Machine Heartbeat Generation via Event Duration Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing predictive methods for monitoring machinery and automated processes fail to sufficiently discriminate sources of variation, leading to inadequate prediction of conditions requiring intervention to prevent downtime, productivity loss, or quality issues.
Innovation Solution
A system and method for generating a 'machine heartbeat' by analyzing the durations of timed events in a process sequence, allowing for the comparison of event durations across cycles to identify trends and initiate preventive or predictive maintenance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional predictive methods (vibration analysis) are used to monitor machinery, then monitoring capability is provided, but discrimination of variation sources is insufficient leading to inadequate prediction accuracy
Solution Approach 1:
The patent segments the process monitoring into multiple discrete timed events within a process cycle. Each event's duration is measured and stored as a separate data point, allowing individual analysis of variation sources for each event rather than treating the entire process as a single measurement unit.
Solution Approach 2:
The patent adds temporal dimensionality by creating a sequence of event durations across multiple process cycles. This transforms single-point vibration measurements into multi-dimensional time-series data, enabling trend analysis and better discrimination of variation sources through temporal patterns.
2Reliability
If event duration monitoring is implemented across multiple process cycles, then predictive capability is improved, but data collection and processing complexity increases
Solution Approach 1:
The system uses the process machinery's own operational data (event durations) to monitor its own health and predict failures. The controller automatically captures timing information from process events without requiring external monitoring equipment, making the system self-diagnostic and reducing overall complexity.
Solution Approach 2:
The system implements feedback by comparing actual event durations against baseline values and using this comparison to generate predictions about process conditions. The controller continuously monitors duration variations and feeds this information back into the prediction algorithm, creating a closed-loop predictive system.
Data Source
AI summary
A method and system for generating a heartbeat of a process including at least one machine configured to perform a process cycle consisting of timed events performed in a process sequence includes determining the duration of each timed event during performance of the process cycle, ordering the durations of the timed events in the process sequence, and generating a heartbeat defined by the ordered durations of a process cycle. One or more process parameters can be sensed and displayed with the heartbeat in real time. The variance of a current heartbeat to a baseline heartbeat and/or a comparison of a process parameter to a parameter limit can be analyzed to monitor and/or control the process or machine. The heartbeat, the process parameter corresponding to the heartbeat can be displayed on a user interface which can include a message corresponding to the heartbeat and/or the process parameter.