Neural Networks Tool Condition Monitoring in Single-point Dressing Operations

D’Addona, Doriana M.; Matarazzo, D.; Aguiar, Paulo Roberto de; Bianchi, Eduardo Carlos; Martins, Carla Braga

doi:10.1016/j.procir.2016.01.001

Cited by 33 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On the other hand, an obstacle for monitoring the dressing process still consists in the lack of a reliable method to estimate the wear of the dresser and the sharpness of the wheel in real time. Several studies with the goal of evaluating single-point dresser were performed, as presented in [13,[20][21][22][23]. They have obtained successful results using statistics as root mean square (RMS) and ratio of power from the AE signals associate with artificial neural networks.…”

Section: Introductionmentioning

confidence: 99%

Digital signal processing of acoustic emission signals using power spectral density and counts statistic applied to single‐point dressing operation

Lopes¹,

Ferreira²,

Alexandre³

et al. 2017

IET Science, Measurement & Technology

View full text Add to dashboard Cite

Dressing is an important operation for the grinding process. Its goal is to recondition the wheel tool to re-establish its cutting characteristics, owing to the wear produced after successive passes. Monitoring systems that use acoustic emission (AE) have been studied to correlate the signals with several tool conditions. This study brings a new approach of processing AE signals with the purpose of identifying the correct moment to stop the dressing, which is essential in an automatic control system. From the AE signals collected in dressing tests with aluminium oxide grinding wheel and single-point dresser, spectral analysis was made through power spectral density, selecting frequencies bands that best characterise the process. The statistical parameter 'counts' was applied to the raw signal unfiltered and filtered in the selected bands in order to identify the tool condition and, in turn, towards a monitoring system implementation. Results showed an expressive relation between tool cutting conditions and processed signals in the selected bands. There was a great disparity of the filtered signals in the selected bands and signals unfiltered, reflecting that the filtered ones were more efficient in terms of process automation.

show abstract

Section: Introductionmentioning

confidence: 99%

Digital signal processing of acoustic emission signals using power spectral density and counts statistic applied to single‐point dressing operation

Lopes¹,

Ferreira²,

Alexandre³

et al. 2017

IET Science, Measurement & Technology

View full text Add to dashboard Cite

show abstract

“…Over the last decade, several studies have been developed with the objective of measuring the dresser wear and proposing an optimized moment to replace the worn tools. A method for characterizing the condition of the dresser wear by using vibration signals and Artificial Neural Networks (ANN) was proposed by [14]. Tests were performed using single-point dresser in a surface grinding machine, and the wear was measured throughout the experiment.…”

Section: Monitoring the Dressing Operationmentioning

confidence: 99%

Tool condition monitoring of aluminum oxide grinding wheel using AE and fuzzy model

Alexandre

Lopes

Dotto

et al. 2018

Int J Adv Manuf Technol

View full text Add to dashboard Cite

The grinding process is situated at the end of the machining chain, where geometric and dimensional characteristics and highquality surface are required. The constant use of cutting tool (grinding wheel) causes loss of its sharpness and clogging of the pores among the abrasive grains. In this context, the dressing operation is necessary to correct these and other problems related to its use in the process. Dressing is a reconditioning operation of the grinding wheel surface aiming at restoring the original condition and its efficiency. The objective of this study is to evaluate the surface regularity and dressing condition of the grinding wheel in the surface grinding process by means of digital signal processing of acoustic emission and fuzzy models. Tests were conducted by using synthetic diamond dressers in a surface grinding machine equipped with an aluminum oxide grinding wheel. The acoustic emission sensor was attached to the dresser holder. A frequency domain analysis was performed to choose the bands that best characterized the process. A frequency band of 25-40 kHz was used to calculate the ratio of power (ROP) statistic, and the mean and standard deviation values of the ROP were inputted to the fuzzy system. The results indicate that the fuzzy model was highly effective in diagnosing the surface conditions of the grinding wheel.

show abstract

“…In order to identify the tool condition and determine a stopping criterion for the dressing process, Lopes et al [41] used the power spectral density and event counts of AE. D’Addona et al [42] proposed a method to characterize the dressing tool utilizing cognitive paradigms.…”

Section: Dressing Operation Monitoringmentioning

confidence: 99%

Dressing Tool Condition Monitoring through Impedance-Based Sensors: Part 2—Neural Networks and K-Nearest Neighbor Classifier Approach

Oliveira

D’Addona

Aguiar

et al. 2018

Sensors

View full text Add to dashboard Cite

This paper presents an approach for impedance-based sensor monitoring of dressing tool condition in grinding by using the electromechanical impedance (EMI) technique. This method was introduced in Part 1 of this work and the purpose of this paper (Part 2) is to achieve an optimal selection of the excitation frequency band based on multi-layer neural networks (MLNN) and k-nearest neighbor classifier (k-NN). The proposed approach was validated on the basis of dressing tool condition information obtained from the monitoring of experimental dressing tests with two industrial stationary single-point dressing tools. Moreover, representative damage indices for diverse damage cases, obtained from impedance signatures at different frequency bands, were taken into account for MLNN data processing. The intelligent system was able to select the most damage-sensitive features based on optimal frequency band. The best models showed a general overall error lower than 2%, thus robustly contributing to the efficient automation of grinding and dressing operations. The promising results of this study foster the EMI-based sensor monitoring approach to fault diagnosis in dressing operations and its effective implementation for industrial grinding process automation.

show abstract

Neural Networks Tool Condition Monitoring in Single-point Dressing Operations

Cited by 33 publications

References 7 publications

Digital signal processing of acoustic emission signals using power spectral density and counts statistic applied to single‐point dressing operation

Digital signal processing of acoustic emission signals using power spectral density and counts statistic applied to single‐point dressing operation

Tool condition monitoring of aluminum oxide grinding wheel using AE and fuzzy model

Dressing Tool Condition Monitoring through Impedance-Based Sensors: Part 2—Neural Networks and K-Nearest Neighbor Classifier Approach

Contact Info

Product

Resources

About