Method for detecting foreign matter target of underground coal mine conveying belt, system, equipment and terminal

Abstract

The invention belongs to the technical field of underground coal mine conveying belt detection, and discloses a method for detecting a foreign matter target of a underground coal mine conveying belt, system, equipment and a terminal, and the method comprises the steps: making a training sample and a test sample through an underground coal mine conveying belt monitoring video; intercepting and labeling foreign matters from the obtained video by using a Labelmg labeling tool, and carrying out adaptive histogram equalization on the conveyor belt image; under a YOLOv5 algorithm framework, introducing an attention model CBAM, simplifying network parameters by using depth separable convolution, optimizing a loss function, and constructing a detection model. According to the method, the foreign matters on the conveying belt can be detected under the conditions of coal dust interference, non-uniform illumination and high-speed movement of the conveying belt, so that higher detection precision is achieved, and the real-time requirement can be well met. Experimental results show that the accuracy and the recall rate of the foreign matter target detection algorithm for the underground coal mine conveying belt are the highest, and meanwhile the algorithm keeps good real-time performance.

Description

technical field [0001] The invention belongs to the technical field of detection of underground coal mine conveyor belts, and in particular relates to a method, system, equipment and terminal for detecting foreign matter targets on underground coal mine conveyor belts. Background technique [0002] In recent years, with the development of artificial intelligence technology, the use of artificial intelligence technology to detect foreign objects on coal mine conveyor belts is a current research hotspot. Among them, the deep learning-based foreign object detection algorithms for coal mine conveyor belts can be roughly divided into two categories: the first category is the region-based target detection method, such as the region-based convolutional neural network (region-based convolutional neural network, R-CNN), fast Regional convolutional neural network (faster region-based convolutional neural network, Faster R-CNN), etc.; the second type is a regression-based target detect...

AI Technical Summary

Problems solved by technology

[0009] (1) The existing detection method based on the Faster R-CNN algorithm framework for the detection of foreign objects on the coal mine conveyor belt has a relatively low detection accuracy and a slower detection speed than the SSD and YOLOv5 algorithms, and can only process 5 objects per second. frame video, unable to meet the detection requirements

[0010] (2) Most of the traditional coal mine conveyor belt foreign object detection methods rely on artificial feature extraction, which is vulnerable to external environment interference and weak generalization ability, and its detection accuracy is often difficult to guarantee

[0011] (3) Due to the complex underground environment, there are problems such as uneven illumination, serious coal dust interference, and high-speed movement of the conveyor belt, which can easily cause image blurring, which makes the target detection method based on artificially extracted features often unsatisfactory in terms of low inspection efficiency and false detection rate. high disadvantage

[0012] (4) Existing Faster R-CNN can be used to detect foreign objects on coal mine conveyor belts, but the detection speed is slow; traditional object detection algorithms have low detection accuracy or even fail to detect them when they are difficult to detect

[0013] The difficulty of solving the above problems and defects is as follows: foreign objects such as large pieces of coal, iron wire, coal gangue and other foreign objects in the conveyor belt of the coal mine, when encountering complex situations such as uneven illumination, coal dust interference, and high-speed movement of the conveyor belt, how to solve the problem? Accurate detection of these foreign objects is a huge challenge

[0014] The significance of solving the above problems and defects is that the conveyor belt is the main equipment for underground coal transportation in coal mines, and its working environment is relatively complicated.

During long-term and high-load use, large pieces of coal, gangue, anchor rods, channel steel and other foreign objects are easy to be mixed with the conveyed materials. If the coal crushing equipment and iron removal equipment are not cleaned in time, the conveyor belt may be damaged when it falls. Localized damage, which can even puncture the belt

In addition, these foreign objects are also easy to get stuck between the trough, idlers and belt body, causing the conveyor belt to be worn through, resulting in tearing of the belt body, which in turn affects the normal production of the coal mine, reduces the output value, and causes a huge safety hazard in coal mining

The number and types of foreign objects in the underground conveyor belt of coal mines are numerous, and the workload of manual inspection is huge. However, the traditional machine vision detection method has the problem of low detection accuracy. Therefore, accurate and reliable detection of these foreign objects is of great importance to the safe operation of coal mines. of great significance

Images