【作者】 柏熙；

【导师】 吴正茂； 鲁远祥；

【作者基本信息】 西南大学 ， 光学， 2006， 硕士

【摘要】 煤矿智能监控网络系统需要解决的关键问题是：如何及时、准确的预测出煤矿井下温度、湿度、以及瓦斯和一氧化碳浓度等一系列参数在井下各个工作面的分布情况及变化趋势。 本论文对人工神经网络和遗传算法，尤其是BP神经网络与遗传算法相结合的理论及使用条件进行了分析研究，在此基础上提出了一个基于神经网络和遗传算法的煤矿智能监控网络系统。该系统通过以遗传算法优化后的人工神经网络的自学习功能来对煤矿井下温度、湿度、以及瓦斯和一氧化碳浓度等一系列参数进行预测；以重庆天府矿务局磨心坡等矿多年来的实测数据为学习模型样本集，建立煤矿智能监控系统的数学模型，结合MATLAB仿真，对该矿部分工作面的瓦斯涌出量进行了预测；并利用已有源代码编程和预测管理软件实现了整个系统的智能化管理。 仿真及实验结果表明：由于此数学模型是将神经网络和遗传算法相结合应用在井下的监控系统中，因此即克服了神经网络容易陷入局部最小误差的缺点，又利用了神经网络本身强大的人工智能；该模型不仅为煤矿监控系统管理提供了一种新方法和新思路，同时也为解决不确定性信息处理问题提供了一种新的尝试和手段；该模型学习功能强大，精度较高，实用性强，具有很好的推广价值。更多还原

【Abstract】 The key problem solved by the intelligent monitor system for coal mine is how to forecast accurately and timely the distributions and varied trends of the parameters for each working face under the ground such as temperature, humidity, and the concentrations of gas and carbon monoxide et al..In this paper, the artificial neural network and genetic algorithm, especially the theory and the applied condition of the BP neural network combined with genetic algorithm, have been investigated, and an intelligent monitor network system has been proposed. Through the self-studying of the artificial neural network optimized by the genetic algorithm, the system can predict the temperature, humidity, and the concentrations of gas and carbon monoxide; Based on the data measured by Moxinpo Coalmine in Tianfu Coalmine Administrant Bureau, the mathematical model of the intelligent monitor system for coalmine has been established and the gas outburst quantity of some working face has been predicted through emulation technology of MATLAB; Moreover the intellectualized management to the whole system has been achieved through using the source code editing and the forecasting managing software.The emulations and experimental results indicate that the theoretical model combined the neural network and genetic algorithm not only can conquer the disadvantage, which network is prone to enmesh the partial minimal error, but also utilize the powerful artificial intelligence of neural network.; This model provides a new method and idea for the monitor systems management, meanwhile it also offer a new method for solving the problems of the undetermined information processing; This model has powerful studying function, high accuracy, and strong practicability, so it has promoted value.更多还原