Coalgangue interface detection during topcoal caving mining is a challenging problem. This paper proposes a new vibration signal analysis approach to detecting the coalgangue interface based on singular value decomposition (SVD) techniques and support vector machines (SVMs). Due to the nonstationary characteristics in vibration signals of the tail boom support of the longwall mining machine in this complicated environment, the empirical mode decomposition (EMD) is used to decompose the raw vibration signals into a number of intrinsic mode functions (IMFs) by which the initial feature vector matrices can be formed automatically. By applying the SVD algorithm to the initial feature vector matrices, the singular values of matrices can be obtained and used as the input feature vectors of SVMs classifier. The analysis results of vibration signals from the tail boom support of a longwall mining machine show that the method based on EMD, SVD, and SVM is effective for coalgangue interface detection even when the number of samples is small.
Today a major problem facing the mining industry is how to develop an automated topcoal caving system that can maximize the ratio of coal to gangue. The working procedure of topcoal caving is automatically controlled by an electrohydraulic system, which determines the recovery ratio of topcoal to gangue. In order to improve the recovery ratio of topcoal, a lot of work has been done on coalgangue interface detection (CID) [
Recently, singular value decomposition (SVD) of matrix has been widely applied to signal processing, statistical analysis, automatic control, and so forth [
In practice, a large number of samples are usually not available. Support vector machine (SVM) is a new machine learning method developed on the basis of statistical learning theory [
In this paper, the SVD technique based on EMD is applied to the feature extraction of vibration signals from coal and gangue collapse during topcoal caving. The SVM is introduced into the CID due to its high accuracy and good generalizatio n for a smaller sample number.
This paper is organized as follows: in the next section, the feature extraction algorithm based on SVD and EMD is discussed. Section
The EMD is a nonlinear and nonstationary signal analysis method proposed by Huang et al. EMD can decompose any timevarying signal into its fundamental intrinsic mode functions (IMFs), which must satisfy two conditions [
In the whole data set of each intrinsic mode function component, the number of extreme values and the number of zerocrossings must be equal to or differ at most by one.
At any point, the mean value of the envelope defined by local maxima and that defined by the local minima is zero.
With the definition, any time series signal
The IMFs
Due to the orthogonality of the EMD method, all IMFs are pairwise orthogonal. Therefore, the matrix
As singular values can reflect the nature characteristic of the matrix, the characteristic of vibration signals of coal and gangue can be described effectively by singular values of the initial feature vector matrix. Thus, the singular values of matrix could be used as feature vectors. The SVM could be chosen as the pattern classifier to classify the caving states after the vibration feature vector has been extracted.
As a new generation learning system, SVM enables the nonlinear mapping of an
Suppose that there is a given training sample set
In order to correctly classify twoclass samples, the optimal hyperplane separating the samples can be obtained as a solution to the following constrained optimization problem:
minimize
subject to
Defining Lagrange multipliers
maximize
subject to
So the decision function can be expressed as follows:
In order to investigate the EMDbased SVD technique and SVM as a means of distinguishing between topcoal and gangue caving impacts on the tail boom of a mining machine, an experiment has been carried out on number 2303 working face, Zhangcun Mine, Shanxi, China. The CID experimental system is composed of a data acquisition device, an embedded signal analysis platform, and vibration acceleration sensors, as shown in Figure
Hydraulic support and installation position of sensors (1: coal, 2: coalgangue, 3: gangue, and 4: sensor).
As an example, two different vibration signals of topcoal caving and coalgangue caving are chosen for further analysis. The sampling frequency of these signals is 8000 Hz and the sampling time is one second. Firstly, the EMD is applied to the analysis of separate vibration signals of pure coal and coalgangue. As shown in Figures
EMD results for topcoal caving.
EMD results for coalgangue.
For each vibration signal of each caving state, the initial feature vector matrix
Comparison of singular values of selected IMFs for each caving state.






