The article presents aspects of the development of a device for wirelessly picking up a vibration acceleration signal from the surface of a ball mill drum. The results of measuring vibration acceleration for a ball mill model for various levels of loading with crushed material are presented. According to these results, with an increase in the load of crushed materials relative to the ball, the level of vibration decreases. The work also presents the obtained pie diagrams of the distribution of vibration load across the mill drum, from which one can judge its current operating mode.

Keywords: ball mill, wireless signal, vibration acceleration, mill loading control

The drilling and blasting method is currently the most widely used for mining rocks. An indicator of the high–quality drilling and blasting operations is the uniform granulometric composition of the exploded rock mass - the percentage of oversized ore pieces should be minimal. The percentage of oversized and its increase have a significant impact on the technical processes of transporting rock mass, leading to an increase in the costs of loading and transportation operations and secondary crushing of oversized ore masses. The paper describes the results of a study of methods for determining the granulometric composition of drilling and blasting operations using neural networks of segmentation Unet and FPN. Images taken from UAVs are used for analysis. A method of classifying ore by size has also been developed, which ensures the accuracy of the proportion of correct answers of more than 0.91. The expected result of the introduction of the system for automatic determination of the granulometric composition of drilling and blasting operations is the possibility of more accurate control over the quality of their performance.

Keywords: granulometric composition, Unet, FPN, classification, segmentation

In this work, the developed system for detecting areas with defects in the development of corn crops was investigated from a photograph taken by an unmanned aerial vehicle (UAV) using computer vision. To solve the problem of detecting such sites, the structures of the YOLOv5 and YOLOv8 neural networks were considered. The use of the developed software will reduce labor and time costs for image analysis, which in turn will reduce the response time when problem areas are detected in agricultural fields to achieve higher yields.

Keywords: instance segmentation, YOLOv5, YOLOv8

Existing methods for determining the geometry of an enclosed space using echolocation assume the presence of a large amount of additional equipment (sound sources and receivers) in the room. This paper investigates a method for determining the geometry of enclosed spaces using sound location. The method does not assume the presence of a priori knowledge about the surrounding space. One sound source and one sound receiver were used to create and capture real impulse characteristics. A microphone was used as a sound receiver and a finger snap was used as a sound source to produce the impulse response. In this work, we used convolutional neural networks that were trained on a large dataset consisting of 48000 impulse responses and a number of room geometry parameters corresponding to them. The trained convolutional neural network was tested on the recorded impulse responses of a real room and showed accuracy ranging from 92.2 to 98.7% in estimating room size from various parameters.

Keywords: convolutional neural networks, room geometry, echolocation, impulse response, robotics, recognition, contactless methods of measuring objects, sonar, geometry prediction, virtual reality

The article deals with the problem of inaccurate allocation of the boundaries of ore pieces after an explosion in a quarry in the photo. In this article, the possibility of using neural networks for segmentation of photographs was investigated, and training, testing and comparison of the pre-trained bases of neural networks were carried out. The family of pre-irradiated bases EfficientNet and SEResNet was tested on the FPN neural network. Neural networks were tested on the same number of learning epochs, and competitively on three, five, seven and ten learning epochs. Training for more than ten epochs was impractical, since almost all networks were undergoing retraining. According to the results of the test and comparison, the result was obtained that the FPN neural network on the pre-trained EfficientNetB2 bases after 7 epochs of training has a segmentation quality of 98.93% in three segmentation classes and 55.1% in the "ore pieces" class.

Keywords: segmentation, neural network, pre-trained foundation, EfficientNet, SEResNet

The article discusses one of the approaches to the management of the ore grinding circuit, in particular, the process of loading the ore mill. For maximum performance, the mill must be loaded 47-50%, there are several ways to measure the mill load level. In this paper, we consider one of the methods of measuring the level of loading of the mill, in order to control the loading of the mill. The article investigates the prospect of using an extreme controller in conjunction with the observer States in the implementation of the control circuits mill loading. The resulting control system produces load control based on the current drive power of the mill. The peculiarity of this control system is that it is able not only to control the mill, but also to recognize the overload and take measures to prevent an emergency. There is no need for additional subsystems and algorithms. In addition, two models of management systems were developed and their effectiveness was compared. The advantages of using the state observer with respect to the classical extreme regulator are indicated.

Keywords: ball mill, automating, mathematical model, control loop, observer state, extreme controller

This article describes the results of research on the possibility of detecting sunflower plants from photographs taken by a UAV. The solution to this problem will allow automated control of an important agricultural parameter - seedling density. The problem is complicated by the limited amount of training sample and "disturbances" associated with field weeding. As the result we obtain that the YOLOv5m neural network is capable on a sample of 122 pictures to qualitatively detect plants with an error of 0.077% of training. Artificially increasing the sample to 363 pictures reduces the learning error to 0.063%. Disturbances reduce the detection efficiency of sunflower plants in the test images. It is possible to increase the detection efficiency either by adding original images to the training sample or by artificially enlarging the sample.

Keywords: detection, YOLOv5, sunflower, seedling density, neural network