Evaluation of expert system for condition monitoring of a single point cutting tool using principle component analysis and decision tree algorithm

Elangovan, M; Devasenapati, S. Babu; Sakthivel, N. R.; Ramachandran, K. I.

doi:10.1016/j.eswa.2010.09.116

Cited by 84 publications

(26 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to Elangovan, Devasenapati, Sakthivel, and Ramachandran, (2011), tool condition monitoring and diagnosis involves collection, processing and analysis of data related to the tool under various experimental conditions and interpreting the results to the real life applications. A variety of techniques have been employed to carry out each phase of tool condition monitoring.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of neural models applied to the estimation of tool wear in the grinding of advanced ceramics

Nakai

Aguiar

Guillardi

et al. 2015

Expert Systems with Applications

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Evaluation of neural models applied to the estimation of tool wear in the grinding of advanced ceramics

Nakai

Aguiar

Guillardi

et al. 2015

Expert Systems with Applications

View full text Add to dashboard Cite

“…Estimar o desgaste das ferramentas envolvidas com o processo de usinagem tem sido uma tônica na comunidade técnico científica atualmente, pois melhorias significativas na eficiência destes processos podem ser obtidas com modelos capazes de identificar e determinar variáveis críticas que M [5,6].…”

Section: Introductionunclassified

Neural Tool Condition Estimation in The Grinding of Advanced Ceramics

Nakai¹,

Guillardi²,

Aguiar³

et al. 2015

IEEE Latin Am. Trans.

View full text Add to dashboard Cite

Ceramic parts are increasingly replacing metal parts due to their excellent physical, chemical and mechanical properties, however they also make them difficult to manufacture by traditional machining methods. The developments carried out in this work are used to estimate tool wear during the grinding of advanced ceramics. The learning process was fed with data collected from a surface grinding machine with tangential diamond wheel and alumina ceramic test specimens, in three cutting configurations: with depths of cut of 120μm, 70 μm and 20μm. The grinding wheel speed was 35m/s and the table speed 2.3m/s. Four neural models were evaluated, namely: Multilayer Perceptron, Radial Basis Function, Generalized Regression Neural Networks and the Adaptive Neuro-Fuzzy Inference System. The models' performance evaluation routines were executed automatically, testing all the possible combinations of inputs, number of neurons, number of layers, and spreading. The computational results reveal that the neural models were highly successful in estimating tool wear, since the errors were lower than 4%.

show abstract

“…This is also defined as a measure of the power content of the vibration signal (Elangovan et al, 2011). The standard deviation is expressed as Eq.…”

Section: Feature Extractionmentioning

confidence: 99%

“…In the case of fatigue and vibration analysis, statistical parameters are frequently used to characterise and classify random signals (Nuawi, Abdullah, Abdullah, Haris, & Arifin, 2009). Elangovan, BabuDevasenapati, Sakhtivel, and Ramachandran (2011) summarised that the kurtosis of time domain vibration signals is a good measurement for tool condition monitoring. This paper presents the monitoring and assessment of AE time domain signatures during the fatigue mechanism of a gas pipeline material, API 5L X70 steel, in a laboratory test and normal field operation.…”

Section: Introductionmentioning

confidence: 99%

Monitoring and Assessment of Acoustic Emission Signatures during Fatigue Mechanism of API5LX70 Gas Pipeline Steel

Fadhlan¹,

Kulthum²,

Abdullah³

et al. 2012

J MECH ENG SCI

View full text Add to dashboard Cite

The detection of early fatigue phenomena in a gas pipeline is crucial in order to avoid catastrophic consequences. Therefore, appropriate inspection is needed to assess fatigue phenomena in a gas pipeline system. Acoustic emission (AE) technology is expected to be suitable in this regard. This paper presents the monitoring and assessment of AE signatures of the fatigue mechanism of gas pipeline material, API 5L X70 steel. The stress amplitude of 65%, 60%, 58% and 53% of the ultimate tensile strength were done in order to observe AE activity during the fatigue mechanism. Field measurements were also done by investigating AE signatures of an operational gas pipeline for comparison purposes. Based on the correlation of the AE signatures and fatigue mechanism, it was found that the AE activities generated during the fatigue mechanism were divided into three different stages. Analysis of the AE features and statistical parameters have shown that the kurtosis values of the time domain AE signatures from the third stage of the fatigue mechanism were different from the field measurements. This results show that the application of the kurtosis was expected to be able to detect the time domain AE signatures from the crack stage.

show abstract

Evaluation of expert system for condition monitoring of a single point cutting tool using principle component analysis and decision tree algorithm

Cited by 84 publications

References 10 publications

Evaluation of neural models applied to the estimation of tool wear in the grinding of advanced ceramics

Evaluation of neural models applied to the estimation of tool wear in the grinding of advanced ceramics

Neural Tool Condition Estimation in The Grinding of Advanced Ceramics

Monitoring and Assessment of Acoustic Emission Signatures during Fatigue Mechanism of API5LX70 Gas Pipeline Steel

Contact Info

Product

Resources

About