Research on multi-source heterogeneous data fusion and intelligent decision-making in intelligent O&M platform

In order to solve the problems of multi-source heterogeneous data redundancy, conflict and low fault diagnosis efficiency of railway signaling equipment, this study proposes a data fusion method based on D-S evidence theory. By constructing the reliability entropy weight factor, the conflicting BPA function was preprocessed, and the multi-level data fusion model was established by combining the analysis of feature similarity, trust and falsehood. The results show that the accuracy of the proposed method in the fault diagnosis is $94.7 \%$ and $94.3 \%$, respectively, the accuracy of the third-level fault identification is $\mathbf{5. 6 \%}$ higher than that of the traditional ontology fusion algorithm, and the computational efficiency is better than that of the comparison method when the data scale is $\leq 700$. This paper verifies the effectiveness of D-S evidence theory in optimizing data quality and decision-making accuracy in the intelligent operation and maintenance platform, and provides technical support for the intelligent early warning of railway signaling system faults.