Facility Asset Representation Using Telemetry for Predictive Maintenance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manual assessment of asset links and relations in facilities is cumbersome and error-prone, leading to undetected faults, failures, and inefficiencies, which complicates facility management.
Innovation Solution
An IoT platform generates dynamic representations of assets using real-time models and visual analytics, integrating telemetry data and static parameters to predict maintenance requirements and optimize asset performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual assessment of asset links and relations is performed, then expertise-based analysis can be achieved, but the process becomes cumbersome and error-prone
Solution Approach 1:
The patent replaces manual mechanical assessment processes with automated computational systems. The system uses processors to automatically discover, model, and analyze asset relationships through executed instructions, eliminating the need for manual expert assessment while maintaining or improving accuracy and reducing time consumption.
Solution Approach 2:
The patent introduces an intermediary computational system that acts as a mediator between raw asset data and meaningful insights. This system automatically discovers relationships, builds models, and generates analyses, serving as an intermediate layer that transforms unstructured data into actionable intelligence without requiring direct manual intervention.
2Reliability
If manual assessment of asset links is performed, then detailed analysis can be achieved, but faults and failures go undetected
Solution Approach 1:
The patent segments the complex assessment process into distinct automated components: relationship discovery, model building, and analysis generation. Each segment is handled by specific instructional routines executed by processors, breaking down the overwhelming complexity into manageable, automated tasks that collectively improve fault detection capability.
Solution Approach 2:
The system implements feedback mechanisms where the automated analysis results are continuously refined and used to improve subsequent assessments. The system learns from discovered relationships and adjusts its modeling approaches, creating a feedback loop that enhances reliability while managing complexity through iterative improvement.
3Loss of information
If comprehensive asset relationship analysis is performed, then insights can be derived, but the process becomes cumbersome
Solution Approach 1:
The system performs self-service by automatically discovering asset relationships, building models, and generating insights without requiring manual operation. The computational system independently executes instructions to analyze data, create relationships, and produce comprehensive insights, eliminating the cumbersome manual processes while maintaining information completeness.
Solution Approach 2:
The system performs preliminary actions by pre-establishing asset models and relationships before actual analysis is needed. The computational system proactively discovers and stores relationship patterns, so when analysis is required, the groundwork is already in place, reducing the operational burden while ensuring comprehensive insight generation.
Data Source
AI summary
Various embodiments described herein relate to systems and methods for providing dynamic representation of assets in a facility. In this regard, a first vector for an asset from amongst a plurality of assets in a facility is determined. The first vector is derived from one or more static parameters associated with the asset. Further, telemetry data from the asset is received in the facility. In this regard, telemetry data includes a plurality of readings from the asset at a plurality of timestamps and each reading from amongst the plurality of readings is received at a respective timestamp. A second vector for the asset at each of the plurality of timestamps is determined. The second vector includes a product of the first vector and a corresponding reading at the respective timestamp. The second vector at each of the plurality of timestamps is convoluted to obtain a dynamic representation of the asset. The dynamic representation of the asset is used to predict a maintenance requirement for the asset.