The change of angle θ between laser cladding powder plane and substrate plane will lead to changes in cladding layer's geometric morphology. Therefore, we established a quantitative numerical prediction model for cladding layer geometry. In this model, we consider the variation of θ, the laser energy attenuation rate and the temperature rise of the powder particles. At the same time, the simulation results were verified by experiments. The results show that when θ is in the range of 50°~90°, the initial temperature is 298 K, the scanning speed is 3.75 mm/s, and the laser spot diameter is 4.5 mm, the Fe#1 powder cladding can achieve better forming effect on Q235. In general, with the decrease of θ, the height of the cladding layer decreases and the width of the layer increases. However, when θ is less than 50°, the quality of the formed morphology significantly deteriorated. The experimental results are in good agreement with the simulation results, which verifies the validity and reliability of the model. This work provides a theoretical reference for further understanding the relationship between the laser cladding morphology and the incident angle. 相似文献
Faced with the problem of valid data shortage data in practical. There's not enough data to train classifiers which can be satisfied to detect impact-rubbing faults in rotary machine. Bedsides, the large number of noises in working enviroment make the useful signal contaminated. Based on this problem, this paper proposes a rubbing fault recognition method based on a generative adversarial nets named deep convolution generative adversarial nets (DCGAN), which is based on a deep convolutional network frame with generation and discrimination models. The acquired signal is processed by time frequency analysis further to get spectrogram. The DCGAN can perform feature conversion and map it to the potential feature subspace to obtain more robust features. The results illustrate that the proposed method can achieve a much more excellent recognition effect. Thus, the proposed DCGAN model is an effective way to recognize impact-rubbing fault in the practical.
Journal of Mechanical Science and Technology - In the reliability analysis of engineering structures, there are usually implict and highly nonlinear performance function problems, which leads to... 相似文献
Journal of Mechanical Science and Technology - As a kind of typical structure, the hat-shaped structure (HSS) is widely used in carbon fiber reinforced plastics (CFRP) aircraft parts. In this work,... 相似文献