fatigue behavior prediction and analysis of shot peened mild carbon steels

Cited by 103 publications

References 66 publications

Active Probability Backpropagation Neural Network Model for Monthly Prediction of Probabilistic Seismic Hazard Analysis in Taiwan

Active Probability Backpropagation Neural Network Model for Monthly Prediction of Probabilistic Seismic Hazard Analysis in Taiwan

Parametric analysis of collapse load factor of planar frames

Assessment of the Impact of Shot Peening on the Fatigue Life of a Compressor Blade Subjected to Resonance Vibrations

Contact Info

Product

Resources

About