HCLTech - Asset Reliability GenAI Suite (ARGiS)

Generative AI (GenAI) is transforming industrial asset maintenance through ARGiS (Asset Reliability GenAI Suite), an innovative solution that enhances traditional machine learning approaches. While conventional ML models have shown good accuracy in predictive maintenance, they often fall short in addressing critical challenges such as knowledge retention of aging workforce, asset issue alarm interpretation, resolution implementation, and knowledge transfer across assets. ARGiS solves these challenges by integrating asset’s real-time IoT sensor data, historical maintenance records, and expert knowledge into one intelligent platform.

The system's multilingual interface removes technical barriers, allowing maintenance technicians to interact with documentation, troubleshoot issues, and record solutions in their preferred language. This post explores ARGiS's solution flow, technical architecture, and its transformative benefits for asset reliability and maintenance operations.

Business Benefits:

Our comprehensive solution empowers reliability engineers with proactive troubleshooting capabilities, allowing them to quickly identify failure root causes by delivering to them actionable maintenance recommendations that minimize downtime.

Engineers and maintenance teams benefit from immediate access to optimal operating parameters, which streamline decision-making and ensure peak system performance. By combining maintenance records with our extensive knowledge base, teams can leverage data-driven maintenance practices to enhance asset reliability and operational efficiency.

Additionally, ARGiS’s multilingual logging feature enables maintenance personnel at all levels to effortlessly document issue resolutions for future reference, creating a continuously improving knowledge repository.

AWS Services used

ARGiS integrates key AWS services to create a comprehensive intelligence platform.

Machine data flows through AWS IoT Greengrass and IoT Core before being stored in Amazon DynamoDB and PostgreSQL databases.

Predictive maintenance is enabled via Amazon SageMaker machine learning models, while operators interact through intuitive interfaces including an Amazon Nova Sonic-powered Voice Bot.

The Machine Alarm Assist feature leverages Amazon Bedrock and Amazon Nova Pro for natural language based troubleshooting.

Maintenance logs are processed using Amazon Textract for handwritten content and Amazon Transcribe for audio, with Amazon Translate and Amazon Bedrock handling smart multi-lingual support.

ARGiS’s knowledge base utilizes Amazon Titan Text Embedding for vector embedding generation of knowledge documents and Amazon OpenSearch Serverless for efficient information retrieval, complemented by Amazon Bedrock agents that provide web search capabilities for accessing external technical information.