Monitoring and forecasting of tool wear based on measurements of vibration accelerations during cast iron milling

Twardowski, Paweł; Czyżycki, Jakub; Felusiak-Czyryca, Agata; Tabaszewski, Maciej; Wiciak-Pikuła, Martyna

doi:10.1016/j.jmapro.2023.04.036

Cited by 11 publications

(4 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Velocity and acceleration sensors are often used to measure and monitor vibrations. Overviews of the measurement process and the analysis requirements for transport noise and vibration have been proposed [12,13]. For example, the root mean square (RMS) values can be used to calculate the vibration amplitude [14,15].…”

Section: Introductionmentioning

confidence: 99%

Determination of Optimal Machining Parameters Based on Roughness and Vibration Measurements of Pieces Produced by Whirling on a Lathe Machine

Botak,

Pisačić,

Horvat

et al. 2024

Machines

View full text Add to dashboard Cite

Worms can be produced using special machines or standard lathes equipped with a whirling thread-cutting device. A blank is placed on the mandrel and tightened using the three-jawed chuck of the standard lathe. If the workpiece diameter is excessively large, passage through the driven pulley is not possible, and the workpiece cannot be supported. Therefore, a new tool holder for whirling devices is needed. During the whirling process, vibrations in the form of machine velocity amplitudes were measured. After whirling was complete, roughness values were calculated. Using numerical procedures of Wolfram Mathematica 10, vibration peaks were extracted, from which frequencies and maximum amplitudes were determined. The data were then inputted into Design Expert, and the rotational speed and amount of separated material were optimized. The results of the study showed that the quality of the processed surface did not improve with processing in two passes of the tool. The measured vibration amplitudes on the lathe carrier and thread whirling attachment increased with cutting speed at the same cutting depth, whereas the quality of the machined surface was best at the smallest and largest cutting depths.

show abstract

Section: Introductionmentioning

confidence: 99%

Determination of Optimal Machining Parameters Based on Roughness and Vibration Measurements of Pieces Produced by Whirling on a Lathe Machine

Botak,

Pisačić,

Horvat

et al. 2024

Machines

View full text Add to dashboard Cite

show abstract

“…With regard to the literature review on machine learning, Twardowski et al [16] applied two different forms of machine learning classification trees to conduct a study, utilizing vibration acceleration measurements as the physical parameters, to predict the possibility of tool wear during the milling process of EN-GJL-250 cast iron. The experiments were carried out using a four-edge cemented-carbide end mill cutter, with vibration acceleration serving as the input data for the models to forecast tool wear.…”

Section: Introductionmentioning

confidence: 99%

Construction of a Cutting-Tool Wear Prediction Model through Ensemble Learning

Lin,

Hsieh

2024

Applied Sciences

View full text Add to dashboard Cite

This study begins by conducting side milling experiments on SKD11 using tungsten carbide TiAlN-coated end mills to compare the surface roughness performance between two combinations of milling process parameters (feed rate and radial depth of cut), along with three ultrasonic-assisted methods (rotary, dual-axis, and rotary combined with dual-axis). The results suggest that the rotary (z-axis oscillation) ultrasonic-assisted method may provide better performance. Subsequently, this superior ultrasonic-assisted method was applied both with and without laser locally preheating assistance, respectively. Using a Taguchi orthogonal array, milling process parameters (spindle speed, feed rate, and radial depth of cut) were planned for experiments with the same cutting tool and the workpiece just mentioned above. The surface roughness serves as the objective function while being constrained by cutting-tool life. The characteristics of the smaller-the-better in the Taguchi method were applied to determine the optimal combination of process parameters. Based on the optimal milling process parameters obtained and the superior hybrid-assisted method adopted, milling experiments were repeatedly performed to collect the data on cutting force and cutting-tool wear. Feature engineering was performed on the cutting force signals, and different domain characteristics from both the time and frequency domains were extracted. Hereafter, feature selection by random forest and data standardization were further applied to feature extractions, and the data processing was thus completed. For the processed data, a cutting-tool wear prediction model was constructed by ensemble learning. This method leverages various machine learning regression models, including decision tree, random forest, extremely randomized tree, light gradient boosting machine, extreme gradient boosting, AdaBoost, stochastic gradient descent, support vector regression, linear support vector regression, and multilayer perceptron. After hyper-parameter tuning, the ensemble voting regression prediction was performed based on these ten mentioned models. The experimental results demonstrate that the ensemble voting regression model surpasses the performance of each individual machine learning regression model. In addition, this regression model achieves a coefficient of determination (R2) of 0.94576, a root mean square error (RMSE) of 0.24348, a mean squared error (MSE) of 0.05928, and a mean absolute error (MAE) of 0.18182. Therefore, the ensemble learning approach has been proven to be a feasible and effective method for monitoring cutting-tool wear.

show abstract

“…This was done using the improved multi-scale entropy to gauge the complexity of the multi-scale E-band-limited intrinsic mode function. Twardowski, Paweł et al [19] under the operation of a cast iron milling cutter, measured the vibration acceleration signal through the vibration acceleration sensor and used the signal as the input data of the model for experimental testing. The outcomes demonstrate that edge wear can be accurately predicted by machine learning.…”

Section: Introductionmentioning

confidence: 99%

Research on multiparameter state monitoring of boring process

Liu,

Shen,

et al. 2024

Preprint

View full text Add to dashboard Cite

Aiming at the problem that the working state of the boring bar cannot be observed in the closed environment during deep hole boring processing, this study designs a multiparameter state monitoring system for the boring bar in the cutting process. The main idea of this monitoring system is to use the piezoelectric effect of the strain gauge in the sensor to measure the change of the voltage, and to obtain the three-way cutting force, the tooltip displacement, the vibration velocity, and the vibration acceleration through the voltage. To realize the online monitoring of multiparameter state in the cutting process, the stress model of the boring bar is established, and the stress analysis is carried out. The overall structure of the online monitoring system is established, and then the various parameters obtained by voltage are analyzed and calculated. The experimental platform of multiparameter state monitoring of the boring bar is built. The monitoring results of the multiparameter state monitoring system and commercial measurement system in the cutting process are compared by boring experiments. The results show that the error of three-dimensional cutting force and vibration acceleration is within 10%, and the error of tooltip displacement fluctuates around 15%, which verifies the feasibility of the monitoring system in the boring process.

show abstract

Monitoring and forecasting of tool wear based on measurements of vibration accelerations during cast iron milling

Cited by 11 publications

References 22 publications

Determination of Optimal Machining Parameters Based on Roughness and Vibration Measurements of Pieces Produced by Whirling on a Lathe Machine

Determination of Optimal Machining Parameters Based on Roughness and Vibration Measurements of Pieces Produced by Whirling on a Lathe Machine

Construction of a Cutting-Tool Wear Prediction Model through Ensemble Learning

Research on multiparameter state monitoring of boring process

Contact Info

Product

Resources

About