Search

Abstract Rock burst disasters severely restrict the safe and efficient mining of coal. The fundamental cause of their occurrence is the concentration of stress within the coal mass. Stress monitoring in coal seam drilling is widely used as an effective method for rock burst monitoring. However, how to scientifically and reasonably set the critical values of early warning indicators that match the conditions of each mine has always been a key issue restricting the accurate prediction of rock burst by the drilling stress method. This paper adopts a method combining theoretical analysis and field practice to conduct research on the critical values of drilling stress early warning indicators. Based on perturbation response instability theory, a mechanical model for the occurrence of impact ground pressure has been established. Based on the instability theory of disturbance response, a mechanical model for the occurrence of impact ground pressure has been established, leading to the derivation of the expression for the near-field critical stress of impact ground pressure events. The theoretical formula for the critical value of drilling stress early warning indicators was obtained based on the difference between the critical stress of rock burst occurrence and the actual stress in the roadway. This formula includes the mechanical parameters of the coal mass and its propensity for rock burst, roadway support stress, mining depth, stress concentration coefficient, and the initial installation pressure of the stress gauge. They can be determined by the geological and mining technical conditions of each mine. This theoretical formula breaks the uniformity of the critical values for stress warning indicators in various mine drill holes, allowing each mine to scientifically determine its critical value based on its own conditions. This theoretical method has been applied to a high-stress mine in Shanxi, China, and the critical values of drilling stress early warning indicators were obtained. When the monitored stress exceeded the critical value, dynamic phenomena of anchor rod and cable fractures occurred in the roadway roof. The distribution of microseismic events also shifted towards the warning area, and the microseismic monitoring indicators reached the warning values. This confirmed the engineering feasibility of the critical values for drilling stress early warning indicators determined by the theoretical method.

Abstract Water from hydraulic technology affects the desorption of gas from coal seams. Gas desorption behavior is critical information for gas control in coal mines. In this study, a designed coal seam water injection simulation experimental device was utilized to conduct dynamic water injection experiments on coal samples at different adsorption equilibrium pressures, analyzing the gas desorption law under dynamic water injection, as well as the role of water replacement, water imbibition and water blockage in gas desorption. The results showed that water altered the gas desorption rate in coal, causing fluctuating attenuation of the desorption rate of a water-injected coal sample (WCS). Under the same adsorption equilibrium pressure, the relationship between the desorption rate of the WCS and the non-water-injected coal samples (NCS) underwent a transition in desorption time. In contrast to the NCS desorption curves, the WCS desorption curves lacked a rapid growth phase and exhibited only a slow growth phase and a stopping phase. Water imbibition and water replacement promoted the desorption of gas in the non-wet area during the water injection process, while it inhibited the desorption of gas in the wet area. Under the effects of water imbibition, water blockage, and water replacement, the discharge rate of WCS is greater than the desorption rate of NCS, indicating that water injection increases the total amount of gas desorption. The study results have significant implications for gas extraction and the prevention and control of coal and gas outbursts.

Abstract Indoor testing are performed to explore the charge induction law during the uniaxial compression fracture process of coal samples, and the charge time and frequency domain signals of coal samples with different primary fissures are analyzed in the paper. On-site monitoring of charge in different fissures distribution areas of underground coal tunnels, and the charge signals of different drillingdepths in coal seams are analyzed. The results show that the uniaxial compressive strength and elastic modulus of multi-fissured coal samples are less than those of less fissured coal samples, and the Poisson’s ratio is greater than those of less fissured coal samples. The charge induction signal intensity during the fracture process of multi-fissured coal samples is relatively low, but it is concentrated at the low frequency of 0–50 Hz in the compacting elasticity stage. The charge signal intensity during the fracture process of coal samples with less fissure is relatively high, and the charge frequency during the reinforcement damage stage is concentrated at a low frequency of 0–50 Hz. Therefore, the sudden appearance of low-frequency charge signals is more suitable as effective precursor information for the instability and failure of less fissured coal bodies. The average charge intensity is small in the multi-fissured area with a drilling depth of 1–4 m in the coal seam, and the average charge intensity of the coal body with less fissures is larger in the 5–12 m region. The on-site charge monitoring results have good consistency with the indoor test results. This study has guiding significance in setting up a charge monitoring warning index of instability failure in different coal body fissures regions.

