AI Batch Processing Control for Real-Time Anomaly Detection
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 processing efficiency as the number of products manufactured using batch processing increases.
Innovation Solution
The integration of artificial intelligence (AI) models that analyze IT and OT data from industrial devices, employing a data model management architecture and AI training portals to generate predictive models for real-time anomaly detection, allowing for efficient and accurate identification of irregularities in batch processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional testing procedures are used to analyze batch data, then measurement precision is maintained, but loss of time increases significantly
Solution Approach 1:
The patent replaces traditional mechanical testing procedures with an AI-based system that uses machine learning models to analyze batch data. The system substitutes manual or conventional automated testing with intelligent algorithms that can process data rapidly while maintaining high detection accuracy, thereby resolving the contradiction between measurement precision and time loss.
Solution Approach 2:
The invention changes the operational parameters of the analysis system by transitioning from traditional testing methods to AI-driven analysis. This parameter change enables the system to achieve both high measurement precision in anomaly detection and significantly reduced analysis time, as the AI models can process batch data much faster than conventional methods while maintaining or improving detection accuracy.
2Productivity
If AI models are integrated for real-time analysis, then productivity increases, but device complexity increases
Solution Approach 1:
The patent implements a universal AI platform that serves multiple functions: data collection, preprocessing, model training, real-time analysis, and anomaly detection. This multi-functional system consolidates what would otherwise require separate systems, thereby increasing productivity while managing device complexity through integration rather than proliferation of components.
Solution Approach 2:
The system introduces an intermediary AI processing layer between data collection and decision-making. This intermediary layer handles the complex computations and model operations, shielding the rest of the system from complexity while enabling real-time productivity improvements. The AI model acts as a mediator that transforms raw data into actionable insights without requiring other system components to become more complex.
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 a set of data associated with industrial devices of an industrial system, and retrieving pre-processing files and training datasets files associated with the industrial devices from a database, wherein the pre-processing files are configured to transform the data for generating a model representative of the industrial devices, and wherein the training dataset files are representative of operational characteristics of the industrial devices over time. The instructions cause the processing circuitry to perform operations including generating a set of prediction data representative of expected operations of the industrial devices based on the set of data and the model, determining commands for adjusting operational settings of the industrial devices based on the set of prediction data, and sending the commands to the industrial devices.