Abstract
Factories of the future are foreseen to evolve into smart factories with autonomous and adaptive manufacturing processes. However, the increasing complexity of the network of manufacturing processes is expected to complicate the rapid detection of process anomalies in real time. This paper proposes an architecture framework and method for the implementation of the Scalable On-line Anomaly Detection System (SOADS), which can detect process anomalies via real-time processing and analyze large amounts of process execution data in the context of autonomous and adaptive manufacturing processes. The design of this system architecture framework entailed the derivation of standard subsequence patterns using the PrefixSpan algorithm, a sequential pattern algorithm. The anomalies of the real-time event streams and derived subsequence patterns were scored using the Smith-Waterman algorithm, a sequence alignment algorithm. The excellence of the proposed system was verified by measuring the time for deriving subsequence patterns and by obtaining the anomaly scoring time from large event logs. The proposed system succeeded in large-scale data processing and analysis, one of the requirements for a smart factory, by using Apache Spark streaming and Apache Hbase, and is expected to become the basis of anomaly detection systems of smart factories.
Highlights
The fourth industrial revolution represented by Big Data, artificial intelligence, and Internet of Things (IoT) technologies is dramatically transforming global industries
The proposed system satisfies the requirements of a large-scale system by using a Big Data processing and analysis framework and real-time distribution streaming technology to track numerous object IDs, derive subsequence patterns, and detect process anomalies in real time in a smart factory
Similar to conformance checking in the field of business processes, many studies have investigated anomaly detection by comparing process patterns and event logs derived from a variety of fields including manufacturing, transportation, logistics, and information communication networks
Summary
The fourth industrial revolution represented by Big Data, artificial intelligence, and Internet of Things (IoT) technologies is dramatically transforming global industries. Recent studies have developed methods to derive a process model in real time [13,14,15] and discover anomalies by aligning on-stream data with the process model in real time [16,17] Applying these results to autonomous and adaptive manufacturing processes is problematic. Our proposed approach derives multi-frequency subsequence patterns by analyzing the implemented process log and determines the overall process anomaly in a smart factory at every moment by comparing the subsequence patterns with the behavior of the flow of each object (that is, sequence) acquired from real-time event streams. The proposed system satisfies the requirements of a large-scale system by using a Big Data processing and analysis framework and real-time distribution streaming technology to track numerous object IDs, derive subsequence patterns, and detect process anomalies in real time in a smart factory.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have