With an aim at printing quality on-line detection, a method based on two-times difference image algorithm was proposed. Firstly, a standard template image and a gray threshold value image were calculated by using statistical methods. Secondly, an abnormal spots image was obtained through two-times difference image of the detection image, the standard template image and gray threshold value image. Lastly, the defects can be detected by analysis of connected region of the abnormal spots image. The results demonstrated that the problems of false detection and omission detection due to edge of image can be solved effectively, and the detection accuracy can be improved through this method.

In order to solve the problems such as low production capacity, high production costs and insufficient resources utilization in Wulongquan mine, the method of grey correlation analysis has been adopted to analyze the main affecting factors about mine production cost. Considering the changes and tendency of these time sequences, grey absolute correlation degree has been used to reflect the strong-weak degrees and orders of the relationship between reference sequence and comparison sequences better based on non-dimensional values. According to the calculating results, labor cost, depreciation cost and materials cost is main factors. So some appropriate measures have been put forward to control total cost.

Multi-level mining caused confusion of air return of overall ventilation system in Jinshandian Iron Mine. Based on fluid simulation software ANSYS-CFX, a modeling method of replacing fans with negative pressure section was proposed to build accurate 3D global model of mine ventilation network. Four feasible ventilation network optimization schemes were proposed. Airflow speed of inlet and air pressure of outlet was simulated in each scheme. To the principle of minimum ventilation energy, the scheme of return air through out3 and-270m level was determined as the optimal scheme. Using orthogonal experiment, three factors and three levels of variance analysis of airflow speed in each return air shaft was carried on. The functions of negative pressure of fans to airflow speed of outlet was built to calculate the optimal negative pressure parameter of each fan, which could realize the optimal allocation of air quantity and pressure in ventilation system.

Underground mining causes the redistribution of surrounding rock stress. The value of rock stress is one of the important factors that should be considered when stope structure size is designed. E’xi iron ore body is gently declined in attitude, thin in thickness, and large in occurrence area. According to mining technological conditions and the selected mining method of E’xi iron mine, a typical section of the mine is selected, and it is abstracted into a plane strain problem. In terms of optional stope structure parameters, 9 calculation schemes are planed. Rock stress distributions of stope caused by mining are simulated by the Finite Element Method. Rational stope parameters are chosen by comparing stress distributions of all calculation schemes. Analysis result shows that 8m net distance between pillars, and 4m pillar width are the optimum stope parameters, which not only stabilize the stope but also improve mining efficiency. Choosing stope parameters based on rock stress distributions calculated with numerical simulations, is provided a scientific analysis method for determining rational mining parameters of underground mines.

According to the analysis of the sum of squared residuals (SSE), this paper have defined the discriminant function and SSE change rate and discussed the discrimination standards and parameter calculation method of weighted forecasting model. Based on the balance of overall SSE and partial SSE, the parameters and forecasting model can be calculated by the value scope of SSE change rate. Through the discriminant and analysis of the mining safety incident weighted forecasting model, the derived model can have a high recent forecasting accuracy, thus it can provide reliable basis for safety management decision making. Discriminant function and SSE change rate have extensive applicability and can be used as a discrimination standard of the security system prediction model.