Packaging Machine Fault Prediction Using Motion Data Dispersion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current condition monitoring methods for packaging machines with independently moving objects are complex and inaccurate, particularly when dealing with variable speed profiles, leading to sub-optimal fault prediction and increased maintenance costs.
Innovation Solution
A method involving data registration, distribution analysis, and dispersion measurement to predict faults in packaging machines, which includes calculating a measure of central tendency and shape of motion data, associating these with condition parameters, and comparing dispersion trends over time to determine potential wear or faults.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If frequency analysis is used to characterize bearing faults, then fault detection capability is improved, but the complexity of implementation increases and accuracy decreases for variable speed systems
Solution Approach 1:
The patent extracts only the essential features needed for fault detection by using statistical parameters (mean, standard deviation, skewness, kurtosis) of vibration signals instead of performing full frequency analysis. This extraction approach maintains fault detection capability while significantly reducing computational complexity and eliminating the need for complex signal processing algorithms.
Solution Approach 2:
The patent changes the parameter domain from frequency domain (requiring FFT and complex analysis) to time domain statistical parameters. By monitoring changes in statistical characteristics of vibration signals over time, the system achieves accurate fault detection without the computational burden of frequency analysis, especially for variable speed conditions where frequency methods struggle.
2Ease of manufacture
If constant speed assumption is made for fault analysis, then calculation simplicity is improved, but accuracy deteriorates for independently movable objects with variable speed profiles
Solution Approach 1:
The patent transitions from static analysis (constant speed assumption) to dynamic analysis by continuously monitoring vibration signals at variable speeds. The statistical parameter approach adapts to changing speed conditions in real-time, allowing accurate fault detection throughout the entire operational range of independently movable objects without requiring speed normalization or complex dynamic models.
Solution Approach 2:
The system implements continuous monitoring of vibration signals and statistical parameters during operation, providing real-time feedback on component condition. This feedback mechanism allows the system to adapt to variable speed profiles and detect faults dynamically, eliminating the need for constant speed assumptions while maintaining calculation simplicity through straightforward statistical computations.
3Ease of operation
If empirical evaluation of vibration levels is performed, then fault assessment is simplified, but accuracy significantly deteriorates leading to underestimation or overestimation of remaining lifetime
Solution Approach 1:
The patent replaces subjective empirical evaluation with objective statistical analysis of vibration signals. By computing statistical parameters (mean, standard deviation, skewness, kurtosis) and monitoring their evolution over time, the system provides quantifiable and accurate predictions of component remaining lifetime, eliminating the inaccuracies inherent in empirical methods while maintaining ease of operation through automated computation.
Data Source
AI summary
A method and system of fault prediction in a packaging machine is disclosed. The method comprises registering data values associated with the motion of independently movable objects along a track in the packaging machine; determining a distribution of the data values; calculating a measure of central tendency of the data values in the distribution; calculating a quantified measure of a shape of the distribution; associating the measure of central tendency with said quantified measure of the shape as a coupled set of condition parameters; determining a degree of dispersion of a plurality of coupled sets of condition parameters associated with a plurality of motion cycles of the independently movable objects; and comparing the degree of dispersion with a dispersion threshold value, or determining a trend of the degree of dispersion over time, for said fault prediction.