通过调查发现，97%以上的煤矿事故都是由矿工的不安全行为造成的，因此减少矿工不安全行为对降低事故的发生率至关重要。通过文献分析发现产生不安全行为的大多数矿工处于不良的心理生理等不安全状态中，这种状态会使其发生不安全行为的概率大大增加。如果能识别出矿工的不安全状态，找出其产生不安全行为的原因并进行调整，则会降低矿工发生不安全行为的可能性。矿工不安全状态可能出现的时间分为岗前和岗中，由于岗中矿工状态的动态性难以即时识别且单一的信息无法全面的对矿工不安全状态进行识别，因此本文基于多源信息融合理论对矿工岗前的不安全状态进行识别研究。

首先，对文献进行分析总结，结合学者对矿工不安全状态的相关研究，对矿工不安全状态进行定义；介绍了组织行为学和多源信息融合理论等相关理论内容。其次，使用文献计量研究法和煤矿实地访谈研究法收集资料；将收集到的资料采用扎根理论进行一级，二级，三级编码并进行理论饱和度检验，基于多源信息构建矿工不安全状态的识别指标体系，得到一级指标3个，二级指标6个，三级指标17个；使用层次分析法将专家打分的结果用于判断矩阵的构造，再根据计算求得矿工不安全状态识别指标的权重并进行一致性检验，按照各个指标的权重大小进行排序得到层次模型独立排序结果和综合排序结果。最后，通过选取排序中每类识别要素中权重较大的2个指标即总排序前6个指标作为多源信息融合的输入数据，对每个指标的具体情况进行介绍和分析，并对每个指标的识别标准进行确定；使用D-S证据理论构建本文的多源信息融合模型；通过对采集到的多源信息进行融合识别并分析该融合方法的准确率等评价指标，发现其识别准确率为87%，均大于单一指标进行识别的准确率，因此可以认为本文的多源信息融合方法对矿工不安全状态识别有足够的有效性；基于对矿工不安全状态的识别，从企业和个体两方面提出了一些管控建议。

识别矿工的不安全状态能够有效预防矿工产生不安全行为，从而减少事故的发生，更好的保障矿工安全，同时为煤矿实现安全生产提供参考依据。

The investigation found that more than 97% of coal mine accidents are caused by the unsafe behaviors of miners,so reducing unsafe behaviors of miners is crucial to reducing the incidence of accidents.Through literature analysis,it is found that most of the miners who produce unsafe behaviors are in an unsafe state such as bad psychophysiology.This state will greatly increase the probability of unsafe behaviors.If the unsafe state of miners can be identified,and the reasons for unsafe behaviors can be found and adjusted,the possibility of unsafe behaviors of miners will be reduced.The possible occurrence of unsafe state of miners is divided into pre-post and in-post.Because the dynamics of miners in post are difficult to identify in real time and a single information cannot comprehensively identify the unsafe status of miners,this article is based on the theory of multi-source information fusion Identify and study the unsafe state of miners before work.

First,it analyzes and summarizes the literature, and combines scholars' related research on the unsafe state of miners to define the unsafe state of miners;introduces related theoretical content such as organizational behavior and multi-source information fusion theory.Secondly, use the bibliometric research method and the coal mine field interview research method to collect data; use grounded theory to carry out the first,second,and third level coding of the collected data and conduct the theoretical saturation test,and build the unsafe state of miners based on multi-source information the identification index system,obtained 3 first-level indicators,6 second-level indicators,and 17 third-level indicators;using the analytic hierarchy process,the expert scored results are used in the construction of the judgment matrix,and then the unsafe state of the miner is identified according to the calculation.The weight of the indicators is checked for consistency,and the ranking is performed according to the weight of each indicator to obtain the independent ranking results and the comprehensive ranking results of the hierarchical model.Finally,by selecting the two indicators with larger weights in each type of identification element in the ranking,that is,the first 6 indicators in the total ranking,as the input data of multi-source information fusion,the specific situation of each indicator is introduced and analyzed,and the specific conditions of each indicator are introduced and analyzed.The identification criteria of the indicators are determined;the DS evidence theory is used to construct the multi-source information fusion model of this article;the accuracy of the identification is found by fusing and identifying the collected multi-source information and analyzing the accuracy of the fusion method and other evaluation indicators It is 87%,which is greater than the recognition accuracy of a single index.Therefore,it can be considered that the multi-source information fusion method in this paper is effective enough to identify the unsafe state of miners.Based on the identification of the unsafe state of miners,both enterprises and individuals Some management and control suggestions were put forward.

Identifying the unsafe state of miners can effectively prevent unsafe behaviors of miners,thereby reducing accidents,better ensuring the safety of miners,and providing a reference for coal mines to achieve safe production.