Industrial Batch Dataset Generation for Faster Anomaly Modeling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional industrial batch processing systems are inefficient in detecting anomalies, leading to delayed solutions and increased pressure to enhance batch processing efficiency as the number of products manufactured using batch processing methods continues to rise.
Innovation Solution
The implementation of an AI modeling system that integrates IT and OT data to analyze collected data, identify baseline trends, and predict anomalous behavior in industrial batch processing systems, utilizing a data model management architecture and automatic AI engines for real-time monitoring and anomaly detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional testing procedures are used to analyze batch data, then anomaly detection can be performed, but the analysis takes days or weeks which delays product development
Solution Approach 1:
The patent replaces traditional mechanical testing procedures with an AI-based automated analysis system. The system uses machine learning models to process batch data, substituting manual or conventional mechanical testing methods with intelligent algorithms that can rapidly identify anomalies without sacrificing detection accuracy.
Solution Approach 2:
The patent introduces an AI processing system as an intermediary between raw batch data and anomaly detection results. This intermediary layer automatically processes and analyzes data, bridging the gap between data collection and actionable insights, thereby reducing analysis time while maintaining precision.
2Productivity
If batch processing capacity is increased to meet rising product demands, then productivity improves, but anomaly detection efficiency remains a bottleneck
Solution Approach 1:
The patent implements preliminary action by pre-training AI models on historical batch data and establishing automated analysis pipelines before new batches are processed. This preparation enables the system to rapidly analyze anomalies in new batches without delay, supporting increased processing capacity while maintaining detection efficiency.
Solution Approach 2:
The AI system performs self-service by automatically analyzing batch data for anomalies without requiring manual intervention. The system autonomously processes data, identifies patterns, and flags anomalies, enabling the infrastructure to scale with increased batch processing capacity while maintaining consistent detection efficiency.
Data Source
AI summary
A non-transitory tangible, computer-readable medium storing instructions that, when executed by processing circuitry, cause the processing circuitry to perform operations including receiving data associated with industrial equipment, pre-processing the data using pre-processing files associated with a modeling technique to generate pre-processed data, generating training dataset files based on the pre-processed data, and generating a model representative of expected operations of the industrial equipment based on the training dataset files. The instructions cause the processing circuitry to perform operations including storing an association between the training dataset files with the modeling technique, the industrial equipment, or both in a database, receiving a request to generate an additional model representative of additional expected operations of additional industrial equipment, receiving additional data associated with the additional industrial equipment, retrieving the training dataset files based on the additional data, and generating the additional model based on the training dataset files and the additional data.