Architectural Design Problems Research Articles

Design of multi-hidden-layer Bayesian neural networks for model updating

Structural health monitoring (SHM) based on artificial neural networks (ANN) has received a lot of attention in recent decades, especially the Bayesian neural network (BNN) approach, which is more robust to noise for training and generalization. Since building a high-quality BNN architecture suitable for a specific task depends highly on user experience, the existing literature generally studies BNNs with simple single-hidden-layer architectures designed by empirical formulas or very few tailor-made algorithms. Multiple hidden layer BNN (MBNN) has a more complex architecture than single hidden layer BNN (SBNN) and is expected to achieve better generalization performance for complex problems. But the corresponding architectural design problem is much more complex, and there is no previous experience in the literature. To achieve this for MBNN, this paper proposes two feasible algorithms to optimize the number of neurons in each hidden layer simultaneously, where a logarithmic evidence metric is introduced to quantitatively characterize the performance of MBNN for a given multi-hidden-layer architecture. The feasibility and effectiveness of the proposed method are verified by the finite element (FE) model updating of both a planar truss model and a real-life pedestrian bridge. The verification results show that the second algorithm is much more computationally efficient for the optimal design of the MBNN architecture and has the potential for practical application.

Development of a DSP based collaborative computing platform for power system

Abstract With the advancement of information technology, there has been tremendous progress in data production, processing, and storage technology, especially in data processing technology. With the rapid development of the power grid, its operation has become more intelligent and efficient. Traditional power system simulation and analysis tools have disadvantages, such as slow message transmission and the inability to share data, which cannot meet the requirements of modern power system simulation calculations. DSP was introduced and developed by the Southern Power Grid Research Institute and can perform various simulation calculations such as transient stability calculation, power flow calculation, and short circuit calculation. It is widely used in departments such as power planning and design. However, the data calculated by DSP is input through a data card, which is cumbersome and difficult to manage. In order to meet the new requirements of power system simulation analysis, a power system collaborative computing platform has been developed based on DSP, which makes DSP data maintenance and management more efficient and intuitive. It comprehensively improves the efficiency of power grid planning work. This article provides a detailed analysis of the architecture design and application problems of the power system collaborative computing platform, clarifies the requirements of large-scale interconnected power grids for simulation computing data management, and proposes solutions that can meet the needs of simulation computing data management in China’s power grid from two aspects: key data architecture issues and software architecture technology.

The Lifestyles of Space Standards: Concepts and Design Problems

Space standards are envisioned as a powerful means to regulate dwelling design, ensuring the quality, functionality, and safety of homes. Their ultimate objective is to guarantee a minimum level of design quality that can accommodate a wide range of domestic activities. While space standards primarily focus on isolated quantitative aspects such as overall size, room dimensions, and occupancy limits, they also make assumptions about activities to be performed by ideal “users” and specific lifestyles to be accommodated within a home. However, these assumptions are being challenged by the increasing demands and diverse activities taking place in the dwelling realm, which call into question the validity of existing space standards. In response to these challenges, this article conducts a critical review of the theoretical basis and various interpretations of space standards, particularly in the context of England. It explores their fundamental concepts and historical approaches, as well as examines specific examples of their application and their correlation with design strategies. By delving into the concepts of “the normal” and “the minimum dwelling,” the article discusses the three main dimensions of space standards: program, user, and size. Consequently, it argues for a more comprehensive understanding of the general application of space standards, which requires incorporating architectural design problems, particularly from the perspective of flexibility. This approach takes into account the evolving needs and diversity of households, as well as the creation of inclusive and adaptable living spaces.

Optimization method of building energy efficiency design based on decomposition multi objective and agent assisted model

In today's global climate crisis, energy-efficient building design is crucial for achieving energy efficiency, environmental sustainability, and resident well-being. However, traditional architectural design is difficult to solve complex multi-objective and multivariate optimization problems. To overcome these challenges, this study proposes a solution: a strategy that combines decomposed multi-objective and agent assisted modeling. The proposed method decomposes complex architectural design problems into multiple manageable sub problems, with each sub problem optimized for a specific design objective. This method effectively simplifies the problem structure, allowing each subproblem to explore its solution space more focused and in-depth. Meanwhile, by combining proxy assisted modeling and utilizing proxy models to approximate actual physical processes or performance evaluations, the computational cost is reduced and the optimization process is accelerated. This study indicates that the improved multi-objective backbone particle swarm optimization algorithm relies on adaptive perturbation factors, with an average measured super volume of 29311 for one bedroom buildings and 49504 for three bedroom buildings. For the same building type, the average volume measurements of the multi-objective particle swarm optimization algorithm assisted by the decomposed surrogate model are 21153 and 40230, respectively. The proposed method effectively addresses complex multi-objective optimization problems in the field of building energy efficiency design, simplifies the problem structure, reduces computational costs through surrogate models, accelerates the optimization process, improves energy efficiency, and can support building construction to better cope with the challenges of climate change.

