Failure Rate Analysis of Shovel and Dumper in Opencast Limestone Mine using RWB and ANN
Harish Kumar. N. S1, R. P. Choudhary2, Ch. S. N. Murthy3
1Harish Kumar. N. S, Department of Mining Engineering, NITK, Surathkal, Mangalore (Karnataka), India.
2R.P Choudhary, Department of Mining Engineering, NITK, Surathkal, Mangalore (Karnataka), India.
3Ch. S. N Murthy, Department of Mining Engineering, NITK, Surathkal, Mangalore (Karnataka), India.
Manuscript received on 07 April 2019 | Revised Manuscript received on 20 April 2019 | Manuscript published on 30 April 2019 | PP: 1765-1770 | Volume-8 Issue-6, April 2019 | Retrieval Number: F3174048619/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: To develop a nonparametric bathtub curve model for a shovel and dumper in an opencast limestone mine, the historical failure data such as time between failure (TBF) and failure frequency of a shovel and dumper were collected from the mine. Based on the collected TBF and failure frequency, Weibull parameters i.e., shape parameter (), scale parameter and location parameter () were calculated under the K-S test (Kolmogorov–Smirnov). A Weibull distribution model has been developed to obtain the probability distribution function (PDF) and the bathtub-shaped failure rate curve for a shovel-dumper system using Reliability Isograph Workbench (RWB). Also, the Artificial Neural Network (ANN) model has been developed to predict the PDF and failure rate for the same shovel-dumper system and compared with the obtained values of Reliability Isograph Workbench. It was found that the values of RMSE and R 2 were 5.96E-5 & 0.999 for PDF and 9.23E-8 & 0.9993 for failure rate respectively.
Keyword: Nonparametric Model, Bathtub Curve, Lifetime Estimation, Failure Rate, Opencast Limestone Mine, K-S Test, Weibull Distribution, Time Between Failure, Failure Frequency, RMSE (Root Mean Square Error) and ANN.
Scope of the Article: Software Analysis, Design and Modelling