Classifier-Based Process Variable Measurement Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Field devices used to determine process variables often have varying measurement accuracies and reliabilities across different media and applications, with some methods being unsuitable for specific conditions, leading to incomplete or inaccurate data.

Innovation Solution

A method employing a classifier that uses artificial intelligence to select the most accurate value for a process variable from multiple measurement methods based on predefinable physical and chemical properties of the medium, allowing for automatic selection and adaptation to different applications, including offline and online training options.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a single measurement method is used for determining a process variable, then the device complexity is reduced, but the measurement precision and reliability vary significantly across different media and applications

Engineering Contradiction:
Improvemeasurement accuracyVSAvoiddevice complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The field device is equipped with multiple measurement methods (first method and second method) for determining the same process variable, enabling the device to handle diverse media and applications universally. The classifier automatically selects the appropriate measurement method based on medium properties, making a single device suitable for multiple applications without requiring separate specialized devices for each measurement scenario.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Reliability

If multiple measurement methods are employed for the same process variable, then the measurement precision and reliability are improved, but the device complexity increases

Engineering Contradiction:
ImprovereliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The classifier automatically evaluates medium properties (such as conductivity, viscosity, or other predefinable properties) and autonomously selects the most appropriate measurement method from the available options. This self-service mechanism eliminates the need for manual configuration or complex control systems, allowing the device to reliably adapt to different media while keeping the operational complexity manageable through automated decision-making.

Inventive Principle:
Principle #25Self-service

3Adaptability or versatility

If a classifier with AI is implemented to select measurement methods, then the adaptability to different applications is enhanced, but the device complexity and computational requirements increase

Engineering Contradiction:
Improvefield of applicationVSAvoiddevice complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The classifier is pre-trained with knowledge about the characteristics of different media and the suitability of various measurement methods for specific medium properties. This preliminary preparation allows the classifier to quickly and accurately select the appropriate measurement method when deployed, enhancing adaptability without requiring complex real-time computations or extensive training data during operation. The heavy computational work is performed in advance during the training phase.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11656115B2Method for determining a process variable with a classifier for selecting a measuring method
Publication Date: 2023.05.23 ENDRESS & HAUSER GMBH & CO KG
  • US11656115B2 patent drawing
  • US11656115B2 patent drawing
  • US11656115B2 patent drawing

AI summary

The present disclosure relates to a method for determining at least one process variable of a medium. The method includes steps of recording a first value for the process variable by means of a first method for determining the process variable and recording a second value for the process variable by means of a second method for determining the process variable. The method also includes steps of selecting at least one of the detected values for the process variable by means of a classifier and outputting the selected value for the process variable. The present disclosure further relates to a computer program designed for executing a method according to the present disclosure, and to a computer program product having a computer program according to the present disclosure.