Machine Control for Targeted Moving-Part Anomaly Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing predictive maintenance techniques require significant resources and expertise, as they often involve collecting and analyzing data from all moving parts, which is inefficient and costly.
Innovation Solution
A control system that identifies and collects data only from moving parts that have caused abnormalities, reducing resource usage and enabling more efficient predictive maintenance by focusing on specific faulty components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data on all moving parts is collected for predictive maintenance, then the accuracy of abnormality detection is improved, but the resource consumption increases significantly
Solution Approach 1:
The patent extracts and collects only the data necessary for predictive maintenance - specifically abnormality signs and operation periods of individual moving parts - rather than collecting data on all moving parts. This selective extraction reduces data volume while maintaining detection accuracy by focusing on relevant information.
Solution Approach 2:
The patent segments the monitoring system to handle each moving part independently, collecting data on abnormality signs and operation periods separately for each part. This segmentation allows the system to process and analyze data from specific moving parts that show abnormalities without being burdened by data from all moving parts.
2Reliability
If data on all operation periods of moving parts is collected, then the predictive maintenance coverage is improved, but the storage requirements and processing time increase
Solution Approach 1:
The patent performs preliminary identification of moving parts that have caused abnormalities before collecting their operation period data. By first detecting abnormality signs and identifying the responsible moving parts, the system prepares in advance to collect only the relevant operation period data, avoiding the need to process all operation period data from all moving parts.
Solution Approach 2:
The patent extracts only the operation period data from moving parts that have been identified as causing abnormalities, rather than collecting operation period data from all moving parts. This extraction approach maintains comprehensive coverage of abnormality causes while significantly reducing storage requirements and processing time.
3Measurement precision
If statistical processing is performed on measured values of all diagnosis targets, then the correct answer rate is improved, but the computational resources required increase
Solution Approach 1:
The patent extracts and performs statistical processing only on measured values from moving parts that have caused abnormalities, rather than processing data from all diagnosis targets. This selective processing maintains the correct answer rate by focusing on relevant data while significantly reducing computational resource requirements.
Solution Approach 2:
The patent applies partial statistical processing to only the necessary subset of data - specifically the measured values from moving parts identified as abnormality causes - rather than performing exhaustive processing on all available data. This partial action achieves the required diagnostic accuracy with reduced computational effort.
Data Source
Figure 1
Figure 2(a)~2(e)
Figure 3
AI summary
A control system (1) according to the present invention comprises: a control device (100) that monitors the operation of a plurality of moving parts for machining a workpiece (155), and controls the operation of the plurality of moving parts in each control cycle by issuing command values to the plurality of moving parts; and an inspection device (200) for inspecting the workpiece (155). The control device (100) comprises: an identification unit (160) for identifying, on the basis of inspection results of the inspection device (200) and the command values issued to the plurality of moving parts, which moving part from among the plurality of moving parts caused an anomaly in the inspection results; and a storage unit (170) for collecting and storing data on the moving part that was identified by the identification unit (160) and caused the anomaly in the inspection results.