Search Results

Now showing 1 - 4 of 4

Access status: Open Access ,
Application of Basic Machine-Learning Classifiers for Automatic Anomaly Detection in Shewhart Control Charts
(Wydawnictwa AGH, 2024) Woźniak, Aleksander; Krawiec, Klaudia; Książek, Roger
In today’s dynamic technological environment, innovation plays a crucial role – especially for manufacturing enterprises that constantly strive to improve the quality of their products. This article examines the quality-management issue in a company producing car rims. It was identified that real-time quality control can sometimes be unreliable due to controller fatigue, leading to erroneous data interpretation or delayed responses to deviations in the production process. The study aimed to investigate the possibility of eliminating or significantly reducing these errors by employing a tool that is based on artificial intelligence. The article covers the preparation of training data, the training of classifiers, and the evaluation of their effectiveness in analyzing control charts in real time. The adopted hypothesis assumes that machine-learning classifiers can be effective methods of support for quality controllers. The research began with collecting measurement data from the machine and dividing it into training and test sets. The obtained results were evaluated using standard quality measures for machine-learning models. The results showed that the use of artificial intelligence can bring significant benefits in improving quality supervision in the production process of car rims.
Access status: Open Access ,
Heuristic algorithm for lot sizing and scheduling on identical parallel machines
(Wydawnictwa AGH, 2022) Książek, Roger
This paper presents a new heuristic algorithm for the task of lot sizing and scheduling for identical parallel machines. The new algorithm is based on the rolling-horizon approach and the fix-and-relax decomposition technique. Two variants of the algorithm are finally proposed for solving the problem of lot scheduling with parallel machines where the number of products and machines is greater than that of the machines. A computational experiment has been conducted for a group of 30 data sets. The results showed that the new algorithm efficiently provided good solutions for tasks with large numbers of machines and products.
Access status: Open Access ,
A MILP model for the municipal solid waste selective collection routing problem
(AGH University of Science and Technology Press, 2019) Korcyl, Antoni; Książek, Roger; Gdowska, Katarzyna
Nowadays, selective solid waste management in the European Union belongs to important responsibilities of municipalities. In Solid Waste Management (SWM) the main operational task is to set a schedule for solid waste collection and to find optimal routes for garbage trucks, so that the total costs of the solid waste collection service can be minimized, subject to a series of constraints which not only guarantee the fulfillment of the SWM's obligations but also ensure the desirable quality level of that service. The optimization in garbage truck routing belongs to so called rich Vehicle Routing Problems as it aims to cover the following constraints: pickup nodes (clients) must be visited during their predefined time windows, the number and capacity of depots and specialized sorting units cannot be exceeded, each garbage truck can be assigned to at most one depot, each route should be dedicated to collecting one type of segregated solid waste, and the route must be served by a garbage truck which can collect that type of solid waste, the availability of garbage trucks and their drivers must be respected, each garbage truck must be drained at a specialized sorting unit before going back to the depot. This paper contributes a newly developed Mixed-Integer Programming (MIP) model for the Municipal Solid Waste Selective Collection Routing Problem (MSWSCRP) with time windows, limited heterogeneous fleet, and different types of segregated solid waste to be collected separately. Results obtained for solving small-sized instance of the MSWSCRP are reported.
Access status: Open Access ,
Przedstawienie wyników działania algorytmu genetycznego dla zadania CLSP planowania wielkości i szeregowania partii produkcyjnej
(Wydawnictwa AGH, 2011) Książek, Roger
This paper presents the results obtained using a genetic algorithm to solve mixed integer programming task for the capacitated lot sizing problem. CLSP model was chosen from among many models with different variants of this problem as a basic for development of genetic algorithm. In this paper is summarized a comparison between the results of a genetic algorithm with the results of mixed integer programming for solving the same problem.

Książek, Roger

Email Address

Employee

Alternative name

Discipline

Author Profiles

Systemy AGH

Filters

Advanced Search

Filter by

Settings

Sort By

Results per page

Search Results