Artificial neural network model for prediction of rock properties from sound level produced during drilling

Kumar, B. Rajesh; Vardhan, Harsha; Govindaraj, M.; Saraswathi, Sowmya P.

doi:10.1080/17486025.2012.661469

Cited by 26 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Effect Of the Feed Rate On The Drilling Sound Andcontrasting

confidence: 51%

“…is conclusion is consistent with [28], while it seems to be in conflict with the results reported elsewhere (e.g., [29][30][31][32]34]). However, the penetration rates in [29][30][31][32]34] were set in the range of 2-6 mm/min, far smaller than those (16.5-71.6 mm/min) in this study. erefore, the conclusion can be modified considering the following condition: within a certain range, there is no significant correlation between the feed rates and the spectral characteristics of drilling sound and vibrations.…”

Section: Effect Of the Feed Rate On The Drilling Sound Andcontrasting

confidence: 51%

“…For example, Kumar et al proposed a group of multiple regression formulas predicting the uniaxial compressive strength (UCS), tensile strength (TS), or porosity from the drill bit diameter, drill bit speed, penetration rate, and equivalent sound level produced during drilling [29]. Subsequently, they used two methods-an ANN method and a regression method-for the prediction of rock properties such as UCS, Schmidt rebound number (SRN), dry density, P-wave velocity, tensile strength, Young's modulus, and percentage porosity from the variation of the equivalent sound level produced during drilling [30,31]. Recently, this team processed the noise signals in rock drilling by using the fast Fourier transform (FFT) method to obtain five dominant frequencies and observed that there is a significant correlation between the dominant frequencies and the physical properties such as tensile strength, compressive strength, and density [32,33].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Study on the Effect of Mineral Particle Sizes on the Spectral Characteristics of Sound and Vibrations in Rock Drilling

Wang

et al. 2020

Shock and Vibration

View full text Add to dashboard Cite

This study aimed to investigate the relationships between particle sizes and spectral characteristics of the sound or vibration signals generated in rock drilling processes. Several drilling experiments were conducted on concrete specimens of different aggregate sizes. By using an indoor signal acquisition and analysis system, data from the sound waves and vibrations were collected, the characteristic signals were extracted, and the spectral characteristics of the sound and vibrations of different aggregate sizes were identified. An approach based on frequency band analysis was adopted. In this approach, the average amplitude of each frequency band was calculated after frequency segmentation. The overall distribution trend in the frequency domain is conveniently observed, and the trend line patterns reflect the effect of aggregate sizes. The time-domain features of sound and vibration, such as the amplitude of sound pressure and vibration, are important indexes that roughly reflect grain sizes. The general trend is that the larger the amplitudes of sound and vibration, the larger the grain size. The frequency domain features of sound and vibration, such as the distribution of energy at high and low frequencies, can also reflect grain sizes. The general trend is that the larger the high-frequency composition of sound and vibration, the smaller the aggregate size. These results are useful for revealing the influence mechanism of rock particle sizes on the vibration spectral characteristics in drilling processes. The study provides a possibility for developing a method to evaluate the information on rock structures collected from drilling vibration or sound signals for the fine exploration of geological surveys.

show abstract

Section: Effect Of the Feed Rate On The Drilling Sound Andcontrasting

confidence: 51%

Section: Effect Of the Feed Rate On The Drilling Sound Andcontrasting

confidence: 51%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Study on the Effect of Mineral Particle Sizes on the Spectral Characteristics of Sound and Vibrations in Rock Drilling

Wang

et al. 2020

Shock and Vibration

View full text Add to dashboard Cite

show abstract

“…Gonzalez (2007) lists the most commonly measured parameters as depth (m), drilling time (s), rotary speed (RPM), pull down force (kgf), and flushing medium pressure (kgf/cm 2 ). Recently, some other parameters such as the vibration (in Nm/s) (Liu & Karen 2001;Smith 2010) and sound level (in dB) are also considered as measured parameters (Rajesh Kumar et al 2013aKumar et al , 2013b).…”

