Search

Assessment of the current state of the near-surface part of the geological environment and understanding of its layered structure play an important role in various scientific and applied fields. The presented work is devoted to the application of phasometric modifications of geoelectric control methods to solve the problem of the detailed complex study of the underground layers of the environment in the process of drilling operations with the use of special equipment. These studies are based on the analysis of variations in phase parameters and characteristics of an artificially excited multiphase electric field to assess poorly distinguishable details and changes in the layered structure of the medium. The proposed method has increased accuracy, sensitivity and noise proofness of measurements, which allows for extracting detailed information about the heterogeneity, composition and stratification of underground geological formations not only in the zone where the drill makes contact with the medium, but also in the entire control zone. This paper considers practical mathematical models of phase images for basic scenarios of drill penetration between the layers of the near-surface part of the geological medium with different characteristics, obtained by means of approximation apparatus based on continuous piecewise linear functions, and also suggests the use of modern machine learning methods for intelligent analysis of its structure. Studying the phase shifts in electrical signals during drilling highlights their value for understanding the dynamics of soil response to the process. The observed signal changes during the drilling cycle reveal in detail the heterogeneity in soil structure and its response to changes caused by drilling. The stability of phase shifts at the last stages of the process indicates a quasi-equilibrium state. The results make a significant contribution to geotechnical science by offering an improved approach to monitoring a layered structure without the need for deep drilling. [ABSTRACT FROM AUTHOR]

Copyright of Coal Geology & Exploration is the property of Xian Research Institute of China Coal Research Institute and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The different flexibility and diversity requirements for respective manufacturing units have made modern cutting tool management much more crucial and complicated, as a greater variety of tools and more frequent tool changes are required to enhance production efficiency and avoid unplanned manufacturing downtime. Developing in-process anomalous change detection methods has been identified as an essential challenge. Machine learning techniques have been widely applied in tool condition monitoring and anomalous change detection. As anomaly data is rare in manufacturing processes, supervised machine learning approaches (such as regression and classification) are not applied to the anomalous change detection problem. Rather, self-supervised machine learning (a representative type of unsupervised machine learning) is applied. This study describes a variational autoencoder (VAE) neural network and proposes a VAE-based method for tool condition monitoring and change detection in a drilling process using the temperature near a drill edge. The proposed VAE evaluates the drill tool condition based on the reconstruction error between the input temperature and its estimate per a drill unit process through the trained network. Computational simulations demonstrate that the proposed VAE network model can avoid overfitting to the anomaly data and that its expressive power is greater than that of the conventional autoencoder model. [ABSTRACT FROM AUTHOR]

Accurate prediction of the rate of penetration (ROP) is a difficult issue in the drilling process, especially under complex formation conditions. Many methods, such as mechanism and machine learning, were introduced to investigate it. However, most of them are offline prediction methods which may not be capable of capturing the online trend of ROP. In this paper, a novel dynamic model for ROP prediction is proposed considering the process characteristics, which consists of three stages. In the first stage, the correlations between ROP and eight drilling parameters are analyzed, and the rotational speed, weight on bit, depth are selected as the model inputs. In the second stage, the drilling data are pre-processed by using the filtering and re-sampling techniques. In the last stage, the moving window strategy, extreme learning machine, and 10-fold cross validation are used to establish the ROP model. Our main idea of online prediction of ROP lies in this last stage. Specifically, two steps (modeling and prediction) are executed alternately in the moving drilling depth windows so as to predict the ROP more accurately. Finally, the proposed ROP prediction model is applied to the drilling well ZK3 in Xiangyang area, Central China. The prediction accuracy is improved by at least 7% compared with seven well-known ROP prediction methods, two online and five offline, which validates the effectiveness of the proposed method. It is believed that the proposed model provides a basis for intelligent optimization control in drilling process. • A novel intelligent dynamic model is proposed for the online prediction of drilling ROP. • The influence of the length of moving window and distance between two windows are investigated thoroughly. • The proposed model can learn autonomously in the drilling process and has a fast computation speed. • The proposed method has a higher prediction accuracy than two online and five offline well-known conventional methods. [ABSTRACT FROM AUTHOR]

