Developing the concept of autonomous control of the quarry vehicles movement

Introduction. The article presents the results of studies related to the description of the synthesis and further analysis of the dynamic behavior of unmanned vehicles (UMVs) operating at coal opencast mines and other mining enterprises. The relevance of the research topic is dictated by the need to create safe and effective conditions for overburden / mining and mining transportation operations. This is ensured, among other things, by the operation of unmanned heavy-duty dump trucks. Purpose of the work: in the course of the research, a concept was developed for the formation of route parameters and models of the dynamics of movement of UMVs along technological routes. Methodology. The paper describes the technology for generating and processing signals in control subsystems as part of an automated dispatching system and an on-board subsystem for autonomous control of the UMV. Research methods include the study of the shapes and characteristics of current trajectories (CT) in relation to a nominal axial trajectory (NAT). In this case, a current trajectory of the UMV is considered within the framework of the so-called S-frames, which are formed as geolocations on a certain working UMV route from a bench face to the place of unloading and vice versa. As a variable characterizing the UMV behavior on a current trajectory, a 1D-signal with a time dependent frequency is adopted, the nature of the change of which is determined by the CT dynamic shape relative to the NAT. Results. Such chirp signals – together with the wavelet transforms technique introduced into consideration – allow us in a semantically transparent and information-rich videographic form to display and subject to further processing signals characterizing the current behavior of a UMV on a route. The resulting parameters of such secondary wavelet representations of the current UMV dynamics (wavelet maps) are further planned to be used in the subsystem of dynamic modal control of the UMV movement in the open pit. Conclusions. The results of the studies carried out make it possible to form current routes of UMV movement according to the models generated based on the analytical tools accompanying the dynamics of the UMVs, proposed in the work.

The concept of controlling the unmanned vehicles in open pit mining

Introduction. The article presents the results of studies related to the description of the synthesis and further analysis of the dynamic behavior of unmanned vehicles (UMV) operating in coal-mining pits and other mining quarries. The urgency of the discussed study is dictated by the need to create safe and effective conditions for stripping / mining and transportation operations. This is ensured, among other things, by the operation of unmanned heavy-duty dump cars. Research aim is to develop the concept for the formation of route parameters and models of the movement dynamics of vehicles along technological routes. Methodology. The paper describes the technology for generating and processing the signals in control subsystems as parts of both the computer-aided dispatching system and the on-board autonomous ISSN 0536-1028 «Известия вузов. Горный журнал», № 8, 2020 119 control subsystem of the UMV. The methods used in the research include the study of the forms and characteristics of current trajectories (CT) in relation to a nominal axial trajectory (NAT). In this case, a current trajectory of the UMV is considered within the framework of the so-called S-frames, which are generated in the form of geolocations on a working route of the UMV from the mining face to the place of unloading and vice versa. As a variable characterizing the behavior of the UMV on a current trajectory, a 1D-signal with a time-dependent frequency is adopted, the nature of the change of which is determined by the dynamic shape of a CT with regard to the NAT. Results. Such chirp-signals, together with the wavelet transform apparatus introduced into consideration, allow in a semantically transparent and information-rich video graphic form to represent and subject to further processing the signals characterizing a certain UMV current behavior on the route. The obtained parameters of such secondary wavelet representations of the UMV current dynamics (wavelet maps) are further planned to be used in the subsystem for dynamic modal controlling the UMV movement in the opencast mine. Conclusions. The results of the research allow us to form current routes of UMVs movement according to the models based on the analytical tools accompanying the dynamics of the UMV, proposed in the work.

Comparative analysis of two new concepts of adaptive training

Two new concepts of adaptive learning are presented. The first of them is based on a self-learning probabilistic model, the second one uses multivariate statistical analysis of wavelet representations for task execution trajectories as well as a matrix of recommended transitions. A comparative analysis of various aspects of their practical application has been carried out.

Developing automatic recognition system of drill wear in standard laminated chipboard drilling process

The paper presents an automatic approach to recognition of the drill condition in a standard laminated chipboard drilling process. The state of the drill is classified into two classes: “useful” (sharp enough) and “useless” (worn out). The case “useless” indicates symptoms of excessive drill wear, unsatisfactory from the point of view of furniture processing quality. On the other hand the “useful” state identifies tools which are still able to drill holes acceptable due to the required processing quality. The main problem in this task is to choose an appropriate set of diagnostic features (variables), based on which the recognition of drill state (“useful” versus “useless”) can be made. The features have been generated based on 5 registered signals: feed force, cutting torque, noise, vibration and acoustic emission. Different statistical parameters describing these signals and also their Fourier and wavelet representations have been used for defining the features. Sequential feature selection is applied to detect the most class discriminative set of features. The final step of recognition is done by using three types of classifiers, including support vector machine, ensemble of decision trees and random forest. Six standard drills of 12 mm diameter with tungsten carbide tips were used in experiments. The results have confirmed good quality of the proposed diagnostic system.