Abstract

In this paper, auto-regressive integrated moving average (ARIMA) time-series data forecast models are evaluated to ascertain their feasibility in predicting human–machine interface (HMI) state transitions, which are modeled as multivariate time-series patterns. Human–machine interface states generally include changes in their visually displayed information brought about due to both process parameter changes and user actions. This approach has wide applications in industrial controls, such as nuclear power plant control rooms and transportation industry, such as aircraft cockpits, etc., to develop non-intrusive real-time monitoring solutions for human operator situational awareness and potentially predicting human-in-the-loop error trend precursors.

Highlights

  • Operator situational awareness (SA) is quintessential in ensuring safe operation of any industrial establishment and more so in nuclear power plants (NPP)

  • As evident from the post-accident reports [2,3,4], include: (1) reduction in situational awareness owing to human factor related deficiencies in legacy human–machine interface (HMI design); (2) normalization to deviance to lax nuclear safety culture; (3) information overload owing to the rapid rate at which information was presented to operators via the control room HMIs; and (4) incorrect mental model of highly dynamic unit evolutions resulting in cognitive errors, owing to conflicting plant information supplied by failed or faulty sensors and incorrect field equipment status monitoring

  • The assumptions outlined in section (Section 3.1) allows HMI state TS data to promise being weakly stationary in nature, allowing application of auto-regressive integrated moving average (ARIMA) forecast models

Read more

Summary

Introduction

Operator situational awareness (SA) is quintessential in ensuring safe operation of any industrial establishment and more so in nuclear power plants (NPP). As evident from the post-accident reports [2,3,4], include: (1) reduction in situational awareness owing to human factor related deficiencies in legacy human–machine interface (HMI design); (2) normalization to deviance to lax nuclear safety culture; (3) information overload (looking-but-not-seeing effects [5]) owing to the rapid rate at which information was presented to operators via the control room HMIs (panel indications, annunciations, etc.); and (4) incorrect mental model of highly dynamic unit evolutions resulting in cognitive errors, owing to conflicting plant information supplied by failed or faulty sensors and incorrect field equipment status monitoring. The rest of the paper is organized as follows: Section 2 presents a review of current state-of-the-art relevant to proposed time-series data forecasting and its applications.

Related Work
HMI Model
Weakly Stationary Assumptions
Tools for Checking Stationarity
Persistence model
Static model
Dynamic mode
Adaptive model
Results
Data Series Analysis
Adaptive Dynamic n-Step Ahead
Adaptive n-Step with Exogenous Input
Adaptive Dynamic n-Step with Exogenous Input
Adaptive ARIMA Model
Exogenous Inputs yield Consistent Performance
Static ARIMA Model
General Limitations of ARIMA Models
Conclusions and Future Work
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call