Search

In drilling operations, by choosing the proper tools and also incorporating more accurate and reliable parameters, this operation can be performed in less time and cost manner. Among drilling parameters, Rate of Penetration (ROP) is viewed as the main parameter in drilling operation evaluation. Field data investigations can be considered the most fruitful approaches to evaluate drilling performance, or ROP, as well as development of predictive models although laboratory tests and experimental formulas are vastly used to identify the drilling problems. In this research, intelligent modeling was used to predict the penetration rate of drilling operations through analyses of an established comprehensive data base from drilling operations in one of Iranian oilfields, Shadegan oilfield, in which novel artificial intelligence techniques such as Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and Grasshopper Optimization Algorithm (GOA) were applied. Since the database includes 400 data, these techniques were utilized due to their effectiveness on a large set of data. In this research, using drilling data compiled from Shadegan oilfield, a precise model was developed to predict the ROP. Results showed that determination coefficient (R2) and Root mean squared error (RMSE) parameters for Particle Swarm Optimization (PSO) are found to be as R2=0.977 and RMSE=0.036, for Grey Wolf Optimization (GWO) R2=0.996 and RMSE=0.014, for Grasshopper Optimization Algorithm (GOA) R2=0.999 and RMSE=0.003, respectively. Ultimately, it can be concluded that all predictive models lead to acceptable results but GOA yields more precise and realistic outcome., Odabirom odgovarajućih alata te primjenom precizno i pouzdano određenih parametara operacija bušenja može se izvesti brže i uz manje troškove. Mehanička brzina bušenja (engl. Rate of Peneration, ROP) smatra se glavnim parametrom u procjeni operacije bušenja. Iako se rezultati laboratorijskih istraživanja i eksperimentalno dobivene formule uvelike koriste za identifikaciju problema u operacijama bušenja, korištenje terenskih podataka smatra se najboljim pristupom za procjenu parametara bušenja ili ROP-a, kao i za razvoj modela predviđanja. U ovome je istraživanju primijenjeno inteligentno modeliranje, u kojemu su korištene nove tehnike umjetne inteligencije kao što su optimizacija Gray Wolf (engl. Gray Wolf Optimization, GWO), optimizacija Particle Swarm (engl. Particle Swarm Optimization, PSO) i optimizacijski algoritam Grasshopper (engl. Grasshopper Optimization Algorithm, GOA) za predviđanje mehaničke brzine bušenja na temelju analize podataka iz sveobuhvatne baze podataka prikupljenih tijekom operacija bušenja na jednome od iranskih naftnih polja, naftnome polju Shadegan. S obzirom na to da navedena baza sadržava 400 podataka, navedene tehnike umjetne inteligencije korištene su zbog učinkovitosti na velikome skupu podataka. U ovome je radu korištenjem podataka bušenja prikupljenih s naftnoga polja Shadegan razvijen precizan model za predviđanje ROP-a. Rezultati provedenoga istraživanja pokazuju da su parametri koeficijenta determinacije (R2) i korijen srednje kvadratne pogreške (RMSE) za optimizaciju Particle Swarm (PSO) R2 = 0,977 i RMSE = 0,036, za optimizaciju Gray Wolf (GWO) R2 = 0,996 i RMSE = 0,014, a za algoritam Grasshopper (GOA) R2 = 0,999 odnosno RMSE = 0,003. U konačnici se može zaključiti da svi prediktivni modeli daju prihvatljive rezultate, ali da GOA daje precizniji i realniji ishod.

Una de las cuestiones más importantes en la excavación mecanizada es predecir la tasa de penetración de TBM. Es importante comprender los factores que influyen en la velocidad de penetración, lo que permite una estimación más precisa de los tiempos de parada y excavación y los costos operativos. En este estudio, los parámetros de entrada y salida incluyen la resistencia a la compresión uniaxial (UCS), la resistencia a la tracción brasileña (BTS), elíndice de pendiente máxima (PSI), la distancia entre los planos de debilidad (DPW), el ángulo alfa y la tasa de penetración (ROP) (m / h) en el túnel de agua de Queens utilizando la máquina de vectores de soporte. Los resultados mostraron que la predicción de la tasa de penetración para el método de la máquina de vectores de soporte (SVM) es R2= 0.9678 y RMSE = 0.064778, según los resultados, la máquina de vectores de soporte (SVM) es efectiva Y tiene una alta precisión., One of the most important issues in mechanized excavating is to predict the TBM penetration rate. Understanding the factors influencing the rate of penetration is important, which allows for a more accurate estimation of the stopping and excavating times and operating costs. In this study, Input and output parameters including Uniaxial Compressive Strength (UCS), Brazilian Tensile Strength (BTS), Peak Slope Index (PSI), Distance between Planes of Weakness (DPW), Alpha angle and Rate of Penetration (ROP) (m/hr) in the Queens Water Tunnel using support vector machine .Results showed that prediction of penetration rate for Support Vector Machine (SVM) method is R2= 0.9678 and RMSE = 0.064778, According to the results, Support Vector Machine (SVM) is effective and has high accuracy., Uma das questões mais importantes na escavação mecanizada é prever a taxa de penetração do TBM. É importante compreender os fatores que influenciam a taxa de penetração, o que permite uma estimativa mais precisa dos tempos de parada e escavação e dos custos operacionais. Neste estudo, os parâmetros de entrada e saída incluem resistência à compressão uniaxial (UCS), resistência à tração brasileira (BTS), índice de inclinação de pico (PSI), distância entre planos de fraqueza (DPW), ângulo alfa e taxa de penetração (ROP) (m / hr) no túnel de água de Queens usando máquina de vetor de suporte. Os resultados mostraram que a previsão da taxa de penetração para o método SVM (Support Vector Machine) é R2= 0,9678 e RMSE = 0,064778. De acordo com os resultados, o SVM (Support Vector Machine) é eficaz e tem alta precisão.

Geotechnical risks play an important role in the selection of tunneling method and machine types. In order to prevent some geological and geotechnical hazards during tunneling, selecting the most appropriate tunneling machine is very important. In this research study the main geotechnical hazards of tunneling by roadheader with their common mitigation measures are discussed. At present, three roadheader are excavating the three drifts of the Tabas coal mine in Iran. Hence, these drifts were used in this research study. The risk assessment matrix method in these tunnels showed that there is a lower risk of tunneling by roadheader than utilising the drilling and blasting method. The determined geotechnical risk assessment showed that the transverse cutter head was more suitable in comparison to a longitudinal cutter head for such tunnels. Then by using an instantaneous cutting rate model, the cutter head power of the roadheader was determined. According to the model, a lightweight roadheader with a cutter head power of about 80-110 KW and 40 t weight are suitable. Finally, four types of manufactured roadheader with similar specifications were selected.