5862 research outputs found
Sort by
Towards Better Energy Efficiency Through Coil-Based Electricity Consumption Forecasting in Steel Manufacturing
No full textForecasting electricity consumption with the possibly-highest accuracy is crucial for cost optimization, operational efficiency, competitiveness, contract negotiation, and achieving the global goals of sustainable development in steel manufacturing. This study focuses on identifying the most appropriate prediction algorithm for coil-based electricity consumption and the most effective implementation purposes in a steel company. Random Forest, Gradient-Boosted Trees, and Deep Neural Networks are preferred because they are suitable for the given problem and widely used for forecasting. The performance of the prediction models is evaluated based on the root mean squared error (RMSE) and the coefficient of determination (R-squared). Experiments show that the Random Forest model outperforms the Gradient-Boosted Trees and Deep Neural Network models. The results will provide benefits for many different purposes. Firstly, during contract negotiations, it will enable us to gain a competitive advantage when purchasing electricity in the day-ahead market. Secondly, in the production scheduling phase, the ones with the highest electricity consumption will be produced during the hours when there is the least demand at the most affordable prices. Finally, when prioritizing sales orders, the use of the existing capacity for orders with lower energy intensity or a higher profit margin will be ensured.Conference Proceedings Citation Index - Scienc
On Symbolic Prediction of Time Series for Predictive Maintenance Based on Sax-Lstm
No full textBu çalışma, Sembolik Toplam Yaklaşım (SAX) ve Parçalı Toplam Yaklaşım (PAA) gibi gelişmiş yaklaşımları makine öğrenme algoritmalarıyla birleştirerek endüstriyel ortamlarda tahmine dayalı bakım tahminine yönelik yeni bir yaklaşımı araştırıyor. Çalışma, üretim süreçlerinin dijitalleşmesinin hem fırsatlar hem de karmaşıklıklar getirdiği Endüstri 4.0 bağlamında bakım tahmini konularını ele almayı amaçlıyor. Çalışma, sentetik verileri kullanarak ve çeşitli veri kümesi boyutları, PAA segment uzunlukları ve SAX alfabe boyutlarıyla denemeler yaparak bakım gereksinimlerini doğru şekilde tahmin edebilen sağlam bir algoritma oluşturmayı amaçlıyor. Süreç, SAX ve PAA teknikleri kullanılarak elde edilen etiketli veriler üzerinde makine öğrenimi modellerinin, özellikle de Uzun Kısa Süreli Bellek (LSTM) ağlarının eğitilmesini gerektirir. Algoritmanın performansı, işletme verimliliğini artırmak ve arıza süresini azaltmak için zamanında bakımın kritik olduğu çelik üretim fırınlarından elde edilen gerçek dünya endüstri verileri kullanılarak değerlendirilir. Çalışmanın bulguları, modern veri işleme ve makine öğrenimi yaklaşımlarının endüstriyel varlık yönetimini ve karar verme süreçlerini nasıl iyileştiribileceğine dair öngörüler sağlayarak tahmine dayalı bakım yöntemlerinin artmasına yardımcı oluyor.This work investigates a new approach to predictive maintenance forecasting in industrial settings, combining advanced approaches like Symbolic Aggregate Approximation (SAX) and Piecewise Aggregate Approximation (PAA) with machine learning algorithms. The study seeks to address the issues of maintenance forecasting in the context of Industry 4.0, in which the digitalization of manufacturing processes brings both opportunities and complexities. The work aims to construct a robust algorithm capable of properly estimating maintenance requirements by using synthetic data and experimenting with various dataset sizes, PAA segment lengths, and SAX alphabet sizes. The process entails training machine learning models, specifically Long Short Term Memory (LSTM) networks, on labeled data obtained using SAX and PAA techniques. The algorithm's performance is assessed using real-world industry data from steel production furnaces, where timely maintenance is critical for increasing operating efficiency and reducing downtime. The study's findings help to increase predictive maintenance methods by providing insights into how modern data processing and machine learning approaches might improve industrial asset management and decision-making processes
Blueprint and Intellectual Property Management in Spare Part Supply Chains in the Existence of Three-Dimensional Printing
