Search

Prediction is a vague concept that is why we need to conceptualize it specifically for underground deformation time-series data. For this impending issue, this paper employs an advanced deep learning model Bi-LSTM-AM to address it. The results show its applicability for practical engineering. The proposed model is compared with other basic deep learning models including long short-term memory (LSTM), Bi-LSTM, gated recurrent units (GRU), and temporal convolutional networks (TCN). These models cover the most common three forms of deep learning for time-series prediction: recurrent neural networks (RNN) and convolutional neural networks (CNN). This research is supposed to benefit the underground deformation time-series prediction.

Stope design is a core discipline within mining engineering. This study analyzes the current state-of-the-art of stope design through a survey addressed to mining industry professionals. In stope design research the dominance of empirical methods has slowly shifted towards numerical methods. Recent advancements have mostly focused on the development of stope optimization algorithms. The survey consisted of 19 questions and was distributed to stope design experts via email, LinkedIn messages, and the Mining Industry Professionals network forum. In total, 36 responses of satisfying quality from 20 countries were received and analyzed. No dominance of a single stope design method was recognized. Empirical methods and personal expertise are still used widely. However, a readiness for change in stope design practice was indicated in 87% of responses. The current needs of the stoping-based underground mining sector are to increase the amount of geotechnical data, automate stope design and implement related software, and integrate these into general mine planning. According to 70% of the participants, acquired geotechnical data should be available within three days to be employed in design practice. The industry is ready to implement more efficient stope design methods if they offer results proven in case studies.

The operating environment for engineers has changed in recent years (Vona et al., 2018; ILO, 2019). Energy transition driven by ecological crises creates a need to have a critical look into engineers’ skill sets and competencies. The renewable energy sector is one of the most significant ones in terms of new job opportunities and the development of new occupational profiles (ILO, 2019). At the same time, the transition to environmentally sustainable and socially just future creates a growing need for expertise that is different from the traditional technically focused competence profile. The project described in this presentation aims to establish best practices for the creation of digital learning environments in a cost-effective way that is easy to integrate with educational contents. We aim to make use of virtual reality-based learning, develop digital and engaging learning environments, and create a radical new opening to develop education and share best practices with other higher education institutions.The learning environment is known to have a significant impact on the success of learning. It is effective to practice skills in a real environment, but this is not always possible because it can be inaccessible or dangerous. For example, it is not possible or allowed to take 100+ students to a nacelle of a large wind turbine at the height of 150 m or in an underground thermal storage cave. Virtual site visits are also cheaper, reduce the need for traveling, and therefore, decrease CO2 emissions, and make learning flexible as the materials can be reached at any time convenient for the students. Virtual learning environments are recognized as viable tools to improve engineering education and training and have been developing rapidly in recent years (Wang et al. 2018, Hirvonen 2021). The use of virtual reality tools allows, for example, easy-to-understand visualisation and communication of complex spatial data (Janiszewski et al., 2021; Du et al., 2017). Virtual learning environments provide great opportunities, but they are challenging to create and require specialist knowledge of 3D scanning, VR development, and programming. The challenge is to integrate them with existing educational content. Educational contents of our project include development of showcases of virtual reality-based learning tools for effective teaching of engineering. Two virtual learning journeys will be demonstrated. One is related to renewable energy engineering. Rapid energy transition challenges us all, also energy engineering education. This requires whole new kinds of learning tools. We will showcase an onshore wind energy site. Along the virtual journey, the student is introduced to technical solutions as well as ecological and social sustainability considerations. The second educational content is about scaling-up existing virtual reality learning systems for rock engineering and engineering geology teaching developed as part of the Aalto Online Learning’s MIEDU, EDUROCK, and COVE pilots (Jastrzebski, 2017; Janiszewski etal., 2020a; Zhang, 2020). This knowledge can further be used to develop a demo on underground thermal energy storage. An example is a virtual rock and mineral database that has more than 100 samples digitised from the university’s collection (EDUROCK, 2019). Test results show that the use of this virtual material enhanced the learning outcomes by 20%. Finally, there will be an evaluation of the student experience and analyses of the pedagogical aspects done. A very important part of the project is to make sure that the tools and materials are pedagogically relevant and support the intended learning outcomes logically. The focus is on developing flexible and engaging teaching scenarios to achieve learning goals. Detailed workflow descriptions of the processes will be developed and published.

