Artificial neural network surrogate modelling for real-time predictions and control of building damage during mechanised tunnelling

Cao, Ba Trung; Obel, Markus; Freitag, Steffen; Mark, Peter; Meschke, Günther

doi:10.1016/j.advengsoft.2020.102869

Cited by 44 publications

(12 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The BEMS is responsible not only to achieve the specific objectives stated above but also to accomplish consumer comfort and preference [147]. Nevertheless, such a situation results in management problems that can conflict with the objectives [159]. For instance, end-use wants to cut down the electricity cost on the condition that the quality of energy services would not be compromised, thus imposing limitations on the control operations [160].…”

Section: Optimization In Building Energy Management Systemmentioning

confidence: 99%

Intelligent Controllers and Optimization Algorithms for Building Energy Management Towards Achieving Sustainable Development: Challenges and Prospects

et al. 2021

View full text Add to dashboard Cite

Buildings account for a significant amount of energy consumption leading to the issues of global emissions and climate change. Thus, energy management in a building is increasingly explored due to its significant potential in reducing the overall electricity expenses for the consumers and mitigating carbon emissions. In line with that, the greater control and optimization of energy management integrated with renewable energy resources is required to improve building energy efficiency while satisfying indoor environment comfort. Even though actions are being taken to reduce the energy consumption in buildings with several optimization and controller techniques, yet some issues remain unsolved. Therefore, this work provides a comprehensive review of the conventional and intelligent control methods with emphasis on their classification, features, configuration, benefits, and drawbacks. This review critically investigates the different optimization objectives and constraints with respect to comfort management, energy consumption, and scheduling. Furthermore, the review outlines the different methodological approaches to optimization algorithms used in building energy management. The contributions of controller and optimization in building energy management with the relation of sustainable development goals (SDGs) are explained rigorously. Discussions on the key challenges of the existing methods are presented to identify the gaps for future research. The review delivers some effective future directions that would be beneficial to the researchers and industrialists to design an efficiently optimized controller for building energy management toward targeting SDGs.INDEX TERMS Building energy management, controller, optimization, scheduling, sustainable development goals I. INTRODUCTIONPresently, buildings take the lead in consuming a substantial amount of energy, indicating about 40% of global energy consumption, which is responsible to release one-third of greenhouse gas (GHG) emissions [1], [2]. Another report demonstrates that buildings hold 49% of the total energy worldwide in which 60% of the energy is consumed for heating and cooling purposes [3], [4]. The poor management and ineffective control approach of appliances used in the building may result in a significant loss of energy in a

show abstract

Section: Optimization In Building Energy Management Systemmentioning

confidence: 99%

Intelligent Controllers and Optimization Algorithms for Building Energy Management Towards Achieving Sustainable Development: Challenges and Prospects

et al. 2021

View full text Add to dashboard Cite

show abstract

“…FFNNs have proven highly capable at approximating a broad range of functions and can be shown to be, in the limit of infinite neurons, universal approximators [37,38]. As such, they are an obvious candidate for metamodelling, and have been widely demonstrated in many such contexts [39,40,41]. Much of the popularity of FFNNs is due to their scalability to very large and high dimensional datasets, and, especially in the scope D R A F T of deep learning methods, power for dealing with highly nonlinear relations [42,43].…”

Section: Feedforward Neural Networkmentioning

confidence: 99%

Model Order Reduction for Real-Time Hybrid Simulation: Comparing Polynomial Chaos Expansion and Neural Network methods

Tsokanas¹,

Simpson²,

Pastorino³

et al. 2021

Preprint

View full text Add to dashboard Cite

Hybrid simulation is a method used to investigate the dynamic response of a system subjected to a realistic loading scenario by combining numerical and physical substructures. To ensure high fidelity of the simulation results, it is often necessary to conduct hybrid simulation in real-time. One of the challenges arising in real-time hybrid simulation originates from high-dimensional nonlinear numerical substructures and, in particular, from the computational cost linked to the computation of their dynamic responses with sufficient accuracy. It is often the case that the simulation time-step must be decreased to capture the dynamic behavior of numerical substructures, thus resulting in longer computation. When such computation takes longer than the actual simulation time, time delays are introduced and the simulation timescale becomes distorted. In such a case, the only viable solution for doing hybrid simulation in real-time is to reduce the order of such complex numerical substructures.In this study, a model order reduction framework is proposed for real-time hybrid simulation, based on polynomial chaos expansion and feedforward neural networks. A parametric case study encompassing a virtual hybrid model is used to validate the framework. Selected numerical substructures are substituted with their respective reduced-order models. To determine the robustness of the framework, parameter sets are defined to cover the design space of interest. A comparison between the full- and reduced-order hybrid model response is delivered. The attained results demonstrate the performance of the proposed framework.

show abstract

“…Recently, it is emerged to utilize AI technology to therapeutic stages of treatment planning and guidance [36], [37], [38], [39], [40], [41]. The use of such data-driven approaches enables the real-time representation of complex physical phenomena that are hard to characterize using mathematical models [42], [43]. Furthermore, it can be effectively applied in the inverse problem that generally requires iterative solution procedure [44].…”

Section: Introductionmentioning

confidence: 99%

Deep Neural Network for Navigation of a Single-Element Transducer During Transcranial Focused Ultrasound Therapy: Proof of Concept

Choi

Jang

Yoo

et al. 2022

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

Transcranial focused ultrasound (tFUS) has gained attention in the field of brain stimulation owing to its non-invasive neurotherapeutic potentials. However, complex interactions between acoustic waves and the cranium may introduce misalignment of the acoustic focus from a geometric target location, thus, necessitate on-site feedback of real-time navigational information of the transducer (spatial coordinates and angular orientation) for the operators to accurately place the acoustic focus to the desired brain area. In this study, we propose a deep-learning-based network model that can provide spatial navigational information of a single-element FUS transducer with respect to the targeted brain region. The training dataset were acquired through forward simulations that reflect the different tFUS transmissions for each skull structure using cranial computed tomography (CT) image data. The performance of the network was evaluated through three ex vivo calvaria. As a result show that the presented neural network-based method can an accurately navigate the FUS transducer with the conformity of ∼99.59% in placement of the transducer and ∼74.49% in the focal volume and an average difference of ∼0.96 mm in the focal point, all capable of real-time operation (∼10 ms).

show abstract

Artificial neural network surrogate modelling for real-time predictions and control of building damage during mechanised tunnelling

Cited by 44 publications

References 40 publications

Intelligent Controllers and Optimization Algorithms for Building Energy Management Towards Achieving Sustainable Development: Challenges and Prospects

Intelligent Controllers and Optimization Algorithms for Building Energy Management Towards Achieving Sustainable Development: Challenges and Prospects

Model Order Reduction for Real-Time Hybrid Simulation: Comparing Polynomial Chaos Expansion and Neural Network methods

Deep Neural Network for Navigation of a Single-Element Transducer During Transcranial Focused Ultrasound Therapy: Proof of Concept

Contact Info

Product

Resources

About