No full textBu tez, mavi kopya lisans anlaşmaları (MKLA) açısından yedek parça tedarik zincirlerine üç boyutlu baskının (3BY) entegrasyonunu incelemektedir. Araştırmanın temel amacı, Orijinal Ekipman Üreticileri'nin (OEÜ) 3BY teknolojisini etkili bir şekilde kullanabileceği koşulları optimize etmek ve aynı zamanda alıcılar için maliyet etkinliğini sağlamaktır. Bu çalışma, oyun teorisi ve ajan tabanlı modelleme (ATM) kullanarak, OEÜ'ler ve alıcılar arasındaki stratejik etkileşimleri ve bu etkileşimlerin envanter yönetimi üzerindeki etkilerini kapsamlı bir şekilde analiz etmektedir. Araştırma, üç temel matematiksel model etrafında yapılandırılmıştır: 3BY ile Tek Kaynaklı Tedarik, 3BY ve Geleneksel Tedarik ile Çift Kaynaklı Tedarik, ve Baskı Kotası Varlığında Geleneksel Tedarik ve 3BY ile Çift Kaynaklı Tedarik. Bu modeller, 3BY'nin tek kaynaklı tedarik yöntemi olarak ya da geleneksel üretim yöntemleriyle birlikte kullanıldığı çeşitli senaryoları incelemektedir. OEÜ'in MKLA şartlarını belirlediği ve alıcının buna göre tedarik stratejisini seçtiği karar verme sürecini modellemek için Stackelberg oyunu kullanılmıştır. Bu çalışmanın ana bulguları, optimal MKLA koşullarının talep değişkenliği ve 3BY ile ilişkili maliyet yapıları gibi faktörlere son derece duyarlı olduğunu göstermektedir. ATM simülasyonları ayrıca, fikri mülkiyet yönetimi ve dinamik envanter kontrolü açısından 3BY'nin getirdiği karmaşıklıkları aşmak için hem OEÜ'ler hem de alıcılar için uyarlanabilir stratejilerin kritik olduğunu göstermektedir. Bu etkileşimlerin ve sonuçta ortaya çıkan optimal stratejilerin detaylı analizi, teorik ve pratik sonuçların daha derin bir şekilde anlaşılmasını sağlamaktadır. Bu tezin katkıları üç ana başlık altında toplanabilir: 3BY bağlamında MKLA'lara yenilikçi bir oyun teorik yaklaşım sunar, karmaşık, çok değişkenli etkilenen sistemleri keşfetmede ATM'nin kullanımını gösterir ve hem OEÜ'ler hem de alıcılar için pratik içgörüler sağlar. Araştırma ayrıca, genişletilmiş modellerin keşfedilmesi ve teorik bulguların gerçek dünya ortamlarında doğrulanması için gelecekteki çalışmaların potansiyelini vurgulamaktadır. Sonuç olarak, bu tez, MKLA'ların 3BY teknolojisinden yararlanmak için nasıl optimize edilebileceğine dair anlayışı geliştirmektedir. Elde edilen içgörüler, OEÜ'ler ve alıcıların bilinçli stratejik kararlar almalarında rehberlik sağlayarak, nihayetinde daha verimli ve dayanıklı tedarik zincirlerine katkıda bulunmaktadır. Anahtar Sözcükler: Mavi Kopya Lisans Anlaşmaları, Üç Boyutlu Baskı, Oyun Teorisi, Ajan Tabanlı Modelleme, Tedarik Zinciri Yönetimi, Fikri Mülkiyet Yönetimi, Stackelberg Oyunu, Yedek Parça Tedarik Zincirleri.This thesis explores the integration of three-dimensional printing (3DP) into spare parts supply chains from the aspect of Blueprint Licensing Agreements (BPLAs). The primary objective of this research is to optimize the conditions under which Original Equipment Manufacturers (OEMs) can effectively employ 3DP technology, while also ensuring cost-efficiency for buyers. By utilizing game theory and agent based modeling (ABM), this study provides a comprehensive analysis of the strategic interactions between OEMs and buyers, and their implications on inventory management. The research is structured around three core mathematical models: Single-Sourcing with 3DP, Dual-Sourcing with 3DP and Traditional Supply, and Dual-Sourcing with Traditional Supply and 3DP in the Existence of Printing Quota. These models examine various scenarios in which 3DP is used either as a single-sourcing method or in combination with traditional manufacturing methods. A Stackelberg game framework is employed to model the decision-making process, where the OEM sets the terms of the BPLA and the buyer chooses the sourcing strategy accordingly. Key findings from this study indicate that optimal BPLA conditions are highly sensitive to factors such as demand variability and the cost structures associated with 3DP. The ABM simulations further indicate that adaptive strategies are crucial for both OEMs and buyers to navigate the complexities introduced by 3DP, particularly in terms of intellectual property management and dynamic inventory control. Detailed analysis of these interactions and the resultant optimal strategies is presented, providing a deeper understanding of the theoretical and practical implications. The contributions of this thesis are threefold: it offers a novel game-theoretic approach to BPLAs in the context of 3DP, demonstrates the utility of ABM in exploring complex, multi-variable influenced systems, and provides practical insights for both OEMs and buyers. The research also highlights the potential for future studies to explore extended models and validate the theoretical findings in real-world settings. In conclusion, this thesis advances the understanding of how BPLAs can be optimized to leverage 3DP technology in supply chains. The insights gained provide valuable guidance for OEMs and buyers in making informed strategic decisions, ultimately contributing to more efficient and resilient supply chains. Keywords: Blueprint Licensing Agreements, Three-Dimensional Printing, Game Theory, Agent-Based Modeling, Supply Chain Management, Intellectual Property Management, Stackelberg Game, Spare Parts Supply Chains
