Indirect monitoring of machining characteristics via advanced sensor systems: a critical review

Korkmaz, Mehmet Erdi; Gupta, Munish Kumar; Li, Zhixiong; Królczyk, Grzegorz M.; Kuntoğlu, Mustafa; Binali, Rüstem; Yaşar, Nafiz; Pimenov, Danil Yurievich

doi:10.1007/s00170-022-09286-x

Cited by 39 publications

(10 citation statements)

References 191 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, to enhance the ability to learn feature representation, a contractive autoencoder (CAE) was developed by adding a contractive penalty term to the loss function [31]. Additionally, the modified reconstruction error is expressed as…”

Section: Sdae and Scaementioning

confidence: 99%

“…Based on the understanding of the above studies, a number of data-driven models with intelligent sensors have been proposed for tool wear monitoring and surface roughness estimation, and satisfactory results were obtained. These studies have made important contributions to the development of intelligent, networked, and digitalized machining processes, in line with the requirements of Industry 4.0 [31]. However, these studies mainly focused on the development and application of intelligent sensing devices and advanced machining algorithms [32].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Multi-Task Learning Model with PSAE Network for Simultaneous Estimation of Surface Quality and Tool Wear in Milling of Nickel-Based Superalloy Haynes 230

Cheng

Jiao

Yan

et al. 2022

Sensors

View full text Add to dashboard Cite

For data-driven intelligent manufacturing, many important in-process parameters should be estimated simultaneously to control the machining precision of the parts. However, as two of the most important in-process parameters, there is a lack of multi-task learning (MTL) model for simultaneous estimation of surface roughness and tool wear. To address the problem, a new MTL model with shared layers and two task-specific layers was proposed. A novel parallel-stacked auto-encoder (PSAE) network based on stacked denoising auto-encoder (SDAE) and stacked contractive auto-encoder (SCAE) was designed as the shared layers to learn deep features from cutting force signals. To enhance the performance of the MTL model, the scaled exponential linear unit (SELU) was introduced as the activation function of SDAE. Moreover, a dynamic weight averaging (DWA) strategy was implemented to dynamically adjust the learning rate of different tasks. Then, the time-domain features were extracted from raw cutting signals and low-frequency reconstructed wavelet packet coefficients. Frequency-domain features were extracted from the power spectrum obtained by the Fourier transform. After that, all features were combined as the input vectors of the proposed MTL model. Finally, surface roughness and tool wear were simultaneously predicted by the trained MTL model. To verify the superiority and effectiveness of the proposed MTL model, nickel-based superalloy Haynes 230 was machined under different cutting parameter combinations and tool wear levels. Some other intelligent algorithms were also implemented to predict surface roughness and tool wear. The results showed that compared with the support vector regression (SVR), kernel extreme learning machine (KELM), MTL with SDAE (MTL_SDAE), MTL with SCAE (MTL_SCAE), and single-task learning with PSAE (STL_PSAE), the estimation accuracy of surface roughness was improved by 30.82%, 16.67%, 14.06%, 26.17%, and 16.67%, respectively. Meanwhile, the prediction accuracy of tool wear was improved by 46.74%, 39.57%, 41.51%, 38.68%, and 39.57%, respectively. For practical engineering application, the dimensional deviation and surface quality of the machined parts can be controlled through the established MTL model.

show abstract

Section: Sdae and Scaementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Novel Multi-Task Learning Model with PSAE Network for Simultaneous Estimation of Surface Quality and Tool Wear in Milling of Nickel-Based Superalloy Haynes 230

Cheng

Jiao

Yan

et al. 2022

Sensors

View full text Add to dashboard Cite

show abstract

“…With the manufacturing industry moving away from the use of lubricants and coolants due to their effects on the environment, reliable temperature measurements during machining operations are becoming increasingly important [12]. In addition, machining performance in terms of cutting forces, surface roughness and tool life, amongst others, is directly linked with temperature [13]. Therefore, in-situ temperature sensing and monitoring aids in realising Industry 4.0 goals.…”