Research on the Intelligent Auxiliary Design of Subway Station Building Space Based on Deep Learning

In recent years, deep learning methods have been used with increasing frequency to solve architectural design problems. This paper aims to study the spatial functional layout of deep learning-assisted generation subway stations. Using the PointNet++ model, the subway station point cloud data are trained and then collected and processed by the author. After training and verification, the following conclusions are obtained: (1) the feasibility of spatial deep learning for construction based on PointNet++ in the form of point cloud data is verified; (2) the effectiveness of PointNet++ for the semantic segmentation and prediction of metro station point cloud information is verified; and (3) the results show that the overall 9:1 training prediction data have 60% + MIOU and 75% + accuracy for 9:1 training prediction data in the space of 20 × 20 × 20 and a block_size of 10.0. This paper combines the deep learning of 3D point cloud data with architectural design, breaking through the original status quo of two-dimensional images as research objects. From the dataset level, the limitation that research objects such as 2D images cannot accurately describe 3D space is avoided, and more intuitive and diverse design aids are provided for architects.

A Guide for Evaluation of the Architectural Design Requirements of Energy Efficiency in City Hotels

Tourism is a sector of great importance in the economic sphere, but it is also one of the services most consumers of conventional energy, for this reason it is necessary to generate strategies aimed at promoting the use of renewable energy sources. This research is aimed at providing a guide for the evaluation of architectural design requirements for energy efficiency in city hotels, allowing the creation of a database with the main architectural design problems that affect the energy efficiency of this category of hotels. In the conformation of the guide, international methods of evaluation and certification of the sustainable energy efficiency of buildings are considered, which allow to complement the current Cuban norms in relation to the design requirements for energy efficiency in buildings.

ARCHITECTURAL DESIGN WITH GENERATIVE ALGORITHM AND VIDEO PROJECTION MAPPING

The innovative and creative approach that is produced for architectural design problems involves quite complex stages. In architectural design, the designer's approach and numerical data make the design process a multi-layered structure. The integration of parametric modeling programs and generative algorithms makes it easy to carry out multi-layered design processes. Generative systems defined through generative algorithms enable conceptual approaches, various geometrical constructs, and different forms to be created in digital environments in solving design problems. The creation of the generative algorithm of the design eliminates the restrictive role of modeling software in the architectural design. The designer gets the opportunity to create every parameter and design criteria specific to his approach. 
 In this study, our aim is to develop a generative algorithm in a computer environment by using the principles of fractal geometry function. The generative system creates by overlaying the developed generative algorithm with the environmental factor parameters. In this system proposal, the goal is to produce various facade design proposals by coding the algorithm fractal functions and to make use of the visualization of various potentials of the generative algorithm in parametric facade proposals. Video projection mapping method is chosen to discuss the functionality of the parameters in the proposed generative system of the developed generative algorithm. Computation of the transformation relating consecutive image frames is an essential operation in video mapping. In this context, the design created with the generative system is reflected on a real scale medium , specifically a column in this study, and various image frames letting new design proposals produced by the algorithm were evaluated. In concluding rmarks, the advantages of architectural designs modeled by coding with the generative algorithm compared to the algorithms obtained directly with the software are discussed.

Model-Free Deep Recurrent Q-Network Reinforcement Learning for Quantum Circuit Architectures Design

Artificial intelligence (AI) technology leads to new insights into the manipulation of quantum systems in the Noisy Intermediate-Scale Quantum (NISQ) era. Classical agent-based artificial intelligence algorithms provide a framework for the design or control of quantum systems. Traditional reinforcement learning methods are designed for the Markov Decision Process (MDP) and, hence, have difficulty in dealing with partially observable or quantum observable decision processes. Due to the difficulty of building or inferring a model of a specified quantum system, a model-free-based control approach is more practical and feasible than its counterpart of a model-based approach. In this work, we apply a model-free deep recurrent Q-network (DRQN) reinforcement learning method for qubit-based quantum circuit architecture design problems. This paper is the first attempt to solve the quantum circuit design problem from the recurrent reinforcement learning algorithm, while using discrete policy. Simulation results suggest that our long short-term memory (LSTM)-based DRQN method is able to learn quantum circuits for entangled Bell–Greenberger–Horne–Zeilinger (Bell–GHZ) states. However, since we also observe unstable learning curves in experiments, suggesting that the DRQN could be a promising method for AI-based quantum circuit design application, more investigation on the stability issue would be required.

