Printing Machine Anomaly Detection Using Variable Relationships
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing anomaly detection methods for printing machines and print-processing machines are ineffective in considering the complex relationships between various variables, leading to missed anomalies and unnecessary downtime.
Innovation Solution
A computer-implemented method that considers the second data points of a second variable during anomaly detection of the first data points of a first variable, allowing for contextual analysis and detection of anomalies that may not be apparent in univariate or multivariate analyses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If univariate anomaly detection is used to analyze only one variable at a time, then the anomaly detection process is simple and fast, but it cannot detect anomalies that are only apparent when considering relationships between multiple variables
Solution Approach 1:
The patent segments the anomaly detection process into two distinct phases: (1) a fast univariate filtering phase that quickly identifies potential anomalies in individual variables, and (2) a more comprehensive multivariate analysis phase that examines relationships between variables. This segmentation allows the system to maintain high detection speed while improving accuracy by considering variable relationships when needed.
Solution Approach 2:
The patent applies partial action by not performing full multivariate analysis on all data points continuously. Instead, it uses univariate detection as a screening mechanism and only applies more resource-intensive multivariate analysis when anomalies are suspected, thus balancing speed and accuracy without the excessive computational cost of continuous multivariate analysis.
2Measurement precision
If multivariate anomaly detection is used to analyze multiple variables simultaneously, then the anomaly detection accuracy is improved by considering variable relationships, but the computational complexity and processing time increase significantly
Solution Approach 1:
The patent segments the anomaly detection process into two distinct phases: (1) a fast univariate filtering phase that quickly identifies potential anomalies in individual variables, and (2) a more comprehensive multivariate analysis phase that examines relationships between variables. This segmentation allows the system to maintain high detection speed while improving accuracy by considering variable relationships when needed.
Solution Approach 2:
The patent applies partial action by not performing full multivariate analysis on all data points continuously. Instead, it uses univariate detection as a screening mechanism and only applies more resource-intensive multivariate analysis when anomalies are suspected, thus balancing speed and accuracy without the excessive computational cost of continuous multivariate analysis.
3Productivity
If anomaly detection considers only individual variables in isolation, then the processing is computationally efficient, but it fails to account for the strong variations in variables due to different production demands, materials, and states
Solution Approach 1:
The patent segments the anomaly detection process into two distinct phases: (1) a fast univariate filtering phase that quickly identifies potential anomalies in individual variables, and (2) a more comprehensive multivariate analysis phase that examines relationships between variables. This segmentation allows the system to maintain high detection speed while improving accuracy by considering variable relationships when needed.
Solution Approach 2:
The patent applies partial action by not performing full multivariate analysis on all data points continuously. Instead, it uses univariate detection as a screening mechanism and only applies more resource-intensive multivariate analysis when anomalies are suspected, thus balancing speed and accuracy without the excessive computational cost of continuous multivariate analysis.
4Adaptability or versatility
If the anomaly detection method is designed to work across different production states and consumables, then the versatility is improved, but the complexity of accommodating variable relationships increases
Solution Approach 1:
The patent implements a universal anomaly detection framework that can handle multiple production states and consumable types through a standardized two-phase approach. The system maintains adaptability by allowing configuration of variable relationships specific to different production contexts while using the same core detection methodology, thus achieving multi-functionality without proportionally increasing complexity.
Data Source
AI summary
The invention relates to a computer-implemented method for the evaluation of data, wherein the method comprises: receiving a data set from at least one component of a printing machine or a print-processing machine, wherein the data set comprises a first variable with a plurality of first data points and at least one second variable with a plurality of second data points, carrying out a computer-implemented anomaly detection of the first data points of the first variable for determining at least one anomaly. The invention is thus based on the object of finding a solution, in the case of which the anomaly detection can be applied for different production states and when using different consumables. The object is solved according to the invention in that at least the second data points of the second variable are considered during the computer-implemented anomaly detection of the first data points of the first variable.