Search

Based on the advanced detection drilling rigs used in underground coal mines, a real-time method of obtaining the depth of drilling is proposed. Displacement sensors are used to measure the stroke of the drilling rig's feeding device during drilling, and an equation to calculate the depth of drilling is put forward. The same measurements are made by several sensors, improving measurement accuracy and reliability. The final drilling depth is obtained using a multi-sensor data fusion algorithm, combined with the calculation equation. The necessary derivation and calculation processes of the multi-sensor, adaptive weighted fusion algorithm are given. To optimize the integrated result, the weighting coefficients can be found through the algorithm corresponding to each sensor in an adaptive mode to optimize the fusion result. Three kinds of displacement sensors are installed on the feeding device of the drilling rig, and the drilling process is simulated in a laboratory test. The test proves that, compared with the mean method of three sensors, the data obtained by the multi-sensor and adaptive weighted fusion algorithm have the higher accuracy, and the sensor with the least variance in the fusion process has the most significant weighting coefficient. The drilling depth data that are obtained are more accurate than those obtained through the mean method with measurement data from a single sensor. The weighted coefficient of the measurement data is minimal when the measurement accuracy of the sensor suddenly deteriorates, so it has little effect on the measurement results. An experiment verifies this method's effectiveness and fault tolerance, showing an improvement in measurement accuracy. [ABSTRACT FROM AUTHOR]

This study establishes a prediction model based on the back propagation (BP) neural network for controlling the underground directional drilling path in a coal mine. The four-layer BP neural network model chooses 11 trajectory parameters (dip angles and azimuths from 12 m after the measurement while drilling (MWD)) and two control parameters as inputs. Two parameters, the dip angle and azimuth at bit, are the outputs. Trained with data from 502 groups, the model was used to forecast 12 test data groups. The results were then compared with the prediction results of artificial experience from 24 technicians. The study shows that the mean absolute error of the dip angle and azimuth at bit are only 0.51° and 0.68°, respectively, as predicted by the prediction model, which uses the logsig activation function and has a double-hidden-layer with a point structure of 9×6. The prediction error also follows a normal distribution. Compared with technicians who have worked for more than five years, the accuracy of prediction results from the BP neural network model is reduced by 33.9% and meets the needs of drilling path control. [ABSTRACT FROM AUTHOR]