Software Output Clustering for Control Abnormality Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing techniques primarily focus on detecting abnormalities in control objects rather than control software, which can lead to erroneous control commands due to software updates, and do not effectively address processing abnormalities in control software.

Innovation Solution

An abnormality detection device that clusters output data series from software, determines normal data within clusters, and identifies data not included in any cluster as abnormal, allowing for the detection of processing abnormalities in software.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If clustering-based abnormality detection is applied to software output data, then software processing abnormalities can be detected, but the device complexity increases

Engineering Contradiction:

Improvesoftware abnormality detection capabilityVSAvoiddetection system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The detection device is divided into distinct functional modules: a data acquisition unit that collects software output data, a clustering unit that groups normal data patterns, and a determination unit that compares new data against clusters. This segmentation allows the complex detection function to be implemented through simple, modular components that can be independently developed and maintained.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The clustering unit pre-processes and stores normal data patterns from software output before actual abnormality detection occurs. By establishing reference clusters of normal behavior in advance, the system creates a baseline against which future data can be quickly compared, enabling rapid abnormality detection without complex real-time analysis.

Inventive Principle:

Principle #10Preliminary action

2Adaptability or versatility

If frequent software updates are performed to improve functionality, then adaptability increases, but the likelihood of mounting errors and processing abnormalities increases

Engineering Contradiction:

Improvesoftware update capabilityVSAvoidsoftware operation accuracy

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The determination unit continuously monitors software output data and provides feedback by identifying when data falls outside established clusters. This feedback mechanism allows the system to detect mounting errors or processing abnormalities that occur during software updates, enabling timely intervention before erroneous control commands are executed.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system proactively detects abnormalities in software output before they result in harmful control commands being sent to the control object. By establishing clusters of normal data patterns and continuously comparing new output against these clusters, the system prevents erroneous operations by identifying software faults early in the process.

Inventive Principle:

Principle #9Preliminary anti-action

Data Source

PatentUS10956251B2Abnormality detection device

Publication Date: 2021.03.23 HITACHI LTD

AI summary

An object of the invention is to provide an abnormality detection device that can detect a processing abnormality of various types of software. The abnormality detection device according to the invention divides an output data series which is output by software into one or more clusters, determines that the output data included in any cluster is normal, and determines that the output data not included in any cluster is abnormal.