In the process of industrial production of sapphire crystals, the seeding step plays a vital role. Seeding needs to be performed under conditions where the temperature gradient is small and the temperature distribution tends to be stable. At present, the industrial production of sapphire mainly relies on manual experience to control the seed rod to achieve the crystal pilot operation, but the low accuracy of manual pilot operation will lead to poor quality of finished products and waste of resources. Therefore, this paper proposes a method based on sapphire visual spokes pattern recognition method to detect the free liquid surface state of sapphire melt, so as to realize an efficient crystal induction mechanism. In this method, classic skeletoning algorithm was used to refine the spoke pattern, and Harris operator was used to extract the characteristic information. The extracted characteristic information was put into the motion trajectory model to judge the stability of the melt, and the stability of the temperature distribution of the liquid surface was analyzed to achieve crystal induction. Experimental results show that this algorithm is effective, the efficiency of sapphire crystal seeding is greatly improved, and the yield of the finished product is also improved, which can effectively guide the industrial production of sapphire.

@en

Aiming at the problem of mismatch between real-time data distribution and modeling data distribution caused by the change of working conditions in industrial process, which leads to the performance deterioration of the soft sensor model, a multi-source unsupervised soft sensor method based on joint distribution alignment and mapping structure preservation is proposed. Firstly, the method uses the hypergraph to establish the complex structure of feature and label, and clusters the hypergraph matrix in multiple views to completely construct the class pseudo label; then dynamic distribution alignment is used to adapt marginal distribution and conditional distribution between the data of historical working conditions and the current working conditions, and the hypergraph Laplacian operator is introduced for manifold regularization to prevent the mapping relationship between feature and label from being destroyed; finally, similar working conditions are introduced to further enhance the robustness of the model. The experimental results show that compared with the traditional unsupervised soft sensor methods, the method used in this paper can effectively improve the prediction accuracy of the model.

@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

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

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

In various industry productions belt conveyors are widely used for continuous dry bulk material transport. A large scale belt conveying system is generally composed of cascaded single conveyors consuming considerable electric power. According to DIN22101 regulating the belt speed and thereby maximizing the load on the belt may lead to a certain reduction of the needed electrical drive power. To avoid the operational risks, which may be caused by the dynamics of the system, preview control strategy has been proposed for belt conveyor speed control. In case the loading scenarios of a primary conveyor can be measured, the material feeding rate to following conveyors can be previewed. To reduce the influence of noises during material flow measurement and control synchronization, this paper presents the research of adopting Kalman filter to preview control to improve the transient operations of controlled belt conveyors as well as the energy efficiency of the system. Compared to two speed control strategies, the non-constraint preview control and the fuzzy speed control, experimental results show that the proposed Kalman filter based preview control reduces the noise interferences towards softer and safer speed regulation process.

@en

When sapphire crystal is prepared with Kyropoulos method, the necking-down growth process is a key stage. Sapphire growth defect is a big problem in this stage. However, diagnosing growth defects is subject to the interference of workers subjectivity and accuracy always goes down. To address the problem, a novel defect diagnosis method is proposed for necking-down growth process in this paper. Industrial CCD sensors replace eyes of skilled workers to observe in this method. A new Defect-Diagnosing Siamese network (DDSN) is used in this method. We use Siamese architecture to learn similarity through pairs of images. We use the deep separable convolution (DSC) into the DDSN to optimize running speed and model size. In experiment, dataset is acquired by industrial CCD sensors in the necking-down growth process. The accuracy of defect diagnosis can reach up to 94.5%. The method significantly improves the traditional way.@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

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

Belt conveying systems require considerable energy consumption that forms a large part in material handling operations. DIN 22101 indicates that reducing the belt speed and thereby maximizing the load on the belt may lead to a certain reduction of the required electrical drive power. Previous researches have proved that the energy savings for belt conveyors can be achieved based on different speed control strategies. However, in some industrial applications, for instance in long wall mining the material to be loaded onto a belt is neither predictable nor controllable, the speed control of conveyors is not always feasible. In large scale material transport, a belt conveying system is composed of a series of individual conveyors. In case the loading scenarios of a primary belt conveyor can be measured, the material feeding rate to following conveyors can be previewed as the input for speed control in overall transport operation. This paper presents how a preview control strategy can be applied to realize the speed regulation of such conveying systems composed of series belt conveyors. After analysing the power consumption of belt conveyors and developing the preview control model, the operational risks regarding speed adjustment are taken into account as the constraints for optimal preview control. Compared to other control strategies such as fuzzy speed control, the proposed preview control system is able to reduce the operational risks during the control process of regulating the speed of belt conveyors.@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

