Accurate localization of the shearer is key to achieving efficient, automated, unmanned mining. Unfortunately, the existing positioning algorithms usually yields low-precision, insufficient applicability and unreliable final estimation due to the existence of non-line-of-sight (NLOS) error and because they ignore the position error of anchor nodes (ANs). To bridge this technology gap, we developed a novel localization strategy by incorporating calibration, variational Bayesian unscented Kalman filter (VBUKF), total least squares (TLS) and water cycle algorithm (WCA) to enhance the location estimation accuracy of Ultra-wideband (UWB) positioning system in complicated underground environment. Firstly, calibration was implemented based on the selection of appropriate reference nodes (RNs) in line-of-sight (LOS) scenarios to estimate the scale-factor error, bias, and the position errors for each AN; then the VBUKF smoothing with the consideration of time-variant measurement noise was used to reduce the interference of NLOS owing to the difficult separation of bias and NLOS error. Secondly, the TLS method was implemented to calculate the target node’s position based on the smoothed distances and calibrated positions of ANs. Lastly, the WCA embedded scheme was executed to further ameliorate estimation accuracy. The experimental results demonstrated that the proposed TLS-WCA approach, after the implementation of calibration and VBUKF, was best able to improve the localization accuracy remarkably, and outperformed the other compared methods, which can efficiently attain higher estimation accuracy, highlighting the outstanding localization performance.

Accurate positioning of the shearer remains a challenge for automation of the longwall coal mining process. In this paper, the popular Ultra-wideband (UWB) positioning system that has attracted considerable attention is adopted to obtain the target node location. Unfortunately, localization accuracy is still unsatisfactory and unreliable in mixed line of sight (LOS) and non-line of sight (NLOS) scenarios. To ameliorate localization accuracy of UWB for complicate underground environment where the positioning scenarios suffered from frequently switching among LOS, NLOS, and mixed LOS-NLOS condition, the novel positioning algorithm GMM-IMM-EKF was proposed. Gaussian mixed model (GMM) was employed to re-estimate the measurement distance, and two parallel variational Bayesian adaptive Kalman filters (VBAKFs) under the structure of interacting multiple model (IMM) was utilized to smoothen the result of GMM to eliminate the LOS and NLOS errors, respectively. Then, the position of the target node was determined by exploiting extended Kalman filter (EKF) based on the outcome of IMM-VBAKF. The proposed approach was assessed by exploiting UWB P440 modules. Comparative experimental verification demonstrated that GMM-IMM-EKF strategy outperformed other positioning approaches, which can effectively reduce the adverse effect of NLOS errors and achieve higher positioning accuracy in underground environment with LOS/NLOS/LOS-NLOS transition conditions.

The achievement of accurate and reliable localization is invariably a predominant bottleneck to the realization of shearer automation. Unfortunately, the positioning accuracy may significantly degrade and the yield may be unsatisfactory due to the existence of the line-of-sight (LOS), non-line-of-sight (NLOS) along with mixed LOS-NLOS situations in complicated under-ground environments. To address this issue, this article proposes a novel localization algorithm called GMM-NNIMM-CLMFO, which is a combination of the Gaussian mixture model (GMM), neural network (NN)-based interacting multiple model (NNIMM), Caffery localization (CL), and moth-flame optimization (MFO). The GMM is first used to re-estimate the range, and the variational Bayesian cubature Kalman filter with the assistance of NN under the IMM framework is then respectively employed to diminish the LOS and NLOS errors. Then, based on the result of GMM-NNIMM, the CL method is used to compute the position coordinates of the target node. Finally, the MFO algorithm is implemented to optimize the positioning outcome sourced from the GMM-NNIMM-CL method. The proposed method is evaluated by using P440 sensors, and the experimental results demonstrate that the proposed technique is able to remarkably enhance the overall positioning accuracy, and outperforms other approaches. It can therefore efficiently alleviate the influence of NLOS errors and achieve more accurate position estimation, thereby manifesting better positioning performance and higher robustness in mixed LOS/NLOS situations.

