Classification of draglines failure types by K-NearestNeighbor algorithm

Date

2017-08-31

Author

Taghızadeh, Amir
Demirel, Nuray

Metadata

Show full item record

Item Usage Stats

194
views

0
downloads

Availability of mining machines plays a significant role in mine production. Dragline’s reliability has a great impact on sustaining economic feasibility of open cast coal mining projects. In that sense, reliability of draglines and optimizing its preventive maintenance are key issues to be addressed. The objective of this study is to apply machine learning methodologies for classifying failure types of a dragline based on a real data. The mean time between failure data was acquired from an operating open cast coal mine in Turkey. Three modified form of K-Nearest Neighbors algorithms have been used as a predictor for failure classification. An approximation function has been generated based on the time to failure and break-down type. In case of parameter tuning, cross validation method has been utilized. This caused more reliable evaluation of the test sample, so average testing performance has been used for test data estimation. The basic model was for parameter tuning; Moreover, for achieving more efficient parameter Grid Search method was utilized. Since, usage of the algorithm is computationally expensive, so Randomized Search method has been carried out in order to figure out the functionality of modeled function in the high dimension datasets. The results of the study revealed that the application of K-Nearest Neighbors method reached the Regression Analysis of 73 percent. Thus, the higher accuracy of prediction of failure type can be helpful in prognostic of dragline’s procedure. The main novelty of this study is utilization of machine learning approach for dragline maintenance for the first time.

Subject Keywords

Machine learning, K-nearest neighbor, Dragline, Reliability, Maintenance

URI

https://docmh.com/classification-of-draglines-failure-types-by-k-nearest-neighbor-algorithm
https://hdl.handle.net/11511/83657

Conference Name

Proceeding of the 26th International Symposium on Mine Planning and Equipment Selection, MPES (2017)

Collections

Department of Mining Engineering, Conference / Seminar

Suggestions

OpenMETU
Core

Reliability analysis for two draglines in Tunçbilek lignite mine Tuncay, Deniz; Demirel, Nuray; Department of Mining Engineering (2014) In modern mining activities, high-capacity complex machines are used and their availability plays a big role on the mine productivity. Draglines are one of the high capacity mining machines which result in decrease in production in case of failure or unavailability. This study aims to determine the effects of different components of two draglines (PAGE 736 and MARION 7820) to their availability and operability by choosing adequate reliability models and conducting fault tree analyses. Reliability analysis w...
Optimization of the lubricating oil inventory policy applied in a mining company Şenses, Sena; Gölbaşı, Onur; Bakal, İsmail Serdar (2021-02-01) The mining industry should sustain mass and continuous production with an essential contribution of high-capacity machinery. Therefore, spare parts inventory management is vital in ensuring the intended mining production rate as an integral part of maintenance policies. In this paper, a mixed-integer model is presented to solve a multi-item and multi-supplier spare parts inventory model. This model is addressed to a lubricating oil inventory problem in one of the biggest multi-process mining companies in Tu...
Microscopic fuel consumption modelling for haulage trucks using discrete-event simulation Kına, Elif; Gölbaşı, Onur; Department of Mining Engineering (2021-2-5) Mining is one of the machine-intensive sectors, and a vast amount of energy is consumed in many stages of mining operations. Among these operations, haulage systems hold a significant share in energy consumption. At this point, diesel fuel, a form of fossil fuel, is frequently used for haul trucks such that fuel-induced cost becomes a major contributor to the operating cost, especially in surface mining. Fuel consumption also leads to greenhouse gas emissions, in addition to its financial burden. Therefore,...
Data warehousing and big data applications in mining industry Erkayaoğlu, Mustafa (2017-04-14) Due to the increased costs and production pressure in the mining sector, mine management and planning becomes more dependent on data. The amount of operational data increases as a result of data gathering and data sharing technologies being available on mining equipment. Reliable collection, cleaning, integration and reporting of data is essential to ensure that the data generated by different data sources such as production, maintenance, and cost are used effectively in decision-making and management. Data...
Development of a Dust Violation Control Tool from Plant Data Erkayaoğlu, Mustafa (null; 2018-11-22) Mining is an equipment-intensive industry that utilizes machinery both in production and mineral processing. As an essential part of sustainable development, mining is subject to environmental management from many aspects. The decision-making process integrated into all stages of mining has to be based on reliable data. Available technology enables to track and monitor the production stages in mining by using various sensors and systems. Data related to mining and mineral processing activities have differen...

Citation Formats

A. Taghızadeh and N. Demirel, “Classification of draglines failure types by K-NearestNeighbor algorithm,” Luleå, Sweden, 2017, p. 291, Accessed: 00, 2021. [Online]. Available: https://docmh.com/classification-of-draglines-failure-types-by-k-nearest-neighbor-algorithm.