Indirect method of tool wear measurement and prediction using ANN network in machining process

Bagga, Prashant J.; Makhesana, Mayur A.; Patel, Hetul; Patel, Kaushik M.

doi:10.1016/j.matpr.2020.11.770

Cited by 22 publications

(20 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simon and Deivanathan (2019) used the K-Star classifier to detect tool wear using vibration signals and statistical features in the drilling operation. Using vibration and force signal data, Bagga et al . (2021) employed ANN for the prediction of tool wear.…”

Section: Literature Reviewmentioning

confidence: 99%

Investigation of the effect of vibration in the multi-objective optimization of dry turning of hardened steel

Ahmed

Juberi

Bari

et al. 2023

IJIEOM

View full text Add to dashboard Cite

PurposeThis study aims to investigate the effect of vibration on ceramic tools under dry cutting conditions and find the optimum cutting condition for the hardened steel machining process in a computer numerical control (CNC) lathe machine.Design/methodology/approachIn this research, an integrated fuzzy TOPSIS-based Taguchi L9 optimization model has been applied for the multi-objective optimization (MOO) of the hard-turning responses. Additionally, the effect of vibration on the ceramic tool wear was investigated using Analysis of Variance (ANOVA) and Fast Fourier Transform (FFT).FindingsThe optimum cutting conditions for the multi-objective responses were obtained at 98 m/min cutting speed, 0.1 mm/rev feed rate and 0.2 mm depth of cut. According to the ANOVA of the input cutting parameters with respect to response variables, feed rate has the most significant impact (53.79%) on the control of response variables. From the vibration analysis, the feed rate, with a contribution of 34.74%, was shown to be the most significant process parameter influencing excessive vibration and consequent tool wear.Research limitations/implicationsThe MOO of response parameters at the optimum cutting parameter settings can significantly improve productivity in the dry turning of hardened steel and control over the input process parameters during machining.Originality/valueMost studies on optimizing responses in dry hard-turning performed in CNC lathe machines are based on single-objective optimization. Additionally, the effect of vibration on the ceramic tool during MOO of hard-turning has not been studied yet.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Investigation of the effect of vibration in the multi-objective optimization of dry turning of hardened steel

Ahmed

Juberi

Bari

et al. 2023

IJIEOM

View full text Add to dashboard Cite

show abstract

“…Therefore, simultaneously employing different sensors and fusion techniques can effectively improve the accuracy and reliability of the systems owing to complementary information [25][26][27][28][29][30][31][32][33][34]. Several approaches have been proposed using neural networks [35][36][37][38], the support vector machine [39][40][41], hidden Markov model [42][43][44], fuzzy inference system [45,46], relevance vector machine [47,48], and long short-term memory networks [49][50][51]. Most of them are based on data-driven approaches [52][53][54].…”

Section: Introductionmentioning

confidence: 99%

Robust tool wear monitoring system development by sensors and feature fusion

Lin

Lee

2022

Asian Journal of Control

View full text Add to dashboard Cite

This study introduces a tool wear monitoring system that uses multiple sensors and a feature fusion technique. To improve the robustness of the system, different tightening torque and spindle speed conditions were considered in the experimental design stage. Vibration signals in three coordinates and sound signals were collected and transformed by fast Fourier transform for feature extraction. Two types of features in the frequency domain were used to establish the proposed system, including the mean value features selected by the class mean scatter feature selection criterion and statistical features by Gradient Class Activation Mapping++ (Grad-CAM++). The proposed monitoring system was established using a hierarchical neural network structure and feature fusion of the sensors. Cross-validation was introduced to demonstrate the performance and effectiveness of our approach under various tightening torque values and spindle speeds.

show abstract

“…Physical parameters monitored were vibration, cutting force, and acoustic emission. Bagga et al [16] evaluated force and vibration signals in dry turning operations. The prediction of tool wear obtained through neural networks was compared with manual measurement, and close correlations were reported.…”

Section: Introductionmentioning

confidence: 99%

Tool life prognostics in CNC turning of AISI 4140 steel using neural network based on computer vision

Bagga

Makhesana

Darji

et al. 2022

Int J Adv Manuf Technol

View full text Add to dashboard Cite

One of the essential requirements for intelligent manufacturing is the low cost and reliable predictions of the tool life during machining. It is crucial to monitor the condition of the cutting tool to achieve cost-effective and high-quality machining. Tool conditioning monitoring (TCM) is essential to determining the remaining useful tool life to assure uninterrupted machining to achieve intelligent manufacturing. The same can be done by direct and indirect tool wear measurement and prediction techniques. In indirect methods, the data is acquired from the sensors resulting in some ambiguity, such as noise, reliability, and complexity. However, in direct methods, the data is available in images resulting in significantly less chances of ambiguity with the proper data acquisition system. The direct methods, which provide higher accuracy than indirect methods, involve collecting images of worn tools at different stages of the machining process to predict the tool life. In this context, a novel tool wear prediction system is proposed to examine the progressive tool wear utilizing the artificial neural network (ANN). Experiments were performed on AISI 4140 steel material under dry cutting conditions with carbide inserts. The cutting speed, feed, depth of cut, and white pixel counts are considered as input parameters for the proposed model, and the flank wear along with remaining tool life is predicted as the output. The worn tool images were captured using an industrial camera during the turning operation at regular intervals. The ANN training set predicts the remaining useful tool life, especially the sigmoid function and rectified linear unit (ReLU) activation function of ANN. The sigmoid function showed an accuracy of 86.5%, and the ReLU function resulted in 93.3% accuracy in predicting tool life. The proposed model’s maximum and minimum root mean square error (RMSE) is 1.437 and 0.871 min. The outcomes showcased the ability of image processing and ANN modeling as the potential approach for developing a low-cost industrial tool condition monitoring system that can measure tool wear and predict tool life in turning operations.

show abstract

Indirect method of tool wear measurement and prediction using ANN network in machining process

Cited by 22 publications

References 15 publications

Investigation of the effect of vibration in the multi-objective optimization of dry turning of hardened steel

Investigation of the effect of vibration in the multi-objective optimization of dry turning of hardened steel

Robust tool wear monitoring system development by sensors and feature fusion

Tool life prognostics in CNC turning of AISI 4140 steel using neural network based on computer vision

Contact Info

Product

Resources

About