Asset Baseline Monitoring for Local Process State Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing industrial control systems require long data gathering periods for signature analysis and operational deviation detection, which is disruptive and costly, and often rely on external data sources for process state identification.

Innovation Solution

A local control system receives data from industrial assets to determine steady-state operation, accesses a baselined device model, and generates control signals based on differences between expected and current operations, enabling in-situ model training without external data sources.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If data gathering is performed over long time periods for signature analysis and operational deviation detection, then measurement precision is improved, but loss of time and productivity deteriorate due to process disruption and high costs

Engineering Contradiction:
Improveoperational deviation detection accuracyVSAvoiddata gathering time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary actions by using the control system to define process states and switch loads before signature analysis is performed. This preliminary structuring of operational states enables the signature analysis algorithm to work with pre-organized data, reducing the need for lengthy data gathering periods while maintaining detection accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The operational data is segmented into distinct process states based on control system definitions. By dividing the continuous operational data into discrete states (e.g., different load conditions, operational modes), the system can perform targeted signature analysis on each state separately, improving measurement precision without requiring excessively long overall data gathering periods.

Inventive Principle:
Principle #1Segmentation

2Adaptability or versatility

If external data sources are used to define process states, then adaptability is improved, but device complexity increases due to reliance on external control systems

Engineering Contradiction:
Improveprocess state identification capabilityVSAvoidsystem architecture complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The signature analysis algorithm serves as an intermediary between the control system and the operational data. It receives process state definitions from the control system and processes sensor data accordingly, producing operational deviation detections. This intermediary layer enables adaptability while managing complexity by providing a dedicated processing function.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system enables self-service by allowing the control system to autonomously define process states and switch loads without requiring external intervention. The signature analysis algorithm then uses these self-defined states to perform deviation detection, reducing the need for external data sources and simplifying the overall system architecture.

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP4715507A1Industrial asset baseline monitoring systems and methods
Publication Date: 2026.03.25 ROCKWELL AUTOMATION TECH INC
  • EP4715507A1 patent drawingFigure 1
  • EP4715507A1 patent drawingFigure 2
  • EP4715507A1 patent drawingFigure 3

AI summary

Systems and methods described herein may improve machine learning operations capable of being applied to many systems, like continuous processes and/or motion devices, without use of a process state identification data from a control system. By identifying process state based on acquired data, such as sensed data, configuration data, and/or motion profiles, or the like, a control system may determine which process state an asset is operated within and select from one or more device models corresponding to that process state to obtain an indication of expected asset operation developed earlier based on in situ training operations. When the control system is disposed within the asset, this analysis may be performed within the "four walls" of the asset, enabling relatively robust analytics to occur locally at the asset as opposed to transmitting the sensing data up into a cloud or the like for analysis.