Molding Machine Abnormality Detection Using Statistical Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for setting threshold values to detect operation abnormalities in high-speed molding processes are difficult and operator-dependent, leading to increased risk of mold or machine damage and production stoppages.
Innovation Solution
An operation abnormality detection method that calculates first and second threshold values based on average values and standard deviations, using equations (1) and (2), to easily set appropriate thresholds for detecting abnormalities in movable parts of molding machines.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If high-speed molding is implemented to increase productivity, then manufacturing output increases, but the risk of machine damage and operational abnormalities increases remarkably
Solution Approach 1:
The system performs preliminary actions by continuously monitoring operation values before abnormalities occur, calculating statistical thresholds in advance, and issuing warnings when approaching critical limits, thereby preventing machine damage before it happens during high-speed molding
Solution Approach 2:
The system implements feedback by continuously acquiring operation values from sensors, comparing them against dynamically calculated thresholds based on historical data, and providing real-time warnings when abnormalities are detected, enabling closed-loop control for improved reliability during high-speed operation
2Measurement precision
If threshold values are set manually by skilled workers based on molding conditions, then detection accuracy may be improved, but the workload and complexity of setting appropriate thresholds increases significantly
Solution Approach 1:
The system performs self-service by automatically calculating optimal threshold values using statistical methods on accumulated operation data, eliminating the need for manual threshold setting by skilled workers while maintaining high detection accuracy through data-driven threshold determination
Solution Approach 2:
The system applies parameter changes by dynamically adjusting threshold values based on statistical analysis of operation data, using equations that incorporate standard deviations and multipliers to adapt thresholds to different operating conditions without manual intervention
3Adaptability or versatility
If threshold values are set excessively dependently on operators, then customization to specific molding conditions is achieved, but the ease of operation and reproducibility decreases
Solution Approach 1:
The system achieves self-service by automatically adapting thresholds to specific molding conditions through statistical analysis of operation data, eliminating operator dependency while maintaining customization capabilities through data-driven parameter optimization
Data Source
AI summary
An operation abnormality detection method for detecting an operation abnormality in a molding device having a movable part includes: acquiring a prescribed measured value relating to operation of the movable part and calculating, as statistical information, an average value of prescribed information values based on the prescribed measured values: calculating a first threshold and a second threshold; acquiring a current measured value and comparing a current information value based on the current measured value with the greater of the first threshold and the second threshold; and issuing a warning if the current information value at least exceeds the greater of the first threshold and the second threshold.