Determination of Geological Strength Index of Jointed Rock Mass Based on Image Processing

In general, knowledge on the mechanical properties of a rock mass is a prerequisite for the numerical simulation and the design of the underground structure, opening-up of mineral deposits and mining processes.

Since the early 1990s, many scholars have proposed a variety of methods to determine the strength and deformation parameters of a rock mass using geological strength index (GSI). The standard GSI chart considers qualitatively the surface condition and blockness of a rock mass, and it is used to estimate values between 0 and 100 representing the overall geotechnical quality of the rock mass. The best outcomes can be achieved only by the collaboration between experienced engineering geologists and geotechnical engineers.

To quantitatively determine the GSI, you have to detect the joints in two-dimensional (2D) photographs of a rock mass surface using image processing technology, then determine the fractal dimension, and finally predict the GSI using artificial neural network (ANN).

The detailed steps for joint detection on the rock mass surface are as follows.

Step 1: Converting the color image of a rock mass into a black and white one

Step 2: Smoothing and sharpening

Step 3: Binary encoding

Step 4: Noise removal

Step 5: Detection of the joints

The fractal dimension of a 2D rock mass surface can be calculated with previous research findings.

A 3-layer BP ANN is used for predicting the GSI of the surface of a jointed rock mass.

On the basis of the GSI chart, an ANN model is established, in which the input neurons are the fractal dimension and surface condition index (i.e. roughness and weathering condition), and the output neuron is a GSI value. And the number of neurons of a hidden layer is first set to three and it is finally determined via learning procedure to establish the most effective ANN structure.

In this way, the GSI of a jointed rock mass can be determined quantitatively and objectively by the interface, coded by using built-in tools of MATLAB 7.0, such as image processing, fractal analysis and ANN.

The details of this can be found in the essay, “Determination of geological strength index of a jointed rock mass based on image processing” by Hong Kun Ui, dean of the Faculty of Mining Engineering, presented to the SCI Journal “Journal of Rock Mechanics and Geotechnical Engineering”.