Tool wear monitoring with wavelet packet transform—fuzzy clustering method

Li, Xiaoli; Yuan, Zhijun

doi:10.1016/s0043-1648(98)00165-3

Cited by 98 publications

(29 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As reported in [16], tool wear conditions could be presented using the feature bank of a clustering-based TCM system. Here, four states for the tool wear, with seven features each, compose the codebook of the clustering method.…”

Section: Application Of Clustering Methods On Wavelet Featuresmentioning

confidence: 99%

“…The fuzzy clustering method was also applied in [16] on the wavelet packet features of AE signals and in [17] and [18] on the energy contents of different scales of the CWT of the force and vibration signals. The power consumption and vertical force features were also clustered in [19], pointing out its applicability.…”

Section: Application Of Clustering Methods On Wavelet Featuresmentioning

confidence: 99%

See 1 more Smart Citation

Application of Clustering Methods for Online Tool Condition Monitoring and Fault Diagnosis in High-Speed Milling Processes

Torabi

et al. 2016

IEEE Systems Journal

View full text Add to dashboard Cite

Tool condition monitoring (TCM) is a necessary action in a high-speed milling (HSM) process. As a worn milling tool might irreversibly damage a workpiece, there is a vital demand for a TCM system to evaluate the tool wear progress, or equivalently the resultant surface roughness, nonintrusively. To build up a condition monitoring system for HSM processes, sensor signals are to be utilized to form a reference model that reflects the performance of the system. Therefore, a desired reference model has to apply more efficient feature extraction and artificial intelligence techniques to be more repeatable and generalizable. This paper illustrates the performance of clustering techniques on high-speed end milling experimental data. Studied clustering methods are applied to the wavelet features of force and vibration signals to illustrate the repeatability of their results. It is shown that clustering methods can coarsely capture the status of the process and can be applied for fault diagnosis and TCM purposes. It is also discussed how the application of clustering methods may improve the performance of existing reference models toward the more efficient utilization of available experimental data and to develop easily generalizable reference models. Finally, a possible application of clustering results is discussed comparing with state-of-the-art papers.

show abstract

Section: Application Of Clustering Methods On Wavelet Featuresmentioning

confidence: 99%

Section: Application Of Clustering Methods On Wavelet Featuresmentioning

confidence: 99%

Application of Clustering Methods for Online Tool Condition Monitoring and Fault Diagnosis in High-Speed Milling Processes

Torabi

et al. 2016

IEEE Systems Journal

View full text Add to dashboard Cite

show abstract

“…AE as a single sensor: tool breakage [16], tool wear [17][18][19], tool wear and chipping [20], tool and workpiece malfunctions [3,21], and tool wear and surface roughness [22,23]. 2.…”

Section: Acoustic Emissions Monitoring In Machiningmentioning

confidence: 99%

Multi-sensor data fusion framework for CNC machining monitoring

Duro

Padget

Bowen

et al. 2016

Mechanical Systems and Signal Processing

109

View full text Add to dashboard Cite

a b s t r a c tReliable machining monitoring systems are essential for lowering production time and manufacturing costs. Existing expensive monitoring systems focus on prevention/detection of tool malfunctions and provide information for process optimisation by force measurement. An alternative and cost-effective approach is monitoring acoustic emissions (AEs) from machining operations by acting as a robust proxy. The limitations of AEs include high sensitivity to sensor position and cutting parameters. In this paper, a novel multi-sensor data fusion framework is proposed to enable identification of the best sensor locations for monitoring cutting operations, identifying sensors that provide the best signal, and derivation of signals with an enhanced periodic component. Our experimental results reveal that by utilising the framework, and using only three sensors, signal interpretation improves substantially and the monitoring system reliability is enhanced for a wide range of machining parameters. The framework provides a route to overcoming the major limitations of AE based monitoring.

show abstract

“…Also, many attempts to predict tool wear have been investigated, such as the pattern-classification methodology, fuzzy classifiers, neural networks, and sensor and data fusion methodology, overviewed in. 20 It is well known that the structure of the workpiece strongly affects the mechanism of chip separation and the machinability of a job. 3,6,23,24 AE techniques adopted for discontinuous chips are less frequently reported.…”

Section: Introductionmentioning

confidence: 99%

Prediction of the catastrophic tool failure in hard turning through acoustic emission

Čilliková¹,

Mičieta²,

Neslušan³

et al. 2015

Mater. Tehnol.

View full text Add to dashboard Cite

The paper deals with a new concept for the detection and prediction of the catastrophic tool failure (CTF) of ceramic inserts using an acoustic emission (AE) technique and an associated analysis of the chip formation during hard turning of bearing steel 100Cr6. The suggested method is based on the application of two sensors and the ratios of parameters of the acoustic emission such as AE RMS, AE absolute energy, and AE strength. The specific character of the segmented chips during hard turning is associated with the raw acoustic signals as well as the extracted AE features. The paper indicates that the conventional data processing of acoustic emission signals enables the detection of CTF. Tool wear connected with the cutting edge micro-chipping is related to the slow increase of tool wear (mainly flank wear VB) and stable values of AE features in the normal phase of tool wear. The CTF alters the AE waveforms as well as the course of the AE features. Conventional AE signal processing enables the detection of tool breakage. However, approaching CTF itself cannot be reliably predicted. Hence, a new concept of AE processing based on the ratios of the extracted AE features obtained in the different frequency ranges is suggested. Keywords: hard turning, acoustic emission, wear, prediction lanek obravnava nov na~in odkrivanja in napovedovanja poru{itve (CTF) kerami~nih vlo`kov z uporabo tehnike akusti~ne emisije (AE), povezano z analizo nastanka ostru`ka med stru`enjem jekla 100Cr6 za le`aje. Predlagana metoda temelji na uporabi dveh senzorjev in razmerij pri akusti~ni emisiji, kot so AE RMS, absolutna energija AE in AE-mo~. Specifi~na oblika delca ostru`ka med stru`enjem je povezana s surovim akusti~nim signalom, kot tudi z lo~enimi AE-lastnostmi.^lanek obravnava, kako konvencionalna obdelava podatkov signalov akusti~ne emisije omogo~a dolo~itev CTF. Obraba orodja je povezana s kru{enjem rezilnega roba ter s po~asnim pove~anjem obrabe orodja (ve~inoma obrabe boka VB) in s stabilnimi vrednostmi AE-lastnosti pri normalni obrabi orodja. CTF spreminja obliko AE-valov, kot tudi AE-lastnosti. Konvencionalna obdelava AE-signalov omogo~a odkritje loma orodja. Vendar pa napovedovanje nastanka CTF ni mogo~e zanesljivo napovedati. Predlagan je torej nov na~in obdelave AE, ki temelji na izbranih AE-lastnostih, dobljenih pri razli~nih obmo~jih frekvenc.

show abstract

Tool wear monitoring with wavelet packet transform—fuzzy clustering method

Cited by 98 publications

References 15 publications

Application of Clustering Methods for Online Tool Condition Monitoring and Fault Diagnosis in High-Speed Milling Processes

Application of Clustering Methods for Online Tool Condition Monitoring and Fault Diagnosis in High-Speed Milling Processes

Multi-sensor data fusion framework for CNC machining monitoring

Prediction of the catastrophic tool failure in hard turning through acoustic emission

Contact Info

Product

Resources

About