0
Article ? AI-assigned paper type based on the abstract. Classification may not be perfect — flag errors using the feedback button. Tier 2 ? Original research — experimental, observational, or case-control study. Direct primary evidence. Environmental Sources Policy & Risk Sign in to save

Pilot Deployment of an AI-Driven Production Intelligence Platform in a Textile Assembly Line Author

2025 5 citations ? Citation count from OpenAlex, updated daily. May differ slightly from the publisher's own count.
Md Faisal Bin Shaikat, Md Faisal Bin Shaikat

Summary

This paper describes the pilot deployment of an AI-powered manufacturing intelligence platform in a textile assembly line in Houston, Texas. The system uses real-time sensor data and predictive modeling to improve production scheduling, reduce downtime, and enhance quality control. The study is relevant to microplastic pollution because textile manufacturing is a major source of synthetic microfiber release into the environment.

This paper presents the pilot deployment of an AI-powered production intelligence platform in a textile assembly line in Houston, Texas. The system integrates real-time IIoT data capture, edge-based analytics, and predictive modeling to enhance production scheduling, downtime reduction, and quality control in legacy factory settings. The deployment aims to demonstrate how low-code, modular AI solutions can deliver measurable operational improvements without requiring significant reengineering or technical retraining. The proposed system-IndusOptima, developed by IndusEdge Solutions, a U.S.-based industrial technology startup-focuses on democratizing access to smart manufacturing tools for small and mid-sized manufacturers (SMMs) in underserved regions. The platform enables operators with minimal programming knowledge to configure machine learning-driven workflows, monitor key performance indicators, and respond to real-time production events with actionable insights. Initial deployment results in the textile sector show notable improvements in line efficiency (14.3%), first-pass yield (9.8%), and predictive maintenance accuracy (92.4%), validating the framework's potential for scalable adoption. This work aligns with national priorities under the CHIPS and Science Act, NIST Smart Manufacturing Goals, and DOE Industrial Decarbonization Roadmap by addressing the technology-access gap in digitally lagging factories.

Share this paper