Comparison of Feature Selection Methods for Mechanical Properties of Cold Rolled Products in Flat Steel Manufacturing
No full textThe mechanical properties of steel are critical for ensuring its quality and are traditionally tested using destructive methods, which involve cutting test samples after the skin-rolling process. This procedure necessitates the scrapping of the last 8 meters of the coil and extracting a 500 mm wide sample, consuming approximately 1 to 1.5 minutes. To eliminate these additional process steps and minimize material waste, this study aims to predict steel coils' yield strength and tensile strength in the flat steel industry using six machine learning models. The models incorporate 24 distinct production parameters as inputs. The models examined include Linear Regression, Support Vector Regressor (SVR), Decision Tree, K-Nearest Neighbors (KNN), Random Forest, and eXtreme Gradient Boosting (XGBoost). To enhance the predictive performance of these models, seven different feature selection methods are employed. These methods systematically rank the production parameters based on their influence and are iteratively utilized within the models to refine their accuracy. The application of these feature selection techniques significantly improves the models' efficiency, leading to substantial operational benefits. The study demonstrates that machine learning models, when optimized with advanced feature selection methods, can accurately predict the mechanical properties of steel, thereby reducing the need for destructive testing. This approach not only conserves material and time but also enhances the overall efficiency of the production process in the flat steel industry. © 2024 IEEE
Dilemmas, Pained Frustration, and New Possibilities: Masculinities, Violences, and Disabilities
No full textDisabled masculinities pose a theoretical and, more importantly, a very visceral, real-life dilemma for many men. This dilemma arises from disability being linked with being reliant on others, feeble and defenceless, yet masculinity is primarily associated with being physically strong, healthy, dominant, and independent. Violence can play an ambiguous role in disabled men’s lives. Some men may have become disabled through their participation and/or exposure to violence, such as in war; men with disabilities may be more exposed to various forms of violence; living with disabilities may lead to violent, negative, ‘coping’ strategies against others and oneself; but disabilities can also lead some men re-assessing their masculinities and adopting more caring ways of being a man. This chapter seeks to explore these dilemmas, vulnerabilities, as well as shifts in masculinities and their links to violence, both amongst men born with disabilities and those who acquired disabilities later in life. It draws mainly on previous work by the authors in four different contexts: Turkey, Kachin State in Myanmar, South African township, and rural areas of Ghana. We thereby cover areas affected by armed conflict and high levels of criminal violence, as well as areas where these are largely absent. © 2024 Taylor and Francis
On the Generalisation Performance of Geometric Semantic Genetic Programming for Boolean Functions: Learning Block Mutations
No full textIn this article, we present the first rigorous theoretical analysis of the generalisation performance of a Geometric Semantic Genetic Programming (GSGP) system. More specifically, we consider a hill-climber using the GSGP Fixed Block Mutation (FBM) operator for the domain of Boolean functions. We prove that the algorithm cannot evolve Boolean conjunctions of arbitrary size that are correct on unseen inputs chosen uniformly at random from the complete truth table i.e., it generalises poorly. Two algorithms based on the Varying Block Mutation (VBM) operator are proposed and analysed to address the issue. We rigorously prove that under the uniform distribution the first one can efficiently evolve any Boolean function of constant size with respect to the number of available variables, while the second one can efficiently evolve general conjunctions or disjunctions of any size without requiring prior knowledge of the target function class. An experimental analysis confirms the theoretical insights for realistic problem sizes and indicates the superiority of the proposed operators also for small parity functions not explicitly covered by the theory. © 2024 Copyright held by the owner/author(s).Engineering and Physical Sciences Research Council, EPSRC, (/M004252/1); Engineering and Physical Sciences Research Council, EPSR
