2results about How to "Rich training samples" patented technology

This invention relates to the field of power equipment condition monitoring and intelligent diagnosis technology, specifically to a transformer fault location method and system based on a palladium thin-film hydrogen sensor array. The system deploys a palladium thin-film resistive hydrogen sensor array at multiple key locations in the transformer tank to collect real-time dynamic changes in hydrogen concentration in the oil. A virtual transformer fault dataset generated from a digital twin model of the transformer's operating state is used for training using artificial intelligence algorithms. The trained model can intelligently analyze and match features from sensor signals collected during actual operation, thereby achieving rapid identification and spatial location of internal transformer faults. This invention, by integrating the high sensitivity of palladium thin-film resistive sensors, the simulation capabilities of a digital twin system, and the data-driven characteristics of artificial intelligence algorithms, achieves early warning, fuzzy location, and intelligent diagnosis of transformer faults, offering advantages such as fast response, high accuracy, and strong scalability.

The utility model discloses a TBM rock slag catalog image automatic acquisition device based on high-speed camera shooting. The TBM rock slag catalog image automatic acquisition device comprises a TBM cutter head, a TBM slag discharging belt conveyor, a high-speed camera and a camera fixing support. A TBM cutterhead capable of achieving rotary cutting is installed at the end of the TBM deslagging belt conveyor, the camera fixing support is installed on the side, close to the TBM cutterhead, of the TBM deslagging belt conveyor, and the high-speed camera is installed on the camera fixing support, arranged above the starting end of the TBM deslagging belt conveyor and used for collecting orthoimages of rock slag on the TBM deslagging belt conveyor in real time. Rock slag image data are collected in real time through the high-speed camera, manual intervention is not needed, the data collecting and processing time is greatly shortened, meanwhile, the device can work continuously, the idle time of manual operation is effectively shortened, massive training samples are accumulated for rock slag image recognition and geological analysis, the precision of a machine learning model is improved, and the working efficiency is improved. And intelligence and automation of geological logging of the rock slag are promoted.