Modern industrial machinery generates large amounts of potentially valuable data. To make use of that data, it is necessary to integrate it with other software components like dashboards or digital assets. Open Plattform Communications Unified Architecture (OPC UA) is an emerging standard for such data and provides rich semantic information. Mapping information from machine data to the data structures used by other software components depends on deep knowledge of the machine data and the software components, therefore requiring a considerable amount of manual effort. In this thesis, we examine how the artificial intelligence technique case-based reasoning (CBR) can be used to assist this task by leveraging existing knowledge. We develop a prototype implementing four different scoring functions that use the CBR approach to score potential candidates for a mapping from an OPC UA address space. We evaluate the prototype using a set of test cases based on four different use cases. The best scoring function placed the correct solution among the top three candidates in 70% of test cases, the worst performing version managed the same in 52% of cases, and the baseline, which relies on string search, did the same in only 28%. The prototype managed to complete test cases at a rate of 1.34 seconds per case. We identify several opportunities for future improvement. We conclude that CBR is a promising method to approach the problem of mapping OPC UA data with the data schemas of other software components. However, further research is necessary to determine its effectiveness in a practical setting.