An intelligent monitoring method for sieve plate fault based on depth image

Abstract

The present invention relates to a method for intelligent monitoring of sieve plate faults based on depth images, which includes the following steps: Step 1. Determine the matrix arrangement of the depth camera installation according to the station of the sieve plate and the internal parameters of the camera itself; Step 2. Dimension conversion of the original data; step 3, processing the invalid data in the data after dimension conversion; step 4, performing pseudo-color rendering on the data after the invalid data processing; step 5, in the depth image according to the At the station, sub-images are divided, and each sub-image is analyzed separately to judge the working condition; step 6, obtain the signal strength data of the image captured by the camera, and compare it with the signal strength data during normal operation, so as to judge the surface of the sieve plate Whether there is coal, further judge whether the raw coal funnel is blocked. Compared with the existing method, the method has faster detection speed and higher detection precision, does not need manual intervention, is a non-intervention monitoring method, and does not affect normal production.

Description

technical field [0001] The invention relates to the field of intelligent monitoring of working conditions of large-scale mechanical equipment in industrial automation production lines, and in particular to an intelligent monitoring method for sieve plate faults based on depth images, which is used for intelligent monitoring of faults in which sieve plates are inclined or fall off due to mechanical vibration. Background technique [0002] The vibrating screen is a mechanical device with a complex structure. It is accompanied by severe vibration during start-up and operation. The vibration amplitude is relatively small but the vibration frequency is relatively high; while in the process of parking and cushioning, the vibration frequency of the screen plate is driven by the motor. It is close to the vibration frequency of the sieve plate itself, and resonance occurs, which leads to a decrease in the vibration frequency of the sieve plate during the shutdown phase, but the vibrat...

AI Technical Summary

Problems solved by technology

The device has a certain detection effect on the situation that a large amount of material on the screen surface falls after the sieve plate falls off, but there are obvious loopholes and deficiencies in the detection method: for example, the detection method belongs to hysteresis detection; the detection method belongs to physical intervention detection; way requires the design of complex circuits, etc.

The special working environment on site requires that interventional or intervening monitoring methods cannot be used, and normal production cannot be affected; in harsh on-site environments, live monitoring methods cannot be used

[0007] In view of the problems of hysteresis, misjudgment, and non-real-time nature of the existing sieve plate fault monitoring technology, it is necessary to design a real-time monitoring system for the operating state of the sieve plate, so that faults can be detected in time, alarmed in time, and accidents and hazards can be minimized. minimized

Images