Overflow remote warning using improved fuzzy c-means clustering in IoT monitoring system based on multi-access edge computing

Abstract

In existing overflow remote intelligent monitoring system, a huge amount of data uploading and multiple processing brings great challenges to the bandwidth load and real-time feedback of the server. Based on the Multiple Access Edge Computing Architecture (MEC), this paper proposes an Internet of Things overflow intelligent monitoring system based on multi-access edge computing. As the middle layer of the system, edge computing can provide real-time local services for field devices, and it can reduce the data uploading amount by preliminarily analyzing the computing tasks of the cloud computing platform. At the same time, for the current domestic and international artificial intelligence-based overflow warning model, it needs a large amount of prior knowledge or training data before use, and the accuracy, real time, and reliability of overflow monitoring are limited by prior knowledge and training data and other issues. In this paper, the information entropy theory has been adopted to improve fuzzy c-means clustering (FCM) algorithm to overcome the disadvantage that the user gives the number of clustering actively in FCM clustering. Then, considering the correlation between the occurrence of overflow accident and the changing trend of standpipe pressure and casing pressure, an intelligent early warning model of drilling overflow accident is proposed by using the improved FCM clustering method based on information entropy. The early warning model uses the adaptive determination of the number of clusters for clustering, which not only ensures the quality of the cluster but also improves the accuracy and reliability of the overflow warning. The warning result of the overflow accident is output according to the clustering fitting result and the sensitivity of the overflow accident. Finally, the drilling data of YY oil well in XX oilfield considered as the research object.