dataPARC, supplier of industrial analytics and manufacturing decision support, announced the release of its next-generation data historian platform, aimed at delivering federated plant operations data to engineering, technology, and operations teams. The new solution boasts improved performance, enhanced security, and broadened manufacturing intelligence capabilities. Notably, the platform's open design supports other vendor historians and enables seamless integration with third-party cloud AI, ML, and data warehousing applications, fostering enhanced efficiency and adaptability in the constantly evolving manufacturing sector.
dataPARC has been working with time-series data from the outset as an essential component of process engineering. The new data historian was designed to allow customers to harness machine data in new ways:
- The new data historian was developed to quickly export data to train artificial intelligence/machine learning (AI/ML) models and for use by third-party vendors for analytics and other applications.
- Time-series data can now be stored in different ways for fast, easy access across platforms, including the enterprise and the cloud.
- The new data historian release has a 10X performance improvement for use cases with the dataPARC application stack.
Often, time-series data is proprietary to a specific equipment or part of an automation vendor’s larger suite of applications, making it difficult to apply that data in third-party applications. Democratizing historian data with an open system gives manufacturing intelligence teams more flexibility and the ability to leverage their data in other systems.
dataPARC customers will see an increase in performance speed, cutting load times in half for custom calculations. Customers can also use dataPARC historian data to support AI and machine learning modeling in the cloud. For example, a predictive use case may have historian data transferred to the cloud for analysis and the modeled data delivered back to manufacturing operations management applications to highlight the source of potential or recurring maintenance or process upsets.
Another use case is to allow stakeholders to quickly access data regardless of where it resides. The goal is for every data call to perform as though the user is local to the data historian, ensuring that remote experts assisting multiple industrial plants experience the same performance as local plant engineers. With an emphasis on openness, the overall architecture allows for easy integration of other vendor historians and provides an SDK for third-party applications, ultimately enabling customers to efficiently leverage their existing and future investments.