During the operation of the belt conveyor, foreign objects such as large gangue and anchor rods may be mixed into the conveyor belt, resulting in tears and fractures, which affect transportation efficiency and production safety. In this paper, we propose a lightweight target detection algorithm, GhostNet-CBAM-YOLOv4, to resolve the problem of the difficulty of detecting foreign objects at high-speed movement in an underground conveyor belt. The Kmeans++ clustering method was used to preprocess the data set to obtain the anchor box suitable for the foreign object size. The GhostNet lightweight module replaced the backbone network, reducing the model’s parameters. The CBAM attention module was introduced to enhance the ability of feature extraction facing the complex environment under the mine. The depth separable convolution was used to simplify the model structure and reduce the number of parameters and calculations. The detection accuracy of the improved method on the foreign body data set reached 99.32%, and the detection rate reached 54.7 FPS, which was 6.83% and 42.1% higher than the original YOLOv4 model, respectively. The improved method performed better than the original model on the other two datasets and could effectively avoid misdetection and omission detection. In comparison experiments with similar methods, our proposed method also demonstrated good performance, verifying its effectiveness.

Water hydraulic piston motor is one of the important transmission components in a water hydraulic system. For lack of enough experimental information to analyze the reliability in water hydraulic motor design, the convex model is chosen as wear reliability model for hydraulic friction pairs, which is more economical and reasonable than the interval model. The non-probabilistic reliability index based on the convex model is established using first-order Taylor series expansion, and the non-probabilistic reliability model of wear reliability analysis for the friction pair of swash-plate/slipper in water hydraulic piston motor is introduced based on the convex model. For the non-probabilistic reliability model, only the bounds on uncertain parameters are needed, instead of probabilistic density distribution or statistical quantities. Numerical examples are used to illustrate the validity and feasibility of the presented method.

Purpose: This paper aims to optimize the weighing control system and compensate weighing error for weighing control system of coal mine paste-filling weighing control system. Design/methodology/approach: The process of the paste-filling weighing control system is analyzed and the mathematical model of the paste-filling material weight is established. Then, the back-propagation (BP) neural network is used to optimize the control system and compensate the weighing error. Findings: Without the BP neural network, the weighing error of the paste-filling control system is more than 3 per cent, whereas after optimization with the BP neural network, the weighing error is less than 1 per cent. With the simulation results, it is seen that the weighing error of the paste-filling control system decreases and the accuracy of the weighing control system improves and optimizes. Originality/value: The method can be further used to improve the control precision of the coal mine paste-filling system.

Air is the environmental foundation for human life and production, and its composition changes are closely related to human activities. Sulfur dioxide (SO₂) is one of the main atmospheric pollutants, mainly derived from the combustion of fossil fuels. But SO₂ is a trace gas in the atmosphere, and its concentration may be less than one part per billion (ppb). This paper is based on the principle of photoluminescence and uses a photomultiplier tube (PMT) as a photoelectric converter to develop a device for real-time detection of SO₂ concentration in the atmosphere. This paper focuses on the impact of noise interference on weak electrical signals and uses wavelet transform to denoise the signals. At the same time, considering that the photoelectric system is susceptible to temperature changes, a multi parameter fitting model is constructed, and a BP neural network is used to further process the signal, separating the real data from the original data. Finally, a high-precision and wide-range trace level sulfur dioxide concentration detection device and algorithm were obtained.

Purpose: This paper aims to study a modular method for designing a paste filling station (PFS) for a coal mine (CM) to reduce the PFS’s input cost and achieve reutilization. Design/methodology/approach: Modular design criteria for the PFS are proposed and a modular division (MDiv) model and an evaluation method are established. The correlation-strength matrix of the PFS parts expressed in the form of rough numbers is transformed into a fuzzy equivalent matrix. The theory of rough sets and the fuzzy clustering method are introduced for PFS MDiv. The evaluating method is established for the PFS MDiv scheme based on the principle of fuzzy comprehensive evaluation. Findings: Taking a particular CM PFS as an example, the above method is used to modularize the PFS, and the optimal division of the PFS is finally determined via the above evaluation system. Applying this method solves the problem of high cost investment in the initial stage of PFS construction. Originality/value: The theory of rough sets and the fuzzy clustering method are introduced for PFS MDiv. An evaluating method is established for the PFS MDiv scheme based on the principle of fuzzy comprehensive evaluation, thereby providing new ideas for PFS transformation and reutilization.

Currently, although semi-supervised image segmentation has achieved significant success in many aspects, further improvement in segmentation accuracy is necessary for practical applications. Additionally, there are fewer networks specifically designed for segmenting 3D images compared to those for 2D images, and their performance is notably inferior. To enhance the efficiency of network training, various attention mechanisms have been integrated into network models. However, these networks have not effectively extracted all the useful spatial or channel information. Particularly for 3D medical images, which contain rich spatial and channel information with tightly interconnected relationships between them, there remains a wealth of spatial and channel-specific information waiting to be explored and utilized. This paper proposes a bidirectional and efficient attention parallel network (BEAP-Net). Specifically, we introduce two modules: Supreme Channel Attention (SCA) and Parallel Spatial Attention (PSA). These modules aim to extract more spatial and channel-specific feature information and effectively utilize it. We combine the principles of consistency training and entropy regularization to enable mutual learning among sub-models. We evaluate the proposed BEAP-Net on two public 3D medical datasets, LA and Pancreas. The network outperforms the current state of the art in eight algorithms and is better suited for 3D medical images. It achieves the new best semi-supervised segmentation performance on the LA database. Ablation studies further validate the effectiveness of each component of the proposed model. Moreover, the SCA and PSA modules proposed can be seamlessly integrated into other 3D medical image segmentation networks to yield significant performance gains.