 

Topcoal caving  5.8913  5.0226  4.7560  3.5182  2.7658  2.6858  1.0905 
Coalgangue caving  19.3695  13.7673  12.2830  6.8331  6.5870  4.2883  3.0371 
IMF component 







It can be seen from Table
Actually, the CID is to distinguish two caving states, that is, to solve a twoclass pattern classification problem. SVM has the advantage of solving a twoclass problem on the basis of searching for structural risk minimization, even in the case of few learning samples [
Acquire
Each signal is decomposed by EMD. Choose the first seven IMFs and construct feature vector matrix
Design SVM classifiers. When the feature input vector is a sample with known state of topcoal caving, the output of SVM classifier is set to 1, otherwise to −1. The singular values of the training samples are used as the input to train the SVM classifier. Then the state of caving can be distinguished after the testing samples have been input into the trained SVM classifier.
The flowchart of the proposed method is presented in Figure
The flowchart of EMDbased SVD and SVM.
The caving state detection method based on SVD, EMD, and SVM is applied to a vibration sample set of both pure coal and coalgangue caving. At first, a total of 126 vibration signals are acquired with a sample frequency of 8000 Hz, 63 signals for each caving state. In addition, the testing data sets consisting of 18 signals for each caving are used for validation of this detection method. Then the singular values of each signal are obtained after applying SVD based on EMD, parts of which are listed in Table
Samples for singular values of IMFs.
Number 







Expected output 

1  6.8036  5.1018  3.8767  2.8366  2.1208  1.8678  1.0817 

2  6.1150  4.8672  4.5894  3.3310  2.8880  2.3330  1.2493 

3  6.2398  5.8762  4.1749  3.0470  2.4142  1.9705  0.8274 

4  5.7488  5.2618  3.9826  3.1724  2.6175  2.1648  1.4194 

5  6.9123  5.8563  4.6258  3.2843  2.2754  2.1075  0.9596 

6  6.3855  5.2633  3.6245  3.2700  2.4509  2.1743  0.8024 

7  8.9377  8.6310  4.5831  4.5361  3.1545  1.8105  0.9570 

8  15.2788  11.2140  7.2233  5.1752  3.4570  1.7460  1.0975 

9  19.2038  13.6730  12.1804  6.7688  6.5208  4.1607  2.5960 

10  14.5418  12.4612  8.7011  6.1077  5.0121  3.2906  1.6954 

11  22.5342  14.4046  9.4929  5.9841  5.3480  3.6622  2.2097 

12  12.0520  10.0045  9.6424  4.9427  4.4479  3.5481  1.3674 

Choose RBF kernel function and set
Classification results of SVM.
Caving states  Test samples  Error  Classification accuracy 

Topcoal caving  18  0  100% 
Coalgangue caving  18  0  100% 
In order for further study of the classification performance of SVM in the case of a small sample, the number of training samples decreases to eight (number 1 to number 4 and number 7 to number 10 from Table
Classification results of SVM under few samples.
Testing sample number 
Real caving state  Distance to optimal hyperplane 
Results  

126 training samples  8 training samples  
5  Topcoal caving  0.9473  0.6561  +1 (right) 
6  Topcoal caving  1.0137  0.9807  +1 (right) 
11  Coalgangue caving  −1.0223  −0.4178  −1 (right) 
12  Coalgangue caving  −1.0004  −0.4182  −1 (right) 
The problem of coalgangue interface detection (CID) on a fully mechanized mining face has been addressed by applying the SVD technique and EMD to extracting longwall mining machine tail boom support vibration features that can be used for topcoal and coalgangue caving state classification. EMD is a selfadaptive analysis method that can decompose the signal into a number of IMFs. These functions provide a compact natural representation of nonstationary, nonlinear signals such as those detected by the vibration monitoring of the tail boom support of a longwall mining machine. Singular values were obtained by the application of SVD to the first seven IMFs of the example raw vibration signals (those IMFs containing key feature information), which could be used as the feature input vectors of the classifier. Based on these results, the SVM applied to the singular value vector is proposed as the classification tool for topcoal or coalgangue caving state. The validation test had a 100% classification accuracy rate, providing strong support for the robustness of this method. Therefore, the analysis based on SVD, EMD, and SVM for longwall mining machine tail boom vibrations offers a new method for CID.
The authors declare that there is no conflict of interests regarding the publication of this paper.
The work for this paper was supported by the Shandong Provincial Natural Science Foundation of China (Grant nos. ZR2013EEM009 and ZR2013FL019). The authors are grateful to the anonymous reviewers for their careful reviews and detailed comments.