Soft Computing Analysis of Pressure Decay Leak Test Detection
-
Ander Garcia [1] ; Juan Luis Ferrando [1] ; Ander Arbelaiz [1] ; Xabier Oregui [1] ; Andoni Bilbao [2] ; Zelmar Etxegoien [2]
-
[1] Basque Research and Technology Alliance
Basque Research and Technology Alliance
Mendaro, España
-
[2] Gaindu. Inzu Group (Elgoibar, Guipúzcoa)
-
- Localización: 15th International Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO 2020): Burgos, Spain ; September 2020 / coord. por Álvaro Herrero Cosío
, Carlos Cambra Baseca , Daniel Urda Muñoz , Javier Sedano Franco , Héctor Quintián Pardo , Emilio Santiago Corchado Rodríguez , 2021, ISBN 978-3-030-57802-2, págs. 299-308 - Idioma: inglés
- Texto completo no disponible (Saber más ...)
-
Resumen
Leak detection is a common and relevant step of manufacturing processes, which takes place throughout the production line. While several leak test methods have been proposed, pressure decay testing is still widespread due to its lower cost, simplicity and sensitivity in relatively small volumes. However, pressure decay testing is very sensitive to external parameters, mainly temperature. While high-end leak test machines can compensate temperature variations integrating specialized hardware, this paper analyses the viability of applying soft computing models on a regular leak test machine to perform the same compensation. Gaindu, an automation company which sells leak test stations, has customized a leak test station to measure and publish key test data. This data has been stored on a database to be analyzed. Moreover, a model compensating temperature variations has been developed and validated. Results encourage to further vary parameters that may affect the leak test, such as part temperature or humidity, to extend the model and integrate it on commercial leak test machines.
