No abstract

In this paper, aiming at the application of online rapid sorting of waste textiles, a large number of effective high-content blending data are generated by using generative adversity network to deeply mine the combination relationship of blending spectra, and A BEGAN-RBF-SVM classification model is constructed by compensating the imbalance of negative samples in the data set. Various experiments show that the model can effectively extract the spectrum of pure textile samples. The classification model has high robustness and high speed, reaches the performance of similar products in the world, and has a broad application market.

Based on the principle of photoelectric thermometry and adaptive Fuzzy-PID control theory, a non-contact and high-speed embedded system for measure and control high temperature has been developed. The real-time information of process temperature was received by using photoelectric sensor and A/D conversion in the system, output power of temperature control module could be real-time adjusted, and the temperature of the objects could be controlled in the required range. Furthermore, the whole system has several characteristics, such as compact structure, small size, easy to carry and installation and can be embedded into machine equipment. High-frequency welding machine in the practical application of the test shows that the system with response speed, wide temperature range can be monitoring and control, high precision, greatly improved the quality of welding products, has broad application prospects.

No abstract