Accurate prediction of rate of penetration is a prerequisite for optimization of drilling parameters. However, characteristics such as multiple drilling conditions, inconsistency in data length and various drilling variables can lead to inaccurate prediction of rate of penetration in actual drilling process. Therefore, it is important to use appropriate methods to predict rate of penetration for the above characteristics. This paper proposes an online prediction method of rate of penetration based on drilling conditions identification. First, data preprocessing and correlation analysis are employed to handle various drilling variables to obtain optimal model inputs. Then, dynamic time warping method is used to solve inconsistency in data length. Further, for multiple drilling conditions, the fuzzy c-means and dynamic time warping are combined to identify drilling conditions. Next, different extreme learning machine models optimized by genetic algorithm are built to predict rate of penetration for different drilling conditions. Finally, the results involving actual data illustrate that the prediction error of the proposed hybrid method of fuzzy c-means, dynamic time warping, extreme learning machine and genetic algorithm meets the requirements. The proposed hybrid method outperforms the comparative methods in four performance metrics, which verify the rationality and necessity of considering drilling conditions when predicting rate of penetration. [ABSTRACT FROM AUTHOR]

One of the most important processes in the aeronautical sector is drilling. The main problem associated with drilling is burr. There is a tolerance level for this burr and it cannot exceed 127 microns, which would provoke structural damage and other problems. Currently, the burr elimination task is carried out visually and manually with the aim of guaranteeing quality in the process. However, it is an expensive procedure and needs to be replaced by a motorized system capable of automatically detecting in which holes the burr exceeds the permitted level and has to be eliminated or reduced. The paper presents a burr prediction model for high speed drilling in dry conditions on aluminium (Al 7075-T6), based on a Bayesian network learned from a set of experiments based on parameters taken from the internal signal of the machine and parameters from the condition process. The paper shows the efficiency and validity of the model in the prediction of the apparition of burr during the drilling and compares the results with other data-mining techniques. [ABSTRACT FROM AUTHOR]

This paper presents a particular problem dealing with the apparition of burr during the drilling process in the aeronautic industry. This burr cannot exceed a height limit of 127 μm as set out by the aeronautical guidelines and must be eliminated before riveting. If this is not performed, it can cause structural damage which would constitute a danger due to the lack of safety. Moreover, the industry needs to find an automated and optimised process in which the drilling and deburring can be carried out in real time, eliminating those other unnecessary tasks, in order to obtain high-quality pieces. The work presents the applicability of data mining and machine learning techniques so as to obtain a real time burr detection model. This model could be implanted in the computer numerical control of the machine allowing the whole process to be automated and optimised. These techniques can be applied to other types of processes. [ABSTRACT FROM AUTHOR]

Tool wear negatively impacts the quality of workpieces produced by the drilling process. Accurate prediction of tool wear enables the operator to maintain the machine at the required level of performance. This research presents a novel hybrid machine learning approach for predicting the tool wear in a drilling process. The proposed approach is based on optimizing the extreme gradient boosting algorithm's hyperparameters by a spiral dynamic optimization algorithm (XGBoost-SDA). Simulations were carried out on copper and cast-iron datasets with a high degree of accuracy. Further comparative analyses were performed with support vector machines (SVM) and multilayer perceptron artificial neural networks (MLP-ANN), where XGBoost-SDA showed superior performance with regard to the method. Simulations revealed that XGBoost-SDA results in the accurate prediction of flank wear in the drilling process with mean absolute error (MAE) = 4.67%, MAE = 5.32%, and coefficient of determination R2 = 0.9973 for the copper workpiece. Similarly, for the cast iron workpiece, XGBoost-SDA resulted in surface roughness predictions with MAE = 5.25%, root mean square error (RMSE) = 6.49%, and R2 = 0.975, which closely agree with the measured values. Performance comparisons between SVM, MLP-ANN, and XGBoost-SDA show that XGBoost-SDA is an effective method that can ensure high predictive accuracy about flank wear values in a drilling process. [ABSTRACT FROM AUTHOR]