With the rapid development of industrial informatization and deep learning technology, modern data-driven fault diagnosis (MIFD) methods based on deep learning have been continuously emphasized by the industry. However, most of these methods require sufficient training samples to achieve the desired diagnostic effect, but the scarcity of fault samples in the actual industrial environment leads to the limited development of MIFD methods. In addition, due to the changes of equipment operating conditions and production requirements, data-driven fault diagnosis methods often need to face the cross domain problem of cross load or even cross different equipment. In this paper, a parameter optimization and feature metric-based fault diagnosis method with few samples, called model agnostic matching network model, is designed for the problem of sparse fault samples and cross-domain between data sets in real industrial environments. The method combines both a parameter-based optimization meta-learning network, which extracts optimization information adapted to different domains, and a metric-based meta-learning network, which extracts metric information for similarity discriminations. The experimental result show that the method outperforms the current baseline method for the 5-shot fault diagnosis problem of rolling bearings under limited data conditions and achieves an accuracy of up to 94.4% in cross-equipment diagnosis experiments from rolling bearings to gas regulators, indicating the feasibility of the method. The features are visualized by T-SNE to show the validity of the model.

No abstract

Arc plasma torch is an effective tool for spheroidization of metallic powders. However, as most conventional plasma torches were not specifically designed for plasma spheroidization, they may exhibit the disadvantages of the radial injection of powders, large fluctuations in the arc voltage, large gas flow rate, and disequilibrium between multiple plasma jets during the spheroidization process. Therefore, this paper presents a triple-cathode cascade plasma torch (TCCPT) for plasma spheroidization. Its structural design, including three cathodes, a common anode, and three sets of inter-electrodes, are detailed to ensure that powders can be inserted into the plasma jet by axial injection, the arc voltage fluctuations are easily maintained at a low level, and the plasma torches can work at a relatively small gas flow rate. Experimental results showed that the proposed TCCPT exhibits the following characteristics: (1) a relatively small arc voltage fluctuation within 5.3%; (2) a relatively high arc voltage of 75 V and low gas flow rate range of 10-30 SLM; (3) easy to be maintained at the equilibrium state with the equilibrium index of the three plasma jets within 3.5 V. Furthermore, plasma spheroidization experiments of SUS304 stainless steel powers were carried out using the proposed TCCPT. Results verified that the proposed TCCPT is applicable and effective for the spheroidization of metallic powders with wide size distribution.

No abstract

No abstract