Simulation Platform for Fault Diagnosis

The previous chapters have described the mathematical principles and algorithms of multivariate statistical methods, as well as the monitoring processes when used for fault diagnosis. In order to validate the effectiveness of data-driven multivariate statistical analysis methods in the field of fault diagnosis, it is necessary to conduct the corresponding fault monitoring experiments. Therefore this chapter introduces two kinds of simulation platform, Tennessee Eastman (TE) process simulation system and fed-batch Penicillin Fermentation Process simulation system. They are widely used as test platforms for the process monitoring, fault classification, and identification of industrial process. The related experiments based on PCA, CCA, PLS, and FDA are completed on the TE simulation platforms.

Displacement Velocity and Strain Analysis of Opak Fault Monitoring Stations

The Opak Fault is an active fault that can potentially cause earthquakes in Yogyakarta. Periodic monitoring of the Opak Fault activity was previously used more GNSS observation data from the measurement campaign by the Geodesi Geometri dan Geodesi Fisis (GGGF) Laboratory Team, Geodetic Engineering Department, Faculty of Engineering, Universitas Gadjah Mada. However, there are several CORS BIG stations located in Yogyakarta. The CORS BIG data is used to increase the precision of the Opak Fault monitoring station. Therefore, the addition of the CORS is evaluated to obtain a displacement in the monitoring station. The computation of the displacement velocity value of the Opak Fault monitoring station has been done before using the Linear Least Square Collocation and grid search methods. The other method, namely the kriging method, needs to be evaluated for producing a more precise displacement velocity value. The research data includes GNSS campaign and CORS BIG data for six years, 2013 to 2020. The CORS stations around DIY are JOGS and CBTL. The GNNS data were processed to determine the solution for the daily coordinate, displacement, and standard deviation values for each Opak Fault monitoring station. The displacement velocity value is generated by the Linear Least Square method then reduced from the influence of the Sunda Block. The velocity value is used in the strain value estimation around the Opak Fault area at each station using the kriging method combined with the gaussian sequential simulation technique. The estimated displacement velocities are examined for statistical significance compared to the research of Adam (2019) and Pinasti (2019). This research generates the value of the displacement velocity in the east and north components of 12.39 to 30.99 mm/year and 1.96 to -14.11 mm/year, respectively. The displacement direction of all monitoring stations is dominant to the southeast. The Sunda Block reduced the displacement velocity. The east and north components are -2.32 to 2.28 mm/year and -0.52 to 4.2 mm/year, respectively. The displacement direction is towards the northwest. The strain estimation using the kriging method combined with the gaussian sequential simulation technique obtained an average strain value of 0.05 microstrain/year. The result of the data processing at each station has different arrow lengths, meaning that each location has a different strain value.

Continuous Productivity Improvement Using IoE Data for Fault Monitoring: An Automotive Parts Production Line Case Study

This paper presents a case study of continuous productivity improvement of an automotive parts production line using Internet of Everything (IoE) data for fault monitoring. Continuous productivity improvement denotes an iterative process of analyzing and updating the production line configuration for productivity improvement based on measured data. Analysis for continuous improvement of a production system requires a set of data (machine uptime, downtime, cycle-time) that are not typically monitored by a conventional fault monitoring system. Although productivity improvement is a critical aspect for a manufacturing site, not many production systems are equipped with a dedicated data recording system towards continuous improvement. In this paper, we study the problem of how to derive the dataset required for continuous improvement from the measurement by a conventional fault monitoring system. In particular, we provide a case study of an automotive parts production line. Based on the data measured by the existing fault monitoring system, we model the production system and derive the dataset required for continuous improvement. Our approach provides the expected amount of improvement to operation managers in a numerical manner to help them make a decision on whether they should modify the line configuration or not.

Research on residual current warning technology based on big data analysis

Residual current is the main cause of electrical fire. The traditional residual current monitoring methods often give delayed alarm, false alarm or even missed alarm, which cannot be applied in practice. This paper put forward the residual current detection solution based on big data analysis. The big data analysis based on residual current, temperature and humidity could detect residual current anomaly information as early as possible, realize fault monitoring and early warning. This method was applied to important facilities such as substation, data center. It could reduce or eliminate fire hazards, and provide decision basis for electrical fire warning.