Publication: Lojistik operasyonlarda kullanılan taşıma ekipmanlarının nesnelerin interneti, yapay zeka ile takibi ve yaşam döngüsü analizi metodu ile incelenmesi
Abstract
Lojistik operasyonlarda kullanılan taşıma ekipmanlarının nesnelerin interneti, yapay zeka ile takibi ve yaşam döngüsü analizi metodu ile incelenmesi Sanayi 4.0 süreci, üretim ve lojistik süreçlerinde dijitalleşmeyi zorunlu hale getirirken, bu dönüşüm sürecinde operasyonel verimliliğin artırılması, sürdürülebilirliğin sağlanması ve karar alma süreçlerinin veri temelli hale gelmesi kritik önem kazanmıştır. Lojistik operasyonlar içerisinde özellikle depo içi hareketliliğin ve yük transferinin sağlandığı taşıma ekipmanları; sistemin genel performansı, enerji kullanımı, zaman yönetimi ve çevresel etkiler üzerinde belirleyici rol oynamaktadır. Bu bağlamda hazırlanan bu çalışmada, forkliftler, konveyör sistemleri ve otomatik yönlendirmeli araçlar (AGV) olmak üzere üç temel taşıma ekipmanı, yapay zeka (AI), nesnelerin interneti (IoT) ve yaşam döngüsü analizi (LCA) metotları ile kapsamlı şekilde incelenmiştir. Çalışma kapsamında öncelikle ilgili ekipmanların teknik özellikleri, operasyonel kullanımları ve lojistik sistemler içindeki konumları detaylı literatür taraması ile değerlendirilmiş daha sonra, ekipmanların gerçek zamanlı takibini sağlayan IoT tabanlı izleme altyapısı modellenmiş ve sensör teknolojilerinin veri toplama kapasitesi analiz edilmiştir. Elde edilen bu veriler, yapay zeka algoritmaları (özellikle regresyon, karar ağaçları ve sınıflandırma teknikleri) aracılığıyla işlenmiş ve ekipman bazlı performans analizleri gerçekleştirilmiştir. Çalışma alanı olarak seçilen model bir depo operasyonu üzerinden yürütülen simülasyonlar, farklı ekipman türlerinin enerji tüketimi, kullanım yoğunluğu, hata eğilimleri ve bakım döngüleri açısından değerlendirilmesini sağlamıştır. Ek olarak, her bir ekipman tipi için yaşam döngüsü analizi gerçekleştirilmiş ve bu analiz kapsamında üretim, kullanım, bakım ve bertaraf aşamalarındaki çevresel etkiler karşılaştırmalı olarak incelenmiştir. Karbon ayak izi, enerji tüketim katsayısı ve atık üretimi gibi metrikler üzerinden yapılan değerlendirmelerde, AGV sistemlerinin operasyonel verimliliği artırma potansiyeline sahip olduğu; ancak ilk yatırım maliyetleri ve altyapı bağımlılığı nedeniyle dikkatli planlanması gerektiği belirlenmiştir. Konveyör sistemleri ise sabit hatlar üzerinden yüksek taşıma kapasitesi sunarken, sistem esnekliği açısından sınırlı kalmıştır. Forkliftler ise mobilite avantajına rağmen insan faktörüne bağımlı yapısı nedeniyle verimlilikte dalgalanmalara sebep olmuştur. Elde edilen bulgular doğrultusunda, teknolojik izleme ve değerlendirme araçlarının kullanımıyla lojistikte karar destek sistemlerinin nasıl geliştirilebileceği gösterilmiş, aynı zamanda operasyonel verimlilik ile çevresel sürdürülebilirlik hedeflerinin birlikte optimize edilebileceği ortaya konmuştur. Bu çalışma, lojistik sektörüne yönelik olarak yapay zeka ve nesnelerin interneti destekli analitik modellemelerin hem akademik hem de pratik boyutlarını bir araya getirerek, alan yazına özgün bir katkı sunmayı hedeflemiştir.
