RED-tag
Innovative platform of Predictive Logistics for supply chain and smart factory
Description
RED-tag is an innovative predictive logistics platform, developed to optimise the supply chain process through a knowledge-based approach and extracting process information to reduce waste and damage to transported goods. Simple and impactful, it is based on small and inexpensive tags that record shock and temperature with great accuracy, on the basis of theoretical studies and experimental analysis. This information, processed with context-specific tailor-made Big Data techniques and Machine Learning algorithms, allows for the creation of a solid background of knowledge on the supply chain process. Configurable dashboards and user-friendly mobile applications allow RED-tag to easily adapt to different verticals such as agrifood, medical, production line. Thanks to the platform, customers benefit from an end-to-end tracking system and are able to identify the weak points in the supply chain, taking corrective actions to reduce the number of breakages and to optimise transport and packaging processes.
Result to be enhanced
RED-tag is a new and flexible solution that significantly differs from existing ones and has been described as ‘disruptive’ by European companies that are leaders in the logistics sector.
The project has several original features:
- Cost-effective tags – cover 90% of use cases at 10% of the cost;
- Compact size – easily applicable both inside and outside the package;
- Low power consumption;
- Comprehensive solution – allows for bidirectional traceability (recipient-package), cloud-based Big Data analysis, detailed statistics, integration with custom company IT frameworks, and clear data presentation;
- Machine Learning analysis – ideal for identifying specific correlations, improving predictive analysis, and enhancing behavioral analysis of the goods being monitored;
Reliable – based on theoretical and experimental studies that allow the interpretation of data from sensors; - Configurable – in accordance with current regulations.
Why is it important?
The primary goal of the RED-tag system, which is to detect critical events that could damage goods during transportation, has a direct impact on reducing costs for consumers, minimizing waste, and promoting environmental sustainability. By providing information on where undesirable events occur, the system enables the establishment of trust-based relationships, the elimination of collaborations with low-quality suppliers, and the ability to measure the impact of best practices within the supply chain. Ultimately, this leads to improved supply chain efficiency.
The increased trust from buyers, who become part of a smarter logistics network, also facilitates the export of high-quality goods (such as those labeled “Made in Italy”) and fosters greater consumer loyalty. Quantitatively, focusing on online sales channels, where 3-6% of orders are typically damaged during shipping, conservative estimates predict that in 2022, the adoption of this technology could prevent waste worth 1 billion euros and reduce the release of 250 million tonnes of CO2 per year. This estimate assumes implementation on just the two largest e-commerce websites, even if the technology’s effect on identifying problems is minimal (estimated at 0.1%).
Looking ahead, the RED-tag system is well-positioned to enhance future supply chains, particularly those utilizing parcel delivery by drones or self-driving vehicles, with specific models tailored for such applications. Additionally, the RED-tag project is highly transferable to other policy areas. The flexibility of the technology allows for easy adaptation and replication across different industries and realities.
Project and Acronym: RED-tag
TRL: ?
Reference call: ?
Innovation Cluster to contact: Polo ICT
Technologies used: Big data, Machine Learning, Artificial Intelligence, Computer Vision
Lead company:
Zirak S.r.l
Collaborating companies:
T&T Elettronica s.r.l., Politecnico di Torino, l’Università della Beira Interior (UBI – PT), l’Istituto Superiore Mario Boella (ISMB)