The Experts below are selected from a list of 11631 Experts worldwide ranked by ideXlab platform

J F Durodola - One of the best experts on this subject based on the ideXlab platform.

  • Artificial neural network for Gaussian and non-Gaussian Random Fatigue loading analysis
    2020
    Co-Authors: J F Durodola
    Abstract:

    There has been a lot of work done on the analysis of Gaussian loading analysis perhaps because its occurrence is more common than non-Gaussian loading problems. It is nevertheless known that non-Gaussian load occurs in many instances especially in various forms of transport, land, sea and space. Part of the challenge with non-Gaussian loading analysis is the increased number of variables that are needed to model the loading adequately. Artificial neural network approach provides a versatile means to develop models that may require many input variables in order to achieve applicable predictive generalisation capabilities. Artificial neural network has been shown to perform much better than existing frequency domain methods for Random Fatigue loading under stationary Gaussian load forms especially when mean stress effects are included. This paper presents an artificial neural network model with greater predictive capability than existing frequency domain methods for both Gaussian and non-Gaussian loading analysis. Both platykurtic and leptokurtic non-Gaussian loading cases were considered to demonstrate the scope of application. The model was also validated with available SAE experimental data, even though the skewness and kurtosis of the signal in this case were mild

  • artificial neural network for Random Fatigue loading analysis including the effect of mean stress
    International Journal of Fatigue, 2018
    Co-Authors: J F Durodola, Shashidhar Ramachandra, Shpend Gerguri, N A Fellows
    Abstract:

    Abstract The effect of mean stress is a significant factor in design for Fatigue, especially under high cycle service conditions. The incorporation of mean stress effect in Random loading Fatigue problems using the frequency domain method is still a challenge. The problem is due to the fact that all cycle by cycle mean stress effects are aggregated during the Fourier transform process into a single zero frequency content. Artificial neural network (ANN) has great scope for non-linear generalization. This paper presents artificial neural network methods for including the effect of mean stress in the frequency domain approach for predicting Fatigue damage. The materials considered in this work are metallic alloys. The results obtained present the ANN method as a viable approach to make Fatigue damage predictions including the effect of mean stress. Greater resolution was obtained with the ANN method than with other available methods.

  • a pattern recognition artificial neural network method for Random Fatigue loading life prediction
    International Journal of Fatigue, 2017
    Co-Authors: J F Durodola, Shashidhar Ramachandra, A N Thite
    Abstract:

    Abstract Random vibration Fatigue loading occurs in automotive, aerospace, offshore and indeed in many structural and machine components. The analysis of these types of problems is often carried out using either time domain or frequency domain methods. Time domain rainflow counting together with Miner’s linear damage accumulation assumption is widely accepted as a method of rationalising stress amplitude and mean stress from Random Fatigue loading and the damage caused to the component. Frequency domain methods provide a faster alternative for the analysis of the same problem but the results are generally conservative compared to those obtained using time domain methods. This paper presents an artificial neural network (ANN) machine learning approach for the prediction of damage caused by Random Fatigue loading. The results obtained for ergodic Gaussian stationary stochastic loading is very encouraging. The method embodies rapid analysis as well as better agreement with rainflow counting method than existing frequency domain methods.

N A Fellows - One of the best experts on this subject based on the ideXlab platform.

  • artificial neural network for Random Fatigue loading analysis including the effect of mean stress
    International Journal of Fatigue, 2018
    Co-Authors: J F Durodola, Shashidhar Ramachandra, Shpend Gerguri, N A Fellows
    Abstract:

    Abstract The effect of mean stress is a significant factor in design for Fatigue, especially under high cycle service conditions. The incorporation of mean stress effect in Random loading Fatigue problems using the frequency domain method is still a challenge. The problem is due to the fact that all cycle by cycle mean stress effects are aggregated during the Fourier transform process into a single zero frequency content. Artificial neural network (ANN) has great scope for non-linear generalization. This paper presents artificial neural network methods for including the effect of mean stress in the frequency domain approach for predicting Fatigue damage. The materials considered in this work are metallic alloys. The results obtained present the ANN method as a viable approach to make Fatigue damage predictions including the effect of mean stress. Greater resolution was obtained with the ANN method than with other available methods.

Shashidhar Ramachandra - One of the best experts on this subject based on the ideXlab platform.

