PLC Soft-Sensor Contextualization for Early Quality Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional programmable logic controllers (PLCs) face limitations in handling and analyzing large amounts of data, leading to inefficient data processing, loss of important data points, and increased computational demands, which results in delayed quality problem detection and increased development costs for business analytics.

Innovation Solution

An intelligent PLC system that selects and updates soft-sensor values during each scan cycle, annotates them with automation system context information, and applies data analytics to adjust data generation parameters, enabling efficient data storage and contextualization, and performing analytics directly on the control layer.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If conventional PLCs process and transmit all automation system data to higher layers, then data completeness is improved, but network bandwidth consumption and storage capacity demands increase significantly

Engineering Contradiction:
Improvedata completenessVSAvoidnetwork bandwidth consumption
Core Design Contradiction:
Loss of informationVSLoss of energy

Solution Approach 1:

The patent segments data into two categories: process data (sensor readings, control outputs) and context data (control program variables, parameter values). This segmentation allows selective transmission where only essential process data is sent to higher layers, while context data remains at the control layer, reducing network bandwidth consumption while maintaining data completeness for control operations.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts and retains context data locally at the PLC level, separating it from process data that needs to be transmitted upward. This extraction allows the system to maintain complete data availability for control decisions while minimizing the volume of data transmitted through the network to higher automation layers.

Inventive Principle:
Principle #2Taking out (Extraction)

2Measurement precision

If conventional PLCs transmit all control program variables to higher automation layers, then data fidelity is improved, but computational demands and development costs increase

Engineering Contradiction:
Improvedata fidelityVSAvoiddevelopment costs
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements local quality by maintaining high data fidelity locally at the PLC where control decisions are made, while providing summarized or selective data to higher layers. The full-fidelity context data remains available locally for precise control operations, while higher layers receive sufficient data for monitoring and analysis without the complexity of processing all control variables.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent introduces a data contextualization layer at the PLC that acts as an intermediary between internal control variables and external higher-layer systems. This intermediary selectively translates and transmits only the most relevant data upward, maintaining data fidelity for control purposes while reducing the complexity burden on higher automation layers and decreasing development costs.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Device complexity

If conventional PLCs monitor only standard sensor data, then system complexity is reduced, but quality problem detection is delayed

Engineering Contradiction:
Improvesystem complexityVSAvoidquality problem detection time
Core Design Contradiction:
Device complexityVSLoss of time

Solution Approach 1:

The patent applies preliminary action by continuously monitoring control program variables and context data at the PLC level, where real-time control decisions are made. This allows quality problems to be detected immediately when they affect control parameters, before they propagate to higher layers or manifest as finished product defects, thereby reducing quality detection time without significantly increasing system complexity.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3213157B1Using soft-sensors in a programmable logic controller
Publication Date: 2024.03.20 SIEMENS AG
  • EP3213157B1 patent drawingFigure 1
  • EP3213157B1 patent drawingFigure 2
  • EP3213157B1 patent drawingFigure 3

AI summary

A method of operating an intelligent programmable logic controller over a plurality of scan cycles includes the intelligent programmable logic controller selecting one or more softsensors available in a control program corresponding to a production unit, each soft-sensor comprising a local parameter or variable used by the control program. The intelligent programmable logic controller determines updated soft-sensor values corresponding to the one or more soft-sensors during each scan cycle and stores those values during each scan cycle on a non-volatile computer-readable storage medium operably coupled to the intelligent programmable logic controller. Additionally, the intelligent programmable logic controller annotates the updated soft-sensor values with automation system context information to generate contextualized data.