Discussion on Common Problems in Civil Air Defense Architectural Design

Discussion on Common Problems in Civil Air Defense Architectural Design

Developing a Method to Connect Thermal Physiology in Animals and Plants to the Design of Energy Efficient Buildings.

The literature shows that translating the thermal adaptation mechanisms of biological organisms to building design solutions can improve energy performance. In the context of bio-inspired thermoregulation several worthwhile attempts have been made to develop a framework for finding relevant thermal adaptation mechanisms in nature as inspiration for architectural design. However, almost all of these have followed a solution-based approach despite the problem-solving nature of architectural design. Given this, this research set out to take a problem-based approach to biomimetic design. The aim was to investigate the most effective way of accessing biological thermoregulatory solutions to assist architects in finding relevant biological inspirations for the thermal design of buildings. This required the development of an optimal structure for categorizing thermoregulatory mechanisms that could then be used as part of a framework for finding appropriate mechanisms for a particular architectural design problem. This development began with a three-step literature review to find, study, generalize and categorize a comprehensive list of thermal adaptation mechanisms used by animals and plants. This article describes how this literature review was carried out leading to the identification of nine main themes which were analysed for their practicality in informing the structure of the proposed framework. The selected themes were built around the common aspects of biology and architecture, and hence facilitated the categorization of biological thermoregulation mechanisms. This article thus explains the steps taken to develop a structure for generalizing and categorizing thermal adaptation strategies in nature. This article does not report on the list of thermal adaptation mechanisms identified in step 2 of the literature review. Instead, it presents the literature review workflow with a focus on step 3. Given that, discussion of the thermal adaptation mechanisms falls outside the scope of this article.

A “pantera rosa” na arquitetura: a abordagem transdisciplinar e um pensamento sem imagem

Abstract: As a form of in vivo knowledge, the transdisciplinary (TR) methodology suggests going beyond disciplines. According to Nicolescu, this methodology occurs at different levels of reality (ontological), different levels of perception (complexity), and within the logic of the included middle (logical) axioms that exist simultaneously. In addressing these levels, the researcher is the interlocutor between the external world of the Object and the internal world of the Subject. In architecture, this knowledge emerges through a variety of disciplines that need to be fused with an approach that is rhizomatic and nomadic, leading to thought without an image as characterized by Deleuze and Guattari. By following their “Pink Panther” metaphor for an imageless thought and approach (which does not imitate or reproduce something else) in TR, this article aims to understand the relationship between the TR methodology and the theory of thought without an image - an approach which can enable the comprehension of ambiguous architecture and urban design problems.

Biomimicry for Energy-Efficient Building Design: A Bibliometric Analysis.

With the development of the biomimicry approach, new and creative ideas have been established to solve problems in architectural design. In the designs based on this process, “nature” is used as a diverse data source for the transfer of these data to various processes, functions, materials, and structures. The primary purpose of this paper is to explore the development of biomimicry as an architectural approach, with a bibliometric review of research related to biomimicry and energy efficiency. Emphasis on the importance of the need for biomimicry in modern designs is another goal of this study. In this study, articles published in the Web of Science database (2010–2021) were analyzed. VOSviewer and SankeyMATIC software were used to represent the analysis results graphically. According to the results of this study, in addition to the inadequacy of biomimicry research, the need for further research became apparent. This review can serve as a reference for future studies to transfer natural phenomena to architecture in order to solve the problem of efficient energy consumption.

Strategies for Parametric Design in Architecture

A new specialist design role is emerging in the construction industry. The primary task related to this role is focused on the control, development and sharing of geometric information with members of the design team in order to develop a design solution. Individuals engaged in this role can be described as a parametric designers. Parametric design involves the exploration of multiple solutions to architectural design problems using parametric models. In the past these models have been defined by computer programs, now commercially available parametric software provides a simpler means of creating these models. It is anticipated that the emergence of parametric designers will spread and a deeper understanding of the role is required. This thesis is aimed at establishing a detailed understanding of the tasks related to this new specialism and to develop a set of considerations that should be made when undertaking these tasks. The position of the parametric designer in architectural practice presents new opportunities in the design process this thesis also aims to capture these. Developments in this field of design are driven by practice. It is proposed that a generalised understanding of applied parametric design is primarily developed through the study of practical experience. Two bodies of work inform this study. First, a detailed analytical review of published work that focuses on the application of parametric technology and originates from practice. This material concentrates on the documentation of case studies from a limited number of practices. Second, a series of case studies involving the author as participant and observer in the context of contemporary practice. This primary research of applied use of parametric tools is documented in detail and generalised findings are extracted. Analysis of the literature from practice and generalisations based on case studies is contrasted with a review of relevant design theory. Based on this, a series of strategies for the parametric designer are identified and discussed.

