Novel texture-based descriptors for tool wear condition monitoring

Antić, Aco; Popović, Branislav M.; Krstanović, Lidija; Stojaković, Vesna; Milošević, Milan

doi:10.1016/j.ymssp.2017.04.030

Cited by 39 publications

(11 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition to the above patterns, the following statistical features can contribute to the analysis of different images, including FKP images [28].…”

Section: Statistically Significant Features Of Fkpmentioning

confidence: 99%

A new biometric identity recognition system based on a combination of superior features in finger knuckle print images

Heidari¹,

Chalechale²

2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Biometric methods are among the safest and most secure solutions for identity recognition and verification.One of the biometric features with sufficient uniqueness for identity recognition is the finger knuckle print (FKP). This paper presents a new method of identity recognition and verification based on FKP features, where feature extraction is combined with an entropy-based pattern histogram and a set of statistical texture features. The genetic algorithm (GA) is then used to find the superior features among those extracted. After extracting superior features, a support vector machine-based feedback scheme is used to improve the performance of the biometric system. Two datasets called Poly-U FKP and FKP are used for performance evaluation. The proposed method managed to achieve 94.91% and 98.5% recognition rates on the Poly-U FKP and FKP datasets and outperformed all of the existing methods in this respect. These results demonstrate the potential of this method as a simple yet effective solution for FKP-based identity recognition. Key words:Entropy-based pattern, texture feature, genetic algorithm, biometric, finger knuckle print based coding scheme was used for FKP recognition [12]. In [13], the local orientation information extracted by Gabor filters and the Fourier transform coefficients were considered, respectively, as local and global features of FKP images. Woodard et al. used a sensor to create a three-dimensional hand dataset and then utilized the features extracted from fingers for identification [14]. However, the cost, size, and weight of the sensor and the prolonged data retrieval and processing of this method limit its use as a practical biometric solution. In a study by Ferrer et al., they developed a biometric identification system that considers the FKP as a biometric feature and uses the hidden Markov model in the identification phase [15]. However, this method has an extensive processing phase and works well only when a limited amount of data is being processed. Rawikanth et al. used the FKP region to detect the orientation and scale of finger images. However, the subspace analysis method used in the feature extraction phase was not able to extract the features of the knuckles very effectively [16].

show abstract

“…In addition to the above patterns, the following statistical features can contribute to the analysis of different images, including FKP images [28].…”

Section: Statistically Significant Features Of Fkpmentioning

confidence: 99%

A new biometric identity recognition system based on a combination of superior features in finger knuckle print images

Heidari¹,

Chalechale²

2020

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…The data are then pre-processed using the fast Fourier transform (FFT) method to reveal the relevant outstanding features in the frequency domain. In [22], the authors analyze the images created on the basis of short-term spectra from the vibration band and obtain information about Probability Density Function (PDF) in the form of lower order moments, thus obtaining robust tool wear state descriptors. The authors [23] created a model to monitor the tool condition in real time.…”

Section: Introductionmentioning

confidence: 99%

Identification of Tool Wear During Cast Iron Drilling Using Machine Learning Methods

Twardowski¹,

Tabaszewski²,

Felusiak-Czyryca³

et al. 2022

Adv. Sci. Technol. Res. J.

View full text Add to dashboard Cite

The paper concerns the monitoring of the tool condition on the basis of vibration acceleration signals. The cutting edge condition is determined by wear on the flank surface of the drill. As tools, a twist drills made of cemented carbide were used. A gray cast iron plate EN-GJL-250 was used as the workpiece. Based on the signals, appropriate measures correlated with the wear of the drill were developed. By using binary decision trees CART (Classification and Regression Tree) with two data partitioning methods (Gini index and Cross-entropy), the original number of measures was limited to the most common and those that provide the smallest error in the tool condition classification. Comparing the results for the best trees built with different measures of partition quality in nodes for all available data indicated a better performance of the Gini index. The applied solution allows for high accuracy of the tool classification. The solution is to be used in industry.

show abstract

“…Compared with the force sensor, the vibration sensor (e.g. the accelerometer and the acoustic emission sensor) is easier to be mounted on the cutting device or the workpiece, and it is more sensitive at higher frequencies for dynamic events 10–13 . Lee et al 14 .…”

Section: Introductionmentioning

confidence: 99%

“…the accelerometer and the acoustic emission sensor) is easier to be mounted on the cutting device or the workpiece, and it is more sensitive at higher frequencies for dynamic events. [10][11][12][13] Lee et al 14 and Gierlak et al 15 indicated that the vibration signal contain useful information about the tool condition. There were much research on condition monitoring based on the vibration signal, but it was not used to estimate the drilling depth in the previous research.…”

Section: Introductionmentioning

confidence: 99%

Vibration‐based drilling depth estimation of bone

Dai

Armand

2021

Robotics Computer Surgery

View full text Add to dashboard Cite

Drilling is one of the most common forms of tissue removal procedures, and drilling to a desired depth contributes to avoid injury to the soft tissue beyond and ensure implant stability. The deformation of the human musculoskeletal system has been a common problem in many drilling processes, making it difficult to achieve accurate estimation of the drilling depth. To remedy this problem, a dynamic model is presented to describe the relationship between the axial vibration of the drill and the feed rate. During drilling process, the amplitude of the main harmonic is estimated from the high‐frequency component of the acceleration signal, while the short‐time integral of the low‐frequency part is calculated. Both the initial contact of the drilling tool to the bone and breakthrough are identified by comparing either the harmonic amplitude or the short‐time integral. The harmonic amplitude is mapped to the data from a non‐contact position sensor tracking the feed rate of the drill. Multiple drilling experiments on both a handheld device and a robotic cutting system demonstrated the effectiveness, stability and accuracy of the method when estimating depth. The mean maximum error for drilling depth estimation is less than 15% of the simulated bone thickness when using the handheld device, while the mean maximum error is less than 5% for the robotic cutting system.

show abstract

Novel texture-based descriptors for tool wear condition monitoring

Cited by 39 publications

References 25 publications

A new biometric identity recognition system based on a combination of superior features in finger knuckle print images

A new biometric identity recognition system based on a combination of superior features in finger knuckle print images

Identification of Tool Wear During Cast Iron Drilling Using Machine Learning Methods

Vibration‐based drilling depth estimation of bone

Contact Info

Product

Resources

About