With the continuous development and progress of society, age estimation based on deep learning has gradually become a key link in human-computer interaction. Widely combined with other fields of application, this paper performs a gradient division of human fall behavior according to the age estimation of the human body, a complete priority detection of the key population, and a phased single aggregation backbone network VoVNetv4 was proposed for feature extraction. At the same time, the regional single aggregation module ROSA module was constructed to encapsulate the feature module regionally. The adaptive stage module was used for feature smoothing. Consistent predictions for each task were made using the CORAL framework as a classifier and tasks were divided in binary. At the same time, a gradient two-node fall detection framework combined with age estimation was designed. The detection was divided into a primary node and a secondary node. In the first-level node, the age estimation algorithm based on VoVNetv4 was used to classify the population of different age groups. A face tracking algorithm was constructed by combining the key point matrices of humans, and the body processed by OpenPose with the central coordinates of the human face. In the secondary node, human age gradient information was used to detect human falls based on the AT-MLP model. The experimental results show that compared with Resnet-34, the MAE value of the proposed method decreased by 0.41. Compared with curriculum learning and the CORAL-CNN method, MAE value decreased by 0.17 relative to the RMSE value. Compared with other methods, the method in this paper was significantly lower, with a biggest drop of 0.51.

Because of the lack of comprehensive evaluation on the control design reliability and their control ability of rockburst in current rockburst mines, the rockburst still occurs in some mines although the rockburst control measures have been taken. Based on the method of evaluating the safety degree by safety factor in geotechnical engineering, the basic idea of rockburst mine safety is put forward. Through site investigations, it is found that the damage area caused by rockburst is limited in proportion to the total working area of the working face. The stress concentration in the surrounding rock of mine roadway is limited, ranging from 1 to 6. The energy released by rockburst accidents is no more than 109 J level, that is, the energy released by rockburst is limited. The safety evaluation of rockburst mine can be transformed into roadway safety evaluation, that is, the safety of roadway can ensure the safety of the whole mine. After rock burst occurs, controlling the shrinkage rate of roadway section within 20% can basically avoid casualties. Therefore, it is pointed out that rockburst can be prevented and controlled. Therefore, the conditions of non-occurrence of rockburst and occurrence of no casualties are put forward, that is, the actual load stress of roadway surrounding rock deformation system is lower than the critical stress of rockburst when roadway instability occurs and the energy released by the instability of the surrounding rock deformation system is lower than that absorbed by the surrounding rock support system. Safety evaluation should be carried out after impact risk evaluation, hazard classification and control design of rockburst, which includes critical condition, calculation of safety factor and classification of safety grade. Based on the instability theory of rockburst disturbance response, two aspects that need to be considered in safety evaluation are given: stress safety and energy safety. The stress safety is determined by the ratio of the actual stress under load to the critical stress of buckling in the surrounding rock deformation system (i.e. the stress safety factor). The energy safety is determined by the ratio of energy released from the instability of surrounding rock deformation system to the energy absorbed by surrounding rock supporting system (i.e. energy safety factor). Furthermore, the mine safety is divided into three levels: A, B and C, corresponding to safety, basic safety and unsafe respectively. Among them, if the stress safety factor is greater than 1.5 and the energy safety factor is greater than 1.0, it is a Grade A safe mine. The mine has control ability of rockburst and can be mined normally. If the stress safety factor is greater than 1.0 and the energy safety factor is greater than 1.5, it is a Grade B basic safety mine. The mine has control ability of rockburst and can be mined normally. If the safety factor is not Grade A or Grade B, it is classified as Grade C unsafe mine. The mine does not have control capability of rockburst or mining activities should be suspended. Taking a mine as an example, the complete flow of mine safety calculation and evaluation results are given. Finally, the stress safety factor and energy safety factor of some coal mines in China are given. Combined with the actual occurrence of rockburst in these mines, the reference of the calculation results of safety factor is verified, which shows that the safety evaluation method has certain reliability and practicability.

