|Theme||Visible||Selectable||Appearance||Zoom Range (now: 0)|
Undoubtedly, Roadheaders are one of the most versatile excavation machine types operated in soft and medium strength rock formations’ tunneling and mining. An essential aspect of a successful roadheader application is definitely the performance prediction which is basically concerned with machine selection, production rate and also bit consumption. Evolving a new roadheaders’ performance prediction model in various operational conditions and also different material is the primary intention of this research. Investigation on previous works revealed that three main features have great influences on the bit wear of a roadheader. Brittleness which can be utilized as a cuttability factor in mechanical excavation perspective is actually one of some parameters which is absolutely in relation with breakage properties. In addition to the rock brittleness, rock quality designation (RQD) and instantaneous cutting rate are employed as input parameters for the prediction of pick (bit) consumption rate (PCR). For the purpose of this paper, using previously published field datasets, a new prediction model using the application of artificial neural networks as an artificial intelligence technique is developed, trained and tested to estimate PCR based on data of brittleness, RQD and instantaneous cutter rate. Results demonstrated that PCR is highly correlated to the input parameters, and the ANN model could produce acceptable predictions.
In recent years, mining business has been under the influences of global trends, environmental limitations, and variant market requirements to be more and more productive and profitable. Utilizing mechanical miners like roadheaders, continuous miners, impact hammers and tunnel boring machines for ore extraction and excavation of development drivages, increases profitability. The mentioned miners result in continuous operations and consequently, the mechanization of mines with mechanical miners is presumed to make mining projects more productive, more competitive, and less costly. As a result, ordinary drill and blast technique could be avoided. Roadheaders which are applicable in tunnelling, mine development, and mine production of rock types of soft to medium strength, are very adaptable excavation facilities. The efficiency of roadheader application is rudimentary related to machine selection, production rate and bit consumption (Ebrahimabadi et al., 2011).
One of the necessities in drilling operations is the ability to predict the performance of rock drills. To explain the effects of various parameters on the drilling rate (drilling velocity) and the drilling tool wear, the term drillability is being used. In this research, drillability is defined as a penetration rate. The correlation between drilling rate index (DRI) and some rock properties is inspected in this survey in order to examine the influences of properties of strength indexes and brittleness of rocks on drillability. To achieve this, uniaxial compressive strength (UCS) and Brazilian tensile strength (BTS) values of different rock samples were used as geomechanical properties data. Then, the brittleness of rocks which use the uniaxial compressive strength and tensile strength of rocks were determined from calculations. Afterwards, artificial neural networks (ANN) as an artificial intelligence technique was employed in order to relate datasets of UCS, BTS and brittleness as input data to the DRI as the target. The suggested correlation between DRI and both mechanical rock properties and brittleness concepts were analyzed, and acceptable correlations between drillability of rocks and the input parameters was achieved. It is concluded that by the use of data of uniaxial compressive strength, Brazilian tensile strength and rock brittleness, ANNs can evaluate drilling rate index accurately.
Nowadays, Tunnel excavation utilizing mechanical excavation techniques such as tunnel boring machines (TBM’s) and roadheaders is growingly becoming common. Choosing the machinery and hardware must be under consideration of physical, mechanical and petrographic properties of rock, otherwise it can result in considerable detriments. Hence, earlier than tunnelling operations, it is vital to investigate rock properties (Yarali and Soyer, 2011).
ABSTRACT: In this study, an artificial neural networks (ANN) model as an artificial intelligence (AI) technique is proposed to determine the formation pore pressure from data of two critical drilling parameters named mechanical specific energy and drilling efficiency. These parameters (MSE and DE) which are closely correlated to differential pressure during drilling were chosen as a result of a literature review of proposed methods of pore pressure estimation. Collected data of a three wellbores drilled in an Iranian sandstone formation were used for the purpose of this research, and pore pressure estimated using this model was in a good agreement with estimates from previously published models including the one derived from conventional sonic logs data. The proposed model results were analyzed, and proved that artificial neural networks are capable to provide reliable independent predictions of pore pressure, and this smart model can be hired to analyze data for pre-drilling prediction models construction and post-well prediction models optimization.
Nowadays, many drilling operations are not being performed with optimum efficiency and management of costs, time and quality. Thus, drilling optimization has become an important and critical challenge for drilling operators in the petroleum industry as there are a lot of variables for consideration in drilling systems optimization. Real-time analysis of drilling parameters’ data is a way to understand drilling mechanics and efficiency. (Amadi and Iyalla, 2012)
Estimates of Formation Pore Pressure before and while drilling, and recognizing deviations from the expected pressure are important inputs for well planning and operational decision making. The effect of Differential Pressure (wellbore pressure minus pore pressure) on drilling responses has long been recognized, and drilling efficiency (DE) and mechanical specific energy (MSE) are chosen as parameters highly correlated to the differential pressure. (Majidi et al. 2016)
Logs and drilling mechanics based estimation methods are independent models of pore pressure estimation when suitable data are available. However, the advantage of drilling mechanics method is that it can provide pressure while drilling in real-time at the bit, not behind the bit, and the error would be diminished.
Tariq, Zeeshan (King Fahd University of Petroleum & Minerals) | Elkatatny, Salaheldin (King Fahd University of Petroleum & Minerals) | Mahmoud, Mohammed (King Fahd University of Petroleum & Minerals) | Ali, Abdelwahab Z. (King Fahd University of Petroleum & Minerals) | Abdulraheem, Abdulazeez (King Fahd University of Petroleum & Minerals)
Abstract Unconfined compressive strength (UCS) is the key parameter to; estimate the insitu stresses of the rock, design optimal hydraulic fracture geometry and avoid drilling problems like wellbore instability. UCS can be estimated by rock mechanical tests on core plugs retrieved from the depth of interest but retrieving reservoir rock samples throughout the depth of the reservoir section and performing laboratory tests on them are extremely expensive as well as time consuming. In absence of core plugs, UCS can be estimated from empirical correlations. Most of the empirical correlations for UCS prediction reported in the literature are based on elastic parameters or on compressional wave velocity. These correlations were developed using linear or non-linear regression techniques. Artificial intelligence tools once optimized for training can successfully model UCS since these tools can capture highly complex and non-linear relationship between input parameters and the output parameter. The objective of this research study is to accurately predict UCS of rock using basic geophysical well logs namely; bulk density, compressional, and shear wave velocities, by applying different artificial intelligence techniques namely; Support Vector Machine (SVM), Adaptive neuro fuzzy inference system (ANFIS) and Artificial neural network (ANN). The data set used in this study, comprised of 200 laboratory measured UCS values on core plugs and their corresponding well logs. The data were collected from 10 wells which were located in a giant carbonate reservoir. Based on minimum average absolute percentage error (AAPE) and highest coefficient of determination (R) between actual and predicted data, ANN model proposed as the best model to predict UCS. A rigorous empirical correlation was developed using the weights and biases of ANN model to predict without the need of any software incorporating AI. A comparison of proposed model with other correlations to predict UCS on new data set also suggested that the proposed model gives less AAPE. Therefore, the proposed model seems very promising and can serve as a handy tool to help geo-mechanical engineers to determine the UCS of the carbonate rock.