Endüstri Mühendisliği Bölümü
https://hdl.handle.net/11491/3172
Industrial Engineering Department2024-03-29T08:30:08ZShortest Confidence Intervals of Weibull Modulus for Small Samples in Materials Reliability Analysis
https://hdl.handle.net/11491/8469
Shortest Confidence Intervals of Weibull Modulus for Small Samples in Materials Reliability Analysis
Yalçınkaya, Meryem; Birgören, Burak
The Weibull distribution has been widely used to model strength properties of brittle materials. Estimation of confidence intervals for Weibull shape parameter has been an important concern, since small sample sizes in materials science experiments bring about large intervals. Many methods have been proposed in the literature for constructing shorter intervals; the methods of maximum likelihood, least square, and Menon are among the most extensively studied methods. However, they all use an equal-tails approach. The pivotal quantities used for constructing confidence intervals have right-skewed and unimodal distributions, thus, they clearly do not produce the shortest intervals for a given confidence level in equal tail form. This study constructs the shortest confidence intervals for the three aforementioned methods and compares their performances by their equal-tails counterparts. To this end, a comprehensive simulation study has been conducted for the shape parameter values between 1 to 80 and the sample sizes between 3 to 20. The comparison criterion is chosen as the expected interval length. The results show that the shortest confidence intervals in each of three methods have yielded considerably narrower intervals. Further, the unknown parameter values are more centered in these intervals.
2023-01-01T00:00:00ZDeep Learning Approach to Technician Routing and Scheduling Problem
https://hdl.handle.net/11491/8418
Deep Learning Approach to Technician Routing and Scheduling Problem
Pekel, Engin
This paper proposes a hybrid algorithm including the Adam algorithm and body change operator (BCO). Feasible solutions to technician routing and scheduling problems (TRSP) are investigated by performing deep learning based on the Adam algorithm and the hybridization of Adam-BCO. TRSP is a problem where all tasks are routed, and technicians are scheduled. In the deep learning method based on the Adam algorithm and Adam-BCO algorithm, the weights of the network are updated, and these weights are evaluated as Greedy approach, and routing and scheduling are performed. The performance of the Adam-BCO algorithm is experimentally compared with the Adam and BCO algorithm by solving the TRSP on the instances developed from the literature. The numerical results evidence that Adam-BCO offers faster and better solutions considering Adam and BCO algorithm. The average solution time increases from 0.14 minutes to 4.03 minutes, but in return, Gap decreases from 9.99% to 5.71%. The hybridization of both algorithms through deep learning provides an effective and feasible solution, as evidenced by the results.
2022-01-01T00:00:00ZA Novel Permutation Based Solution Representation Technique for Vehicle Routing Problems on GPUs
https://hdl.handle.net/11491/8305
A Novel Permutation Based Solution Representation Technique for Vehicle Routing Problems on GPUs
Özçetin, Erdener; Öztürk, Gürkan
In this study, the vehicle routing problem (VRP) which is a well-known NP-hard combinatorial optimization problem is handled on graphic processing units (GPUs). Solving any kind of VRP is extremely hard when the instance size is large. For this reason, researchers tend to solve the VRP with meta-heuristics. Although, many well-designed meta-heuristics produce near-optimal solutions in reasonable time, still a challenge to solve large scale instances. To accomplish this issue, researchers need novel, fast and wisely designed parallel operators for the proposed algorithms. Furthermore, the success of these operators directly depends on the way the solution is represented. This paper offers a new permutation based solution representation technique (?+) for vehicle routing problems on GPUs. Results show that proposed technique can be used in many algorithms to accelerate computations.; Bu çalışmada, NP-Hard kombinatorik optimizasyon problemlerinden olan araç rotalama problemi (ARP), grafik işlem birimleri (GPU) üzerinde ele alınmıştır. Problem boyutunun büyümesiyle birlikte ARP'nin herhangi bir türünü optimal olarak çözmek oldukça zorlaşmaktadır. Araştırmacılar bu yüzden metasezgisel yöntemlere yönelmektedir. Her ne kadar bu metasezgisel algoritmalar kabul edilebilir sürelerde optimale yakın sonuçlar üretse de büyük boyutlu problemler için bu durum farklıdır. Bu durumu aşmak için, araştırmacılar önerilen algoritmalar için yeni, hızlı ve akıllıca tasarlanmış paralel operatörlere ihtiyacı bulunmaktadır. Bu operatörlerin başarısı doğrudan çözümün temsil edilme şekline bağlıdır. Bu makale, ARP'yi GPU'lar üzerinde etkin bir şekilde ele alabilmek için yeni bir permütasyon tabanlı çözüm gösterim tekniği (? +) sunmaktadır. Sonuçlar, önerilen tekniğin hesaplamaları hızlandırmak için birçok algoritmada kullanılabileceğini göstermektedir.
2021-01-01T00:00:00ZKarma modelli tip-2 montaj hattı dengeleme problemi için bir kısıt programlama modeli
https://hdl.handle.net/11491/4974
Karma modelli tip-2 montaj hattı dengeleme problemi için bir kısıt programlama modeli
Alağaş, Hacı Mehmet; Pınarbaşı, Mehmet; Yüzükırmızı, Mustafa; Toklu, Bilal
Bu çalışmada karma modelli montaj hattı dengeleme problemleri için yeni bir kısıt programlama modeli sunulmuştur. Önerilen model verilen bir istasyon sayısı ile çevrim zamanını en küçüklemektedir. Önerilen model literatürdeki örnek problemler ile test edilmiştir ve modelin performansı karma modelli montaj hattı dengeleme problemlerinin matematiksel modeli ile karşılaştırmalı olarak değerlendirilmiştir. Performans kriterleri olarak ulaşılan en iyi çözüm değeri ve CPU süresi kullanılmıştır. Deneysel sonuçlar önerilen kısıt programlama modelinin problemin çözümünde iyi performans gösteren bir alternatif modelleme tekniği olduğunu göstermiştir.; This paper presents a new constraint programming model for mixed-model assembly line balancing problem. The proposed model minimizes the cycle time for a given number of stations. The proposed model is tested with literature problems and its performance is evaluated by comparing to mathematical model. Best obtained solution and elapsed CPU time are used as performance criteria. The experimental results show that the proposed constraint programming model performs well and can be used as an alternative modeling technique to solve the problem.
research
2016-01-01T00:00:00Z