Local Analytics Device for Asset Predictive Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current asset-monitoring systems are typically reactionary, leading to costly downtime due to network latency and inefficiencies in local diagnostic procedures, as they rely on remote computing systems for monitoring and diagnosis, which can be hindered by communication network issues and require a mechanic's presence.
Innovation Solution
A network configuration that facilitates secure communication between assets and a remote computing system, enabling the deployment of predictive models and workflows to assets for proactive monitoring and diagnosis, using a local analytics device to execute model-workflow pairs and adapt to conditions, reducing reliance on remote systems and minimizing downtime.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If remote computing systems are used for asset monitoring and diagnosis, then centralized control and data processing are achieved, but network latency and communication issues cause delays in detecting and responding to abnormal conditions
Solution Approach 1:
The patent divides the monitoring system into local and remote segments. The local analytics device executes predictive models and workflows directly at the asset location, while the remote computing system handles aggregate data processing and model updates. This segmentation enables immediate local response to abnormal conditions without waiting for remote system communication, thereby reducing detection time while maintaining centralized control capabilities.
Solution Approach 2:
The patent implements preliminary action by deploying predictive models and workflows to the local analytics device before abnormal conditions occur. These pre-configured models continuously analyze sensor data and can automatically trigger diagnostic tools and maintenance workflows locally, eliminating the need to wait for remote system instructions and enabling proactive maintenance before failures occur.
2Ease of operation
If local diagnostic tools are stored on assets, then on-site diagnosis capability is provided, but the process becomes inefficient and cumbersome requiring a mechanic's presence to execute tools
Solution Approach 1:
The patent implements self-service by enabling the local analytics device to automatically execute predictive models and diagnostic workflows without requiring a mechanic's presence. The system autonomously monitors asset conditions, detects abnormalities, runs appropriate diagnostic workflows, and generates maintenance recommendations, transforming the diagnostic process from a manual mechanic-driven task to an automated self-diagnosing system that improves both accessibility and efficiency.
3Ease of manufacture
If simple on-asset abnormality detection mechanisms are used, then the system is easy to implement, but network dependency and simplistic detection algorithms lead to reactionary rather than proactive monitoring
Solution Approach 1:
The patent applies preliminary action by pre-deploying sophisticated predictive models to the local analytics device. These models are trained on historical asset data and can predict future failures before they occur. The local device continuously executes these models with current sensor data, enabling proactive identification of potential issues without requiring complex remote processing or network communication for each analysis cycle.
Solution Approach 2:
The local analytics device serves as an intermediary between the simple sensor inputs and the complex remote computing system. It performs sophisticated local data processing and predictive analysis, then communicates only essential results or anomalies to the remote system. This intermediary approach maintains system simplicity at the asset level while achieving advanced monitoring effectiveness through the local device's computational capabilities.
Data Source
AI summary
Disclosed herein are systems, devices, and methods related to assets and predictive models and corresponding workflows that are related to the operation of assets. In particular, examples involve assets configured to receive and locally execute predictive models, locally individualize predictive models, and/or locally execute workflows or portions thereof.