AI Model Factory Automating Asset-Specific Model Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Generating artificial intelligence models for large numbers of assets, such as wind turbines or power plant fans, is a time-consuming and labor-intensive process, requiring manual intervention and lacking scalability.
Innovation Solution
A computer-implemented method and system that uses a model recipe to automate the generation, deployment, and maintenance of artificial intelligence models for assets. The system selects a model recipe, identifies recipe parameters, creates a training dataset, trains artificial intelligence models, evaluates their performance, and selects the best models for deployment, all without user intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated machine learning is used to build and optimize models, then model building speed increases, but the complexity of the system increases
Solution Approach 1:
The system segments the model building process into distinct automated components: data preprocessing, feature selection, model selection, hyperparameter optimization, and evaluation. Each component is handled by specialized algorithms working in sequence, which increases productivity while containing complexity through modular organization.
Solution Approach 2:
The patent introduces an intermediary automated machine learning system that acts as a mediator between raw data and final AI models. This intermediary layer handles the complex transformations and optimizations automatically, shielding users from complexity while delivering high-speed model generation.
2Reliability
If manual intervention is used in model creation, then model quality can be controlled, but the process becomes time-consuming and labor-intensive
Solution Approach 1:
The automated machine learning system performs self-service by automatically executing data preprocessing, feature engineering, model selection, and hyperparameter optimization without human intervention. The system evaluates multiple models and selects the best ones based on predefined criteria, maintaining quality control through systematic evaluation while dramatically reducing creation time.
Solution Approach 2:
The system implements feedback mechanisms where model performance is continuously evaluated against validation data, and this feedback is used to automatically adjust hyperparameters and select optimal models. This closed-loop approach ensures quality control while automating the iterative refinement process that would otherwise require extensive manual time.
Data Source
AI summary
An approach for generating an artificial intelligence system configurable for use with assets. In this approach, a model recipe is selected for generating the artificial intelligence system for use with assets. Recipe parameters specified in the model recipe are identified. A training dataset is created using the model recipe and input data. A set of artificial intelligence models is trained using the training dataset, the recipe parameters, and the model recipe. The training creates artifact models. The artifact models resulting from training are evaluated. The evaluation is used to select a set of the artifact models in the artifacts that form the artificial intelligence system that is configurable for use in assets.