Section: Introductionmentioning

confidence: 99%

“…This is a valuable resource for signal conditioning and processing. Korkmaz et al [13] reviewed literature on online detection methods and signal processing systems used in machining, including some literature for cutting temperature online monitoring systems. Zhao et al [19] reviewed the temperature measurement methodologies employed by researchers investigating the effect of tool coatings on cutting temperature.…”

Section: Introductionmentioning

confidence: 99%

A Comparative Review of Thermocouple and Infrared Radiation Temperature Measurement Methods during the Machining of Metals

Leonidas

Ayvar-Soberanis

Laalej

et al. 2022

Sensors

View full text Add to dashboard Cite

During the machining process, substantial thermal loads are generated due to tribological factors and plastic deformation. The increase in temperature during the cutting process can lead to accelerated tool wear, reducing the tool’s lifespan; the degradation of machining accuracy in the form of dimensional inaccuracies; and thermally induced defects affecting the metallurgical properties of the machined component. These effects can lead to a significant increase in operational costs and waste which deviate from the sustainability goals of Industry 4.0. Temperature is an important machining response; however, it is one of the most difficult factors to monitor, especially in high-speed machining applications such as drilling and milling, because of the high rotational speeds of the cutting tool and the aggressive machining environments. In this article, thermocouple and infrared radiation temperature measurement methods used by researchers to monitor temperature during turning, drilling and milling operations are reviewed. The major merits and limitations of each temperature measurement methodology are discussed and evaluated. Thermocouples offer a relatively inexpensive solution; however, they are prone to calibration drifts and their response times are insufficient to capture rapid temperature changes in high-speed operations. Fibre optic infrared thermometers have very fast response times; however, they can be relatively expensive and require a more robust implementation. It was found that no one temperature measurement methodology is ideal for all machining operations. The most suitable temperature measurement method can be selected by individual researchers based upon their experimental requirements using critical criteria, which include the expected temperature range, the sensor sensitivity to noise, responsiveness and cost.

show abstract

“…16 However, supplying the desired cutting conditions is an arduous task when many design parameters are considered in machining. 17 Within these factors, the significance of cooling and lubrication strategies have been totally discussed priorly. 18 Many reasons can be listed about their extensive usage for improving significant parameters in manufacturing such as commercially, environmentally, feasibility and fertility.…”

Section: Introductionmentioning

confidence: 99%

Performance evaluation of AlTiN coated carbide tools during machining of ceramic reinforced Cu-based hybrid composites under cryogenic, pure-minimum quantity lubrication and dry regimes

Şap

Usca

Uzun

et al. 2022

Journal of Composite Materials

Self Cite

View full text Add to dashboard Cite

In this study, the machining performance of 10 wt.% B-Ti-SiCp particles reinforced Cu-based hybrid composites were investigated under dry, minimum quantity lubrication (MQL) and cryogenic LN2 assisted environments during milling. In-depth analyses comprising of tool wear development, surface roughness, surface texture, cutting temperature, cutting energy, and chip morphologies were thoroughly performed. According to the experimental results, MQL environment was found to be most influential method to prevent build-up-edge formation. In addition, LN2 assisted cryogenic coolant medium is the most powerful method in all machining characteristics as providing better tribological properties. The paper proposes a novel approach for improved machinability performance of Cu-based hybrid composites with sustainable techniques.

show abstract

Indirect monitoring of machining characteristics via advanced sensor systems: a critical review

Cited by 39 publications

References 191 publications

A Novel Multi-Task Learning Model with PSAE Network for Simultaneous Estimation of Surface Quality and Tool Wear in Milling of Nickel-Based Superalloy Haynes 230

A Novel Multi-Task Learning Model with PSAE Network for Simultaneous Estimation of Surface Quality and Tool Wear in Milling of Nickel-Based Superalloy Haynes 230

A Comparative Review of Thermocouple and Infrared Radiation Temperature Measurement Methods during the Machining of Metals

Performance evaluation of AlTiN coated carbide tools during machining of ceramic reinforced Cu-based hybrid composites under cryogenic, pure-minimum quantity lubrication and dry regimes

Contact Info

Product

Resources

About