Qualitative evaluation of the regeneration process of a technical object in a maintenance system with an artificial neural network

• Published in: Neural computing & applications Vol. 20; no. 5; pp. 741 - 752
• Main Author: Duer, Stanisław
• Format: Journal Article
• Language: English
• Published: London Springer-Verlag 01.07.2011; Springer
• Subjects: Applied sciences; Artificial Intelligence; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer Science; Computer science; control theory; systems; Data Mining and Knowledge Discovery; Exact sciences and technology; General topics; Global analysis, analysis on manifolds; Image Processing and Computer Vision; Learning and adaptive systems; Mathematics; Neural networks; Numerical analysis; Numerical analysis. Scientific computation; Numerical approximation; Original Article; Probability and statistics; Probability and Statistics in Computer Science; Sciences and techniques of general use; Statistics; Topology. Manifolds and cell complexes. Global analysis and analysis on manifolds; Diagnostics information; Knowledge base; Servicing process; System modelling; Expert system; Artificial neural networks; System evaluation; Neural computation; Error estimation; System maintenance; Analytical method; Qualitative analysis; Metric; Neural network
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-010-0418-0

The present article includes a description of a qualitative evaluation of the regeneration process of a reparable technical object in a maintenance system with an artificial neural network. The delineated spaces of the operational features of a new technical object and of a technical object after regeneration in a maintenance system constitute the basis of the evaluation proposed of a maintenance system. The proposed evaluation of the maintenance system is realized in a graphical and analytical method. The graphical evaluation makes the use of the spaces of maintenance information: the operation features of a new technical object (as a model) and the spaces of maintenance information after a regeneration of an object was performed in a maintenance system. For this purpose, a nominal (model) space was described and defined of maintenance information: the operational properties of a technical object and the space of theoretical maintenance information: the current operational properties of a technical object after maintenance. In the proposed qualitative analysis of regeneration, examinations covered the level of the features of the object’s operation after regeneration was performed in relation to the level of the operational properties of a new object (which was only put to operation) as a model. The resulting differences in the metrics of the distances between these spaces of the object’s operational properties indicate directly the errors (the qualitative evaluation level) in the organization process of the maintenance system.