Offset-Free Model Predictive Control for a cone-shaped active magnetic bearing system

Active Magnetic Bearings (AMB) are mechatronic systems that support a rotating shaft using magnetic levitation. The standard AMB architecture includes two radial actuators and one for the axial direction. An alternative geometry with cone-shaped magnetic cores allows for a more compact layout without a dedicated axial actuator. However, this configuration reduces the axial force generation capability and requires a more complex control architecture due to the inherent coupling of the axial and radial control actions. When using decentralized control, effective handling of the coil current limitations together with the axial disturbance rejection is difficult to achieve. In this context, the present paper demonstrates the benefits of applying Offset-Free Model Predictive Control (OF-MPC) for a cone-shaped AMB system. A procedure for the overall design is presented and supported by the experimental work conducted in a scaled machine that reproduces an on-board turbo-compressor unit for an aircraft. The modeling of the system is described together with the design of the OF-MPC in all its parts: general control architecture, disturbance model and observer design, target calculation and control problem formulation. An OF-MPC variant with reduced control horizon is proposed and implemented in real time. Experimental results demonstrate that the prototype is compliant with application-specific stability requirements from the ISO 14839-3:2006 standard. In addition, experiments show that OF-MPC outperforms decentralized PID controllers in terms of axial disturbance rejection. OF-MPC yields a favorable constrained optimal control technique for cone-shaped AMBs because intrinsic coupling and current saturation are optimally handled by the controller.

Understanding Capacity Saturation in Incremental Learning

In class-incremental learning, a model continuously learns from a sequential data stream in which new classes are introduced. There are two main challenges in class- incremental learning: catastrophic forgetting and capacity saturation. In this work, we focus on capacity saturation where a learner is unable to achieve good generalization due to its limited capacity. To understand how to increase model capacity, we present the continual architecture design problem where at any given step, a continual learner needs to adapt its architecture to achieve a good balance between performance, computational cost and memory limitations. To address this problem, we propose Continual Neural Architecture Search (CNAS) which takes advantage of the sequential nature of class- incremental learning to efficiently identify strong architectures. CNAS consists of a task network for image classification and a reinforcement learning agent as the meta-controller for architecture adaptation. We also accelerate learning by transferring weights from the previous learning step thus saving a large amount of computational resources. We evaluate CNAS on the CIFAR-100 dataset in several incremental learning scenarios with limited computational power (1 GPU). We empirically demonstrate that CNAS can mitigate capacity saturation and achieve performances comparable with full architecture search while being at least one order of magnitude more efficient.

RETRACTED ARTICLE: SMAP satellite ocean surface salinity observations and music classroom effects in coastal areas: environmental numerical prediction

The ocean surface salinity is an important indicator for monitoring the changes in the chemical composition of the sea surface. It can be used to evaluate and optimize the quality of the seawater and then analyze the process of marine fluid mechanics and predict the ocean. Therefore, it has attracted the attention of relevant government departments, and it is the focus of research by experts and scholars. Satellite remote sensing technology, as an effective means to obtain a large amount of continuous observation of sea surface salt data, overcomes the time and space limitations of conventional observation methods. SMAP’s ocean surface salinity data shows quality advantages, excellent application value, and considerable research potential due to its own characteristics. However, since the emergence of applied technology, due to slow progress and mainly carried out in foreign countries, research results have been few. This paper analyzes the research situation of SMAP data, with the purpose of providing reference for the application of remote sensing data of SMAP in China; reviews the progress of the main research of SMAP; and provides support for the development of research in China. So as to summarize the problems existing in the sound environment of university music classrooms, from the perspectiive of the sound environment in campus planning, the architectural design problems of music classrooms and the problems of music classroom teaching are considered. Then use the sound environment of the music classroom to analyze and summarize the problems, and propose simple and effective improvement measures to the music classroom, construct reasonable proposals, and try to avoid the same problem from happening again, which can not only optimize the service to users but also provide a good sound environment for the normal development of university music classroom teaching.

