SOFTWARE APPLICATION FOR THE ANALYSIS OF THE RELIABILITY OF A TEXTILE EQUIPMENT
SOFTWARE APPLICATION FOR THE ANALYSIS OF THE RELIABILITY OF A TEXTILE EQUIPMENT
Author(s): Adrian Vilcu, Ion Verzea, Catalin VilcuSubject(s): Social Sciences
Published by: Carol I National Defence University Publishing House
Keywords: textile technological process; statistical modelling; reliability; neuronal network; safety in operation;educational software.;
Summary/Abstract: The comparative analysis of data predicted for the reliability of a technical system with data determined during the operation within a time period represents a permanent challenge for the engineering design in the field of integrity of systems in general, and the textile processes in particular. The basic and unitary understanding of these concepts is mainly connected with statistical techniques for the measurement and/or estimation of system's reliability, as well as with predicting techniques from artificial intelligence field. Researches performed until now, based in an overwhelming proportion on statistic methods that imply collecting data sometimes hard to determine and obtain on large time horizons, often prohibited, and with predicted results that need validation, lead to the necessity of a new approach for the calculation of this parameter from the management of safety in operation. The main objective of our research consists in the determination of an alternative technique for reliability statistic calculation. In this connection, we propose an integrated software application that comparatively determines and evaluates the values of the reliability function determined both statistically and by a neuronal system. Within the work structure, one defines the management problem of safety in operation, one applies quantitative research on a system from textile spinning (determining the good operation time and mean intensity of technical system failures within an established time horizon), and determines statistically the values of reliability function, by correlating the theoretical and experimental repartitions; one generates the neuronal pattern for function and compares the results. The two approaches are correlated in a unitary software application that can be used as a tool in decision problems from the disciplines of Maintenance Management and in practical cases of technical textile processes.
Journal: Conference proceedings of »eLearning and Software for Education« (eLSE)
- Issue Year: 13/2017
- Issue No: 01
- Page Range: 475-480
- Page Count: 6
- Language: English