Volume: 2, 2023
2nd International PhD Student’s Conference at the University of Life Sciences in Lublin, Poland:
ENVIRONMENT – PLANT – ANIMAL – PRODUCT
Abstract number: T006
DOI: https://doi.org/10.24326/ICDSUPL2.T006
Published online: 19 April 2023
ICDSUPL, 2, T006 (2023)
Identification of input signals in the process of estimating the lenght of the assembly cycle of complex products using Artificial Neural Networks
Jolanta Brzozowska1*
1 Department of Computerization and Robotization of Production, Mechanical Faculty, Lublin University of Technology; Nadbystrzycka 38D, 20-618, Lublin, Poland
* Corresponding author: d562@pollub.edu.pl
Abstract
One of the main steps in the manufacturing process is assembly, which is one of the one of the key stages in the manufacturing process of customized products, where products are assembled according to customer needs. Time standards are among one of the most important indicators of the efficiency of the manufacturing process. An accurate analysis of the assembly time of a particular product that a customer wants to order influences the actual completion of the order within the agreed time, and consequently, the shipment of the finished product within the time specified in the contract. Nevertheless, the determination of this time by traditional methods is in many cases impossible, which prompts the search for techniques using the latest advances in science and technology. For complex problems that require multi-criteria analysis of a large amount of data, analytical and optimization methods give way to heuristic methods. Although they can be considered more accurate, the time-consuming nature of obtaining results can disqualify them in many situations such as pre-designing complex systems or acting in the face of an unexpected crisis. Combining heuristic methods with artificial intelligence in the areas of technological processes and machine assembly can increase the productivity and competitiveness of manufacturing companies. Taking into account the research carried out so far, it can be concluded that it is possible to develop a model using neural networks that, after input parameters, will generate information on the output about the estimated assembly cycle of a particular type of machine. The development of the model with the use of artificial neural networks can be based on the following steps: development of training and test sets and finding the best structure of the artificial neural network. The preliminary results of the analysis carried out on the collected database made it possible to determine what input factors should be taken into account for building the model, i.e. the availability of parts, the availability of resources and the novelty factor.
How to cite
J. Brzozowska, 2023. Identification of input signals in the process of estimating the lenght of the assembly cycle of complex products using Artificial Neural Networks. In: 2nd International PhD Student’s Conference at the University of Life Sciences in Lublin, Poland: Environment – Plant – Animal – Product. https://doi.org/10.24326/ICDSUPL2.T006