A study on fatigue damage modeling using neural networks

Fatigue crack growth and life have been estimated based on established empirical equations. In this paper, an alternative method using artificial neural network (ANN) -based model developed to predict fatigue damages simultaneously. To learn and generalize the ANN, fatigue crack growth rate and life data were built up using in-plane bending fatigue test results. Single fracture mechanical parameter or nondestructive parameter can’t predict fatigue damage accurately but multiple fracture mechanical parameters or nondestructive parameters can. Existing fatigue damage modeling used this merit but limited real-time damage monitoring. Therefore, this study shows fatigue damage model using backpropagation neural networks on the basis of X-ray half breadth ratioB/B ₀ , fractal dimensionD _f and fracture mechanical parameters can estimate fatigue crack growth rateda/dN and cycle ratioN/N _f at the same time withinengineering limit error (5%).     

Nonlinear ultrasonic techniques for nondestructive assessment of micro damage in material: A review

The nondestructive assessment of the damage that occurs in components during service plays a key role for condition monitoring and residual life estimation of in-service components/structures. Ultrasound has been widely utilized for this; however most of these conventional methods using ultrasonic characteristics in the linear elastic region are only sensitive to gross defects but much less sensitive to micro-damage. Recently, the nonlinear ultrasonic technique, which uses nonlinear ultrasonic behavior such as higher-harmonic generation, subharmonic generation, nonlinear resonance, or mixed frequency response, has been studied as a positive method for overcoming this limitation. In this paper, overall progress in this technique is reviewed with the brief introduction of basic principle in the application of each nonlinear ultrasonic phenomenon.     

A nonlinear control scheme based on dynamic evolution path theory for improved dynamic performance of boost PFC converter working on nonlinear features

This paper is concerned to performance improvement of boost PFC converter under large random load fluctuation, ensuring unity power factor (UPF) at source end and regulated voltage at load side. To obtain such performance, a nonlinear controller based on dynamic evolution path theory is designed and its robustness is examined under both heavy and light loading condition. In this paper, %THD and zero-cross-over dead-zone of input current is significantly reduced. Also, very less response time of input current and output voltage to that of load and reference variation is remarked. A simulation model of proposed system is designed and it is realized using dSPACE 1104 signal processor for a 390V_DC, 500 W prototype. The relevant experimental and simulation waveforms are presented.