Deep convolutional neural network architecture design as a bi-level optimization problem

During the last decade, deep neural networks have shown a great performance in many machine learning tasks such as classification and clustering. One of the most successful networks is the CNN (Convolutional Neural Network), which has been applied in many application domains such as pattern recognition, medical diagnosis, and signal processing. Despite the very interesting performance of CNNs, their architecture design is still so far a major challenge for researchers and practitioners. Several works have been proposed in the literature with the aim to find optimized architectures such as ResNet and VGGNet. Unfortunately, most of these architectures are either manually defined by experts or automatically designed by greedy induction algorithms. Recent works suggest the use of Evolutionary Algorithms (EAs) thanks to their ability to escape locally-optimal architectures. Despite the fact that EAs have shown interesting performance, researchers in this direction have considered the design task as a single-level optimization problem; which represents the main research gap we tackle in this paper. The main contribution behind our work consists in the fact that CNN architecture design has a hierarchical nature and thus could be seen as a Bi-Level Optimization Problem (BLOP) where: (1) the upper level minimizes the network complexity defined by the number of blocks and the number of nodes per block; and (2) the lower level optimizes the convolution block ‘graphs’ topologies by maximizing the classification accuracy. Motivated by the originality of our observation with respect to the state of the art, we frame for the first time the CNN architecture design problem as a BLOP and then solve it using an adapted version of an existing efficient bi-level EA; through the definition of the solution encoding, the fitness function, and the variation operators at each level. The adapted EA is named BLOP-CNN and is assessed on the image classification task using the commonly employed CIFAR-10 and CIFAR-100 benchmark data sets. The analysis of our experimental results show the merits of our proposed method in providing the user with optimized architectures that outperform many recent and prominent architectures coming from the three different approaches, namely: manual design, reinforcement learning-based generation, and evolutionary optimization. Moreover, to show the applicability of our approach, we have conducted a case study on the detection of the COVID-19 using a set of benchmark chest X-ray and Computed Tomography (CT) images.

New approaches of the Next-gen collaborative design platform

The architecture design process always changes because the software always updates with new tools and thedevelopment - innovation is in the first line of progress. The human-machine cooperation has become commonplacethrough Computer-Aided Design tools, but a more improved collaboration appears possible only through anendeavor into a kind of artificial design intelligence and Augmented Reality. According to all the above, the researchshown in this paper the core ideas - identifying design specifications - of a next-generation collaborative designplatform. The direct coupling of introducing multi-industry systems - tools, 3D databases, AEC, and Open-BIMtechnologies opens up totally new ways of approaching architectural design problems resulting in a new flexiblemodeling workflow with real-time visualization. Finally, this critical examination research makes an originalcontribution to changing 'attitude' towards the 3d modeling of architectural design thinking. A collaborative designplatform creating a more efficient and versatile architecture.

Bio-informed Research in the Discipline of Architecture: A Bibliometric Analysis

Bio-informed research reveals innovative, creative and original ideas for the solution to various problems in architectural design and many design disciplines. In the designs that adopt this approach, "nature" can be considered as a "data warehouse" providing various data that can be transferred from nanoscale to mesoscale regarding process, function, material, structure. Within the scope of this study, bibliometric research was carried out in the CumInCAD database to reveal what kind of information and outputs have been achieved through the data/capta taken from nature. In this process, the aim is to discover and understand the conceptual relationships, not only the purpose of the data taken from nature but also the relationships between the data and the patterns. All the data obtained were analysed within the scope of the determined parameters and visuals, including data relations, were prepared. As a result of the study, it can be seen that the bio-informed studies examined in this paper have the potential to open up a wide range of new research in the discipline of architecture. The findings show that the biomimetic approach has set the stage for the scientific and interdisciplinary studies that have the potential to change paradigms in architecture.

The Lampedusa Studio: A Multimethod Pedagogy for Tackling Compound Sustainability Problems in Architecture, Landscape Architecture, and Urban Design

In architecture, landscape architecture, and urban design, entangled multiscale and multidomain, or compound, sustainability problems and associated design requirements are becoming rapidly more demanding, complex, and interdisciplinary due to demographic, social, economic, environmental, and technological changes. This places considerable pressure on developing adequate pedagogical approaches to provide the next generation of architects, landscape architects, and urban designers with the knowledge, approaches, and skills to meet these challenges. This article discusses an attempt to develop an adequate pedagogy for a research-integrated master-level design studio along a multimethod approach. Key concepts, approaches, and methods are discussed, along with selected studio projects and a follow-up master thesis project. The projects are examined in terms of their responses to the themes, concepts, approaches, and methods of the pedagogical approach. Finally, further questions concerning the development of the portrayed pedagogical approach are discussed.