Plant Sensor Verification Models for Drift-Aware Calibration

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for verifying sensor information in plant processes, such as water treatment, are inadequate in detecting drifting sensor readings that can lead to inefficient operation and non-compliance, as they rely on interval-based comparisons and calibrations, which are resource-intensive and may miss issues between scheduled checks.

Innovation Solution

A method using a verification model that compares received sensor information with expected information based on other plant process data, such as second sensor readings, process parameters, and control activities, to output a verification signal when deviations occur, allowing for event-based calibration and ensuring accurate sensor readings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If interval-based comparison and calibration of sensor devices is performed, then sensor reading accuracy is maintained, but time consumption and resource usage increase

Engineering Contradiction:
Improvesensor reading accuracyVSAvoidtime consumption
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements a feedback mechanism where sensor readings are continuously verified against expected values derived from process models and other sensor data. This creates a real-time validation system that only triggers calibration when deviations indicate actual drift, eliminating the need for routine interval-based calibrations while maintaining measurement accuracy.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system performs self-verification by using its own process data and models to validate sensor readings. The verification model automatically detects drifting sensor readings by comparing sensor information against expected values calculated from process parameters and relationships, enabling the system to identify calibration needs without external intervention or scheduled maintenance.

Inventive Principle:
Principle #25Self-service

2Reliability

If interval-based calibration is performed, then sensor device reliability is maintained, but productivity decreases due to frequent maintenance

Engineering Contradiction:
Improvesensor device reliabilityVSAvoidoperational efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The continuous feedback loop constantly monitors sensor readings against expected values and automatically triggers calibration only when verification fails indicate actual sensor drift. This on-demand calibration approach maintains sensor reliability while minimizing operational disruptions, as calibration activities are performed only when necessary rather than following fixed schedules.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system transitions from static, predetermined calibration intervals to dynamic, condition-based calibration timing. The calibration schedule adapts in real-time based on actual sensor performance and process conditions, allowing the system to maintain reliability while optimizing productivity by performing maintenance only when verification failures indicate genuine calibration needs.

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If verification model continuously monitors sensor information, then detection precision of faulty readings improves, but computational load increases

Engineering Contradiction:
Improvedetection precisionVSAvoidcomputational energy
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The verification model applies partial verification by focusing computational resources only on validating specific sensor readings that have verification failures, rather than continuously processing all sensor data at full depth. The system performs lightweight initial checks and only triggers intensive verification when anomalies are detected, reducing overall computational energy consumption while maintaining high detection precision for faulty readings.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4020109B1Method for verifying the plausibility of sensor information in a plant process
Publication Date: 2024.09.11 HACH LANGE HACH LANGE
  • EP4020109B1 patent drawingFigure 1
  • EP4020109B1 patent drawingFigure 2

AI summary

An aspect of the invention relates to a method for verifying the plausibility of sensor information sensed by a sensor device associated with a plant process, in particular a water treatment process and/or a wastewater treatment process, wherein the sensor information relates to the plant process, the method comprising: receiving (S100), by a control unit, the sensor information; performing (S110), by the control unit, a verification model, the verification model determining an expected sensor information of the sensor device based on at least one other information related to the plant process and having a relationship to the sensor information; comparing the expected sensor information with the received sensor information; and upon determining (S120) that the sensor information deviates from the expected sensor information, outputting (S130), by the control unit, a verification signal.