Examination of material handling equipments used in logistics operations through internet of things, artificial intelligence tracking, and lifecycle analysis method During the Industry 4.0 era, the digitalization of production and logistics processes has become a necessity. In this context of transformation, enhancing operational efficiency, ensuring sustainability, and making data-driven decision-making processes have gained critical importance. Among logistics operations, material handling equipment particularly those facilitating internal warehouse mobility and load transfer plays a decisive role in overall system performance, energy consumption, time management, and environmental impact. Within this framework, the present study comprehensively examines three primary types of handling equipment forklifts, conveyor systems, and automated guided vehicles (AGVs) through the methodologies of Artificial Intelligence (AI), Internet of Things (IoT), and Life Cycle Assessment (LCA). As part of the study, the technical specifications, operational applications, and roles of the selected equipment types within logistics systems were first evaluated through a detailed literature review. Subsequently, an IoT-based monitoring infrastructure enabling real-time tracking of the equipment was modeled, and the data collection capacities of sensor technologies were analyzed. The collected data were processed using artificial intelligence algorithms, particularly regression, decision trees, and classification techniques, and equipment-specific performance analyses were conducted. Simulations were performed based on a model warehouse operation, allowing the evaluation of different equipment types in terms of energy consumption, usage intensity, fault trends, and maintenance cycles. In addition, a life cycle assessment was conducted for each equipment type, in which the environmental impacts during production, operation, maintenance, and disposal stages were comparatively analyzed. Evaluations based on metrics such as carbon footprint, energy consumption coefficients, and waste generation revealed that AGV systems have significant potential to improve operational efficiency; however, their initial investment costs and dependence on infrastructure necessitate careful planning. While conveyor systems offer high transport capacity through fixed lines, they are limited in terms of system flexibility. Forklifts, on the other hand, offer mobility advantages but are subject to efficiency fluctuations due to their reliance on human operators. The findings of the study demonstrate how decision support systems in logistics can be enhanced through the use of technological monitoring and evaluation tools. At the same time, the study emphasizes that operational efficiency and environmental sustainability goals can be optimized simultaneously. By combining both academic and practical dimensions of AI and IoT-based analytical modeling in the logistics sector, this study aims to contribute uniquely to the existing body of literature.
Examination of material handling equipments used in logistics operations through internet of things, artificial intelligence tracking, and lifecycle analysis method During the Industry 4.0 era, the digitalization of production and logistics processes has become a necessity. In this context of transformation, enhancing operational efficiency, ensuring sustainability, and making data-driven decision-making processes have gained critical importance. Among logistics operations, material handling equipment particularly those facilitating internal warehouse mobility and load transfer plays a decisive role in overall system performance, energy consumption, time management, and environmental impact. Within this framework, the present study comprehensively examines three primary types of handling equipment forklifts, conveyor systems, and automated guided vehicles (AGVs) through the methodologies of Artificial Intelligence (AI), Internet of Things (IoT), and Life Cycle Assessment (LCA). As part of the study, the technical specifications, operational applications, and roles of the selected equipment types within logistics systems were first evaluated through a detailed literature review. Subsequently, an IoT-based monitoring infrastructure enabling real-time tracking of the equipment was modeled, and the data collection capacities of sensor technologies were analyzed. The collected data were processed using artificial intelligence algorithms, particularly regression, decision trees, and classification techniques, and equipment-specific performance analyses were conducted. Simulations were performed based on a model warehouse operation, allowing the evaluation of different equipment types in terms of energy consumption, usage intensity, fault trends, and maintenance cycles. In addition, a life cycle assessment was conducted for each equipment type, in which the environmental impacts during production, operation, maintenance, and disposal stages were comparatively analyzed. Evaluations based on metrics such as carbon footprint, energy consumption coefficients, and waste generation revealed that AGV systems have significant potential to improve operational efficiency; however, their initial investment costs and dependence on infrastructure necessitate careful planning. While conveyor systems offer high transport capacity through fixed lines, they are limited in terms of system flexibility. Forklifts, on the other hand, offer mobility advantages but are subject to efficiency fluctuations due to their reliance on human operators. The findings of the study demonstrate how decision support systems in logistics can be enhanced through the use of technological monitoring and evaluation tools. At the same time, the study emphasizes that operational efficiency and environmental sustainability goals can be optimized simultaneously. By combining both academic and practical dimensions of AI and IoT-based analytical modeling in the logistics sector, this study aims to contribute uniquely to the existing body of literature.