Abstract
Fault diagnosis in multistage manufacturing processes (MMPs) is a challenging task where most of the research presented in the literature considers a predefined inspection scheme to identify the sources of variation and make the process diagnosable. In this paper, a sequential inspection procedure to detect the process fault based on a sequential testing algorithm and a minimum monitoring system is proposed. After the monitoring system detects that the process is out of statistical control, the features to be inspected (end of line or in process measurements) are defined sequentially according to the expected information gain of each potential inspection measurement. A case study is analyzed to prove the benefits of this approach with respect to a predefined inspection scheme and a randomized sequential inspection considering both the use and non-use of fault probabilities from historical maintenance data.
Highlights
Inspection Procedure for FaultIn the last several years, international institutions such as the European Factories of the Future Research Association (EFFRA) have promoted the development of strategies for modeling, monitoring, and controlling complex manufacturing systems to achieve zero-defects [1].Multistage Manufacturing Processes (MMPs) are sequential manufacturing processes where workpieces move throughout different stages in order to perform specific manufacturing operations
Sequential inspection in MMPs can be of interest to reduce the inspection cost and provide fast fault detection
This paper has proposed a methodology to implement a sequential inspection procedure based on the information gain index of the inspection measurement
Summary
In the last several years, international institutions such as the European Factories of the Future Research Association (EFFRA) have promoted the development of strategies for modeling, monitoring, and controlling complex manufacturing systems to achieve zero-defects [1]. In the field of fault diagnosis, a model that relates key product characteristics (KPCs) to sources of variation is needed for an effective root cause analysis This model can be defined by engineering or data-driven approaches. Li and Tsung [13] used the SoV model and EWMA charts for detecting and identifying the faults that affect the process covariance matrix in MMPs. On the other hand, data-driven models are based on shop-floor data to extract the spatial pattern vectors (SPVs) that define the relationships between KPCs and sources of variation. Despite the large contributions in the field of fault diagnosis in MMPs, most of the research works are based on the existence of diagnosability conditions [7], which means that enough measurements are available to detect and identify the source of variation.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