Infrared and visible light image fusion technology is a hot spot in the research of multi-sensor fusion technology in recent years. Existing infrared and visible light fusion technologies need to register before fusion because of using two cameras. However, the application effect of the registration technology has yet to be improved. Hence, a novel integrative multi-spectral sensor device is proposed for infrared and visible light fusion, and by using the beam splitter prism, the coaxial light incident from the same lens is projected to the infrared charge coupled device (CCD) and visible light CCD, respectively. In this paper, the imaging mechanism of the proposed sensor device is studied with the process of the signals acquisition and fusion. The simulation experiment, which involves the entire process of the optic system, signal acquisition, and signal fusion, is constructed based on imaging effect model. Additionally, the quality evaluation index is adopted to analyze the simulation result. The experimental results demonstrate that the proposed sensor device is effective and feasible.

@en

Real-time and reliable detection of conveyor belt longitudinal tear is an important task in mining operations. This paper presents a novel method of Integrative Binocular Vision Detection (IBVD) to detect the longitudinal tears of conveyor belts. Based on infrared and visible fusion, the IBVD sensor device collects the fusion images of the belt. After extracting the tear features by projection method, the progress of potential tears can be evaluated and the tears can be identified. The IBVD method is verified by an experiment platform fulfilling the acquisition, pro-processing and analysis of fusion images for tear detection. The fusion image processing time is less than 18 ms, which satisfies the requirement of real-time online monitoring. Compared to the individual measurement technique of either infrared detection or visible light detection, the average accuracy of the IBVD method reaches up to 96%, the IBVD method is more reliable in tear detection.

@en

Multi-layer Artificial Neural Networks (ANN) has caught widespread attention as a new method for time series forecasting due to the ability of approximating any nonlinear function. In this paper, a new local time series prediction model is established with the nearest neighbor domain theory, in which the hybrid Euclidean distance is used as the similarity measurement between two sets of time series. In order to improve the efficiency, prediction performance, as well as the ability of real-time updating of the model, in this paper, the recombination samples of the model is derived by Deep Extreme Learning Machine (DELM). The experiments show that local prediction model gets accurate results in one-step and multi-step forecasting, and the model has good generalization performance through the test on the five data sets selected from Time Series Database Library (TSDL).

@en

Conveyor belt longitudinal tear is one of the most serious problems in coal mining. Existing systems cannot realise lossless and real-time detection for longitudinal tear of conveyor belt. Currently, visual detecting systems are proposed by many researchers and are becoming the future trend. A visual recognition system based on using laser and area light sources is designed in this study, which can recognise and count abrasions, incomplete-tears, and complete-tears. The advantage of the system is to prevent longitudinal tear based on multi-feature information. In the process of detecting conditional characteristics, laser and area light sources are responsible for enhancing contrast between conditional features and conveyor belt surface, meanwhile false corner filtration and single-point feature identification method are designed for improving recognition accuracy of the system. Compared with several current systems, the designed system has a better performance on recognising complex tear characteristics of conveyor belt, thus the problem of starting warning only based on single feature can be effectively avoided.@en

Conveyor belt longitudinal tear is one of the most serious problems in coal mining. It is very important to detect it in real-time before the length of the tear is too long. In this study, a method of longitudinal tear detection based on visible light charge coupled device (CCD) and infrared CCD is proposed. A visible light and infrared vision real-time detection system for conveyor belt longitudinal tear is designed based on this method. In this method, the infrared CCD uses adaptive histogram equalisation coordinating with Hough transform line detection. The visible light CCD, coordinating with a laser line source, uses the Hough transform algorithm and the features from accelerated segment test algorithm. These two kinds of CCDs work together to make detection results reliable. Experimental results show that the proposed method is effective and adaptive, and meets the requirements for reliable, real-time and online longitudinal tear detection. Compared to several current methods, the proposed method has a better performance on efficiency of detection.

@en