Tool wear and remaining useful life prediction in micro-milling along complex tool paths using neural networks

Bagri, Sumant; Manwar, Ashish; Varghese, Alwin; Mujumdar, Soham S.; Joshi, Suhas S.

doi:10.1016/j.jmapro.2021.09.055

Cited by 41 publications

(12 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Manufacturing parameters and tool condition images captured during the process were used to support a deep belief network (DBN) model to perform prediction. A transfer learning strategy was designed to conduct cutting tool prognostics for customised machining processes [11]. In [12], the advantages, disadvantages, and prospects of using sensors, including force sensors, vibration sensors, acoustic emission sensors, current and power sensors, image sensors, and thermal sensors, for milling operations were discussed.…”

Section: Literature Reviewmentioning

confidence: 99%

Distributed deep learning enabled prediction on cutting tool wear and remaining useful life

Zhang

Wang

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

To optimise the utilisation cost of cutting tools, it is imperative to develop an online system to efficiently and accurately predict tool wear conditions and remaining useful lives (RULs). With this aim, a novel system is proposed based on deep learning algorithms distributed over an edge-cloud computing architecture. The system is innovative in the following aspects: (i) a lightweight convolutional neural network-random forest (CNN-RF) model is designed to be executed on an edge device to assess tool wear conditions efficiently, which supports severe tool resilience and tool replacement when necessary; (ii) a convolutional neural network-long short-term memory (CNN-LSTM) model is designed to be executed on a cloud to process long-term signals to predict the RUL of the cutting tool, which supports fine-tuning tool parameters dynamically; (iii) a signal compression mechanism is developed to condense the signals of tooling conditions into 2D images so the signal volumes transferred over the network are minimised and signal security is improved. Experiments were performed in a real-world machining workshop for research methodology validation. It showed that the prediction accuracies for tool wear and RUL achieved 90.6% and 93.2%, respectively, and the volume of signals transferred over the network was reduced by 89.0%. The experiments and benchmarks with comparative algorithms demonstrated that the system and its methodology exhibited great potential to reinforce cutting tool optimisation for real-world applications.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Distributed deep learning enabled prediction on cutting tool wear and remaining useful life

Zhang

Wang

et al. 2023

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

show abstract

“…The energy and feature samples of the vibration acceleration signal are synthesized into feature x (0) x (1) = [100.00, 100.75, 101.64, 102.19, . .…”

Section: Vibration Signal Prediction Modelmentioning

confidence: 99%

“…x (1) The matrix B and vector Y n are obtained according to the Grey-Markov rule as follows The residuals E 1 , E 2 , E 3 , E 4 , E 5 of the five error states are divided according to 1-300 groups of data. The partition state of the residual range is shown in Table 7.…”

Section: Acoustic Emission Signal Prediction Modelmentioning

confidence: 99%

“…The coal, rock and hard rock are in contact with each other over a prolonged period under a state of high impact and stress, thereby, damaging and shortening the life of the pick severely and warranting replacements of coal mining machinery parts. Therefore, the pick wear has become one of the main research problems in the coal mining (Bagri et al, 2021;Boing et al, 2020;Chen et al, 2020;Fan et al, 2020).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recognition of pick wear condition based on Grey-Markov chain model

Zhang¹,

Zhang²

2023

Journal of Theoretical and Applied Mechanics

View full text Add to dashboard Cite

An attempt is made in this paper to solve the pick wear problem of mining machinery and propose a pick wear degradation model based on the Grey-Markov chain by using generated characteristics signals and certain pick wear parameters to enhance the prediction accuracy. The vibration and acoustic emission signals generated during the catting pick are extracted and analyzed. The energy and the value of the characteristic signal are obtained by wavelet analysis to construct a characteristic sample library of the signals. Two kinds of signals are applied to the model to analyze the error between the real and the predicted values. The model prediction results demonstrate a 1.43% error of the vibration signal, 1.64% error of the acoustic emission signal with 98% prediction accuracy, thus offers a new method for monitoring the pick wear of mining machinery.

show abstract

“…An inverse hyperbolic cosine function was fitted to enveloped signal for sensitivity enhancement, and later the obtained signal was used for HI construction. Using the obtained HI, the existing machine learning (ML) models such as artificial neural network (ANN) [13,14], kernel extreme learning machine (KELM) [5,15], convolution neural network (CNN) [4,16], random forest regression (RFR) [12], recurrent neural network (RNN) [11], long short term memory (LSTM) [6,11,16,17], deep belief network [13], transfer learning [18,19], etc. can be used for tool wear prediction.…”

Section: Introductionmentioning

confidence: 99%

A novel current sensor indicator enabled WAFTR model for tool wear prediction under variable operating conditions

Kundu

Luo

Qin

et al. 2022

Journal of Manufacturing Processes

View full text Add to dashboard Cite

Tool wear and remaining useful life prediction in micro-milling along complex tool paths using neural networks

Cited by 41 publications

References 13 publications

Distributed deep learning enabled prediction on cutting tool wear and remaining useful life

Distributed deep learning enabled prediction on cutting tool wear and remaining useful life

Recognition of pick wear condition based on Grey-Markov chain model

A novel current sensor indicator enabled WAFTR model for tool wear prediction under variable operating conditions

Contact Info

Product

Resources

About