Telemetry-Based Asset Optimization for Adaptive Maintenance Software

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing asset performance monitoring systems fail to adapt to changing user needs and asset conditions, leading to outdated analytics and maintenance strategies that do not optimize asset functionality and longevity effectively.

Innovation Solution

The Asset Performance Optimization System (APS) utilizes a recommendation engine that combines asset data, telemetry data, user intent, and purchase history to recommend software upgrades and maintenance actions, ensuring optimal monitoring and maintenance of assets by identifying issues and providing targeted software packages for improvement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional asset performance monitoring systems are used, then basic monitoring functionality is provided, but the systems cannot adapt to changing user needs and asset conditions, resulting in outdated analytics and maintenance strategies

Engineering Contradiction:
Improveadaptability to changing user needs and asset conditionsVSAvoidoutdated analytics and maintenance strategies
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system transitions from static monitoring to dynamic adaptation by continuously learning from asset data, user interactions, and maintenance outcomes. The machine learning models are retrained periodically to adapt to changing asset conditions and user needs, ensuring analytics remain current and reliable.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system implements feedback loops where maintenance outcomes and asset performance data are fed back into the machine learning models. This feedback mechanism allows the system to learn from past maintenance actions and their results, continuously improving the reliability of analytics and maintenance strategy recommendations.

Inventive Principle:
Principle #23Feedback

2Measurement precision

If comprehensive asset monitoring is implemented, then asset performance and health can be tracked, but the system lacks the capability to provide customized recommendations and software optimization

Engineering Contradiction:
Improveasset performance monitoring accuracyVSAvoidcustomized recommendations and software optimization
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system automatically generates customized maintenance recommendations and software optimization suggestions without requiring manual expert intervention. The machine learning models analyze asset data and autonomously produce tailored recommendations, making the system both precise in monitoring and easy to operate for users.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system dynamically adjusts monitoring parameters and recommendation thresholds based on asset-specific characteristics and performance patterns. This allows the system to provide precise monitoring adapted to each asset's unique parameters while automatically generating customized recommendations without manual configuration.

Inventive Principle:
Principle #35Parameter changes

3Productivity

If manual maintenance strategies are used, then basic maintenance can be performed, but production downtime increases and asset longevity is not optimized

Engineering Contradiction:
Improveproduction outputVSAvoidproduction downtime
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary maintenance actions by predicting asset failures before they occur. The machine learning models analyze current asset conditions and forecast potential issues, enabling maintenance to be scheduled proactively during planned downtime rather than causing unexpected production interruptions.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system maintains continuous asset monitoring and performance optimization, ensuring assets operate at peak efficiency throughout their lifecycle. By continuously analyzing asset data and adjusting maintenance strategies, the system maximizes productive operation time while minimizing unplanned downtime.

Inventive Principle:
Principle #20Continuity of useful action

4Ease of manufacture

If generic maintenance approaches are applied, then maintenance can be performed across multiple assets, but maintenance costs increase and asset-specific optimization is lost

Engineering Contradiction:
Improvemaintenance scalabilityVSAvoidasset-specific optimization
Core Design Contradiction:
Ease of manufactureVSReliability

Solution Approach 1:

The system applies local quality by generating maintenance recommendations tailored to each asset's specific characteristics, performance patterns, and operational context. The machine learning models analyze asset-specific data to produce customized maintenance strategies that optimize each asset individually while maintaining scalable deployment across multiple assets through automated processing.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4235537A1Customized asset performance optimization and marketplace
Publication Date: 2023.08.30 HONEYWELL INTERNATIONAL INC
  • EP4235537A1 patent drawingFigure 1
  • EP4235537A1 patent drawingFigure 2
  • EP4235537A1 patent drawingFigure 3

AI summary

Various embodiments for a customized asset performance system and marketplace are described herein. An embodiment operates by receiving asset data indicating one or more assets that are being monitored by a control system. Telemetry data for at least a first asset is received, the telemetry data including data corresponding to a previous functionality of the asset over a specified period of time. The telemetry data is compared to an expected functionality over the specified period of time. A problem with the first asset is identified based on the comparing. One or more software packages that are configured to address the problem with the first asset are identified based on comparing the telemetry data to an expected functionality of the first asset over the specified period of time. A selection of a first software package from the one more software packages is received and the selected first software package is updated.