EventiC: A Real-Time Unbiased Event-Based Learning Technique for Complex Systems

Abstract

An improved method for the real time sensitivity analysis in large scale complex systems is proposed in this paper. The method borrows principles from the event tracking of interrelated causal events and deploys clustering methods to automatically measure the relevance and contribution made by each input event data (ED) on system outputs. The ethos of the proposed event modeling (EM) technique is that the behavior or the state of a system is a function of the knowledge acquired about events occurring in the system and its wider operational environment. As such it builds on the theoretical and the practical foundation for the engineering of knowledge and data in modern and complex systems. The proposed EM platform EventiC filters noncontributory ED sources and has the potential to include information that was initially thought irrelevant or simply not considered at the design stage. The real-time ability to group and rank relevant input-output ED in order of its importance and relevance will not only improve the data quality, but leads to an improved higher level of mathematical formulization in the modern complex systems. The contribution of the approach to systems' modeling is in the automation of data analysis, control, and plant process modeling. EventiC has been validated as the monitoring and the control system for a cement factory. In addition to the previously known parameters, the proposed EventiC identified new influential parameters that were previously unknown. It also filtered 18% of the input data without compromising the data quality or the integrity. The solution has improved the quality of input variable selection and simplify plant control strategies.

EGEP: An Event Tracker Enhanced Gene Expression Programming for Data Driven System Engineering Problems

“…It should be pointed out that the selection of a trigger threshold remains a challenging issue in the Event Tracker, which relies on a static process. We have further developed EventiC [38] to cluster the events. A future work will research how the clustering results of the EventiC can be utilized to select a trigger threshold dynamically.…”

“…Those component behavior changes and whole system state changes are further analyzed in order to provide a sensitivity index of the involved components. In our recent work on EventiC [38], events detected from snapshots of the target system running at ideal conditions are further clustered into a lookup table. Although a full track of the target system state changes is not achievable with Event Tracker, some good states are feasible to be repeated with the guide of the lookup table.…”

Event Modeller Data Analytic for Harmonic Failures

“…One significant difference between the proposed event modeller and other traditional data modelling techniques is how the input data assumes its output data. The traditional method assumes the input-output relationship as a true representation of a known data series, while the event modeller technique makes no assumption about it (unbiased) [32]. This fundamentally makes the approach non-unbiased vis-à-vis input-output relationship.…”

“…This technique interprets the changes in input-output data's value at the given level, detecting the coincidence and finally groups it as a related event. The process of calculating the number of coincidence occurs at a specified scan rate time interval, to ensure a relationship weight is established for modelling and control purposes [32]. Despite filtering the unimportant relationship between the input-output relationship, event clustering can identify new influencing parameters that were previously thought irrelevant, making it unique and interesting to improve the data quality.…”

Simulation of Event-Based Technique for Harmonic Failures

“…This relationship has made the EventiC a unique tool, as it does not rely on any prejudgement of data relevancy. It also has the capability of identifying new influential parameters that were previously unknown [2]. The interpreting rate is fast which only focuses on the unique coincidence activity between the input and output.…”