Belt conveyor is considered as a momentous component of modern coal mining transportation system, and thus it is an essential task to diagnose and monitor the damage of belt in real time and accurately. Based on the deep learning algorithm, this present study proposes a method of conveyor belt damage detection based on ADCN (Adaptive Deep Convolutional Network). A deep convolution network with unique adaptability is built to extract the different scale features of visible light image of conveyor belt damage, and the target is classified and located in the form of anchor boxes. A data set with data diversity is collected according to the actual working conditions of the conveyor belt. After training and regression, the ADCN model can perfectly capture and classify the damaged target in the video of the conveyor running. Compared with the SVM based method, the method based on ADCN can better meet the real-time and reliability requirements of belt damage detection, and it has the positioning function which SVM does not have.

@en

Conveyor belt tear detection is a very important part of coal mine safety production. In this paper, a new method of detecting conveyor belt damage named audio-visual fusion (AVF) detection method is proposed. The AVF method uses both a visible light CCD and a microphone array to collect images and sounds of the conveyor belt in different running states. By processing and analyzing the collected images and sounds, the image and sound features of normal, tear and scratch can be extracted respectively. Then the extracted features of images and sounds are fused and classified by machine learning algorithm. The results show that the accuracy of AVF method for conveyor belt scratch is 93.66%, and the accuracy of longitudinal tear is higher than 96.23%. Compared with existing methods AVF method overcomes the limitation of visual detection condition, and is more accurate and reliable for conveyor belt tear detection.

@en

A novel approach based on infrared spectrum analysis for early-warning of longitudinal tearing of the conveyor belt was proposed in the paper. Unlike most existing methods, the proposed method monitors the change process of the infrared radiation field of the longitudinal tearing through the infrared thermal imaging technology, and judges whether there is the risk of the longitudinal tearing of the conveyor belt through the frequency-domain characteristic coefficient T of the infrared radiation field. Experimental results exhibit that the characteristic coefficient T can quantitatively describe the change characteristics of infrared radiation field during the tearing process of conveyor belt. When the conveyor belt is complete penetration, the T value fluctuates violently from 0.6 to 1.6. This characteristic can be used as the precursor information of the tearing process, which broadens the train of thought for identification and early warning of conveyor belt longitudinal tearing.@en

The seeding technique is critical to the quality of the sapphire single crystal. The core of the seeding technique is the identification of seeding state. The MIVD method is proposed in the paper to detect the optimal seeding state. Compared with the OCS method, the MIVD method detects the characteristics of spoke pattern before a single point is formed on melt surface. Based on the similarity and periodicity of the melt motion, the optimal seeding state is detected by Fréchet distance. In the experiment, the MIVD method was compared with the OCS method and the artificial seeding method in terms of seeding efficiency and crystal quality. The MIVD method improves the quality of the sapphire crystal, at same time, it ensures seeding efficiency. The MIVD method is more suitable for practical production.

@en

During the operation of the belt conveyor, measuring speed of the belt conveyor is vital to the safe and efficient operation. In the existing measuring speed system, the measurement instrument is required contacting with the surface of the belt. The contact measurement method cannot avoid the occurrence of measuring error caused by slipping on the contact surface and wear of the measurement instrument. In order to solve the problems mentioned above, a new contactless measuring speed system is proposed in this paper. The system uses the CCD camera to capture the side image of belt. The speed of belt conveyor can be obtained by measuring the regularity of image texture. The proposed measuring system can meet the requirement of measuring speed in long running process of belt conveyor. Experimental results show that the measuring accuracy indicators can reach RMSE of 0.018 m/s and MAE of 0.010 m/s.

@en

As an important part of modern coal mine production, conveyor belts are widely used in the coal collection and transportation. In order to ensure the safe operation of the coal mine conveyor belt and solve the drawbacks of the existing conveyor belt longitudinal tear detection technology, a multispectral visual detection method for conveyor belt longitudinal tear is proposed in this paper. The experimental results show that the multispectral visual detection method not only can identify the conveyor belt longitudinal tear, but also accurately classifies and identify other states of the conveyor belt. The accuracy of multispectral visual detection method is over 90.06%, and the precision of longitudinal tearing recognition is over 92.04%. The proposed method is verified to meet the requirements of reliability and real-time in the industrial field.

@en

Impurity in transparent-bottled liquid is a serious production accident in the field of beverage and medicine industry. However, the existing detection systems are difficult to distinguish impurities with dynamic interference (bubbles and stains) and detect impurities located at the edge of the bottle. In order to solve the problems stated above, a new machine vision system for detecting tiny and dynamic impurities is proposed in this paper. In the system, circularity calculation, longitudinal frame-difference method, orthogonal-axis inspection and K-Nearest Neighbor (KNN) machine learning algorithm are combined together to realize the automatic and real-time detection. Experimental results demonstrate that, after completing machine learning, the weighted error of the proposed system for detecting impurities can be effectively controlled at about 0.9% even in dynamic interference environment, which is great significance to safety production in beverage and medicine industry.

@en