Rapid Evaluation of Maintenance Process Using Statistical Process Control and Simulation

Petrović, Sanja; Milosavljevic, Pedja; Šajić, Jasmina Lozanović

doi:10.2507/ijsimm17(1)424

Cited by 8 publications

(6 citation statements)

References 22 publications

(38 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we describe the extendable modules of the software framework. Rapid and extendable are two advantages features of the software framework [14]. GUI of the software at the front-end is associated with rapid and easy implementation.…”

Section: A the Software Frameworkmentioning

confidence: 99%

Rapid Software Framework for the Implementation of Machine Learning Classification Models

Rahman¹,

Masrom²,

Rahman³

et al. 2021

IJETAE

View full text Add to dashboard Cite

Reseachers have acknowledged that machine learning is useful to be utilized in many different domains of complex real life problem. However, to implement a complete machine learning model involves some technical hurdles such as the steep learning curve, the abundance of the programming skills, the complexities of hyper-parameters, and the lack of user friendly platform to be used for the implementation. This paper provides an insight of a rapid software framework for implementing machine learning. This paper also demonstrates the empirical research results of machine learning classification models from the rapid software framework. Additionally, this paper explains comparisons of results between two platforms of rapid software; the proposed software and Python program. The machine learning model in the two platforms were tested on breast cancer and tax avoidance datasets with Decision Tree algorithm. The results indicated that although the software framework is easier than the programming platform for implementing the machine learning model, the results from the software framework were highly accurate and reliable. Keywords- Software framework, rapid, implementation, machine learning

show abstract

Section: A the Software Frameworkmentioning

confidence: 99%

Rapid Software Framework for the Implementation of Machine Learning Classification Models

Rahman¹,

Masrom²,

Rahman³

et al. 2021

IJETAE

View full text Add to dashboard Cite

show abstract

“…Also, numerical methods enable results of full covered stress-strain field that can be easily verified by the data obtained from experiment. This 3D DIC method has high accuracy (up to 1 μm) and it has been used in variety of cases so far: different material testing, structure testing, model verification, fracture mechanism [24][25][26][27][28][29][30][31][32][33][34][35][36][37].…”

Section: Introductionmentioning

confidence: 99%

Experimental and numerical stress and strain analysis of the boiler reversing chamber tube plate

et al. 2022

View full text Add to dashboard Cite

Boilers are one of the most used units for both heat generation plants and industry systems. Their operation is subjected to different working loads and maintenance requirements. Exploitation experience points out critical boiler zones where failures and break downs typically occur. This paper analyzes critical zones in hot water fire-tube boiler. Experimental procedure was performed on the model of this type of boilers and its critical element. The tube plate of hot water boiler was identified as the most critical one. Experimental analysis and numerical model verification were performed using Aramis system based on 3D Digital Image Correlation method. Numerical analysis was done in Ansys Software Package and verification of results was done based on measurements obtained by strain gauges and local measurements performed by the Aramis system. Stress-strain analysis indicates the critical zones of boiler tube plate. The character of change parameters such as strain and stress occurring in the critical zones can be verified both by experimental and numerical data. The paper presents a novel approach in experimental and numerical analyses that can be conducted in similar units and used for existing unit optimization, as well as for new product testing on different loads and provide opportunity for further development and improvement for practical industrial application.

show abstract

“…Some foreign surveys show that the maintenance and repair costs (including warehousing costs and tied capital here) may account for up to 25% of the company's turnover and 15% to 40% of the total operating costs [3,19]. The maintenance process shares a significant part of the operating costs in an industrial organization [15,23,24]. Bevilacqua and Braglia stated that in the United States, the estimated maintenance costs increased from $ 200 billion in 1979 to $ 600 billion in 1989 [1].…”

Section: Introductionmentioning

confidence: 99%

Potential of Using TPM to Increase the Efficiency of Production Processes

et al. 2020

View full text Add to dashboard Cite

The goal of the submitted paper is to implement the principles of TPM and to achieve almost 100% usability of machines, when there will be no failures and unwanted incidents. The effectiveness of implementing the TPM principles has been experimentally verified in an engineering company. Workplaces for the assembly of rails on Unimatic lines were chosen as a pilot workplace. Prior to the implementation of the TPM, analyses of technical downtime and unplanned shutdowns of the manufacturing devices due to failures, unplanned repairs and maintenance were carried out. The resulting analysis concentrated mainly on two main variables-total cumulative technical downtime at individual workplaces and frequency of occurrence of failures in individual sections of the workplaces. The presented approach and the results obtained underline the importance of applying the TPM principles in practice and their indisputable contribution to the ability to increase business performance. The TPM's progressive maintenance management system represents a prerequisite for the reduction of production costs and losses resulting from unscheduled failures now and in the future.

show abstract

Rapid Evaluation of Maintenance Process Using Statistical Process Control and Simulation

Cited by 8 publications

References 22 publications

Rapid Software Framework for the Implementation of Machine Learning Classification Models

Rapid Software Framework for the Implementation of Machine Learning Classification Models

Experimental and numerical stress and strain analysis of the boiler reversing chamber tube plate

Potential of Using TPM to Increase the Efficiency of Production Processes

Contact Info

Product

Resources

About