Acoustic emission identification of wheel wear states in engineering ceramic grinding based on parameter-adaptive VMD

Wan, Linlin; Zhang, Xianyang; Zhou, Qiming; Wen, Dongdong; Ran, Xiaoru

doi:10.1016/j.ceramint.2022.12.238

Cited by 14 publications

(2 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AE is a well-studied Non-Destructive Testing (NDT) method which has been utilised in a large range of applications. Recently it has been used to monitor the wear of tools during turning [10], milling [11], and grinding [12][13][14]. The AE technique utilises the phenomenon in which a material experiences a permanent change from damage, whether it be crack propagation, delamination, plastic deformation or corrosion [15,16], energy is spontaneously released in the form of elastic waves.…”

Section: Introductionmentioning

confidence: 99%

Utilising Machine Learning for Tool Condition Monitoring of Diamond-Coated Burrs with Acoustic Emission

Jessel,

Byrne,

Eaton

et al. 2023

Preprint

View full text Add to dashboard Cite

Within manufacturing there is a growing need for autonomous in-line Tool Condition Monitoring (TCM) systems with the ability to predict tool wear and failure. This need is only increased when using specialised tools such as Diamond-Coated Burrs (DCBs), in which the random nature of the tool and inconsistent manufacturing methods, create large variance in tool life. This unpredictable nature leads to a significant fraction of a DCB tools life being under-utilised. Acoustic Emission (AE) presents a possible inline monitoring technique which in conjunction with Machine Learning (ML) models could be used as a prediction method for DCB wear. Four wear life tests were conducted with a ø1.3 mm #1000 DCB, in which AE was continuously acquired during grinding passes, followed by surface measurements of the DCB. Three ML model architectures were trained on AE features to predict DCB mean radius, an indicator of overall tool wear. All architectures showed potential of learning from the dataset, with Long Short-Term Memory (LSTM) models performing the best, resulting in prediction error of MSE = 0.559 μm2. Additionally, links between AE kurtosis and the tool’s runout/form error were identified during an initial review of the data, showing potential for future work to focus on grinding effectiveness as well as overall wear. This paper has shown that AE contains sufficient information to enable inline monitoring of DCBs during the grinding process. ML models have been shown to be sufficiently precise in predicting overall DCB wear and have the potential of interpreting grinding condition.

show abstract

Section: Introductionmentioning

confidence: 99%

Utilising Machine Learning for Tool Condition Monitoring of Diamond-Coated Burrs with Acoustic Emission

Jessel,

Byrne,

Eaton

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Bazi et al [ 25 ] monitored tool wear using VMD in conjunction with the hybrid convolutional neural networks–bidirectional long short-term memory (CNN-BiLSTM) approach. Wan et al [ 26 ] proposed a signal reconstruction method based on parameter adaptive VMD to accurately differentiate and identify various wear states of ceramic grinding wheels. To enhance the recognition performance of bearing fault signals, Li et al [ 27 ] applied the genetic algorithm (GA) to optimize a combination of VMD parameters, resulting in the GA-VMD algorithm that improved the decomposition accuracy of VMD.…”

Section: Introductionmentioning

confidence: 99%

Identification of NOL-Ring Composite Materials’ Damage Mechanism Based on the STOA-VMD Algorithm

Jiang,

Li,

Yan

et al. 2023

Polymers

View full text Add to dashboard Cite

This research utilized the sooty tern optimization algorithm–variational mode decomposition (STOA-VMD) optimization algorithm to extract the acoustic emission (AE) signal associated with damage in fiber-reinforced composite materials. The effectiveness of this optimization algorithm was validated through a tensile experiment on glass fiber/epoxy NOL-ring specimens. To solve the problems of a high degree of aliasing, high randomness, and a poor robustness of AE data of NOL-ring tensile damage, the signal reconstruction method of optimized variational mode decomposition (VMD) was first used to reconstruct the damage signal and the parameters of VMD were optimized by the sooty tern optimization algorithm. The optimal decomposition mode number K and penalty coefficient α were introduced to improve the accuracy of adaptive decomposition. Second, a typical single damage signal feature was selected to construct the damage signal feature sample set and a recognition algorithm was used to extract the feature of the AE signal of the glass fiber/epoxy NOL-ring breaking experiment to evaluate the effectiveness of the damage mechanism recognition. The results showed that the recognition rates of the algorithm in matrix cracking, fiber fracture, and delamination damage were 94.59%, 94.26%, and 96.45%, respectively. The damage process of the NOL-ring was characterized and the findings indicated that it was highly efficient in the feature extraction and recognition of polymer composite damage signals.

show abstract

Tool condition monitoring of diamond-coated burrs with acoustic emission utilising machine learning methods

Jessel,

Byrne,

Eaton

et al. 2023

Int J Adv Manuf Technol

View full text Add to dashboard Cite

Within manufacturing there is a growing need for autonomous Tool Condition Monitoring (TCM) systems, with the ability to predict tool wear and failure. This need is increased, when using specialised tools such as Diamond-Coated Burrs (DCBs), in which the random nature of the tool and inconsistent manufacturing methods create large variance in tool life. This unpredictable nature leads to a significant fraction of a DCB tool’s life being underutilised due to premature replacement. Acoustic Emission (AE) in conjunction with Machine Learning (ML) models presents a possible on-machine monitoring technique which could be used as a prediction method for DCB wear. Four wear life tests were conducted with a $$\varnothing $$ ∅ 1.3 mm #1000 DCB until failure, in which AE was continuously acquired during grinding passes, followed by surface measurements of the DCB. Three ML model architectures were trained on AE features to predict DCB mean radius, an indicator of overall tool wear. All architectures showed potential of learning from the dataset, with Long Short-Term Memory (LSTM) models performing the best, resulting in prediction error of MSE = 0.559 $$\mu $$ μ m$$^{2}$$ 2 after optimisation. Additionally, links between AE kurtosis and the tool’s run-out/form error were identified during an initial review of the data, showing potential for future work to focus on grinding effectiveness as well as overall wear. This paper has shown that AE contains sufficient information to enable on-machine monitoring of DCBs during the grinding process. ML models have been shown to be sufficiently precise in predicting overall DCB wear and have the potential of interpreting grinding condition.

show abstract

Acoustic emission identification of wheel wear states in engineering ceramic grinding based on parameter-adaptive VMD

Cited by 14 publications

References 37 publications

Utilising Machine Learning for Tool Condition Monitoring of Diamond-Coated Burrs with Acoustic Emission

Utilising Machine Learning for Tool Condition Monitoring of Diamond-Coated Burrs with Acoustic Emission

Identification of NOL-Ring Composite Materials’ Damage Mechanism Based on the STOA-VMD Algorithm

Tool condition monitoring of diamond-coated burrs with acoustic emission utilising machine learning methods

Contact Info

Product

Resources

About