A data-driven approach to diagnosing throughput bottlenecks from a maintenance perspective

Subramaniyan, Mukund; Skoogh, Anders; Muhammad, Azam Sheikh; Johansson, Björn; Roser, Christoph

doi:10.1016/j.cie.2020.106851

Cited by 19 publications

(6 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A data-driven approach was used to develop a working model of the characteristics of the stockpile. This approach combined the knowledge of the mine planners with that of the researchers in a process similar to the one demonstrated by Subramaniyan et al [47]. For the purposes of this paper, as it is an example of the modelling technique, the exact data presented are not real data but exemplify real data seen by researchers and demon-strate a hypothetical stockpile created to show the design method.…”

Section: Approachmentioning

confidence: 98%

Modelling Large Heaped Fill Stockpiles Using FMS Data

Young¹,

Rogers²

2021

Minerals

View full text Add to dashboard Cite

The frequent best practice for managing large low-grade run-of-mine (ROM) stockpiles is to average the entire stockpile to only one grade. Modern ore control and mineral processing procedures need better precision. Low-precision models hinder the ability to create a digital mine-to-mill model and optimize the holistic mining process. Prior to processing, poorly characterized stockpiles are often drilled and sampled, despite there being no geological reason for relationships between samples to exist. Stockpile management is also influenced by reserve accounting and lacks a common operational workflow. This paper provides a review of base and precious metal run-of-mine (ROM) pre-crusher stockpiles in the mining industry, and demonstrates how to build a spatial model of a large long-term stockpile using fleet management system (FMS) data and geostatistical code in Python and R Studio. We demonstrate a framework for modelling a stockpile believed to be readily workable for most modern mines through use of established geostatistical modelling techniques applied to the type of data generated in a FMS. In the method presented, each bench of the stockpile is modeled as its own geological domain. Size of dump loads is assumed to contain the same volume of material and grade values that match those of the grade data tracked in the FMS. Despite the limitations of these inputs, existing interpolation techniques can lead to increased understanding of the grade distribution within stockpiles. Using the framework demonstrated in this paper, engineers and stockpile managers will be able to leverage operational data into valuable insight for empowered decision making and smoother operations.

show abstract

Section: Approachmentioning

confidence: 98%

Modelling Large Heaped Fill Stockpiles Using FMS Data

Young¹,

Rogers²

2021

Minerals

View full text Add to dashboard Cite

show abstract

“…Many works found propose a prioritization approach from a maintenance perspective, with data-oriented approaches and aiming at the preventive diagnosis of problems. Several methods have been developed to identify performance bottlenecks related to maintenance activities in production systems [9]. The underlying logic behind all of them lies in analyzing the machines' event log data [10].…”

Section: Related Workmentioning

confidence: 99%

Anomaly Detection in Spot Welding Machines in the Automotive Industry for Maintenance Prioritization

Brandão¹,

Martins-Jr²,

Kopte³

et al. 2022

Proceedings of the 34th International Conference on Software Engineering and Knowledge Engineering

View full text Add to dashboard Cite

Based on the need of prioritization of maintenance activities in a BOSCH Spot Welding process in the automotive industry, this work aims to develop anomalous equipment selection methodologies for assisting it. The first one is proposed based on data exploration by checking every possible set of alarms of the machines. A second one is created using multiple data clustering models in order to identify machines that behave differently from the others for certain time periods. Bayesian networks were also applied to assist the identification of cause-and-effect relationships between the warning and error logs. The clustering method proved effective in identifying anomalies, which were later inspected on the shop floor.

show abstract

“…Each participant needs different support and outputs to work efficiently. In the literature, we can find various studies on parameters that need to be visualized for different participants [52,53]. Some are interested in the quality and quantity of products, bottlenecks, maintenance times, overall equipment effectiveness (OEE), while others are interested in the dimensions of the manufacturing line, the number of robots, etc.…”

Section: Stepmentioning

confidence: 99%

A Five-Step Approach to Planning Data-Driven Digital Twins for Discrete Manufacturing Systems

et al. 2021

View full text Add to dashboard Cite

A digital twin of a manufacturing system is a digital copy of the physical manufacturing system that consists of various digital models at multiple scales and levels. Digital twins that communicate with their physical counterparts throughout their lifecycle are the basis for data-driven factories. The problem with developing digital models that form the digital twin is that they operate with large amounts of heterogeneous data. Since the models represent simplifications of the physical world, managing the heterogeneous data and linking the data with the digital twin represent a challenge. The paper proposes a five-step approach to planning data-driven digital twins of manufacturing systems and their processes. The approach guides the user from breaking down the system and the underlying building blocks of the processes into four groups. The development of a digital model includes predefined necessary parameters that allow a digital model connecting with a real manufacturing system. The connection enables the control of the real manufacturing system and allows the creation of the digital twin. Presentation and visualization of a system functioning based on the digital twin for different participants is presented in the last step. The suitability of the approach for the industrial environment is illustrated using the case study of planning the digital twin for material logistics of the manufacturing system.

show abstract

A data-driven approach to diagnosing throughput bottlenecks from a maintenance perspective

Cited by 19 publications

References 33 publications

Modelling Large Heaped Fill Stockpiles Using FMS Data

Modelling Large Heaped Fill Stockpiles Using FMS Data

Anomaly Detection in Spot Welding Machines in the Automotive Industry for Maintenance Prioritization

A Five-Step Approach to Planning Data-Driven Digital Twins for Discrete Manufacturing Systems

Contact Info

Product

Resources

About