PLC Predictive Module for In-Controller Anomaly Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Industrial operations face challenges in creating diagnostic analytics solutions due to the need for expert data scientists, which can be time-consuming and costly, and there is a lack of available resources to employ them, hindering the digital transformation of industrial customers.

Innovation Solution

An industrial controller with a predictive module integrated into the programming logic controller, capable of receiving configuration data, creating user-defined controller tags, and calculating operation monitoring and value estimation data, allowing for predictive analytics within the automation layer without the need for intermediate data structures, thus enabling faster and more efficient anomaly detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If expert data scientists are employed to create diagnostic analytics solutions, then measurement precision and reliability are improved, but loss of time and loss of substance increase due to the weeks, months, or years required for understanding and modeling systems

Engineering Contradiction:

Improvediagnostic analytics accuracyVSAvoidtime to implement analytics

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs self-service by automatically collecting operational data from controllers, training machine learning models, and generating predictive analytics without requiring expert data scientists. The automated model training and evaluation process enables the system to serve itself, eliminating the time-consuming manual work of expert analysts while maintaining diagnostic accuracy

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system performs preliminary actions by pre-collecting and storing operational data from multiple controllers before model training is needed. This advance data preparation and the automated model training process enable rapid deployment of diagnostic analytics when needed, eliminating the weeks to years of manual work that would otherwise be required

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If expert data scientists are employed to create diagnostic analytics solutions, then measurement precision is improved, but loss of substance increases due to the high costs of employing specialists

Engineering Contradiction:

Improvediagnostic analytics accuracyVSAvoidcost to implement analytics

Core Design Contradiction:

Measurement precisionVSLoss of substance

Solution Approach 1:

The system eliminates the need for expensive expert data scientists by implementing self-service automation. The automated data collection, model training, and evaluation processes replace the need for specialized human expertise, significantly reducing the cost of implementing diagnostic analytics while maintaining measurement precision through systematic automated procedures

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system uses automated software-based analytics models that can be rapidly created, tested, and discarded without the long-term commitment and high cost of employing expert data scientists. These automated models provide the necessary diagnostic precision at a fraction of the cost of human expertise

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

3Productivity

If automated predictive analytics are implemented, then productivity is improved by enabling non-expert users to detect anomalies efficiently, but device complexity increases due to the integration of machine learning modules and automated data processing

Engineering Contradiction:

Improveanomaly detection efficiencyVSAvoidsystem architecture complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system merges the predictive analytics functionality directly into the existing controller infrastructure by integrating machine learning model training and data collection capabilities within the controller network. This consolidation enables non-expert users to access advanced anomaly detection without requiring separate complex external systems, improving productivity while managing complexity through integration

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system introduces an intermediary automated model training module that acts as a mediator between raw controller data and predictive analytics outputs. This intermediary layer handles the complexity of data processing and model training automatically, allowing non-expert users to benefit from advanced analytics without directly managing the underlying system complexity

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11347211B2Industrial control system with predictive machine learning module

Publication Date: 2022.05.31 ROCKWELL AUTOMATION TECH INC

AI summary

An industrial controller within an industrial automation environment is provided. The industrial controller includes a programming logic controller, configured to control an industrial device, and a predictive module, coupled with the programming logic controller. The predictive module is configured to receive configuration data from the programming logic controller, create a user-defined controller tag, and transfer the user-defined controller tag to the programming logic controller. The predictive module is also configured to receive operational data from the programming logic controller, and calculate operation monitoring data and value estimation data based on the operational data. The predictive module is further configured to write the operation monitoring data and value estimation data to the user-defined controller tag.