Accurate and reliable location estimation of the shearer remains a crucial challenge to the realization of automated and unmanned mining. The poor positioning accuracy of conventional methods produces limited applicability owing to non-line-of-sight (NLOS) ranging errors, and the location errors of anchor nodes (ANs) and the velocity of the mobile target node (TN) are rarely considered. To tackle these issues, this article presents a new positioning strategy integrating calibration, the variational Bayesian (VB), constrained square root-unscented Kalman filter (CSRUKF), and robust Taylor series (RTS) algorithm to improve the ultra-wideband (UWB) positioning system accuracy in harsh underground coal mine environments. First, more accurate ANs position coordinates can be obtained using the proposed compensation method with the aid of reference nodes (RNs) under line-of-sight (LOS) conditions; then, the least squares (LSs) method is implemented to return the location of the TN using the compensated coordinates and corrected distance. Secondly, the VB-CSRUKF technique, which takes into account of the time-variant measurement noise and sigma points violating the constraints in the square root unscented Kalman filter (SRUKF), is used to eliminate the adverse effects of the NLOS error. Finally, the RTS method, in which robustness and the velocity of the TN in Taylor series are embedded, isadopted to further enhancethe final estimation accuracy. The experimental results corroborated that the developed VB-CSRUKF-RTS technique can efficiently and effectively ameliorate the overall accuracy, and is able to yield more accurate position estimation as compared with other approaches, possessing the high robustness and prominent performance.

Appropriate deployment of anchor nodes (ANs) is an essential prerequisite for achieving high-precision positioning. To ameliorate the comprehensive positioning performance, the weight position dilution of precision (WPDOP) that is utilized to evaluate the appropriateness of the ANs placement geometry is proposed by taking into account different error variances for each AN. A simple closed-form calculation WPDOP method is theoretically derived for ultrawideband (UWB) positioning system by utilizing elementary symmetric polynomials and Newton’s identity, which is applied to evaluate the UWB deployment at the end of coal mine working face (CMWF). Several basic ANs layout strategies, based on the projection shape in the $xy$ plane, are designed for the end of CMWF, and the modified gray wolf optimizer (MGWO) algorithm is executed to optimize the ANs deployment scheme to attain the better configuration and higher positioning accuracy. Simulation and experiments verification are simultaneously performed via the UWB positioning system. The experimental results sufficiently demonstrate that MGWO deployment scheme offers lower average WPDOP values than the obtained ones when applying random placement, and the lowest average improvement percentage was approximately equal to 37.6%. Furthermore, after implementing the MGWO algorithm, the V-shape deployment configuration is capable to provide the lowest average WPDOP values and outperforms the other arrangements, keeping the lowest localization error. This is regarded as the best deployment and it gives significant guidance for the ANs sensor deployment at the end of CMWF.

The high-precision positioning of the shearer in underground coal mines remains a significant challenge task for realizing automation and intelligent coal mining. Most of the presently conventional positioning approaches, nonetheless, tend to deliver low accuracy and unreliable estimations in the GPS-denied underground coal mine environment. Additionally, the current experiments remain in the simulation verification stage while lacking of the real field experiments. In order to improve reliability and positioning accuracy of target node (TN) in coal mines, this article proposes a fusion positioning scheme with the combination of the inertial measurement unit (IMU) and ultrawideband (UWB) based on error state extended Kalman filter (ESEKF) approach with the utilization of the available measurements obtained from IMU system and the established UWB localization system. Subsequently, the variational Bayesian UKF (VBUKF) method that incorporates the variational Bayesian (VB) and unscented Kalman filter (UKF) is implemented to the result of fusion localization with consideration of the changeable measurement noise to further eliminate the trajectory error and refine the final estimation accuracy. Furthermore, to bridge the research gap of the real field experiments using the IMU/UWB fusion system, the experimental investigation is performed to evaluate the effectiveness of the proposed method in the underground coal mine environment. The experimental results demonstrate that the presented ESEKF method, after applying the VBUKF smoothing, is capable to achieve better performances than the contrasted methods in terms of localization, and also can significantly improve the positioning accuracy of the shearer in the coal mining working face.