AI Sensor Assembly Signature Checking for Fail-Safe Monitoring

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing sensor arrangements in industrial applications, particularly in safety technology, face challenges in ensuring high reliability and fail-safety due to complex calculation methods and vulnerabilities to component-related failures and external influences, which can lead to errors in monitoring and automation functions.

Innovation Solution

A sensor arrangement utilizing AI processing algorithms with signature calculation and comparison for error checking, along with a multi-channel evaluation system, to enhance reliability and fail-safety by adapting to changing conditions and detecting errors caused by component failures or external influences.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If complex calculation methods are used to generate monitoring functions from sensor readings, then the reliability and fault tolerance of the sensor array is improved, but the device complexity and computational requirements increase

Engineering Contradiction:
Improvefault toleranceVSAvoidcalculation complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The sensor array is divided into multiple independent sensor units, each with its own processing capabilities. The monitoring area is segmented into multiple zones that can be independently evaluated. This segmentation allows the complex monitoring task to be distributed across multiple simpler processing units, improving reliability through redundancy while managing complexity through modular design.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

A central control unit acts as an intermediary that receives data from multiple sensors, performs the complex calculations for determining monitoring functions, and coordinates the safety responses. This intermediary approach centralizes the computational complexity in a dedicated unit while keeping individual sensor units simpler, thereby improving overall system reliability without excessively increasing the complexity of each component.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If the protective field is adapted to current driving situations using measured values, then the automation function and monitoring accuracy are improved, but the calculation complexity and processing time increase

Engineering Contradiction:
Improvemonitoring accuracyVSAvoidprocessing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The protective field parameters are made dynamic and adaptable to current driving situations. The sensor array continuously adjusts the monitoring zones based on real-time measured values from sensors, the driver's position, and the automated guided vehicle's state. This dynamic adaptation improves monitoring accuracy while the modular architecture manages processing complexity through distributed computation.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system pre-defines multiple protective field configurations and monitoring scenarios that can be quickly activated based on the current driving situation. Instead of calculating optimal protective field parameters in real-time, the system selects from pre-computed configurations, thereby improving response speed and reducing processing complexity while maintaining high monitoring accuracy through situation-appropriate selections.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If signature calculation and error checking are implemented for AI processing algorithms, then the reliability and error detection capability are improved, but the computational overhead and processing time increase

Engineering Contradiction:
Improveerror detection capabilityVSAvoidprocessing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

Signature calculation and error checking are performed periodically at specific intervals rather than continuously for every data point. The system calculates signatures for monitoring zones and evaluates them at defined processing cycles, which maintains reliable error detection capability while significantly reducing the computational overhead and processing time compared to continuous verification.

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

Instead of performing complex error checking calculations on the actual sensor data, the system creates simplified signature representations (checksums or hash values) of the data and processing results. These signatures are much smaller and faster to compute and verify, enabling efficient error detection with minimal computational overhead while maintaining high reliability through the mathematical properties of signature algorithms.

Inventive Principle:
Principle #26Copying

Data Source

PatentEP4098928A1Sensor assembly and method for operating a sensor assembly
Publication Date: 2022.12.07 LEUZE ELECTRONIC GMBH & CO KG
  • EP4098928A1 patent drawingFigure 1~2
  • EP4098928A1 patent drawingFigure 3
  • EP4098928A1 patent drawingFigure 4

AI summary

The invention relates to a sensor arrangement (1) with at least one sensor (2) for detecting objects in a monitoring area, wherein sensor signals from the at least one sensor (2) are supplied to at least one processing unit with an AI (Artificial Intelligence) processing algorithm (212, 222). An output signal of the sensor arrangement (1) is generated as an overall result from the processing results generated in the processing unit. Signatures are calculated for calculation parameters of the AI ​​(Artificial Intelligence) processing algorithm (212, 222), which are compared with predefined target values ​​to perform error checks. The invention further relates to a corresponding method.