Vibration Trend Monitoring for Early Rotating Machine Failure Alerts
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing machine vibration monitoring systems rely on absolute pre-established alert limits, which are often difficult for users to set and maintain, and fail to provide reliable indications of imminent machine failure without user manipulation.
Innovation Solution
An automated system that monitors the rate of change of vibration values to detect stages of mechanical deterioration, such as in rolling element bearings, without requiring user-set alert levels, by analyzing sustained increases in vibration energy over time using algorithms like curve fitting and PeakVue™ data processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If absolute pre-established alert limits are used for vibration monitoring, then the system can detect gross failures, but it fails to reliably detect progressive deterioration and requires user input and manipulation
Solution Approach 1:
The system automatically determines alert limits by analyzing the machine's own vibration history and operational characteristics. The processor calculates dynamic alert limits based on measured vibration data, eliminating the need for users to manually input or adjust threshold values. This self-configuring approach resolves the contradiction by making the system both reliable (through adaptive limits) and easy to operate (no user manipulation needed).
Solution Approach 2:
The system dynamically changes the alert limit parameter based on the machine's operational state and vibration history. Instead of using fixed absolute thresholds, the alert limits are continuously adjusted according to the measured vibration trends and machine characteristics, enabling reliable detection across varying operating conditions without requiring user intervention to set appropriate thresholds.
2Measurement precision
If narrowband analysis with frequency-specific limits is used, then specific defects can be detected, but the system still relies on pre-established absolute limits that require user input
Solution Approach 1:
The system automatically determines frequency-specific alert limits by analyzing the vibration spectrum and machine operational characteristics. The processor identifies characteristic frequencies and their corresponding alert thresholds without requiring users to manually configure frequency bands or input limit values, thus maintaining high measurement precision while reducing system complexity from the user perspective.
3Loss of time
If trend projection to future vibration values is used, then the system can predict failure timing, but it still requires comparison to absolute pre-established limits
Solution Approach 1:
The system dynamically determines the alert limit parameter for trend projection by analyzing the relationship between vibration trends and machine operational history. Instead of comparing projected values to fixed absolute limits, the system adapts the threshold based on the specific machine's deterioration pattern, improving both the reliability of failure prediction and the timing of maintenance interventions.
Data Source
AI summary
A method for detecting defects in a rotational element of a machine based on changes in measured vibration energy includes: (a) collecting vibration data over an extended period of time using vibration sensors attached to the machine; (b) processing the vibration data to generate a time waveform comprising processed vibration values sampled during sequential sampling time intervals within the extended period of time; (c) detecting multiple time blocks within the extended period of time during which the processed vibration values exhibit sustained increases at progressively increasing rates; and (d) generating alerts based on detection of the multiple time blocks during which the processed vibration values exhibit sustained increases at progressively increasing rates. The multiple time blocks may include a first time block during which the processed vibration values increase at a first rate, and a second time block occurring after the first time block during which the processed vibration values increase at a second rate that is greater than the first rate.