Image Processing Based Fault Detection and Isolation for Mechanical Components
C. Bharathi Priya1, V.Sudha2
1C.Bharathi Priya, Assistant Professor II, Department of Computer Science and Engineering, Kumaraguru College of Technology Coimbatore (Tamil Nadu), India.
2V.Sudha, Assistant Professor II, Department of Computer Science and Engineering, Kumaraguru College of Technology Coimbatore (Tamil Nadu), India.
Manuscript received on 15 August 2019 | Revised Manuscript received on 27 August 2019 | Manuscript Published on 06 September 2019 | PP: 96-98 | Volume-8 Issue- 6S, August 2019 | Retrieval Number: F10200886S19/19©BEIESP | DOI: 10.35940/ijeat.F1020.0886S19
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Fault Detection and Isolation (FDI) is essential in mechanical industry to detect and isolate objects with manufacturing defect. At present in assembly line, mechanical components are transported from one stage to other stage for assembly, packing etc. During this process, components are randomly drawn from the conveyor belt and manually inspected. Since the random inspection is done manually, there is a chance of missing out defected components in the assembly line. Manual inspection is time consuming and all the features of the components cannot be verified accurately. Hence, there is a need for a image processing based system to detect the anomalies in the components sent in the conveyor belt. In this work, camera is mounted above the conveyor module and captures the images of nuts and bolts which moving on conveyor belt. Captured images are preprocessed to remove background noise, then image is enhanced to get the appropriate features and Region of Interest (diameter of nut) is extracted to measure the diameter. If any anomaly is found in the attributes (diameter) of the mechanical components, an electrical signal will be sent to the Solenoid valve and then it actuates deflector plate by the pneumatic cylinder. Defected component is then carried by the secondary conveyor to the re-matching and the quality product are then carried to the packaging will passed to the separator through microcontroller. In this way, components with manufacturing defect are identified and isolated from assembly line.
Keywords: Fault Detection, Isolation, Segmentation, Feature Extraction.
Scope of the Article: Image Processing and Pattern Recognition