Accurate and rapid recognition of coal and gangue is an important prerequisite for safe and efficient mining in top coal caving face. In this paper, a novel coal-gangue recognition method is put forward based on improved ant-lion optimization algorithm (IALO), variational modal decomposition (VMD) and improved MobileNetV2 network. Firstly, two strategies of trap boundary adjustment and chaotic mapping are designed for ALO to sufficiently explore the solution space and prevent falling into local optimization. Subsequently, IALO is employed to search the optimal parameters of VMD and the superiority of IALO-VMD can be reasonably embodied through some simulation analysis. Then, the vibration signal-image mapping is performed to produce rich sample data for MobileNetV2. The coordinate attention mechanism and Inception structure are combined with MobileNetV2 to accelerate the training speed and improve the classification accuracy, and the improved MobileNetV2 based classifier is constructed to fulfill an automatic coal-gangue recognition. Finally, an experimental platform of coal-gangue impacting the tail beam of hydraulic support is built and many comparison experiments are carried out. The experiment results indicate that the proposed coal-gangue recognition method has the prediction accuracy of 99.66%, which is increased by 1.43% compared to the classical MobileNetV2. The underground on-site testing results show that the average prediction accuracy of the proposed coal-gangue recognition model can exceed 93%, and can effectively and accurately distinguish different top coal caving states.

Current positioning methods for indoor or outdoor robots show poor applicability and limited performance for underground mobile equipment with complex scene interference, such as narrow roadways, heavy dust, and poor illumination. Therefore, a fusion positioning framework is proposed based on redundant inertial measurement units (IMUs) and ultra-wideband (UWB) by using a factor graph (FG). In this framework, six layout models of redundant IMUs are designed and compared to fundamentally inhibit the accumulation of positioning errors to a large extent. Then, the optimal layout parameters of base stations are explored through many simulation experiments in terms of the number, shape, and height to preliminarily improve the positioning accuracy of the UWB system. A hybrid calculation method based on bacterial foraging optimization algorithm and Taylor is provided to further enhance the positioning accuracy of UWB in a complex environment. Subsequently, the UWB credibility factor is developed to dynamically adjust the fusion weight of UWB information, to weaken the influence of the non-line of sight errors. Furthermore, FG architecture integrated with the UWB credibility factor is applied to fuse redundant IMUs and UWB for accurate positioning. Some simulations and experiments are carried out and the comparison results verify the superiority and practicability of the proposed positioning method for underground equipment.

Roboticized coal mining equipment is an important way to achieve intelligent coal mining. The perception system of robots is crucial for coal mine robots to understand their operating environment and conditions, serving as the functional foundation for autonomous operation in coal mines. However, due to the harsh and complexly changing conditions in underground coal mine environments, it is difficult for robotized coal mining equipment to obtain information about the underground environment accurately and reliably. In response to the characteristics of underground coal mine environments, an adaptive enhancement method for coal-mine underground images based on no-reference image quality evaluation is proposed in that paper. Its core is to establish a quality evaluation model for visible light images for underground coal mines, and to develop an adaptive optimization algorithm for image enhancement parameters based on the improved Sparrow Search Algorithm. Relevant experiments are conducted to demonstrate the performance of the proposed method. Experimental results show that, for three common enhancement methods, including CLAHE, homomorphic filtering and AutomateMSRCR algorithms, the results obtained from the optimized algorithms are improved by an average of 41.28%, 2.67%, 19.06%, 43.62%, and 129.46% respectively in terms of the SMD function, entropy function, variance function, Brenner gradient function, and Laplacian gradient function indicators, and the proposed adaptive image enhancement method shows strong application potential for the scene perception tasks including the anchor-rod tail detection and etc.

Accurate recognition of coal-rock properties (CRPs) is an important prerequisite for ensuring the intelligent control and stable operation of shearer. The main challenges in industrial applications are potential safety hazards and single cutting mode in coal mining face, resulting in samples with insufficient number, unbalanced distribution, and background interference. However, most current CRPs recognition methods rely on sufficient and balanced samples, limiting their application efficiency and scope. To this end, this article proposes a dual discriminator and adaptive multisource feature fusion Wasserstein generative adversarial network with gradient penalty for generating high-quality infrared thermal (IRT) images to assist in CRPs recognition under limited samples. First, dual discriminator network with U-Net model is designed to obtain the global and local feature and optimize the training strategy of the generator. Then, adaptive multisource feature fusion mechanism is constructed by combining random noise and intermediate feature to guide the generator for adversarial learning and avoid violent oscillations at the initial stage of model training. Finally, conditional random field is employed to perform postprocessing operations to improve the accuracy of the sample generation boundaries. The experimental results show that the proposed method outperforms other state-of-the-art models and effectively assists in the recognition of CRPs under limited samples.

Anti-disturbance vibration control is a crucial component in a hydraulic suspension system. However, random input excitation and prolonged service can cause hydraulic suspension system parameters to drift, leading to system vibration with suppression failure. The resulting states of nonlinearity and disturbance will lead to a gradual deterioration of pressure control. Therefore, designing a viable controller for a hydraulic suspension system that considers system nonlinearity, computing capacity, and sensor configuration is essential. To address this need, we present a double-layer control strategy in this work. A hybrid sliding mode control algorithm based on the reference skyhook and groundhook model is proposed to regulate the expected force of reverse compensation. An output controller is then applied based on the expected force observer to mitigate low-frequency vibrations to realize a steady state. A logic rule is designed to ensure that the two controllers work to suppress sprung mass vibration, and a comprehensive system model is derived to help characterize system nonlinearities and design the hybrid sliding model controller. Numerical and physical validations are then carried out to demonstrate the feasibility of the strategy and test the performance of the controller. The experimental results show that the hybrid sliding mode controller can suppress vibration under disturbance excitation and reduce the vibration acceleration to a 2.3 m/s² random response when system parameters vary.

The drilling robot is the key equipment for pressure relief in rockburst mines, and the accurate recognition of a pressure relief hole is the premise for optimizing the layout of pressure relief holes and intelligent drilling. In view of this, a pressure relief hole recognition method for a drilling robot, based on single-image generative adversarial network (SinGAN) and improved faster region convolution neural network (Faster R-CNN), is proposed. Aiming at the problem of insufficient sample generation diversity and poor performance of the traditional SinGAN model, some improvement measures including image size adjustment, multi-stage training, and dynamically changing iteration times are designed as an improved SinGAN for the generation of pressure relief hole images. In addition, to solve the problem that the traditional depth neural network is not ideal for small-size target recognition, an improved Faster R-CNN based on multi-scale image input and multi-layer feature fusion is designed with the improved SqueezeNet as the framework, and the sample data collected from ground experiments are used for comparative analysis. The results indicate that the improved SinGAN model can improve the diversity of generated images on the premise of ensuring the quality of image samples, and can greatly improve the training speed of the model. The accuracy and recall rate of the improved Faster R-CNN model were able to reach 90.09% and 98.32%, respectively, and the average detection time was 0.19 s, which verifies the superiority of the improved Faster R-CNN model. To further verify the practicability of the proposed method, some field images were collected from the underground rockburst relief area in the coal mine, and a corresponding test analysis was carried out. Compared with three YOLO models, the accuracy and recall rate of improved Faster R-CNN model improved significantly, although the training time and recognition time increased to a certain extent, which proves the feasibility and effectiveness of the proposed method.