Structure-from-Motion Multi-View Stereo (SfM-MVS) photogrammetry is a viable method to digitize underground spaces for inspection, documentation, or remote mapping. However, the conventional image acquisition process can be laborious and time-consuming. Previous studies confirmed that the acquisition time can be reduced when using a 360-degree camera to capture the images. This paper demonstrates a method for rapid photogrammetric reconstruction of tunnels using a 360-degree camera. The method is demonstrated in a field test executed in a tunnel section of the Underground Research Laboratory of Aalto University in Espoo, Finland. A 10 m-long tunnel section with exposed rock was photographed using the 360-degree camera from 27 locations and a 3D model was reconstructed using SfM-MVS photogrammetry. The resulting model was then compared with a reference laser scan and a more conventional digital single-lens reflex (DSLR) camera-based model. Image acquisition with a 360-degree camera was 3× faster than with a conventional DSLR camera and the workflow was easier and less prone to errors. The 360-degree camera-based model achieved a 0.0046 m distance accuracy error compared to the reference laser scan. In addition, the orientation of discontinuities was measured remotely from the 3D model and the digitally obtained values matched the manual compass measurements of the sub-vertical fracture sets, with an average error of 2–5°.

Funding Information: The authors thank their partners (City of Helsinki, Ecolan Oy, Finnsementti and Nordkalk Oy) for providing the binders/clays. The technical group at Aalto Civil Engineering Department helped in building the photogrammetric studio. The comments of Professor Jean-Marie Fleureau on the initial draft of this paper are acknowledged. Data presented in the present study are available from the corresponding author upon request. Publisher Copyright: © 2022 This study examined the performances of four newly developed binders in stabilising soft Finnish clay by considering both the mechanical behaviour and environmental effect (i.e., carbon footprint). Thirty-six compacted clay-binder mixtures were investigated via uniaxial compression tests, during which photogrammetric scans were performed at axial strains of 0, 1, 3, and 7.5%. The testing protocol enabled the characterisation of full-field radial deformations and fracture developments. Experimental results demonstrated that varying the amounts and types of industrial by-products used in the production of binders has substantial potential to reduce carbon footprints. In terms of radial deformations, their distributions were highly non-uniform at different heights and loading stages. Radial displacements increased continuously at axial strains smaller than 3% (corresponding to peak strength point), whereas such a continuity disappeared afterwards, and global failures appeared. Based on three-dimensional (3D) reconstructions, the observed failures were categorised into three modes: inclined shearing (IS), axial splitting (AS) and hybrid shearing-splitting (HSS). For the studied specimens, shearing was the most common mechanism leading to failure. (C) 2022 Production and hosting by Elsevier B.V. on behalf of The Japanese Geotechnical Society. This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Rock discontinuities play an important role in the behavior of rock masses and have a high impact on their mechanical and hydrological properties, such as strength and permeability. The surfaces roughness and physical aperture of rock joints are vital characteristics in joint shear strength and fluid flow properties. This study presents a method to digitally measure the physical aperture of a rock fracture digitized using photogrammetry. A 50 cm × 50 cm rock sample of Kuru grey granite with a thoroughgoing fracture was digitized. The data was collected using a high-resolution digital camera and four low-cost cameras. The aperture and surface roughness were measured, and the influence of the camera type and 3D model rasterization on the measurement results was quantified. The results showed that low-cost cameras and smartphones can be used for generating 3D models for accurate measurement of physical aperture and roughness of rock fractures. However, the selection of appropriate rasterization grid interval plays a key role in accurate estimations. For measuring the physical aperture from the photogrammetric 3D models, reducing rasterization grid interval results in less scattered measurement results and a small rasterization grid interval of 0.1 mm is recommended. For roughness measurements, increasing the grid interval results in smaller measurement errors, and therefore a larger rasterization grid interval of 0.5 mm is recommended for high-resolution smartphones and 1 mm for other low-cost cameras.

DOI 10.12989/gae.2018.16.5.503 ei toimi (4.1.2019) Globally there is an increasing need to reduce the greenhouse gas emissions and increase the use of renewable sources of energy. The storage of solar thermal energy is a crucial aspect for implementing the solar energy for space heating in high latitudes, where solar insolation is high in summer and almost negligible in winter when the domestic heating demand is high. To use the solar heating during winter thermal energy storage is required. In this paper, equations representing the single U-tube heat exchanger are implemented in weak form edge elements in COMSOL Multiphysics (R) to speed up the calculation process for modelling of a borehole storage layout. Multiple borehole seasonal solar thermal energy storage scenarios are successfully simulated. After 5 years of operation, the most efficient simulated borehole pattern containing 168 borehole heat exchangers recovers 69% of the stored seasonal thermal energy and provides 971 MWh of thermal energy for heating in winter.