Overall Predictive Maintenance through Trusted Data Sharing

Facilitating secure and sovereign data sharing across systems, platforms, and companies, enabling the creation of new services that benefit all participants by leveraging collective data without exposing it to unauthorized access. This includes the exchange of production and operational data to monitor specific textile machine components, enable intelligent maintenance planning, and optimize production schedules and other supply chain phases. Additionally, it incorporates the monetization of currently underutilized historical data, unlocking its untapped value.​

This generates significant value for ITEMA and its industrial customers participating in the Data Space, enabling the development of personalized and transversal services across the entire supply chain.

Optical sensors continuously monitor components wear, transmitting data through a secure gateway to the Itema’s MyWeave platform. Predictive models estimate residual life, enabling proactive maintenance. Forecasts of aggregate needs allow optimized production planning and just-in-time delivery. Data sharing through a Data Space ensures collaboration across OEM, suppliers, and third parties. It can be summarized with three different scenarios:

1. Predictive Maintenance Service​;
2. Supply Chain Optimization Service;
3. Third-Party Dataspace Collaboration​: Data monetization​.

For the first scenario, operational weaving machines data will be shared by customers to implement predictive maintenance service, which output will be made available through dedicated dashboards and alerts. For the second scenario, historical sales and production data will be utilized to produce supply chain scheduling activities, consumed by ITEMA itself. For the third and last scenario, unused ITEMA operational data will be monetized.

As part of the PoC, a Data Space infrastructure was set up to enable automated and secure data flows between partners, using Sovity’s Connector-as-a-Service. This setup allowed seamless integration with an AI module handling basic analytics tasks. Access to the data was regulated through digital certificates and contract-based rules, ensuring only authorized participants could interact with the shared resources, thus preserving data sovereignty and building trust.
While the setup process largely followed Sovity’s documentation, a few custom elements were required, including the implementation of an auxiliary service to trigger automatic data exchange between the different participants’ connectors at scheduled intervals.

The pilot demonstrates strong replication potential across various industrial contexts where secure, automated data exchange is required for predictive maintenance and supply chain optimization. The modular architecture, based on Sovity’s Connector-as-a-Service and standardized Data Space components (e.g., certificate-based access, contract policies), makes it adaptable to different use cases with minimal structural changes.

From a technical standpoint, the implementation is highly feasible in similar environments, requiring only moderate integration efforts (e.g., setting up connectors, developing data triggers, and preparing datasets in compatible formats).

From an economic perspective, the cost of replication remains manageable with limited efforts required for initial setup and light customization.

However, a key barrier to replication may lie in the lack of a clear and widely accepted business model. Many companies remain reluctant to share their data due to concerns over confidentiality and competitive advantage. To overcome these cultural and organizational resistances, the benefits of participating in a Data Space must be tangible, well-communicated, and aligned with the strategic interests of the stakeholders involved.