Machine Operation Anomaly Detection With Automated Thresholding

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional methods for monitoring machine systems, such as those in food and beverage packaging, are time-consuming and unreliable, often detecting anomalies too late or failing to identify subtle changes due to manual threshold settings and lack of real-time, automated anomaly detection.

Innovation Solution

A method involving signal acquisition, categorization, feature extraction, correlation analysis, and automated threshold setting to detect anomalies in machine operation, using statistical methods like kernel density estimation for precise threshold determination.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual inspections and simple alarm systems are used, then device complexity is reduced, but anomaly detection reliability deteriorates

Engineering Contradiction:
Improveanomaly detection reliabilityVSAvoidmonitoring system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system automatically categorizes signals into process type groups and determines threshold values without manual intervention. The computer device autonomously performs feature extraction, correlation analysis, and threshold determination, eliminating the need for manual inspections while maintaining high detection reliability.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

Manual inspection methods are replaced with automated computational analysis. The system uses computer-based signal processing, statistical analysis, and automated threshold determination to substitute human operators and simple alarm systems, achieving both high reliability and automated operation.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If automated anomaly detection is implemented, then anomaly detection reliability improves, but loss of time increases due to data processing

Engineering Contradiction:
Improveanomaly detection reliabilityVSAvoiddata processing time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs feature extraction and correlation analysis on historical signal data during a reference period before actual monitoring begins. This preliminary processing establishes baseline characteristics and threshold values in advance, enabling rapid real-time anomaly detection without extensive processing delays during operation.

Inventive Principle:
Principle #10Preliminary action

3Measurement precision

If manual threshold setting is used, then device complexity is reduced, but measurement precision deteriorates

Engineering Contradiction:
Improvethreshold determination precisionVSAvoidthreshold setting complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

Manual threshold setting is replaced with automated statistical analysis. The computer device performs correlation analysis on extracted features and automatically determines optimal threshold values based on the data, eliminating subjectivity and improving precision while managing complexity through software automation.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentEP4692972A1Automatic detection of an anomaly in a machine operation
Publication Date: 2026.02.11 KRONES AG
  • EP4692972A1 patent drawingFigure 1
  • EP4692972A1 patent drawingFigure 2
  • EP4692972A1 patent drawingFigure 3

AI summary

The invention relates to a method, a computer device, and a system for automatically detecting anomalies in machine operation. The machine operation in question is, in particular, that of machines for filling and packaging food and/or beverages. Anomaly detection comprises the acquisition of sensor data, the automatic categorization of this data according to operating states, and the extraction of relevant features for each category of operating states. Thresholds are determined using statistical methods to define precise operating limits. This model is monitored and adapted to react to anomalies at an early stage and to ensure operational safety. The invention provides a robust monitoring system that enables real-time monitoring of the machine system's condition and allows for early responses to deviations in operating conditions.This contributes to increased operational reliability, avoidance of downtime and optimization of maintenance processes.