Sensor anomaly detection in the industrial internet of things based on edge computing

Abstract

In the industrial internet of things (IIoT), because thousands of pieces of hardware, instruments, and various controllers are involved, the core problem is the sensors. Detection using sensors is the bottom line of the IIoT, directly affecting the detection accuracy and control indicators of the IIoT system. However, when a large number of realtime data generated by IIoT devices are transferred to cloud computing centers, large-scale data will inevitably bring computing load, which will affect the computing speed of cloud computing centers and increase the computing load of cloud computing data centers. These factors directly lead to instability and delay in sensor data collected in real time in the IIoT. In this paper, a sensor outlier detection algorithm based on edge calculation is proposed. Firstly, focusing on the problem of the large amount of data in terminal equipment of the IIoT, the edge technology method of data compression is used to optimize the compression of sensor data, and different thresholds are set according to different industrial process requirements, so as to ensure the real-time aspect and authenticity of the data. Then, using the K-means clustering algorithm, the compressed test data sets are analyzed and the abnormal sensor detection values and labels are obtained. Finally, the effectiveness of such an approach is evaluated through a sample case study involving a temperature control system.

The Dynamics of the Ubiquitous Internet of Things (IoT) and Trailblazing Data Mining (DM)

“…In a statement by Hancock and Hancock [3], authors indicate that it is hard to know the size or state of the IoT because it is evolving so rapidly. A similar opinion is observed by Kong, et al [1] where an increase in data mining and consequent demand for data storage is predicted. It has been understood that in the future, the IoT technologies will better integrate with the internet for developing accurate solutions to interchange and communicate information through sensing devices.…”

“…Morgan referred to the future concerning IoT as an assertion based on an informed observation of the trend in the IoT space. For instance, according to Kong et al [1], various countries have adopted strategies based on the rapid development of IoT technologies with good examples being China with its Made-in-China 2025 strategy, the US through its American Advanced Manufacturing Partnership Program, and Germany's German Industry 4.0 strategy. In light of these strategies accordingly, the IoT will continue to influence significant paradigm shifts, especially in data management and applications.…”

“…For instance, when Jacob Morgan mentions that eventually "anything that can be connected will be connected", it signifies that the implication of IoT on data mining will be significant. For instance, even Kong, et al [1], mentioned that with the increase in IoT business, the demand for data storage and computing will put pressure on the ability of cloud computing. In this regard, data mining's scope in the future must also be explored.…”

“…It was the increase in communication protocol development, network creations, and increased focus on Artificial Intelligence that birthed the IoT. According to Kong [1], the IoT involves the information of physical objects, including sensors, machines, cars, buildings, and other items, that allow interaction and cooperation of these objects for achieving specific goals. Others, such as Welbourne et al [2], provided more detailed descriptions.…”

IoT Sistemlerde Sınır Bilişim Destekli Anomali Tespiti

“…Ancak, IIoT cihazları tarafından üretilen çok sayıda gerçek zamanlı veri bulut bilgi işlem merkezlerine aktarıldığında, büyük ölçekli veriler kaçınılmaz olarak bilgi işlem yükünü getirecek ve bu da bulut bilgi işlem merkezlerinin bilgi işlem hızını etkileyecek ve bulut bilgi işlem veri merkezlerinin bilgi işlem yükünü artıracaktır. Bu faktörler, IIoT'de gerçek zamanlı olarak toplanan sensör verilerinde doğrudan kararsızlığa ve gecikmeye yol açar [12].…”