Search

In response to the challenge of noise filtering for the impulsive vibration signals of rolling bearings, this paper presented a novel filtering method based on the improved Morlet wavelet, which has clear physical meaning and is more conducive to parameter optimization through employing Gaussian waveform width to replace the traditional Morlet wavelet shape factor. Simultaneously, the marine predation algorithm was employed and the minimum Shannon entropy was used as the parameter optimization index while optimizing the shape width and center frequency of the improved Morlet wavelet. The vibration waveform of the rolling bearing was matched perfectly by using the optimized Morlet wave. Shannon entropy was used as the evaluation index of noise filtering, and the quantitative analysis of noise filtering was realized. Through experimental validation, this method was proved to be effective in noise elimination for rolling bearing. It is significance to preprocessing of vibration signal, feature extraction and fault recognition of rolling bearing. [ABSTRACT FROM AUTHOR]

Neural networks (NNs) are increasingly used in design to construct the objective functions and constraints, which leads to the needs of optimization of NN models with respect to design variables. A Neural Optimization Machine (NOM) is proposed for constrained single/multi-objective optimization by appropriately designing the NN architecture, activation function and loss function. The NN's built-in backpropagation algorithm conducts the optimization and is seamlessly integrated with the additive manufacturing (AM) process-property model. The NOM is tested using several numerical optimization problems. It is shown that the increase in the dimension of design variables does not increase the computational cost significantly. Next, a brief review of the physics-guided machine learning model for fatigue performance prediction of AM components is given. Finally, the NOM is applied to design processing parameters in AM to optimize the mechanical fatigue properties through the physics-guided NN under uncertainties. One novel contribution of the proposed methodology is that the constrained process optimization is integrated with physics/knowledge and the data-driven AM process-property model. Thus, a physics-compatible process design can be achieved. Another significant benefit is that the training and optimization are achieved in a unified NN model, and no separate process optimization is needed. This article is part of the theme issue 'Physics-informed machine learning and its structural integrity applications (Part 1)'. [ABSTRACT FROM AUTHOR]