  • artificial neural network for Random Fatigue loading analysis including the effect of mean stress
    International Journal of Fatigue, 2018
    Co-Authors: J F Durodola, Shashidhar Ramachandra, Shpend Gerguri, N A Fellows
    Abstract:

    Abstract The effect of mean stress is a significant factor in design for Fatigue, especially under high cycle service conditions. The incorporation of mean stress effect in Random loading Fatigue problems using the frequency domain method is still a challenge. The problem is due to the fact that all cycle by cycle mean stress effects are aggregated during the Fourier transform process into a single zero frequency content. Artificial neural network (ANN) has great scope for non-linear generalization. This paper presents artificial neural network methods for including the effect of mean stress in the frequency domain approach for predicting Fatigue damage. The materials considered in this work are metallic alloys. The results obtained present the ANN method as a viable approach to make Fatigue damage predictions including the effect of mean stress. Greater resolution was obtained with the ANN method than with other available methods.

  • a pattern recognition artificial neural network method for Random Fatigue loading life prediction
    International Journal of Fatigue, 2017
    Co-Authors: J F Durodola, Shashidhar Ramachandra, A N Thite
    Abstract:

    Abstract Random vibration Fatigue loading occurs in automotive, aerospace, offshore and indeed in many structural and machine components. The analysis of these types of problems is often carried out using either time domain or frequency domain methods. Time domain rainflow counting together with Miner’s linear damage accumulation assumption is widely accepted as a method of rationalising stress amplitude and mean stress from Random Fatigue loading and the damage caused to the component. Frequency domain methods provide a faster alternative for the analysis of the same problem but the results are generally conservative compared to those obtained using time domain methods. This paper presents an artificial neural network (ANN) machine learning approach for the prediction of damage caused by Random Fatigue loading. The results obtained for ergodic Gaussian stationary stochastic loading is very encouraging. The method embodies rapid analysis as well as better agreement with rainflow counting method than existing frequency domain methods.

Zili Wang - One of the best experts on this subject based on the ideXlab platform.

  • probabilistic Fatigue crack growth analysis under stationary Random loading with spike loads
    IEEE Access, 2018
    Co-Authors: Shan Jiang, Wei Zhang, Zili Wang
    Abstract:

    The in-service loading condition of many engineering structures is generally composed of a stationary Random loading caused by the mechanical vibration, and the spike loads due to occasional events, such as the sudden shock and accidental turbulence. In this paper, a physical-based method is proposed to evaluate the reliability of structure subjected to the stationary Random Fatigue loading superimposed by occasional spike loads. First, since the interaction effects of stationary Random loading are approximately stable, the realistic Random loading can be transferred to an equivalent constant amplitude loading. This equivalent transformation method can avoid the complicated cycle-by-cycle calculation. This approach is derived from the two-parameter Fatigue crack growth model, in which the driving parameters of the Fatigue crack growth are the stress intensity factor of peak load and the stress intensity factor range. Second, the spike loads lead to the high nonlinearity of interaction effect, which can be accounted for by the plasticity. Therefore, the generalized Willenborg model is employed to calculate the Fatigue crack propagation under the spike loading effects. Then, the extensive experimental data of aluminum alloys are used to validate the proposed method, in which the indeterminacies of material parameter and spike loads are considered. It is observed that all the testing data are contained within the prediction 90% confidence interval bounds. In addition, a Monte Carlo simulation example of Fatigue life reliability assessment under stationary Random loading with spike loads is performed. Two scenarios of different spike load distributions are discussed. In the first scenario, the spike loads are applied at a fixed time interval, while in the other scenario, the spike loads occur with varying time period. The results indicate that the proposed approach can appropriately evaluate the Fatigue reliability of the structure under stationary Random loading with spike loads.

A N Thite - One of the best experts on this subject based on the ideXlab platform.

  • a pattern recognition artificial neural network method for Random Fatigue loading life prediction
    International Journal of Fatigue, 2017
    Co-Authors: J F Durodola, Shashidhar Ramachandra, A N Thite
    Abstract:

    Abstract Random vibration Fatigue loading occurs in automotive, aerospace, offshore and indeed in many structural and machine components. The analysis of these types of problems is often carried out using either time domain or frequency domain methods. Time domain rainflow counting together with Miner’s linear damage accumulation assumption is widely accepted as a method of rationalising stress amplitude and mean stress from Random Fatigue loading and the damage caused to the component. Frequency domain methods provide a faster alternative for the analysis of the same problem but the results are generally conservative compared to those obtained using time domain methods. This paper presents an artificial neural network (ANN) machine learning approach for the prediction of damage caused by Random Fatigue loading. The results obtained for ergodic Gaussian stationary stochastic loading is very encouraging. The method embodies rapid analysis as well as better agreement with rainflow counting method than existing frequency domain methods.