As part of the systematic literature review on neuro-symbolic AI in knowledge graph construction for manufacturing, the research question of "For which manufacturing use cases are knowledge graphs constructed with neuro-symbolic AI?" is of paramount importance.

Upon conducting an extensive review of the literature, it has been observed that knowledge graphs constructed with neuro-symbolic AI have been applied to various manufacturing use cases. These use cases include, but are not limited to, supply chain management, predictive maintenance, quality control, process optimization, and anomaly detection.

In the context of supply chain management, knowledge graphs leveraging neuro-symbolic AI have been utilized to model complex supply chain networks, optimize inventory management, and enhance demand forecasting. Furthermore, in the domain of predictive maintenance, knowledge graphs have been employed to integrate heterogeneous data sources, enabling the prediction of equipment failures and proactive maintenance scheduling. Quality control processes have also benefited from the application of knowledge graphs, facilitating the identification of potential defects, root cause analysis, and the implementation of corrective actions. Moreover, in the realm of process optimization, knowledge graphs have been instrumental in modeling manufacturing processes, identifying inefficiencies, and optimizing resource utilization. Lastly, the use of knowledge graphs with neuro-symbolic AI has demonstrated efficacy in anomaly detection, enabling the timely identification of irregularities and deviations in manufacturing processes.

It is evident from the literature that the construction of knowledge graphs with neuro-symbolic AI has provided valuable insights and decision support across a spectrum of manufacturing use cases, contributing to enhanced operational efficiency, improved quality, and informed decision-making.

In conclusion, the application of knowledge graphs constructed with neuro-symbolic AI in manufacturing encompasses a diverse range of use cases, each presenting unique opportunities for leveraging the combined strengths of symbolic reasoning and neural networks to address complex manufacturing challenges.