In recent years, the research of autonomous driving and mobile robot technology is a hot research direction. The ability of simultaneous positioning and mapping is an important prerequisite for unmanned systems. Lidar is widely used as the main sensor in SLAM (Simultaneous Localization and Mapping) technology because of its high precision and all-weather operation. The combination of Lidar and IMU (Inertial Measurement Unit) is an effective method to improve overall accuracy. In this paper, multi-line Lidar is used as the main data acquisition sensor, and the data provided by IMU is integrated to study robot positioning and environment modeling. On the one hand, this paper proposes an optimization method of tight coupling of lidar and IMU using factor mapping to optimize the mapping effect. Use the sliding window to limit the number of frames optimized in the factor graph. The edge method is used to ensure that the optimization accuracy is not reduced. The results show that the point plane matching mapping method based on factor graph optimization has a better mapping effect and smaller error. After using sliding window optimization, the speed is improved, which is an important basis for the realization of unmanned systems. On the other hand, on the basis of improving the method of optimizing the mapping using factor mapping, the scanning context loopback detection method is integrated to improve the mapping accuracy. Experiments show that the mapping accuracy is improved and the matching speed between two frames is reduced under loopback mapping. However, it does not affect real-time positioning and mapping, and can meet the requirements of real-time positioning and mapping in practical applications.

Aiming at the problem that the model of YOLOv4 algorithm has too many parameters and the detection effect of small targets is poor, this paper proposes an improved helmet fitting detection model based on YOLOv4 algorithm. Firstly, this model improves the detection accuracy of small targets by adding multi-scale prediction and improving the structure of PANet network. Then, the improved depth-separable convolution was used to replace the standard 3 × 3 convolution, which greatly reduced the model parameters without reducing the detection ability of the model. Finally, the k_means clustering algorithm is used to optimize the prior box. The model was tested on the self-made helmet dataset helmet_dataset. Experimental results show that compared with the safety helmet detection model based on Faster RCNN algorithm, the improved YOLOv4 algorithm has faster detection speed, higher detection accuracy and smaller number of model parameters. Compared with the original YOLOv4 model, the mAP of the improved YOLOv4 algorithm is increased by 0.49%, reaching 93.05%. The number of model parameters was reduced by about 58%, to about 105 MB. The model reasoning speed is 35 FPS. The improved YOLOv4 algorithm can meet the requirements of helmet wearing detection in multiple scenarios.

It is of great significance to study the pattern of displacing methane gas with water in the coal seam water injection process for the prevention and control of gas disasters. A two-phase displacement test device was used to conduct experiments on the water injection of coal samples to displace methane gas under different water injection pressures, and the influence of the water injection pressure on the displacement was analyzed. The test results show that with the same displacement time, the ratio of displaced methane increases with the increase in the water injection pressure. The displacement rate increases with the increase in the water injection pressure at the stage without water discharge, while the water displacement rate under different water injection pressures differed slightly; in the later displacement stage, a higher water injection pressure of the coal sample results in a faster attenuation of the displacement rate and water displacement rate due to the decrease in the methane content in the coal sample. There is a critical water injection pressure to displace methane gas. When the critical water injection pressure is exceeded, the displacement time does not change appreciably. Flowing water can displace a large amount of methane gas in coal, and the methane displacement rate increases with the increase in the water injection pressure. The high solubility of methane in water is the reason for the high methane displacement rate. The results of this study can provide theoretical guidance for coal seam water injection to control gas disasters.

