The relationships between the fatigue crack growth rate $\left(da/dN\right)$ and stress intensity factor range $\left(\Delta K\right)$ are not always linear even in the Paris region. The stress ratio effects on fatigue crack growth rate are diverse in different materials. However, most existing fatigue crack growth models cannot handle these nonlinearities appropriately. The machine learning method provides a flexible approach to the modeling of fatigue crack growth because of its excellent nonlinear approximation and multivariable learning ability. In this paper, a fatigue crack growth calculation method is proposed based on three different machine learning algorithms (MLAs): extreme learning machine (ELM), radial basis function network (RBFN) and genetic algorithms optimized back propagation network (GABP). The MLA based method is validated using testing data of different materials. The three MLAs are compared with each other as well as the classical two-parameter model ( $K^{*}$ approach). The results show that the predictions of MLAs are superior to those of $K^{*}$ approach in accuracy and effectiveness, and the ELM based algorithms show overall the best agreement with the experimental data out of the three MLAs, for its global optimization and extrapolation ability.

In the aerospace and aviation sectors, the damage tolerance concept has been applied widely so that the modeling analysis of fatigue crack growth has become more and more significant. Since the process of crack propagation is highly nonlinear and determined by many factors, such as applied stress, plastic zone in the crack tip, length of the crack, etc., it is difficult to build up a general and flexible explicit function to accurately quantify this complicated relationship. Fortunately, the artificial neural network (ANN) is considered a powerful tool for establishing the nonlinear multivariate projection which shows potential in handling the fatigue crack problem. In this paper, a novel fatigue crack calculation algorithm based on a radial basis function (RBF)-ANN is proposed to study this relationship from the experimental data. In addition, a parameter called the equivalent stress intensity factor is also employed as training data to account for loading interaction effects. The testing data is then placed under constant amplitude loading with different stress ratios or overloads used for model validation. Moreover, the Forman and Wheeler equations are also adopted to compare with our proposed algorithm. The current investigation shows that the ANN-based approach can deliver a better agreement with the experimental data than the other two models, which supports that the RBF-ANN has nontrivial advantages in handling the fatigue crack growth problem. Furthermore, it implies that the proposed algorithm is possibly a sophisticated and promising method to compute fatigue crack growth in terms of loading interaction effects.

Structural health monitoring has been studied by a number of researchers as well as various industries to keep up with the increasing demand for preventive maintenance routines. This work presents a novel method for reconstruct prompt, informed strain/stress responses at the hot spots of the structures based on strain measurements at remote locations. The structural responses measured from usage monitoring system at available locations are decomposed into modal responses using empirical mode decomposition. Transformation equations based on finite element modeling are derived to extrapolate the modal responses from the measured locations to critical locations where direct sensor measurements are not available. Then, two numerical examples (a two-span beam and a 19956-degree of freedom simplified airfoil) are used to demonstrate the overall reconstruction method. Finally, the present work investigates the effectiveness and accuracy of the method through a set of experiments conducted on an aluminium alloy cantilever beam commonly used in air vehicle and spacecraft. The experiments collect the vibration strain signals of the beam via optical fiber sensors. Reconstruction results are compared with theoretical solutions and a detailed error analysis is also provided.

Degradation modeling and remaining useful life (RUL) prediction for products with multiple degradation features are hot topics in the prognostic and health management. The key to this problem is to describe the dependence among multiple degradation features effectively. In this paper, a multivariate degradation modeling approach based on the Bayesian dynamic linear model (BDLM) is proposed to calculate the RULs of degradation features, and the Copula function is employed to capture the dependence among RUL distributions. A combined BDLM is used to establish the multivariate degradation model, which includes two typical BDLMs, namely, the linear growth model and seasonal factors model. After the model parameters get calibrated by the maximum likelihood estimation, the model can predict the degradation process of features. Once the failure thresholds are given, the probability density function and cumulative distribution function (CDF) of RUL for each degradation feature can be obtained. Since these RUL distributions are not independent of each other, the Copula function is adopted herein to couple the CDFs. Finally, some practical testing data of a microwave component, which has two degradation features, are utilized to validate our proposed method. This paper provides a new idea for the multivariate degradation modeling and RUL prediction.

Failure analysis and fatigue life prediction are necessary and critical for engineering structural materials. In this paper, a general methodology is proposed to predict fatigue life of smooth and circular-hole specimens, in which the crack closure model and equivalent initial flaw size (EIFS) concept are employed. Different effects of crack closure on small crack growth region and long crack growth region are considered in the proposed method. The EIFS is determined by the fatigue limit and fatigue threshold stress intensity factor △K_th. Fatigue limit is directly obtained from experimental data, and △K_th is calculated by using a back-extrapolation method. Experimental data for smooth and circular-hole specimens in three different alloys (Al2024-T3, Al7075-T6 and Ti-6Al-4V) under multiple stress ratios are used to validate the method. In the validation section, Semi-circular surface crack and quarter-circular corner crack are assumed to be the initial crack shapes for the smooth and circular-hole specimens, respectively. A good agreement is observed between model predictions and experimental data. The detailed analysis and discussion are performed on the proposed model. Some conclusions and future work are given.

An asymmetric three-degree-of-freedom parallel mechanism is adopted in rehabilitation robots for assisting patients suffering from stroke or trauma in the hip. It is necessary to keep its kinematic singularity out of the workspace of human normal gait and increase the output power efficiency. Therefore, a novel method is proposed to optimize geometrical parameters of the mechanism. To describe the kinematic singularity in a better way, the improved force transmission indexes based on previous methods are proposed using the reciprocal product and mobility condition of the closed-loop mechanism. The indexes mainly represent the force transmission performance of unactuated parts of subchains and moving platform. Together with the driving force transmission indexes and geometrical constraints, the multiobjective optimization model is established. The differential evolution algorithm, which is widely applied to mechanism optimization, is used to achieve optimal results. The Jacobian matrix singularity and output power efficiency along giving trajectory before and after optimization are compared to verify the effectiveness of the method.