Intelligent ore identification method and device based on combination of laser radar and vibration signals

Abstract

The invention discloses an artificial intelligence ore identification method and device based on laser imaging, and relates to the technical field of photoelectric imaging, image processing and target detection. The volume characteristic of ore can be obtained by using a distance echo point cloud collected by a laser radar, and the defect of ore identification by using vibration signals only is overcome by using the volume characteristic. The method comprises the following steps that: ores fall from a discharge port, freely fall to a vibration signal acquisition plate and collide to generate a vibration signal, the vibration signal is acquired, and the vibration signal is demodulated to obtain an impact characteristic parameter; the ore falls onto a conveyor belt moving at a constant speed after impacting the vibration signal acquisition plate; the ores are scanned by using a laser radar to obtain distance echo point cloud data of the ores, and the distance echo point cloud data is processed to obtain a volume parameter of the ores; and combined processing is performed on the impact characteristic parameter and the volume parameter to obtain a combined characteristic parameter, and ore type identification is performed on the combined characteristic parameter by using a neural network model.

Description

technical field [0001] The invention relates to the technical fields of photoelectric imaging, image processing and target detection, in particular to an intelligent ore identification method and device using laser radar combined with vibration signals. Background technique [0002] In the industrial field, especially in the field of object detection and recognition based on conveyor belts, steps such as object segmentation, positioning, and recognition are essential, but the realization of these steps is usually based on clear images without background noise interference. For ordinary CCDs, when the background is relatively complex, using algorithms to remove image background noise cannot achieve an ideal effect, which makes object segmentation and positioning more difficult, and ultimately leads to a lower recognition rate. [0003] The applicability and stability of the existing ore identification methods are poor, and the requirements for the cleanliness of the ore surfa...

AI Technical Summary

Problems solved by technology

In recent years, some scholars in China have carried out research on ore identification based on vibration signals, but due to the lack of relevant theories and the limitations of production sites, the engineering progress of ore identification based on vibration signals has been severely restricted.

Images