Visual attention mechanism has been widely used in computer vision and plays a vital role in the research of human action recognition. In this paper, we explore a novel moving target detection mechanism for human action recognition and propose a new 3D CNN (3D Convolutional Neural Network) model, dubbed LaM-2SRN (Local Features Enhanced and Moving target detected 2Stream-ResNet) for extracting and learning attention-enhanced spatiotemporal features. The contributions of this paper are as follow: First, the traditional CAM (Class Activation Map) based visual attention algorithm is used to obtain the optical flow information of the human region, thus eliminating the influence of irrelevant optical flow information (such as background clutter). Second, the ViBe algorithm is used to identify the moving target in the continuous frame, retain the optical flow information of the moving target, and make it complement with the optical flow information of the human region, to obtain a complete motion descriptor. After the motion information is marked in the video frame, we put the marked video frames and the original video frames into the 3D CNN and 2D CNN models respectively, to acquired mixed descriptor, which serves as the basis for video classification. Different from most of the previous target detection algorithms, this paper not only detects the human target, but also detects the moving foreground targets in the video, so that the pre-trained CNN model can obtain more complete motion information from videos. We use RGB-only video data for evaluation on two benchmarks: UCF101 and HMDB51, the experimental results demonstrate that our LaM-2SRN is comparable to the previous state-of-the-art algorithms.

Safety equipment detection is an important application of object detection, receiving widespread attention in fields such as smart construction sites and video surveillance. Significant progress has been made in object detection due to the rapid development of deep learning. Multi-scale targets and complex scenes increase the likelihood of false positives and missed detections, which can affect the accuracy of the detection. To address this issue, this study proposes YOLOv7-DSE. It is a small complex target scene detection network based on the improved YOLOv7. Also, we have created a private dataset of safety equipment. First, we enhanced the ELAN and MP backbone networks. Backbone is replaced by ordinary convolution by the depthwise separable convolution. We enabled the backbone network to extract deeper image features without increasing the amount of parameters and computation. Simultaneously, the model incorporates the EIOU loss function to improve its convergence speed and positioning effect. Secondly, we propose a new ELAN-SPD structure in the head network. Based on the ELAN structure, a space-to-depth convolutional layer is added to fully downsample the feature map, preserving all learnable features. Our network model can better detect objects with significant size differences faced with complex scenes. YOLOv7-DSE achieved the mAP of 82.38%, surpassing the original YOLOv7 with 2.64%. The YOLOv7-DSE model has a minor size compared to the baseline model. Our improvement has reduced the model parameters by 22.4%. [ABSTRACT FROM AUTHOR]

To enhance the capability of classifying and localizing defects on the surface of hot-rolled strips, this paper proposed an algorithm based on YOLOv7 to improve defect detection. The BI-SPPFCSPC structure was incorporated into the feature pyramid in this algorithm, enabling enhanced extraction of features from small objects and improved accuracy in network model positioning. Additionally, a small object detection layer was introduced to enhance shallow feature capture. Then the CARAFE sampling operator was used for up-sampling to reduce the feature loss problem of small objects. Finally, the WIoU served as the loss function for network model training to expedite convergence. The NEU-DET dataset was utilized for ablation and comparison tests. The findings indicated that the enhanced YOLOv7 model's mAP value had increased to 80.7%. The detection impact was much enhanced in comparison to other traditional models, and the frequency of false and missing detections was also decreased. [ABSTRACT FROM AUTHOR]

Aiming at the problems of low recognition accuracy and large calculation amount of age estimation, this paper proposes a staged single aggregation backbone network VoVNetv4. In order to improve the feature extraction ability of the network, the Regional One-Shot Aggregation (ROSA) module is proposed in the network for regional encapsulation of the feature module. The classifier adopts the COnsistent RAnk Logits (CORAL) framework, which can solve the problem of inconsistency of classifiers in ordered regression CNNs for multiple binary classification tasks. This paper conducts experimental verification on the Asian Face Age Dataset (AFAD) and compares it with other research methods. The experimental results show that VoVNetv4 can effectively improve the feature extraction and detection ability of the network and improve the detection efficiency of age estimation. [ABSTRACT FROM AUTHOR]

