基于人工智能的矿井水害水源自动识别方法研究

Research on method of automatic recognition of water sources based on artificial intelligence

为了提高识别水害水源的正确率,本文给出了对地面水质化验分析的多个指标的单位归一化的方法,转化为与单位无关的数据,然后再归类识别的方法。综合了自下向上和自上向下分类识别方法的优点,提出了一种能够自动地进行水源(类)的合并、分裂和吸取中间结果所得到的经验的新的水害水源识别方法,实验和生产实践证明该方法效果较好。

In order to improve the recognition correct rate of flood water,a method for normalizing data unit of multiple index analysis of water is developed in the paper.In the method,the data tested are changed Into the ones which has nothing to do with the unit of data,then the changed data are applied to classifing recognition flood water.Combining the advantages of the bottom-up and top-down classification recognition method,a new method for identification flood water is put forward in the paper,in which method,merger and division of water（class） sources can be carried out automatically.The intermediate results experience can be added in the method.Experiment and production practice show that the method is effective.