Data-Fusion Predictive Maintenance for Vibration-Based Equipment Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional predictive maintenance methods in the petrochemical industry rely solely on equipment signals, neglecting production line schedules and process parameters, leading to misjudgments and failures.
Innovation Solution
An electronic system that integrates first and second vibration sensing devices with a processor to detect time-domain signals, perform data fusion, and train predictive models using process parameters and historical data to diagnose equipment health, incorporating structural vibration transmission characteristics and time-series analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional predictive maintenance methods rely solely on monitoring signals from a single piece of equipment, then the system complexity is low, but the diagnostic accuracy and reliability of maintenance predictions deteriorate due to misjudgments and failures
Solution Approach 1:
The patent merges data from multiple equipment pieces (first equipment and second equipment) and multiple data sources (vibration signals, process parameters, production schedules) into a unified predictive maintenance system. The processor integrates these diverse data streams to comprehensively assess the health status of the target equipment, thereby improving diagnostic accuracy while managing system complexity through systematic data fusion.
Solution Approach 2:
The predictive maintenance system is designed to handle multiple types of data (time-domain vibration signals, process parameters, production schedules) and apply them universally to assess equipment health. The system can monitor multiple equipment pieces simultaneously and provides comprehensive diagnostic capabilities across different equipment types in the production line.
2Reliability
If the system integrates multiple data sources including vibration signals from multiple equipment and process parameters, then the reliability of predictive maintenance improves, but the device complexity increases
Solution Approach 1:
The system combines multiple data sources (vibration signals from first and second equipment, process parameters, production schedules) into a unified analysis framework. The processor integrates these diverse inputs to reliably predict maintenance needs, with the merging of data streams directly improving prediction reliability while the systematic integration approach manages the inherent complexity.
Solution Approach 2:
The processor acts as an intermediary that receives, integrates, and analyzes data from multiple sources before generating maintenance predictions. This intermediary component manages the complexity of data integration by providing a centralized processing mechanism that coordinates information from vibration sensors, process parameters, and production schedules.
3Measurement precision
If the system performs comprehensive data fusion and time-series analysis on multiple signals, then the measurement precision of equipment health assessment improves, but the processing time and complexity increase
Solution Approach 1:
The system performs preliminary processing of vibration signals by extracting features in the time domain before conducting more complex analyses. This preliminary feature extraction prepares the data for subsequent spectral analysis and pattern recognition, improving assessment precision while reducing the computational burden and time required for detailed processing.
Solution Approach 2:
The data processing is segmented into distinct stages: time-domain feature extraction, spectral analysis, and pattern recognition. This segmentation allows the system to process comprehensive data systematically, improving health assessment precision through multi-stage analysis while managing processing time by breaking down complex operations into manageable segments.
Data Source
Figure 1
Figure 2
Figure 3A
AI summary
An electronic system includes a first vibration sensing device, a second vibration sensing device, a database, and a processor. The first vibration sensing device is disposed on a surface of first equipment, and detects a first time-domain vibration signal when the first equipment is operating. The second vibration sensing device is disposed on a surface of second equipment, and detects a second time-domain vibration signal when the second equipment is operating. The database stores process parameters associated with at least one of the first equipment and the second equipment. The processor receives the first time-domain vibration signal, the second time-domain vibration signal, and the process parameters, and trains a predictive model based on the first time-domain vibration signal, the second time-domain vibration signal, and the process parameters. The predictive model diagnoses a health status of the first equipment.