Analog and Multi-modal Manufacturing Datasets Acquired on the Future Factories Platform V2

2025-02-07

AI Summary

This work addresses the lack of high-fidelity, long-duration, and reproducible multimodal time-series benchmark data in AI research for manufacturing. To this end, we construct and open-source the first synchronized industrial-grade simulation platform coupled with a multimodal time-series dataset. The dataset is collected over an 8-hour continuous operation of a production line at the Future Factory Lab, encompassing OPC UA/Modbus protocol data, actuator and controller states, multi-source sensor signals, and high-frame-rate visual streams. Hardware-level time synchronization and embedded sensor fusion ensure millisecond-precision temporal alignment across modalities. Our contributions are: (1) the first open-source, high-accuracy simulated time-series dataset; and (2) the first open multimodal dataset featuring precisely timestamped, system-level telemetry–image synchronization. This dataset has already enabled algorithm validation and model training for anomaly detection, digital twin construction, and closed-loop control in industrial AI applications.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Machine Learning: Time-Series/Data Streams

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Security and Privacy: Data transparency and provenance

Abstract

This paper presents two industry-grade datasets captured during an 8-hour continuous operation of the manufacturing assembly line at the Future Factories Lab, University of South Carolina, on 08/13/2024. The datasets adhere to industry standards, covering communication protocols, actuators, control mechanisms, transducers, sensors, and cameras. Data collection utilized both integrated and external sensors throughout the laboratory, including sensors embedded within the actuators and externally installed devices. Additionally, high-performance cameras captured key aspects of the operation. In a prior experiment [1], a 30-hour continuous run was conducted, during which all anomalies were documented. Maintenance procedures were subsequently implemented to reduce potential errors and operational disruptions. The two datasets include: (1) a time-series analog dataset, and (2) a multi-modal time-series dataset containing synchronized system data and images. These datasets aim to support future research in advancing manufacturing processes by providing a platform for testing novel algorithms without the need to recreate physical manufacturing environments. Moreover, the datasets are open-source and designed to facilitate the training of artificial intelligence models, streamlining research by offering comprehensive, ready-to-use resources for various applications and projects.

Problem

• Industry-grade manufacturing datasets collection
• Support for testing novel algorithms in manufacturing
• Open-source datasets for AI model training

Innovation

• Multi-modal time-series datasets
• Integrated and external sensors
• Open-source AI training resources