In modern society, image encryption is critical to protecting digital visual information. A chaotic image encryption scheme based on RNA operations and heart-shaped chunking is proposed for a color image. There are five phases to the program. Firstly, a new chaotic system, 2D-NICM, is designed to improve the infinite folding chaotic mapping of twodimensional. Secondly, the segmented linear chaotic map (PWLCM) is associated with plains to generate chaotic sequences. This step leads to an improvement in the sensitivity of plain. Thirdly, the color images are layered. Then the downward and leftward circular shift diffusion operations are performed using the RNA algorithm. The selection of operators is based on the class of amino acids. Chaotic sequences ultimately control the coding rules of RNA computation. This step makes the result of the operation more unpredictable. Fourthly, this section chunks the initial cipher image after RNA operation. Finally, the chunked initial cipher images are encrypted in heart shape. The final password image is obtained after all five steps. Simulation results show that the proposed model outperforms the others. Furthermore, based on the highentropy value, the model has a high anti-jamming ability for common attacks. [ABSTRACT FROM AUTHOR]

To enhance the reliability and effectiveness of image encryption, a perceptron neural network based on HPW chaotic system is proposed. First, this algorithm combines Henon chaotic map with PWLCM chaotic map to get the improved chaotic map. It is called the HPW map. After that, input the array obtained from image decomposition into the perceptron neural network. Finally, it is combined with the chaotic matrix to complete digital image encryption. Throughout encryption, this encryption method simultaneously inputs two points into the perceptron neural network for operation, and uses the method of diffusion and scrambling to encrypt at the same time. In addition, the plain correlation method is used to complete the image encryption. This paper tests the encryption algorithm through 6 image encryption indexes, and the outcomes demonstrate that the algorithm has good efficiency and security. [ABSTRACT FROM AUTHOR]

Aiming at the problem that human behavior is difficult to identify, a bottom-up and horizontal connections Cross-dimensional Feature Fusion MLP model (CFF-MLP) was proposed in this paper. To improve the detection performance of human behavior and realize the effective capture of continuous behavior features, a human key point Vector tracking (VT) algorithm based on optical flow was designed in the CFF-MLP model. This model can obtain the behavioral features and local dependencies of different layers hierarchically. Furthermore, it enhances the generalization ability of the model. The validity of the proposed model is verified and analyzed using KTH dataset and compared with other research methods. The experimental results show that the CFF-MLP model can effectively improve the detection ability of human micro-motion, and its average accuracy rate reaches 94.23%. It improves the detection efficiency of human behavior. [ABSTRACT FROM AUTHOR]

In this digital age, images have become one of the most important digital information. In order to ensure the security of images, various image encryption algorithms have come out one after another. Many excellent characteristics of chaotic maps can effectively enhance the stability of image encryption algorithms. Image encryption algorithms based on chaotic systems have become the focus of image encryption algorithm research. This paper proposes an image encryption algorithm combining neural network and chaotic map. A chaos matrix is generated by the Hopfield neural network model for image diffusion. The keys can be selected in the range of pixel values, and the keys space is larger. In this paper, the value of the keys are selected as three random pixel values of the image after the separation of the three primary colors of the plain. Because the pixel value of each image is different, the key is also different. Each image generates a different chaotic sequence, achieving "one key at a time". A chaos matrix is generated by Lorenz chaotic system for image scrambling. The diffusion and scrambling are carried out at the same time. Several indicators are analyzed in the experiment, and the experimental results show that the algorithm improves the key sensitivity and plain sensitivity, expands the key space, and can resist some common attacks, such as differential attack, individual diffusion attack, individual scrambling attack, etc. [ABSTRACT FROM AUTHOR]

To overcome the challenges of obstacle avoidance for Unmanned Aerial Vehicles (UAVs) in autonomous flights, this paper proposes the Dual Experience Attention Convolution Soft Actor-Critic (DAC-SAC) algorithm. This algorithm integrates a dual experience buffer pool, a self-attention mechanism, and the Soft-Actor-Critic algorithm with a convolutional network. The dual experience buffer pools are used to solve the problem of ineffective UAV training due to the scarcity of successful training data. To overcome the drawbacks of the original Soft Actor-Critic (SAC) algorithm in handling image data, a Convolutional Neural Network (CNN) is applied to reconstruct the actor and critic network, allowing for better image feature extraction and classification. Furthermore, a self-attention mechanism is employed by adding a convolutional self-attention layer to the network. This modification enables dynamic adjustments for the attention weights based on varying input image features, effectively addressing focus-related challenges. Two simulation experiments are performed and the DAC-SAC algorithm achieves a 99.5% success rate in a known environment and an 84.8% success rate when dealing with an unknown environment. These results confirm that the proposed algorithm enables autonomous obstacle avoidance for UAVs even when considering depth images as input. [ABSTRACT FROM AUTHOR]

