Analytics Avatars for Cross-Platform Industrial Asset Diagnostics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing predictive diagnostics for industrial assets are often developed separately for each asset type, leading to inefficiencies and redundant development across different platforms, such as cloud, edge, and embedded devices, without leveraging previously developed products or solutions.

Innovation Solution

The use of analytics avatars, which are containerized packages of predictive diagnostic components and functions, allowing for reuse and deployment across multiple platforms, including cloud, edge, and embedded devices, by leveraging existing models and components from a repository, and enabling flexible data processing pipelines.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If predictive diagnostics are developed separately for each asset type and platform, then each solution can be optimized for specific requirements, but development time and effort are significantly increased and redundancy occurs

Engineering Contradiction:

Improvepredictive diagnostic accuracyVSAvoiddevelopment time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system segments predictive diagnostic functionality into reusable components called 'analytics avatars' that can be independently developed, stored in a repository, and assembled into customized solutions for different asset types and platforms. This segmentation allows parallel development and reduces redundancy while maintaining solution quality.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Analytics avatars are pre-developed, validated, and stored in a repository before being deployed. These pre-built components contain proven predictive diagnostic logic that can be directly reused across multiple asset types and platforms, eliminating the need to redevelop solutions from scratch and significantly reducing development time.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If predictive diagnostics are customized for each specific asset and platform, then diagnostic accuracy is improved, but system complexity and deployment effort increase

Engineering Contradiction:

Improvediagnostic accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

Analytics avatars are designed as universal, platform-agnostic components that can be deployed across cloud, edge, and embedded devices. Each avatar encapsulates complete predictive diagnostic functionality that adapts to different asset types through configuration rather than code changes, reducing system complexity while maintaining accuracy.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system merges multiple analytics avatars into integrated diagnostic solutions that can handle complex multi-asset monitoring scenarios. This merging approach consolidates redundant logic into shared components while maintaining the ability to customize diagnostic accuracy for specific asset types through selective avatar组合.

Inventive Principle:

Principle #5Merging (Combining)

3Adaptability or versatility

If predictive diagnostic solutions are developed from scratch for each platform, then platform-specific optimization is achieved, but resource utilization and efficiency decrease

Engineering Contradiction:

Improveplatform compatibilityVSAvoiddeployment efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

Analytics avatars are copied from a centralized repository to multiple deployment targets (cloud, edge, embedded devices) without modification to the core diagnostic logic. This copying approach ensures consistent diagnostic accuracy across platforms while eliminating redundant development work and improving deployment efficiency.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system dynamically assigns analytics avatars to different platforms and asset types based on runtime requirements rather than static compilation. This dynamic approach allows the same avatar to serve multiple platforms and asset types, maximizing resource utilization and deployment efficiency while maintaining platform-specific optimization.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentEP4042345B1Automating construction and deployment of predictive models for industrial plant assets

Publication Date: 2025.12.10 SCHNEIDER ELECTRIC SYSTEMS USA INC

Figure 1
Figure 2
Figure 3

AI summary

Systems and methods provide a way for users to leverage existing data-driven models, components, and functions to deploy predictive diagnostics on industrial assets. The systems and methods allow the users to retrieve and assemble existing models, components, and functions into individual packages or containers called "analytics avatars" that can be saved and stored as independent predictive diagnostic units or entities. The analytics avatars can then be deployed on virtually any analytics platforms to provide predictive diagnostics for the industrial assets. The ability to leverage existing predictive diagnostic models and components from plant to plant across different platforms for equipment of the same type provides consistency and reduces the time and effort required to engineer and deploy predictive diagnostics.