Architectural intelligence最新文献

The Vibrant Fields project endeavors to construct novel representational tectonics of urbanization, aiming to comprehend the materiality of forms and the genesis of multispectral relations within complex information systems governing the interplay of atmospheric and embodied energy cycles in the biosphere. This project asserts that any perceivable condition of nature arises from dynamic processes that transcend human sensory perception.

Inspired by theoretical biology, the project models the urban environment as a systemic entity characterized by modularity, representing the biosphere's dynamic interplay of chemical and physical elements engaged in information exchange within ecological systems, influenced by technology, geography, and atmospheric conditions.

Vibrant Fields utilizes layers of observation systems to translate the complex biosphere into dimensionally reduced data streams. It introduces complementary devices, bridging the gap between global and local data to better understand microclimatic phenomena.

The project observes the simultaneous realities and temporalities of urban field information within its ecological context. It investigates the architecture, technology, flora, and fauna of cities in relation to their geographic, geological, and ecological conditions, analyzing multiple temporal historical and geological scales.

The recent advancements in digital technologies and artificial intelligence in the architecture, engineering, construction, and operation sector (AECO) have induced high demands on the digital skills of human experts, builders, and workers. At the same time, to satisfy the standards of the production-efficient AECO sector by reducing costs, energy, health risk, material resources, and labor demand through efficient production and construction methods such as design for manufacture and assembly (DfMA), it is necessary to resolve efficiency-related problems in mutual human‒machine collaborations. In this article, a method utilizing artificial intelligence (AI), namely, generative adversarial imitation learning (GAIL), is presented then evaluated in two independent experiments related to the processes of DfMA as an efficient human‒machine collaboration. These experiments include a) training the digital twin of a robot to execute a robotic toolpath according to human gestures and b) the generation of a spatial configuration driven by a human's design intent provided in a demonstration. The framework encompasses human intelligence and creativity, which the AI agent in the learning process observes, understands, learns, and imitates. For both experimental cases, the human demonstration, the agent's training, the toolpath execution, and the assembly configuration process are conducted digitally. Following the scenario generated by an AI agent in a digital space, physical assembly is undertaken by human builders as the next step. The implemented workflow successfully delivers the learned toolpath and scalable spatial assemblies, articulating human intelligence, intuition, and creativity in the cocreative design.

This research presents an innovative approach that integrated gesture recognition into a Mixed Reality (MR) interface for human–machine collaboration in the quality control, fabrication, and assembly of the Unlog Tower. MR platforms enable users to interact with three-dimensional holographic instructions during the assembly and fabrication of highly custom and parametric architectural constructions without the necessity of two-dimensional drawings. Previous MR fabrication projects have primarily relied on digital menus and custom buttons within the interface for user interaction between virtual and physical environments. Despite this approach being widely adopted, it is limited in its ability to allow for direct human interaction with physical objects to modify fabrication instructions within the virtual environment. The research integrates user interactions with physical objects through real-time gesture recognition as input to modify, update, or generate new digital information. This integration facilitates reciprocal stimuli between the physical and virtual environments, wherein the digital environment is generative of the user’s tactile interaction with physical objects. Thereby providing user with direct, seamless feedback during the fabrication process. Through this method, the research has developed and presents three distinct Gesture-Based Mixed Reality (GBMR) workflows: object localization, object identification, and object calibration. These workflows utilize gesture recognition to enhance the interaction between virtual and physical environments, allowing for precise localization of objects, intuitive identification processes, and accurate calibrations. The results of these methods are demonstrated through a comprehensive case study: the construction of the Unlog Tower, a 36’ tall robotically fabricated timber structure.

The present contribution addresses both the topics of the design of timber-to-timber joints and the design of innovative and structurally efficient timber structures with the aid of a computational tool based on vector-based graphic statics (VGS).

First, this manuscript explains how the latest developments of graphic statics and its use applied to both timber joints and structures can improve the design of structures made of this low embodied carbon material. An exhaustive review of timber assemblies focussing on their sustainability and their structural behaviour is presented. Among these is the notch joint specifically identified in the context of digital fabrication and circular use of timber.

Afterwards, the theoretical framework of this research is explained. Taking advantage of the lower bound theorem of the theory of plasticity, the main hypotheses that enable the use of graphic statics and strut-and-tie modelling (STM) for timber are then presented. In addition, the structural behaviour of the single notch joint is evaluated using algebraic dimensioning method. The limitations of this method are pointed out and the article proposes an integrated universal approach to investigate the problem using Strut and Tie Modelling (STM) and stress fields. The results of this theoretical framework are validated trough 1/1 scale lab tests. Finally, the third chapter illustrates the potential of VGS via a Research-by-Design approach. In the aim of testing if designing simultaneously creative and efficient timber structures could be effective while using the VGS, architectural engineering student were asked to focus on both the primary load-bearing structure and the joint-systems.

Traditional method to evaluate outdoor thermal comfort which used indicators (UTCI, PET, SET, etc.) has its limitations. Firstly, emotional factors are not included in the assessment, and secondly, the results lead to less accessibility, and it is difficult for non-experts to understand.

