LLM-Based Drive AI Agent for Edge Analytics and Commissioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The availability and expertise of data engineers and data scientists for drive analytics applications are limited, leading to suboptimal ML algorithm execution and increased time and resource consumption in tasks such as commissioning and error handling, with a high learning curve for replacements.
Innovation Solution
A large language model (LLM)-based generative AI agent, called DriveAIAgent, is developed to automate the splitting, optimization, and deployment of analytics and ML algorithms in resource-constrained edge and device environments, utilizing drive operational data and tools to identify drive parameters and relationships, and assist in commissioning and error resolution.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data engineers and data scientists are used for ML algorithm execution and drive analytics operations, then expertise and understanding of drive parameters are improved, but availability and capacity are limited leading to increased time and resource consumption
Solution Approach 1:
The patent creates an AI agent that copies and encapsulates the expertise of data engineers and data scientists into a digital entity. This AI agent is trained on drive operational data and technical documentation to replicate human expert knowledge, enabling continuous operation without the availability limitations of human workers while maintaining the same level of expertise in drive parameter analysis
Solution Approach 2:
The AI agent is designed to autonomously perform analytics operations, commissioning tasks, and error handling without requiring constant human intervention. It can independently analyze drive data, identify parameters, and resolve errors, making the system self-sufficient and eliminating the need for continuous human resource allocation
2Reliability
If human experts are used for commissioning and error handling, then quality of work is improved, but time consumption and resource intensity increase
Solution Approach 1:
The patent replaces the mechanical system of human experts performing manual commissioning and error handling with an automated AI agent. This substitution maintains the quality of work through sophisticated algorithms and data analysis while dramatically reducing the time required for these tasks, as the AI agent can process information and execute operations much faster than human workers
3Reliability
If new data engineers or data scientists are trained to replace experts, then continuity is maintained, but training time and resource intensity increase
Solution Approach 1:
Instead of training new human employees to replace departing experts, the patent creates a digital copy of expert knowledge in the form of an AI agent. This AI agent can be replicated and deployed immediately without the lengthy training process required for human employees, ensuring continuous operation and eliminating the knowledge loss that occurs when experts leave
Data Source
AI summary
A method for obtaining an artificial intelligence (AI) agent applicable on a drive application. The method comprises obtaining training data indicative of predetermined drive operational data related to predetermined drive applications and/or of predetermined drive parameters related to the predetermined drive applications. The method further comprises training a large language model-, LLM-, based generative AI agent using the obtained training data to identify at least one of the following: first drive parameters related at least partly to the drive application, and relationships among the first drive parameters.