Multi-Sensor Data Fusion Identification for Shearer Cutting Conditions Based on Parallel Quasi-Newton Neural Networks and the Dempster-Shafer Theory

Lei Si,Kehong Zheng,Jing Xu,Xinhua Liu,Chao Tan,Zhongbin Wang

doi:10.3390/s151128772

Lei Si, Kehong Zheng + Show 4 more

Open Access

https://doi.org/10.3390/s151128772

Copy DOI

Journal: Sensors	Publication Date: Nov 13, 2015
Citations: 23	License type: CC BY 4.0

Affiliation: China University of Mining and Technology

Abstract

In order to efficiently and accurately identify the cutting condition of a shearer, this paper proposed an intelligent multi-sensor data fusion identification method using the parallel quasi-Newton neural network (PQN-NN) and the Dempster-Shafer (DS) theory. The vibration acceleration signals and current signal of six cutting conditions were collected from a self-designed experimental system and some special state features were extracted from the intrinsic mode functions (IMFs) based on the ensemble empirical mode decomposition (EEMD). In the experiment, three classifiers were trained and tested by the selected features of the measured data, and the DS theory was used to combine the identification results of three single classifiers. Furthermore, some comparisons with other methods were carried out. The experimental results indicate that the proposed method performs with higher detection accuracy and credibility than the competing algorithms. Finally, an industrial application example in the fully mechanized coal mining face was demonstrated to specify the effect of the proposed system.

Highlights

In a fully mechanized working face, the shearer is one of the most important pieces of coal mining equipment and monitoring its cutting condition has played an indispensable important segment for the automatic control of shearer
According to the above analysis, a sample of BP-neural networks (NNs) or parallel quasi-Newton neural network (PQN-NN) could be composed of the kernel feature KFi and the maximum energy Eimax, crest factor CFimax, kurtosis Kuimax of intrinsic mode functions (IMFs) for the ith signal
The main contribution of this paper is that a methodology based on parallel quasi-Newton neural network (PQN-NN) and Demspter-Shafer (DS) theory for the identification of shearer cutting condition is presented

Summary

Introduction

In a fully mechanized working face, the shearer is one of the most important pieces of coal mining equipment and monitoring its cutting condition has played an indispensable important segment for the automatic control of shearer. Due to the poor mining environment and complex component structure of a shearer, the operator cannot identify the shearer cutting conditions timely and accurately only with the help of visualization. Under this circumstance, the shearer drum may cut the rock, which will cause harm to the machine and lead to poor coal quality and low mining efficiency. The shearer drum may cut the rock, which will cause harm to the machine and lead to poor coal quality and low mining efficiency Another concern is that many casualties occur in collieries. Coal-rock interface recognition technology requires too harsh geological conditions of the coal seam, and the recognition precision cannot help the shearer achieve automatic control

Methods

Results

Conclusion