Addressing the problem that the human body is difficult to be correctly identified in the process of falling, this study proposes an Attention Mechanism and Time Series MLP (AT-MLP) model. To realize the capture of body features during the state and process of the fall of the human body, the time series is combined in the submodule. Thus, the subspace Angle Time Series algorithm (ATS) and the subspace Angle Difference-value Time Series algorithm (ADTS) are designed. The AT-MLP stage composed of Convolutional Block Attention Module (CBAM) and MLP blocks is constructed in the model to strengthen the relation between the time and space dimensions. Comparing with other methods on the Le2i Fall detection Dataset (LFDD) to verify the effectiveness of the AT-MLP model, the experimental results show that the AT-MLP model effectively improves the detection efficiency of human falls and has strong generalization ability. [ABSTRACT FROM AUTHOR]

In understanding human behaviour, computers sometimes condense their analysis of human behaviour into an analysis of the state of movement of keypoints in the human body. Thus, the technique of human pose estimation provides a convenient means for machines to recognise people's behaviour. The lightweight pose estimation network enables computers to detect human poses in real-time. This paper proposes Lightweight HRNet, a bottom-up lightweight network for multi-person human pose estimation. The network is proposed based on the HRNet architecture and includes four network branches with different resolutions and two network stages. The network backbone uses the ShuffleNet model, which allows the network to be better used on smaller devices. Notably, Lightweight HRNet focuses on a problem with multi-resolution, multi-branch parallel networks: not all stages of the network contain information about the feature maps of all its branches. Therefore, we proposed the Channel Exchange Module (CEM), which improves the exchange of information between each stage of the network and each of its branches. Among the tasks of human pose estimation, the addition of CEM improved the network accuracy of Lightweight HRNet by 0.9% in the COCO2017 test-dev. Finally, the network was able to achieve 46.6% accuracy on the COCO2017 test-dev. This accuracy is superior in the study of bottom-up lightweight human pose estimation networks. [ABSTRACT FROM AUTHOR]

Deep learning is proliferating within the field of computer vision. Road damage detection technology, as its offshoot, already plays vital role in road maintenance and traffic safety. With road damage such as potholes and cracks, accurate and efficient detection results are essential for timely road safety repair and maintenance. Therefore, road damage detection algorithms based on deep learning have attracted wide attention. YOLOv5 is an advanced target detection algorithm known for its efficient detection speed and good accuracy. However, there is still room for further improvement in its performance for road damage detection. The ability of multi-scale damage detection and spatial structure capture is not perfect. Therefore, this paper proposes three improvement points to improve the accuracy of road damage detection based on YOLOv5. The first introduced module is the Non-linear Spatial Pyramidal Pooling-Fast (NSPPF) module. This module allows for better capture of detailed features of road damage areas. Non-linear transformation and fast pyramid operation improve the sensing ability and multi-scale damage detection ability. Secondly, a combination of the CoordConv and SK attention modules is constructed. The CoordConv module fuses coordinate information with features to provide a more spatially informed representation. The SK attention module also learns correlations between global and local features, enhancing the model's ability to detect damages at different scales. This paper can better capture road injuries' spatial structure and context information by combining these two modules. Finally, experimental results on the RDD2020 dataset demonstrate the effectiveness of our model. Compared to the baseline model, the proposed improvement algorithm increases the accuracy by 2.2%, resulting in a mAP of 58.2%. This demonstrates its effectiveness and feasibility. [ABSTRACT FROM AUTHOR]