Continuous Glycemic Monitoring Enabled by a Wi-Fi Energy-Harvesting Wearable Sweat-Sensing Patch
No full textMirlou, Fariborz/0000-0003-0545-7504; Istif, Emin/0000-0003-4700-7050; Abbasiasl, Taher/0000-0002-8366-7737; Mirzajani, Hadi/0000-0001-7747-2389Continuous monitoring of multiple physiological parameters, such as glucose levels, temperature, and heart rate variability (HRV) is crucial for effective diabetes management and mitigating the risks associated with hypoglycemic events. These events often occur without apparent symptoms, posing a challenge for diabetic patients in managing their condition. Therefore, a non-invasive wearable device capable of continuously measuring multiple body signals to predict hypoglycemic events would be highly beneficial. In this study, a wearable patch that continuously measures glucose, temperature, and HRV is presented. The device uses a novel power harvesting system to convert radiofrequency (RF) signals with the frequency of 2.45 GHz to direct current (DC) signals to extend the battery life for further continuous monitoring. The patch is small and has a conformal structure that can easily fit onto different body parts. The screen-printed glucose sensor demonstrates a sensitivity of 10.3 nA cm-2 mu M-1, a limit of detection (LOD) of 8.9 mu M, and a limit of quantification (LOQ) of 27 mu M. The device employs a photoplethysmography (PPG) module with a peak-finding algorithm to calculate the HRV values. In vivo experiments demonstrate the validation of the device's proper operation in glucose, HRV, and temperature measurement. This study introduces a wearable patch for diabetes management, employing a unique Wi-Fi energy harvesting system for extended battery life. The device's conformal structure enables effortless placement on the body, providing continuous monitoring of glucose, HRV, and temperature. The platform presents a non-invasive physiological monitoring approach that enhances diabetes care by offering real-time data in a compact and efficient design. imageScientific and Technological Research Council of Turkey (TUBITAK) [118C295, 120M363, HORIZON-TMA-MSCA-PF-EF-2021-101068646, 121Z184, 101043119]; Marie Sklodowska-Curie Postdoctoral Fellowship; European Research Council (ERC) [118C155]; [2210822]F.M., T.A., and L.B. were supported by The Scientific and Technological Research Council of Turkey (TUBITAK) through 2244 (#118C155), 2232 (#118C295), and 3501 (120M363) programs. H.M. acknowledges the support through a Marie Sklodowska-Curie Postdoctoral Fellowship (HORIZON-TMA-MSCA-PF-EF-2021-101068646, HAMP). E.I. acknowledges the support through The Scientific and Technological Research Council of Turkey (TUBITAK) 3501 (grant no. 121Z184) and 1512 (grant no. 2210822) programs. L.B. acknowledges European Research Council (ERC) (grant no. 101043119). Authors gratefully acknowledge Koc University Nanofabrication and Nano-characterization Center (N2Star) for infrastructure access
Subtask-Based Virtual Hand Visualization Method for Enhanced User Accuracy in Virtual Reality Environments
No full textGemici, Mucahit/0009-0004-4655-4743; Hatira, Amal/0009-0006-6452-0672; Bashar, Mohammad Raihanul/0000-0002-5271-457XIn the virtual hand interaction techniques, the opacity of the virtual hand avatar can potentially obstruct users' visual feedback, leading to detrimental effects on accuracy and cognitive load. Given that the cognitive load is related to gaze movements, our study focuses on analyzing the gaze movements of participants across opaque, transparent, and invisible hand visualizations in order to create a new interaction technique. For our experimental setup, we used a Purdue Pegboard Test with reaching, grasping, transporting, and inserting subtasks. We examined how long and where participants concentrated on these subtasks and, using the findings, introduced a new virtual hand visualization method to increase accuracy. We hope that our results can be used in future virtual reality applications where users have to interact with virtual objects accurately.Conference Proceedings Citation Index - Scienc