Section: Measured Parametersmentioning

confidence: 99%

The use of soft computing methods for the prediction of rock properties based on measurement while drilling data

Başarır¹,

Wesseloo²,

Karrech³

et al. 2017

Proceedings of the International Conference on Deep and High Stress Mining

View full text Add to dashboard Cite

Due to recent technological advancements drilling operations conducted for different purposes such as exploration, blasting and even grouting are not considered as auxiliary operations any longer. On the contrary, nowadays onsite drilling operations are considered as important resources for getting more information about rock properties. Many researchers have been working on measurement while drilling (MWD) techniques and their possible use for the prediction of rock mass properties. This paper presents a literature survey on the use of MWD technology for the prediction of rock mass properties. The survey indicates that the analysis and interpretation of MWD data is as important as recording the data. Both blackbox modelling such as regression and soft computing or grey-box modelling techniques are used as a tool for the analysis and interpretation of MWD data. This paper presents a case study showing the integration of soft computing methods such as adaptive fuzzy inference system (ANFIS) with MWD data for the prediction of rock mass properties such as rock quality designation (RQD). The results indicated that such soft computing methods can successfully be used as an analysis and interpretation tool.

show abstract

“…In recent years, research efforts have been devoted to the in-depth optimization of the marble block extraction, since this operation can induce geometrical defects, which in turn reduce the effective economic value of the stone considerably. 8 Several researchers [9][10][11] have developed a predictive optimization of numerous models using artificial intelligence approaches for marble processing. Simsir 12 studied the optimization of the computer numerical control (CNC) marble sawing process for different stone sizes.…”

Section: Introductionmentioning

confidence: 99%

Experimental study of drilling white Calacatta–Carrara marble using artificial neural approach

Abbassi

Akrichi

Yahia

2019

Advances in Mechanical Engineering

View full text Add to dashboard Cite

Highly accurate marble processing is increasingly needed to comply with tight parametric/geometric tolerances and surface integrity specifications encountered while structuring, sculpture, and decorating. In this study, a new approach based on the artificial neural network technique is evaluated for the prediction of process parameters in the machining of white Calacatta-Carrara marble. The rotation speed, feed speed, drill bit diameter, drill bit height, number of pecking cycles, and drilling depth were considered as input factors. Corresponding surface roughness, hole circularity, hole cylindricity, and hole-location error were sought in output. A series of experiments was carried out using a 5-axes computer numerical control vertical machining center (OMAG) to obtain the data used for the training and testing of the artificial neural network with reasonable accuracy, under varying machining conditions. A MATLAB TM interface was developed to predict surface roughness and geometric defects (circularity, cylindricity, and localization). A 6 3 4 size multilayered neural network was developed. The number of iterations was 1000 and no smoothing factor was used. The drill quality (holelocation error, hole circularity, and hole cylindricity) and the surface roughness were modeled and evaluated individually. One hidden layer used for all models, with the number of neurons for all the responses being executed separately, was 12 while the number of neurons in the hidden layer, with all the responses executed together, was 14. In conclusion, from the obtained verified experimentally optimization results, the errors are all within acceptable ranges, which, again, confirm that the artificial neural network technique is an efficient and accurate method in predicting responses in drilling.

show abstract

Artificial neural network model for prediction of rock properties from sound level produced during drilling

Cited by 26 publications

References 16 publications

Study on the Effect of Mineral Particle Sizes on the Spectral Characteristics of Sound and Vibrations in Rock Drilling

Study on the Effect of Mineral Particle Sizes on the Spectral Characteristics of Sound and Vibrations in Rock Drilling

The use of soft computing methods for the prediction of rock properties based on measurement while drilling data

Experimental study of drilling white Calacatta–Carrara marble using artificial neural approach

Contact Info

Product

Resources

About