Purpose: The purpose of this paper is to provide a theoretical foundation for improving the selective laser melting (SLM) surface roughness. To improve the part’s surface quality during SLM process, the upper surface roughness of SLM parts was theoretically studied and the influencing factors were analyzed through experiments. Design/methodology/approach: The characteristics of single track were first investigated, and based on the analysis of single track, theoretical value of the upper surface roughness would be calculated. Two groups of cubic sample were fabricated to validate SLM parts’ surface roughness, the Ra and relative density of all the cubic parts was measured, and the difference between theoretical calculation and experiment results was studied. Then, the effect of laser energy density on surface roughness was studied. At last, the SLM part’s surface was improved by laser re-melting method. At the end of this paper, the curved surface roughness was discussed briefly. Findings: The SLM upper surface roughness is affected by the width of track, scan space and the thickness of powder layer. Measured surface roughness Ra value was about 50 per cent greater than the theoretical value. The laser energy density has a great influence on the SLM fabrication quality. Different laser energy density corresponds to different fabricating characteristics. This study divided the SLM fabrication into not completely melting zone, balling zone in low energy density, successfully fabricating zone and excessive melting zone. The laser surface re-melting (LSR) process can improve the surface roughness of SLM parts greatly without considering the fabricating time and stress accumulation. Originality/value: The upper surface roughness of SLM parts was theoretically studied, and the influencing factors were analyzed together; also, the LSR process was proven to be effective to improve the surface quality. This study provides a theoretical foundation to improve the surface quality of SLM parts to promote the popularization and application of metal additive manufacturing technology.

The decomposition number K and penalty factor α in the variational mode decomposition (VMD) algorithm have a great influence on the decomposition effect and the accuracy of subsequent fault diagnosis. Therefore, a gear fault diagnosis method based on genetic mutation particle swarm optimization VMD and probabilistic neural network (GMPSO-VMD-PNN) algorithm is proposed in this paper. Firstly, the GMPSO algorithm is used to optimize the [K,α] parameter combination in the VMD algorithm, and the optimal [K,α] parameter combination of each gear fault vibration signal to be decomposed is selected. Then, the gear fault vibration signal is decomposed into several intrinsic mode functions (IMFs) by VMD, and the sample entropy value of each IMFs is extracted to form the feature vector of subsequent fault diagnosis. Finally, the characteristic vector of gear fault vibration signal is input into PNN model, and gear fault is accurately classified. By comparing with fixed parameter VMD algorithm, empirical mode decomposition (EMD) and complete ensemble empirical mode decomposition adaptive noise (CEEMDAN) algorithm, the superiority of this method in gear fault diagnosis is verified. Therefore, the GMPSO-VMD-PNN algorithm proposed in this paper has certain application value for gear fault diagnosis.

A gear fault diagnosis method based on kurtosis criterion variational mode decomposition (VMD) and self-organizing map (SOM) neural network is proposed. Firstly, the VMD algorithm is used to decompose the gear vibration signal, and the instantaneous frequency mean is calculated as the evaluation index, and the characteristic curve is drawn to screen out the most relevant intrinsic mode functions (IMFs) of the original vibration signal. Then, the number of VMD decompositions is determined, and the kurtosis value of IMFs are extracted to form the feature vectors. Then, the kurtosis value feature vectors of IMFs are normalized to form the kurtosis value normalized vectors. Finally, the normalized vectors of kurtosis value are input into SOM neural network to realize gear fault diagnosis. When the number of training times of SOM neural network is 100, the gear fault category is accurately classified by SOM neural network. The results show that when the training times of SOM neural network is 100 times, the gear fault diagnosis method, based on the kurtosis criterion VMD and SOM neural network is 100%, which indicates that the new method has a good effect on gear fault diagnosis.