Aggregated Asset Risk Modeling With Predictive Confidence Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional techniques for monitoring and analyzing assets are inaccurate and inconsistent due to reliance on operator opinions, leading to reduced asset uptime and increased maintenance costs, as they fail to provide accurate and useful risk assessments.
Innovation Solution
A computing system that utilizes predictive models to determine aggregated risk values for assets by evaluating operating data, outputting confidence and severity values, and combining them with a risk dataset to provide objective and customizable risk assessments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional techniques rely on individual machinery operator opinions for risk assessment, then the system is simple to operate, but the measurement precision and reliability of risk assessment deteriorate due to inconsistency and inaccuracy
Solution Approach 1:
The patent replaces the mechanical system of human operator judgment with an automated computing system that executes predictive models. The computing system processes operating data through multiple predictive models to generate confidence values and severity values, which are then combined to produce aggregated risk values. This substitution eliminates the inconsistency and inaccuracy of human opinion while maintaining operational simplicity through automated execution.
Solution Approach 2:
The patent introduces a computing system as an intermediary between the raw operating data and the final risk assessment. This intermediary executes predictive models that transform operating data into confidence values and severity values, which are then synthesized into aggregated risk values. The intermediary layer ensures consistent, objective, and accurate risk assessment while preserving the simplicity of the overall system through automation.
2Reliability
If conventional techniques combine operator opinions with model-based predictions, then the system maintains ease of operation, but the reliability of risk assessment deteriorates due to low-confidence predictions
Solution Approach 1:
The patent replaces the manual process of combining operator opinions with model predictions with an automated computing system. The system executes multiple predictive models, generates confidence values for each prediction, and synthesizes these with severity values to produce aggregated risk values. This automation maintains operational simplicity while significantly improving reliability by eliminating the subjectivity and low confidence associated with human judgment and single-model predictions.
Solution Approach 2:
The patent merges multiple predictive model outputs into a single aggregated risk value. By combining confidence values from multiple models with severity values, the system produces a comprehensive risk assessment that is more reliable than any single model or operator opinion alone. The merging process is automated, maintaining ease of operation while enhancing reliability through synthesis of multiple independent predictions.
3Measurement precision
If the system uses multiple predictive models with confidence and severity values, then the risk assessment accuracy improves, but the device complexity increases
Solution Approach 1:
The patent segments the risk assessment process into distinct components: multiple predictive models each evaluating specific portions of operating data, generating confidence values and severity values independently. This segmentation allows each model to specialize in specific aspects of asset condition monitoring, improving overall accuracy while the modular structure manages computational complexity through organized, independent processing units.
Solution Approach 2:
The computing system performs multiple functions through the predictive models: evaluating different portions of operating data, generating confidence values, generating severity values, and synthesizing aggregated risk values. This multi-functionality improves risk determination accuracy by comprehensively analyzing various aspects of asset condition while managing complexity through a unified automated platform that handles all functions systematically.
Data Source
AI summary
Computing systems and methods for determining aggregated risk are disclosed herein. An exemplary computing platform includes: a communication interface, one or more processors, a non-transitory computer-readable medium, and program instructions stored on the non-transitory computer-readable medium. The program instructions, when executed, cause the computing platform to: execute a set of predictive models that are each configured to (i) evaluate operating data for the asset and (ii) output a respective prediction related to an operation of the asset; detect a triggering event for determining an aggregated risk value for the asset; identify (i) a set of predictions related to the operation of the asset and (ii) a risk dataset; determine the aggregated risk value of the asset based on the set of predictions and the risk dataset; and cause a client device to display a visual representation of the aggregated risk value.