An Agent-Orchestrated Containerized Laboratory Information Management System for NABL-Accredited Civil Engineering Testing Facilities
Sagar Singh *
Department of Artificial Intelligence and Data Science, Ajeenkya DY Patil School of Engineering, Pune, India.
Pranav Chavan
Department of Artificial Intelligence and Data Science, Ajeenkya DY Patil School of Engineering, Pune, India.
Prathamesh Badgujar
Department of Artificial Intelligence and Data Science, Ajeenkya DY Patil School of Engineering, Pune, India.
Atharva Garole
Department of Artificial Intelligence and Data Science, Ajeenkya DY Patil School of Engineering, Pune, India.
Varsha Babar
Department of Artificial Intelligence and Data Science, Ajeenkya DY Patil School of Engineering, Pune, India.
*Author to whom correspondence should be addressed.
Abstract
Laboratory Information Management Systems (LIMS) play a critical role in ensuring traceability, accuracy, and regulatory compliance in modern testing laboratories, particularly under ISO/IEC 17025 and NABL accreditation requirements. This paper presents the design, implementation, and evaluation of ATLAS – Automated Testing and Laboratory Accreditation System, a next-generation AI-integrated Laboratory Information Management System (LIMS) developed specifically for NABL-accredited Civil Engineering laboratories. The system integrates artificial intelligence (AI) and natural language processing (NLP) to modernize traditional workflows that are heavily dependent on manual data recording, paper-based approvals, and isolated record systems. ATLAS achieves complete digital tracking of samples, testing procedures, and reports while ensuring compliance with ISO/IEC 17025 standards. By leveraging NLP for automated and standardized report generation, and AI-driven analytics for anomaly detection and workflow optimization, the solution enhances accuracy, traceability, and decision-making within laboratory operations. The system architecture employs a four-layered, containerized microservices model using Flask, Zope, Plone CMS, MongoDB, ZODB, and ReportLab, deployed via Docker for scalability and reproducibility. Role-based access control (RBAC), real-time dashboards, audit trails, and seamless integration with laboratory equipment collectively ensure data integrity and operational transparency. Experimental evaluation demonstrates significant improvements in turnaround time, data accuracy, and NABL audit readiness (Bruschi et al., 2021). Feasibility analysis confirmed that, despite the Non-deterministic Polynomial-time Hard (NP-Hard) complexity associated with laboratory scheduling tasks, heuristic optimization techniques and modern solver approaches enable practical and scalable deployment in real-world laboratory environments. The proposed LIMS transforms manual, error-prone laboratory processes into a smart, efficient, and future-ready framework, improving productivity, regulatory adherence, and service quality for civil engineering testing laboratories.
Keywords: Laboratory information management system, ATLAS, AI anomaly detection, NLP report generation, ISO/IEC 17025, Docker containerization, civil engineering laboratory.