Industrial Process Subsystem Synchronization Using ML Setpoint Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In large-scale industrial automation systems, such as industrial mining operations, disparate process subsystems often run independently, leading to synchronization challenges and inefficiencies due to their distributed nature, which affects operational performance and requires predictive and preventative maintenance.
Innovation Solution
A computing system utilizes machine learning models to synchronize and optimize process subsystems by generating duration predictions and adjusting set points across interconnected systems, integrating time-series data and AI to enhance predictive and prescriptive analytics for improved system integration and maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If process subsystems run independently in distributed locations, then operational flexibility and decentralization are improved, but synchronization between subsystems deteriorates
Solution Approach 1:
The system implements feedback loops where each subsystem reports its status, duration, and performance data to a central coordination system. The coordination system analyzes this feedback and sends adjustment commands back to subsystems to maintain synchronization. This is evident in the continuous monitoring and adjustment of subsystem operations based on real-time data exchange.
Solution Approach 2:
The patent combines multiple independent subsystems into a unified coordinated system where a central coordination mechanism integrates the operations of disparate subsystems. The coordination system merges data from multiple sources and generates unified control decisions that ensure synchronized operation across distributed locations.
2Device complexity
If traditional control systems are used without machine learning, then system simplicity is maintained, but predictive maintenance and optimization capabilities deteriorate
Solution Approach 1:
The machine learning models perform preliminary analysis of historical and real-time data to predict future subsystem performance, potential failures, and optimization opportunities. This predictive capability allows the system to take preventive actions before problems occur, such as scheduling maintenance before equipment failure or adjusting parameters to prevent inefficiencies.
Solution Approach 2:
The patent introduces machine learning models as intermediary components between raw sensor data and control decisions. These models process and interpret data, generating insights and predictions that bridge the gap between simple data collection and complex control actions, enabling intelligent decision-making without requiring complete system redesign.
3Reliability
If real-time data processing is implemented across all subsystems, then operational coordination is improved, but computational load and processing time deteriorate
Solution Approach 1:
The system segments data processing tasks by assigning different processing levels to different subsystems. Critical real-time data is processed immediately by local subsystems, while less time-sensitive data is aggregated and processed centrally. This segmentation allows coordinated operation without requiring all subsystems to process all data in real-time, reducing overall computational burden.
Data Source
AI summary
Techniques to facilitate synchronization of industrial assets in an industrial automation environment are disclosed herein. In at least one implementation, a computing system receives time-series industrial process data associated with a plurality of process subsystems of an industrial automation process. The time-series industrial process data is fed into a machine learning model associated with the industrial automation process to dynamically generate a process duration prediction for a first one of the process subsystems and responsively determine an updated set point for a second one of the process subsystems based on the process duration prediction for the first one of the process subsystems. The updated set point for the second one of the process subsystems is provided to an industrial controller associated with the second one of the process subsystems.