A review on deep learning in machining and tool monitoring: methods, opportunities, and challenges

Nasir, Vahid; Sassani, Farrokh

doi:10.1007/s00170-021-07325-7

Cited by 185 publications

(77 citation statements)

References 138 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Considering that the vibration activity of the tool and the cutting temperature are related to each other through the evolution (wear) of the cutting wedge under metal processing, a third task arises. It is assessing the residual tool life and/or providing the maximum value of this parameter [ 7 , 8 , 9 , 10 ]. In modern machine-building production, a tool is just a consumable material that must be replaced when its cutting properties are exhausted.…”

Section: Introductionmentioning

confidence: 99%

“…As for the disadvantages of previous studies carried out in this area, it should be noted that there are two main directions of development of scientific thought in the field of mathematical modeling of temperature effects when cutting metals in metal-cutting machines. The first such direction is the direction in which the temperature in the contact zone of the tool and the workpiece has a static design value, for example, as in [ 6 , 7 ], determined by static design values of forces and processing speeds. As a result of this approach, there is a gap between the subsystems of the vibrational activity of the tool [ 1 , 2 , 3 , 4 , 5 ] and the thermodynamics of the cutting process [ 6 , 7 ]; however, experimental studies show that such a relationship exists [ 9 , 10 ].…”

Section: Introductionmentioning

confidence: 99%

“…The first such direction is the direction in which the temperature in the contact zone of the tool and the workpiece has a static design value, for example, as in [ 6 , 7 ], determined by static design values of forces and processing speeds. As a result of this approach, there is a gap between the subsystems of the vibrational activity of the tool [ 1 , 2 , 3 , 4 , 5 ] and the thermodynamics of the cutting process [ 6 , 7 ]; however, experimental studies show that such a relationship exists [ 9 , 10 ]. The second direction is related to the modeling of the temperature field in the tool itself, this approach is very well presented in [ 8 ], and it should be noted that this approach quite accurately connects the development of wear of the cutting wedge with the temperature gradient in the same cutting wedge.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Turning Tool Wear Estimation Based on the Calculated Parameter Values of the Thermodynamic Subsystem of the Cutting System

Lapshin

2021

Materials

View full text Add to dashboard Cite

Today, modern metalworking centers are not yet able to reliably assess the degree of wear of the tool used in metal cutting. Despite the fact that a large number of methods for monitoring the service life of the tool have been developed, this issue still remains a difficult task that needs to be solved. Idea: The article proposes a new, previously unused method for estimating the power of a cutting wedge in metalworking. The aim of the study is to develop a method for indirectly estimating the tool wear rate based on a consistent model of intersystem communication that describes the force, thermal and vibration reactions of the cutting process to the shaping movements of the tool. Research methods: The study consists of experiments on a measuring stand and a homemade measuring complex. It also uses the Matlab mathematical software package for processing and graphical interpretation of data obtained during experiments. The results show that the proposed method of estimating the current tool wear is applicable for the interpretation of experimental data. Statistically, the modified Voltaire operator of the second kind models the temperature more accurately; at the peak, this method is three times more accurate than the other.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Turning Tool Wear Estimation Based on the Calculated Parameter Values of the Thermodynamic Subsystem of the Cutting System

Lapshin

2021

Materials

View full text Add to dashboard Cite

show abstract

“…The regression model was one of the most important stages in our research, and the LSTM model was selected for its ability to work with sequences and to memorize long and short term dependencies [43,59] . Here, we were interested in characterizing the training of MH users, with the aim of predicting future workout sessions during the fourth month, based on their training during the first three months.…”

Section: Regression Resultsmentioning

confidence: 99%

Predicting Physical Exercise Adherence in Fitness Apps Using a Deep Learning Approach

Jossa-Bastidas

Zahia

Fuente-Vidal

et al. 2021

IJERPH

View full text Add to dashboard Cite

The use of mobile fitness apps has been on the rise for the last decade and especially during the worldwide SARS-CoV-2 pandemic, which led to the closure of gyms and to reduced outdoor mobility. Fitness apps constitute a promising means for promoting more active lifestyles, although their attrition rates are remarkable and adherence to their training plans remains a challenge for developers. The aim of this project was to design an automatic classification of users into adherent and non-adherent, based on their training behavior in the first three months of app usage, for which purpose we proposed an ensemble of regression models to predict their behaviour (adherence) in the fourth month. The study was conducted using data from a total of 246 Mammoth Hunters Fitness app users. Firstly, pre-processing and clustering steps were taken in order to prepare the data and to categorize users into similar groups, taking into account the first 90 days of workout sessions. Then, an ensemble approach for regression models was used to predict user training behaviour during the fourth month, which were trained with users belonging to the same cluster. This was used to reach a conclusion regarding their adherence status, via an approach that combined affinity propagation (AP) clustering algorithm, followed by the long short-term memory (LSTM), rendering the best results (87% accuracy and 85% F1_score). This study illustrates the suggested the capacity of the system to anticipate future adherence or non-adherence, potentially opening the door to fitness app creators to pursue advanced measures aimed at reducing app attrition.

show abstract

“…Additionally, timber monitoring requires dataset of a larger size and perhaps other types of data-driven modeling. The choice of data-driven method depends on both the size and complexity of the data [ 85 , 86 ]. Different machine learning or deep learning models could be studied to choose the one that better fits the dataset of a larger size [ 87 ].…”

Section: Discussion and Remarksmentioning

confidence: 99%

Prediction of Mechanical Properties of Artificially Weathered Wood by Color Change and Machine Learning

et al. 2021

Self Cite

View full text Add to dashboard Cite

Color parameters were used in this study to develop a machine learning model for predicting the mechanical properties of artificially weathered fir, alder, oak, and poplar wood. A CIELAB color measuring system was employed to study the color changes in wood samples. The color parameters were fed into a decision tree model for predicting the MOE and MOR values of the wood samples. The results indicated a reduction in the mechanical properties of the samples, where fir and alder were the most and least degraded wood under weathering conditions, respectively. The mechanical degradation was correlated with the color change, where the most resistant wood to color change exhibited less reduction in the mechanical properties. The predictive machine learning model estimated the MOE and MOR values with a maximum R2 of 0.87 and 0.88, respectively. Thus, variations in the color parameters of wood can be considered informative features linked to the mechanical properties of small-sized and clear wood. Further research could study the effectiveness of the model when analyzing large-sized timber.

show abstract

A review on deep learning in machining and tool monitoring: methods, opportunities, and challenges

Cited by 185 publications

References 138 publications

Turning Tool Wear Estimation Based on the Calculated Parameter Values of the Thermodynamic Subsystem of the Cutting System

Turning Tool Wear Estimation Based on the Calculated Parameter Values of the Thermodynamic Subsystem of the Cutting System

Predicting Physical Exercise Adherence in Fitness Apps Using a Deep Learning Approach

Prediction of Mechanical Properties of Artificially Weathered Wood by Color Change and Machine Learning

Contact Info

Product

Resources

About