Interactive Simulation Training Assessment with Root-Cause Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing interactive computer simulation systems face challenges in providing comprehensive and objective assessments of user performance due to inconsistencies in data collection and subjective evaluations, leading to potential discrepancies in training quality and effectiveness.

Innovation Solution

A simulation mapping system and method that constructs a dataset of performance metrics by synchronizing dynamic data from multiple subsystems, inferring missing data, and applying linear quadratic estimation or probabilistic directed acyclic graphical models to provide standardized grading and identify root causes of performance issues.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If data is collected from multiple dynamic subsystems separately, then data collection is simpler, but data consistency and synchronization become problematic

Engineering Contradiction:
Improveperformance assessment accuracyVSAvoiddata synchronization complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system divides the complex assessment task into separate data collection modules for each dynamic subsystem (e.g., flight parameters, engine performance, navigation systems). Each subsystem independently collects and processes its own data, then the results are integrated through a unified assessment algorithm. This segmentation allows simple data collection at each level while achieving comprehensive and synchronized assessment through the integration layer.

Inventive Principle:
Principle #1Segmentation

2Adaptability or versatility

If subjective evaluation methods are used, then assessment flexibility is improved, but objectivity and consistency deteriorate

Engineering Contradiction:
Improveassessment flexibilityVSAvoidevaluation objectivity
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system implements automated feedback mechanisms where assessment results are continuously generated based on objective data from multiple subsystems. The feedback loop compares actual performance against predefined criteria and standards, providing consistent and measurable evaluation. This automated feedback maintains flexibility in assessment criteria while ensuring objectivity through algorithmic processing rather than subjective judgment.

Inventive Principle:
Principle #23Feedback

3Loss of information

If comprehensive data from all subsystems is collected, then assessment completeness is improved, but data processing time increases

Engineering Contradiction:
Improveassessment completenessVSAvoiddata processing time
Core Design Contradiction:
Loss of informationVSLoss of time

Solution Approach 1:

The system performs preliminary data processing and filtering at each subsystem level before integration. Data is pre-processed, validated, and formatted according to assessment requirements before being combined with other subsystem data. This preliminary action reduces the complexity and time required for final integration while ensuring all necessary information is captured and prepared for comprehensive assessment.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3547288B1Assessing a training activity performed by a user in an interactive computer simulation
Publication Date: 2025.09.03 CAE INC
  • EP3547288B1 patent drawingFigure 1
  • EP3547288B1 patent drawingFigure 2
  • EP3547288B1 patent drawingFigure 3

AI summary

An interactive computer-based training system, station and method for assessing a training activity performed by a user interacting with tangible instruments for controlling the virtual element in an interactive computer simulation. A processor module obtains a plurality of performance metric datasets related to the virtual element and obtains a plurality of expected maneuvers of the virtual element during the training activity. The processor module computes the plurality of performance metric datasets to identify actual maneuvers of the virtual element during the training activity, identifies one or more failed actual maneuvers of the virtual element during the training activity against corresponding ones of the expected maneuvers and performs computational regression on the actual maneuvers of the virtual element compared to the expected maneuvers of the virtual element to identify one or more root causes of the failed actual maneuvers.