Twin Computing Simulation for Proactive Delay Mitigation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing resource utilization algorithms for scheduling project activities, such as the Critical Path Method (CPM), struggle to proactively address delays caused by asynchronous assembling rates and spare part delivery in complex manufacturing and assembly processes.

Innovation Solution

A computer-implemented method and system for critical path based proactive optimization, which involves collecting data on tasks, training twin computing simulation models, running contextual situation simulations to determine critical paths, and using machine learning to identify optimized tasks that mitigate delays.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional Critical Path Method (CPM) is used for scheduling project activities, then the basic scheduling functionality is provided, but the system cannot proactively address delays caused by asynchronous assembling rates and spare part delivery

Engineering Contradiction:

Improveproactive delay mitigationVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by running multiple simulation scenarios before actual project execution to identify potential delays and critical paths. The digital twin model predicts future states and allows proactive adjustment of schedules to prevent delays rather than reacting to them after occurrence.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent creates a digital twin copy of the physical project system that replicates its behavior through simulation. This virtual copy allows extensive what-if analysis and scenario testing without affecting the actual project, enabling proactive identification of delays through multiple simulated contexts.

Inventive Principle:

Principle #26Copying

2Loss of time

If multiple simulation scenarios are run to identify critical paths, then proactive delay identification is improved, but computational resources and time consumption increase

Engineering Contradiction:

Improvedelay identification timingVSAvoidcomputational resource consumption

Core Design Contradiction:

Loss of timeVSUse of energy by moving object

Solution Approach 1:

Instead of running all possible simulation scenarios to exhaustion, the system uses intelligent sampling and prioritization to execute only the most relevant simulation scenarios. The digital twin model selectively explores critical scenarios based on predicted risk factors, achieving sufficient delay identification without exhaustive computational effort.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system incorporates feedback mechanisms where simulation results inform subsequent simulation selections. Based on initial analysis, the system identifies high-risk scenarios and prioritizes those for detailed simulation, while low-risk scenarios are skipped, creating an adaptive computational approach that reduces overall resource consumption.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12282874B2Scheduling project activities using twin computing simulation

Publication Date: 2025.04.22 INTERNATIONAL BUSINESS MACHINE CORPORATION

AI summary

A critical path based proactive optimization that includes collecting data on the tasks of contextual situation for performing a process and training a twin computing simulation model using the collected data for each task in the process. A contextual situation simulation is run using the simulation models for each task in the process to determine a critical path that causes delay in the process. An optimized task is determined from the tasks of the contextual situation using machine learning employing the collected data, wherein the optimized task mitigates delay in the process from the critical path.