– Revista Iberoamericana de Automática e Informática Industrial
Este artículo describe el diseño e implementación de un novedoso sistema de inspección basado en visión artificial para detectar defectos en carrocerías de vehículos automóviles. El sistema ha sido implantado en la factoría Ford de Almussafes (Valencia) como consecuencia de varios proyectos de I+D entre Ford España S.A. y el Instituto de Diseño y Fabricación de la Universidad Politécnica de Valencia que han derivado en dos patentes internacionales. El sistema se basa en la detección de defectos mediante un barrido de iluminación, estando el sistema de visión fijo, al igual que el objeto a inspeccionar. Tras la adquisición de las imágenes, los defectos se detectan como consecuencia de las transiciones generadas por el barrido de iluminación al verse deformado el patrón de reflexión. La alta sensibilidad del sistema permite detectar defectos milimétricos de 0.2mm de diámetro, gracias al efecto de amplificación. La principal innovación introducida por este proyecto industrial reside en el hecho del que el sistema es capaz de detectar casi el 100% de los defectos detectados mediante inspección humana.
Esto ha supuesto mejoras significativas en la reducción del número de vehículos rechazados, además de una reducción del consumo energético, pintura utilizada, del menor impacto medioambiental y por supuesto una reducción en los costes de producción. El sistema también ha supuesto una mejora de las condiciones laborales de los trabajadores al reducirse los problemas como la fatiga ocular. En la actualidad el sistema está siendo rediseñado para su implantación y explotación en otras factorías Ford a nivel mundial con varios modelos de vehículos
– European Automotive Congress 2011
In a typical painting plant, sealing and cavity waxing operations take place to ensure water tightness and sheet metal edge corrosion protection. Paint defects appear as an inevitable variation of the optimum conditions because of powder, worker mistakes, temperature variation, etc. and show up as surface alterations in the layer they are present. Defects may consist of small particles on the surface, which are difficult to detect. In the case of small particles, their size increase incrementally with each additional paint application until they do not meet the quality control standards, resulting in the rejection of the vehicle. This paper presents the design and construction of a completely automated inspection system (inspection tunnel) for defect detection and monitoring of painted bodies based on computer vision techniques and distributed computation. It is an absolutely new inspection system that has been installed in the Almussafes plant of the FORD Company. The system is able to detect 100% of millimetric defects on large volumes such as car bodies within a time processing less than 10sec.
– 2011 IEEE International Conference on Robotics and Automation
This paper describes the design and implementation of a novel inspection system for detecting defects on car bodies based on artificial vision, implemented in Ford Factory at Almussafes (Spain). The system is based on the principle of performing a lightning sweeping with static imagining system, which causes shadows surrounding defects when merging consecutive images, coined as defect augmentation phenomena. As a result, we can detect millimetric defects of 0.3mm diameter or greater with different shapes which were very hard to detect with existing technology without that phenomena. The project has generated two PTC patents, the first one protects the defect augmentation phenomena, while the second protects the industrial system itself. The main innovation of this industrial project is the development of a system that improves in almost 100% the human inspection. As a consequences, it reduces the number of invalid vehicles, energy consumption, saving painting which also implies a significant cost reduction. It also improves working conditions for workers by reducing ocular fatigues.
– Revista Iberoamericana de Automática e Informática Industrial
– European Automotive Congress 2011
In a typical painting plant, sealing and cavity waxing operations take place to ensure water tightness and sheet metal edge corrosion protection. Paint defects appear as an inevitable variation of the optimum conditions because of powder, worker mistakes, temperature variation, etc. and show up as surface alterations in the layer they are present. Defects may consist of small particles on the surface, which are difficult to detect. In the case of small particles, their size increase incrementally with each additional paint application until they do not meet the quality control standards, resulting in the rejection of the vehicle. This paper presents the design and construction of a completely automated inspection system (inspection tunnel) for defect detection and monitoring of painted bodies based on computer vision techniques and distributed computation. It is an absolutely new inspection system that has been installed in the Almussafes plant of the FORD Company. The system is able to detect 100% of millimetric defects on large volumes such as car bodies within a time processing less than 10sec.
– 2011 IEEE International Conference on Robotics and Automation