Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
3 results
Search Results
Article Citation - WoS: 3Citation - Scopus: 5Deterioration of Pre-War and Rehabilitation of Post-War Urbanscapes Using Generative Adversarial Networks(SAGE Publications, 2023) Çiçek, Selen; Turhan, Gözde Damla; Taşer, AybükeThe urban built environment of contemporary cities confronts a constant risk of deterioration due to natural or artificial reasons. Especially political aggression and war conflicts have significant destructive effects on architectural and cultural heritage buildings. The post-war urbanscapes demonstrate the striking effects of the armed conflicts during the hot war encounters. However, the residues of the urbanscapes become the actual indicators of damage and loss. Since today we can make future predictions using a variety of machine learning algorithms, it is possible to represent hybrid projections of urban heterotopias. In this context, this research proposes to explore dystopian post-war projections for modern cities based on their architectural styles and demonstrate the utopian scenarios of rehabilitation possibilities for the damaged urban built environment of post-war cities by using generative adversarial network (GAN) algorithms. Two primary datasets containing the post-war and pre-war building facades have been given as the input data for the CycleGAN and pix2pix GAN models. Thus, two different image-to-image GAN models have been compared regarding their ability to produce legible building facade projections in architectural features. Besides, the machine learning process results have been discussed in terms of cities' utopian and dystopian future predictions, demonstrating the war conflicts' immense effects on the built environment. Moreover, the immediate consequence of the destructive aggression on tangible and intangible architectural heritage would become visible to inhabitants and policymakers when the AI-generated rehabilitation potentials have been exposed.Article Generating Plan Layouts: a Case Study on Visualization of Implicit Knowledge by “doctor Architects”(SAGE Publications, 2022) Kasalı, AltuğAim: This article presents an opportunistic case with particular focus on instances from an extended procurement operation in which medical professionals run a proactive process involving the generation of layouts through distinct modes of representational practices without any actual collaboration with designers. The questions of inquiry involve an analysis on how the visualizations came into being and a discussion into the content of drawings that was shaped by individuals without any formal design education. Background: Although the literature introduces examples of genuine participation, particularly in healthcare design practices, the instances in which nondesigners demonstrate accomplished skills in spatial reasoning and representation are limited. Method: The research was formulated as a qualitative case study including a series of observations of the activities of the participants followed by interviews recorded at different locations. The investigation also focuses on the features of these authentic graphics which illustrate the intentions of the medical professionals concerning the function of spaces. Results: In this research, the participants went through a labor intensive and elaborate effort to produce “architectural representations” with the intention to convey their implicit professional expertise in the domain. The layouts were introduced to be the vital elements to visualize the implicit knowledge regarding the functioning of space. Conclusions: The productive and creative engagement of clinicians within this research makes the case for a multidisciplinary approach that reframes the limits and potential contributions of participants alongside drawings, which are exclusively claimed by and strategically employed by architects as negotiation devices within participatory design processes.Article Citation - WoS: 1Citation - Scopus: 1Fatigue Life Prediction and Optimization of Gfrp Composites Based on Failure Tensor Polynomial in Fatigue Model With Exponential Fitting Approach(SAGE Publications, 2022) Güneş, Mehmet Deniz; İmamoğlu Karabaş, Neslişah; Deveci, Hamza Arda; Tanoğlu, Gamze; Tanoğlu, MetinIn this study, a new fatigue life prediction and optimization strategy utilizing the Failure Tensor Polynomial in Fatigue (FTPF) model with exponential fitting and numerical bisection method for fiber reinforced polymer composites has been proposed. Within the experimental stage, glass/epoxy composite laminates with (Formula presented.), (Formula presented.), and (Formula presented.) lay-up configurations were fabricated, quasi-static and fatigue mechanical behavior of GFRP composites was characterized to be used in the FTPF model. The prediction capability of the FTPF model was tested based on the experimental data obtained for multidirectional laminates of various composite materials. Fatigue life prediction results of the glass/epoxy laminates were found to be better as compared to those for the linear fitting predictions. The results also indicated that the approach with exponential fitting provides better fatigue life predictions as compared to those obtained by linear fitting, especially for glass/epoxy laminates. Moreover, an optimization study using the proposed methodology for fatigue life advancement of the glass/epoxy laminates was performed by a powerful hybrid algorithm, PSA/GPSA. So, two optimization scenarios including various loading configurations were considered. The optimization results exhibited that the optimized stacking sequences having maximized fatigue life can be obtained in various loading cases. It was also revealed that the tension-compression loading and the loadings involving shear loads are critical for fatigue, and further improvement in fatigue life may be achieved by designing only symmetric lay-ups instead of symmetric-balanced and diversification of fiber angles to be used in the optimization.