Due to the above reasons, some scholars have investigated how to evaluate outdoor thermal comfort by ‘English vocabulary’, and there is still a gap in exploring the multidimensional semantic assessment of outdoor thermal comfort by using ‘Chinese vocabulary’. This paper established a ‘Chinese vocabulary’ thesaurus for outdoor thermal comfort evaluation through online and on-site questionnaire survey including 63 words, and an outdoor experiment was carried out to validate the effectiveness of the thesaurus. The results showed a significant correlation between the 2-phases results, revealing the effectiveness of the multidimensional semantic Chinese thesaurus. PET value has a wide range when Thermal Comfort Vote (TCV) are the same, and the words people used to describe the thermal environment in 5 dimensions are very different. The results showed that it is necessary to evaluate the thermal environment by the way of multidimensional semantic, which could make up the short comings of the traditional way (thermal comfort indicators).

The field validation experiment of this study was only carried out for 3 days in spring in Shenyang city, thus the result was highly influenced by the experiment conditions and has its limitations. This study could be a fundamental exploration of thermal comfort evaluation by semantic way in Chinese words.

Biosafety laboratories are specialized in handling dangerous microorganisms, but there are cases where contaminants are leaked due to improper handling and other reasons. Therefore, an in-depth understanding of the pattern of infection after a laboratory spill can help laboratory personnel get out of danger as soon as possible and avoid the occurrence of infection events. In this paper, we take the COVID-19 virus outbreak in recent years as an example to explore the probability of infection of laboratory personnel under different circumstances. The study used computational fluid dynamics (CFD) to predict the change of contaminant concentration over time in a typical laboratory, and then analyzed the relationship between contaminant concentration and infection probability by using a metrological response model, and calculated the infection probability of indoor personnel over time in the presence or absence of obstacles in the laboratory and the different locations of contaminant leakage, respectively. The results showed that the probability of personnel infection remained basically stable after 8 min of contaminant leakage; at the same time, the probability of infection was higher when the contaminant source was located below the exhaust vent than in other locations; and the probability of illness was lower in laboratories with obstacles than in laboratories without obstacles under the same conditions. This finding is helpful for laboratory layout design.

This paper proposes an effective approach to realise circular construction with concrete, and shows Unreinforced Masonry as a foundational building block for it.

The paper outlines the importance of circularity in building structures. It specifically focuses on the impact of circular construction with concrete on improving the sustainability of the built environment in a rapidly urbanising world economy. Subsequently, the relevance of principles of structural design and construction of unreinforced masonry to achieve circularity is articulated. Furthermore, the paper presents and summarises recent developments in the field of Unreinforced Concrete Masonry (URCM) including digital design tools to synthesise structurally efficient shapes, and low-waste digital fabrication techniques using lower-embodied-emission materials to realise the designed shapes. The paper exemplifies these using two physically realised, full-scale URCM footbridge prototypes and a commercially available, mass-customisable building floor element, called the Rippmann Floor System (RFS).

The paper also outlines the benefits of mainstream, industrial-scale adoption of the design and construction technologies for URCM, including accelerating the pathway to decarbonise the concrete industry. In summary, the paper argues that URCM provides a solution to significantly mitigate the carbon emissions associated with concrete and reduce the use of virgin resources whilst retaining its benefits such as widespread and cheap availability, endurance, fire safety, low maintenance requirements and recyclability.

The shift towards bio-economies of architectural fabrication necessitates particular consideration of how characterizing aspects of bio-materials such as heterogeneity and anisotropy impact the designed performance of architectural elements. These aspects must be integrated into the modelling and representation of architecture and must be instrumentalised for digital design and fabrication processes. The use of timber in construction is challenging due to its complex material behaviours, and therefore robust methods for predicting and modelling these are crucial for exploiting the timber resource more effectively. In light of this, we focus on developing a holistic and integrated digital modelling approach for glue-laminated timber construction elements that connects the digital design model to the specific material resource and incorporates its material complexity into design simulation workflows. We question the role of the lamella in the glulam blank and trace its agency through a series of four disparate projects, from an initially silent and generic constituent of the blank to a key, operative actor in the design of performance-graded timber products through the added specificity of material composition and a liberation of its form. The first project develops a modelling approach that connects material specification and lamella sizing to free-form timber element geometries. It uses principles of industrial glulam production and knowledge of the anisotropic nature of timber to speculate on new forms of glulam blanks that could arise from a deeper engagement with the glue-lamination process. The second project looks further back in the timber value chain at the processing of the specific forest resource into tailored building elements, attaching a material specificity to the lamella. The third project expands the modelling and prototyping of non-standard glulam blanks into considerations of timber waste streams and aesthetics. The final project aims to further speciate the lamella by tailoring its form as well as its material composition to respond to simulated performance demands. Through these projects we outline the development of a novel digital framework that begins as a modelling approach for free-form glulam beams and grows to accommodate the mapping and allocation of specific, heterogeneous input material. As the digital framework matures, increasingly detailed and interlinked digital simulations of mechanical performance are integrated.