No abstract

No abstract

In the design process of traditional ship shafting, the design quality is generally hard to get guaranteed for the lack of discipline coupling. In this paper, Multidisciplinary Design Optimization (MDO) is innovatively introduced to ensure design quality. Multidisciplinary decomposition of shafting can help to construct the MDO model of ship shafting based on multidisciplinary feasibility method. Then the sub-discipline model of shifting design can be further established, including calibration neutron discipline model, whirling vibration model, and dynamic stiffness of radial oil film bearing model. Collaborative operation is implemented by the multidisciplinary model of shifting to obtain the experimental results. Based on Radial Basis Function (RBF) neural network, the responsive surfaces of variable, bearing load, and support stiffness can be constructed, in the meanwhile the dynamic stiffness decoupling of vibration model can be obtained. Fireworks algorithm is used to establish multidisciplinary optimization of seven-dimensional design variable. The results show that MDO helps improve the quality of shafting alignment and whirling vibration. The work in present paper also provides insight for the future optimization of research methods, design quality, and engineering experiments.

Ventilator vibration signal is usually mixed with some signals and shows strong nonlinearity, nonstationarity and nonGaussian. It presents a great challenge to feature extraction and recognition. We applied the independent component analysis (ICA) to ventilator vibration signal analysis, used FastICA algorithm to get a group of independent variables with the useful feature information, adopted residual self-information (RSI) to compress further for the group of independent variables, and chose the larger RSI to form the new estimating component. And then we used support vector machine (SVM) to find the ventilator healthy pattern and/or the ventilator fault pattern. The experiment result shows that by using the methods above the correct identification rate of ventilator healthy and fault state reaches 100%. Keywords-independent component analysis(ICA); residual self information(RSI); support vector machine (SVM); fault diagnosis

No abstract