National Technical University of Athens (NTUA)
Ανάπτυξη ολοκληρωμένου συστήματος προγραμματισμού παραγωγής και διαχείρισης αποθεμάτων με χρήση μεθοδολογιών υπολογιστικής νοημοσύνης, θεωρίας ελέγχου και μαθηματικού προγραμματισμού
Abstract
dc:descriptionThe objective in this dissertation is the development of an integrated system for production scheduling and inventory management based on artificial intelligence, control theory and mathematical programming. A methodology for time series modeling was initially developed that utilizes advanced artificial intelligence methods in order to construct a sales volume forecasting model with a sophisticated structure, capable of integrating the characteristics of complex temporal phenomena, while at the same time it is able to select the most appropriate variables for model inclusion and model building. The time series model is subsequently used as a vital element in the development of two production scheduling and inventory management systems. The first system deals with the optimization of the operation of parallel machines that produce multiple products and is based on the solution of a Mixed Integer and Linear Programming problem. A number of constraints, commonly found in industrial practice are included in the model formulation, making it capable of producing realistic production schedules applicable on real-life industrial problems. The prediction methodology can provide valuable knowledge on the expected variations in demand, allowing for the production schedule to modified on time. The use of the method can lead to significant reductions in production costs, as it was shown through its extensive application to dairy industrial production plant. The second methodology developed in this thesis tackles the problem of production scheduling for products with a large sales volume (such as milk, cement, paper pulp etc.) and it is used for strategic decision making on production rates and inventory management. The method is based on an advanced automatic control technique known as Model Predictive Control (MPC), which facilitates the direction of the operation of the supply chain to a desired path. The simultaneous use of a model to forecast sales, which are regarded by the control module as distrurbances, significantly improves system performance and leads to decisions that stabilize inventory levels to a desired point, while at the same time rapidly responding to demand variability.
Degree
thesis:*- Grantor dc:publisher
- National Technical University of Athens (NTUA)
- Year dc:date
- 2006
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Doganis, Philippos
- Δογάνης, Φίλιππος
Subjects
dc:subject × 22- Προγραμματισμός παραγωγής
- Διαχείριση αποθεμάτων
- Υπολογιστική νοημοσύνη
- Μαθηματικός προγραμματισμός
- Πρόβλεψη πωλήσεων
- Ρύθμιση προβλεπτικού μοντέλου
- Θεωρία ελέγχου
- Production scheduling
- Inventory management
- Computational intelligence
- Control theory
- Mathematical programming
- Sales forecasting
- Model predictive control
- Φυσικές Επιστήμες
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Επιστήμες Μηχανικού και Τεχνολογία
- Επιστήμη Ηλεκτρολόγου Μηχανικού, Ηλεκτρονικού Μηχανικού, Μηχανικού Η/Υ
- Natural Sciences
- Computer and Information Sciences
- Engineering and Technology
- Electrical Engineering, Electronic Engineering, Information Engineering
Rights
- Language dc:language
- gre
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/18665