Growing demand for raw materials forces mining companies to reach deeper deposits. Difficult environmental conditions, especially high temperature and the presence of toxic/explosives gases, as well as high seismic activity in deeply located areas, pose serious threats to humans. In such conditions, running an exploration strategy of machinery parks becomes a difficult challenge, especially from the point of view of technical facilities inspections performed by mining staff. Therefore, there is a growing need for new, reliable, and autonomous inspection solutions for mining infrastructure, which will limit the role of people in these areas. In this article, a method for detection of conveyor rollers failure based on an acoustic signal is described. The data were collected using an ANYmal autonomous legged robot inspecting conveyors operating at the Polish Ore Enrichment Plant of KGHM Polska Miedź S.A., a global producer of copper and silver. As a part of an experiment, about 100 m of operating belt conveyor were inspected. The sound-based fault detection in the plant conditions is not a trivial task, given a considerable level of sonic disturbance produced by a plurality of sources. Additionally, some disturbances partially coincide with the studied phenomenon. Therefore, a suitable filtering method was proposed. Developed diagnostic algorithms, as well as ANYmal robot inspection functionalities and resistance to underground conditions, are developed as a part of the “THING–subTerranean Haptic INvestiGator” project.
Conveying systems are responsible for a large part of continuous horizontal transportation in underground mines. The total length of a conveyor network can reach hundreds of kilometers, while a single conveyor usually has a route length of about 0.5–2 km. The belt is a critical and one of the most costly components of the conveyor, and damage to it can result in long unexpected stoppages of production. This is why proper monitoring of conveyor belts is crucial for continuous operation. In this article, algorithms for the detection of potential damage to a conveyor belt are described. The algorithms for analysis used video recordings of a moving belt conveyor, which, in case the of hazardous conditions of deep mines, can be collected, for example, by a legged autonomous inspection robot. The video was then analyzed frame by frame. In this article, algorithms for edge damage detection, belt deviation, and conveyor load estimation are described. The main goal of the research was to find a potential application for image recognition to detect damage to conveyor belts in mines.
This article presents the concept of using the DTW algorithm to partially solve the problem of locating LHD (load, haul, dump) in an underground mine. The concept assumes the recognition of characteristics—patterns that are hidden in vibrations recorded by vehicles—in segments of the route in the underground excavation, which under appropriate conditions enables the obtainment of information similar to that obtained through the use of RFID gates. With the use of this solution in practice, there are several problems that are addressed in this article. One of the main issues is the different arrangement of the signal fragments resulting from driving along with characteristic parts of the route (bumps, paving damage, lumps of excavated material, etc.) at different driving speeds. This problem was solved by using a combination of the road quality detection algorithm and the DTW algorithm, which estimates the similarity of time series with different lengths. The concept was developed and pre-tested using a test rig and a constructed wheeled robot, and then validated in the conditions of the KGHM underground copper mine in Poland, where the readings from the typical haulage process of an LHD vehicle were analyzed.
The task of ore transportation is performed in all mines, regardless of their type (open pit/underground) or mining process. A substantial number of enterprises utilize wheeled machines to perform ore haulage, especially haul trucks and loaders. These machines’ work consists of repeating cycles, and each cycle can be divided into 4 operations: loading, driving with full box/bucket, unloading and driving with empty box/bucket. Monitoring this process is essential to create analytical tools that support foremen and other management crew in achieving effective and optimal production and planning activities. Unfortunately, information gathered regarding the process is frequently based on operators’ oral testimony. This process not only allows for abuse but is also a repetitive and tedious task that must be performed by foremen. The time and attention of foremen is valuable as they are responsible for managing practically everything in their current mine section (machines, operators, works, repairs, emergencies, safety, etc.). Therefore, the automatization of the described process of information gathering should be performed. In this article, we present two neural network models (one for haul trucks and one for loaders) build for detecting work cycles of the ore haulage process. Both models were built utilizing a 2-stage approach. In the first stage, the models’ structures were optimized, while the second was focused on optimizing hyperparameters for the structure with best performance. Both of the proposed models were trained using data collected from on-board monitoring systems over hundreds of the machines’ work hours and utilized the same input features: vehicle speed, fuel consumption, selected gear and engine rotational speed. Models have been subjected to comprehensive testing during which the efficiency and stability of the model responsible for haul trucks was proven. Results for loaders were not as high quality for haul trucks; however, some interesting facts were discovered that indicate possible directions for future development.
The Inertial Measurement Unit (IMU) is widely used in the monitoring of mining assets. A good example is the Polish underground copper ore mines of KGHM, where research work with the use of the IMU has been carried out for several years. The potential of inertial sensors was ensured by the development of advanced analytics using machine learning methods to support the maintenance management of an extensive machine park and machine manufacturer in adapting various construction elements to mining conditions. The key algorithms developed in the field of inertial data concern: identification of cycles and components of the haulage process operations, identification of dynamic overloads, technical diagnostics of rotating elements, assessment of road conditions (bumps, slopes, damages), assessment of the technical condition of the pavement, assessment of the operator’s driving style, and finally the machine location in the mining excavation. One of the key operational contexts, necessary in the development of analytics for underground mining vehicles, is the identification of the turning moment of the machine at the intersection together with the determination of the driving direction and the turn angle. In the case of a mine with a room-and-pillar system, where the excavation system has the Manhattan structure, it is possible to use many simplifications to correctly estimate the machine motion path. The identification of the spatial context and the turning maneuver is of key importance both in the development of the machine location system, but also in multi-dimensional analyzes, including the analysis of dynamic overloads or the assessment of the operator’s driving style and work safety. The article presents a comparison of several mathematical models used for the machine turn detection problem, which were trained and tested on the real-life industrial data recorded using IMU during a single working shift of the self-propelled machine.