Recent emphasis has been placed on improving the processes in manufacturing by employing early detection or fault prediction within production lines. Whilst companies are increasingly including sensors to record observations and measurements, this brings challenges in interpretation as standard approaches do not highlight the presence of unknown relationships. To address this, we have proposed a new data analytics framework for predicting faults in a large-scale manufacturing system and validated it using both a publicly available Bosch manufacturing dataset with a focus on preprocessing of the data and the open-source SECOM industrial dataset. This paper is an extension to the work presented at International Conference on Intelligent Manufacturing and Internet of Things. The additional material includes a detailed focus on feature selection and the various approaches for identifying important features in the data, an updated framework methodology and description, an extension of XGBoost to allow this model to be used for prediction/classification and a comparison for classification with a Random Forest, tree-based model. The framework was used to explore two public manufacturing datasets and successfully identified the most influential features related to product failure in each production line data.
Abstract-Manufacturing companies can benefit from the early prediction and detection of failures to improve their product yield and reduce system faults through advanced data analytics. Whilst an abundance of data on their processing systems exist, they face difficulties in using it to gain insights to improve their systems. Bayesian networks (BNs) are considered here for diagnosing and predicting faults in a large manufacturing dataset from Bosch. Whilst BN structure learning has been performed traditionally on smaller sized data, this work demonstrates the ability to learn an appropriate BN structure for a large dataset with little information on the variables, for the first time. This paper also demonstrates a new framework for creating an appropriate probabilistic model for the Bosch dataset through the selection of statistically important variables on the response; this is then used to create a BN network which can be used to answer probabilistic queries and classify products based on changes in the sensor values in the production process.
Increasingly manufacturing companies are looking to use sensors to collect data from production lines to help analyse their performance. More rigorous approaches are needed to process and analyse the resulting data, particularly when considering missingness. In this paper, we present the results from a major study into missingness in Seagate’s disc head manufacturing process in Londonderry UK. Working in collaboration with company staff, a detailed approach for analysing missingness has been developed. The work shows how missing data analytics can be employed to analyse the quality of the data, identify relationships and diagnose the presence of any patterns.
Recent emphasis has been placed on improving the processes in manufacturing by employing early detection or fault prediction within production lines. Whilst companies are increasingly including sensors to record observations and measurements, this brings challenges in interpretation as standard approaches for artificial intelligence (AI) do not highlight the presence of unknown relationships. To address this, we propose a new data analytics framework for predicting faults in a large-scale manufacturing system and validate it using a publicly available Bosch manufacturing dataset with a focus on pre-processing of the data.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.