Javascript must be enabled to continue!
BOOKBINDING OPERATIONAL PLANNING AND SCHEDULING OPTIMIZATION WITH DEEP LEARNING ALGORITHMS
View through CrossRef
This work focuses on the scheduling optimization of the bookbinding process through the application of industrial engineering principles, complemented by artificial intelligence as a key factor in achieving operational efficiency. Flexibility and the need to adapt quickly to fluctuating market conditions in the publishing industry present challenges that require precise operational planning. This includes detailed planning of resources such as time, labour and machinery as well as the optimization of technical and technological processes. Each subprocess is meticulously documented in technological specifications, which precisely describe manufacturing process, product specifications and required quality controls. By analysing input and output parameters in four case studies, a mathematical model was developed to optimize the production process for soft book binding. The model is based on deep learning algorithms that analyse extensive data about the production process and enable an accurate prediction of the optimal production parameters based on current demand and production capacities. For this purpose, an artificial neural network was constructed, which is considered suitable due to its ability to learn complex patterns from data and generate predictions or recommendations based on a large amount of input data. The artificial neural network consists of input, hidden and output layers, each using an activation function that determines the activation of the neurons based on the input data. When training the artificial neural network, the weighting factors between the neurons in the hidden layers are adjusted to minimize the errors between the actual and predicted results. This architecture enables the artificial neural network to learn complicated data patterns and use the derived model for predictions and optimization of the production process in bookbinding. In addition, the model’s predictions facilitate continuous monitoring and analysis of product quality, identifying potential defects or problems before they impact production. By integrating this model, bookbinderies are able to continuously improve their production process and thereby achieve greater efficiency and competitiveness in the market
UNIVERSITY OF NOVI SAD FACULTY OF TECHNICAL SCIENCES DEPARTMENT OF GRAPHIC ENGINEERING AND DESIGN 21000 Novi Sad, Trg Dositeja Obradovića 6
Title: BOOKBINDING OPERATIONAL PLANNING AND SCHEDULING OPTIMIZATION WITH DEEP LEARNING ALGORITHMS
Description:
This work focuses on the scheduling optimization of the bookbinding process through the application of industrial engineering principles, complemented by artificial intelligence as a key factor in achieving operational efficiency.
Flexibility and the need to adapt quickly to fluctuating market conditions in the publishing industry present challenges that require precise operational planning.
This includes detailed planning of resources such as time, labour and machinery as well as the optimization of technical and technological processes.
Each subprocess is meticulously documented in technological specifications, which precisely describe manufacturing process, product specifications and required quality controls.
By analysing input and output parameters in four case studies, a mathematical model was developed to optimize the production process for soft book binding.
The model is based on deep learning algorithms that analyse extensive data about the production process and enable an accurate prediction of the optimal production parameters based on current demand and production capacities.
For this purpose, an artificial neural network was constructed, which is considered suitable due to its ability to learn complex patterns from data and generate predictions or recommendations based on a large amount of input data.
The artificial neural network consists of input, hidden and output layers, each using an activation function that determines the activation of the neurons based on the input data.
When training the artificial neural network, the weighting factors between the neurons in the hidden layers are adjusted to minimize the errors between the actual and predicted results.
This architecture enables the artificial neural network to learn complicated data patterns and use the derived model for predictions and optimization of the production process in bookbinding.
In addition, the model’s predictions facilitate continuous monitoring and analysis of product quality, identifying potential defects or problems before they impact production.
By integrating this model, bookbinderies are able to continuously improve their production process and thereby achieve greater efficiency and competitiveness in the market.
Related Results
Modeling Hybrid Metaheuristic Optimization Algorithm for Convergence Prediction
Modeling Hybrid Metaheuristic Optimization Algorithm for Convergence Prediction
The project aims at the design and development of six hybrid nature inspired algorithms based on Grey Wolf Optimization algorithm with Artificial Bee Colony Optimization algorithm ...
Modeling Hybrid Metaheuristic Optimization Algorithm for Convergence Prediction
Modeling Hybrid Metaheuristic Optimization Algorithm for Convergence Prediction
The project aims at the design and development of six hybrid nature inspired algorithms based on Grey Wolf Optimization algorithm with Artificial Bee Colony Optimization algorithm ...
DPTM: An Adaptive Scheduler Design Utilizing Timeslot Matching and Release Methods for Concurrent and Multi-task Interleaved Pipelining-oriented CGRA
DPTM: An Adaptive Scheduler Design Utilizing Timeslot Matching and Release Methods for Concurrent and Multi-task Interleaved Pipelining-oriented CGRA
Coarse-grained reconfigurable architectures (CGRAs) are increasingly employed as domain-specific accelerators due to their efficiency and flexibility. However, the existing CGRA ar...
Visual versus Tabular Scheduling Programs
Visual versus Tabular Scheduling Programs
Effective scheduling in construction is crucial for ensuring timely project completion and maintaining budget control. Scheduling programs play an important role in this process by...
Advanced Scheduling Schemes in 4G Systems
Advanced Scheduling Schemes in 4G Systems
The deterministic factor for 4G wireless technologies is to successfully deliver high value services such as voice, video, real-time data with well defined Quality of Service (QoS)...
Adaptive Scheduling of Mixing Trucks in Construction Sites with an Improved Deep Q-Network
Adaptive Scheduling of Mixing Trucks in Construction Sites with an Improved Deep Q-Network
The management of concrete mixing station distribution is evolving toward more intelligent and efficient methods. Additionally, in the context of the group operations of commodity ...
Deep convolutional neural network and IoT technology for healthcare
Deep convolutional neural network and IoT technology for healthcare
Background Deep Learning is an AI technology that trains computers to analyze data in an approach similar to the human brain. Deep learning algorithms can find complex patterns in ...
Integrating quantum neural networks with machine learning algorithms for optimizing healthcare diagnostics and treatment outcomes
Integrating quantum neural networks with machine learning algorithms for optimizing healthcare diagnostics and treatment outcomes
The rapid advancements in artificial intelligence (AI) and quantum computing have catalyzed an unprecedented shift in the methodologies utilized for healthcare diagnostics and trea...

