Contextual reliability discounting in welding process diagnostic based on DSmT

Abstract

The monitoring and diagnosing of the welding process is an important task in assuring the quality of welded joints. Observation of such a dynamic process is often performed by measuring various signals of different modality. The main problem is how to use several of the possible signals simultaneously. Many techniques that can deal with this kind of task were elaborated and introduced in practical application. One of these is decision fusion, with a group of methods based on belief function theories: Dempster–Shafer and Dezert–Smarandache (DSmT). In this paper, extended fusion scheme for assessment of welding process condition, with contextual discounting of evidence sources reliability in DSmT framework, is presented. Discounting operation was used to distinguish the objective ability of each evidence source, to give a correct assessment of process condition. To validate this method, several series of welded joints representing different process conditions that result in various joint quality were made. On the basis of performed research, it was proven that contextual reliability discounting leads to increase of the condition recognition accuracy.

Application of Laser Vibrometry to Assess Defects in Ship Hull’s Welded Joints’ Technical Condition

“…NDT testing techniques are well researched and give results with usually sufficient reliability [ 10 , 11 , 12 , 13 , 14 ]. However, they have a fundamental disadvantage—they are carried out periodically.…”

An inference model for combustion diagnostics in an experimental oil furnace

“…Considering that a flame exhibits visual characteristics that depend on complex physical phenomena resulting from the assignment of operational parameters, a robust image‐based control policy for a furnace cannot be implemented unless the diagnostics issued by the monitoring system is based on a matrix of expert sensors that are able to establish one‐to‐several cause‐and‐effect relationships between visual features and combustion states in a similar manner a human being would do. Making robust decisions by combining heterogeneous signals—a typical problem concerning Industrial Information Integration Engineering (Chen, )—is an issue that can be properly approached by inference methods based on belief functions, as reported in the recent literature (Benslama, Batatia, & Messai, ; Jamrozik, ; Kessentini, Burger, & Paquet, ; Pande, Sondawale, Keswani, & Walke, ).…”