Based on the coal-rock mass deformation model, hydraulic pressure descent model in fracture, fracture propagation model and its growth criterion, the mathematical model of hydraulic fracturing of low permeable coal-rock mass is established, and the influencing factors such as injection pressure, elastic modulus of coal-rock mass and in-situ stress, which affect the characteristics of hydraulic fracture propagation, are studied using the ANSYS software. The results show that fracture length presents a linear increase and widest width increases as an exponent function with the increase of injection pressure, and the ability of making fracture width is greater than fracture length during late fracturing; besides, with the increase of Young’s modulus of coal-rock mass and least horizontal stress, fracture length and widest width decrease, which are independent of maximum horizontal stress. The obtained conclusions provide a guiding role for the optimization of operation parameters of field hydraulic fracturing of low permeable coal-rock.

Based on Fisher discriminant theory, the Fisher discriminant analysis model (FDA) was established for predicting the possibility of drilling downhole accidents. Six factors such as WOB、pump pressure、pump flow、running speed、ROPand torque were selected as the discriminant factors of the FDA mode. A series of data from drilling downhole accidents were taken as the training samples, and then some practical engineering datas were used to verify this mode. It was showed that FDA model is one of simple and accurate method in solving the prediction of drilling downhole accidents.

The cementing quality is directly related to the normal operation of the gas well, therefore, the evaluation of cementing quality is key to the correctly use the gas well as well as to take measures to protect the gas well. In this paper, four first wave amplitudes at the same depth point when using the borehole compensated sonic logger with double transceiver technique to carry out the acoustic amplitude log operation are served as the discriminant factors to evaluate the cementing quality. Taking the engineering actual measured data as the learning samples and using the particle swarm optimization to optimize the parameters of support vector machine, this paper established the intelligent evaluation model for cementing quality based on particle swarm optimization (PSO) and support vector machine (SVM). The model employs the excellent characteristic of SVM which has high speed of solving and could describe nonlinear relation as well as the characteristic of PSO which has global optimization. Through test of engineering samples, the research result showed that this model has fast astringency and high precision, providing a new method and approach for the fast and accurate evaluation of the well cementing quality.

The situation of road traffic in China was analyzed, and the results showed that the numbers of RTD decreased year by year, but the absolute numbers are still large. The main influence factors including human factor, vehicle factor, road factor and environmental factor were analyzed, and the results showed that human factor is the most important factor. Some measures on safety management of road traffic were given with references to the advanced management experiences of developed countries.

Sand liquefaction is a problem of complex evolution of the disaster, there is no accurate way to judge at present, this study put forward an analytical method to improve and optimize the evaluation system of sand liquefaction based on rough set. The significance of indexes are confirmed by calculating rough dependability between indexes and result for appraisement, the result show that SPT blow count has the greatest impact on the evaluation system, the groundwater level has greater impact, followed by the sand depth, epicenteral distance and duration. The proposed approach overcame the subjectivity of traditional weight determination method, so it is more objective and accurate, and it is reasonable and effective to optimize the evaluation index of sand liquefaction.