Operation Plan Sampling for Reliable Factory Simulation Decisions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing factory operation planning systems are prone to decision-making bias and inefficiencies due to user experience-based simulations, lacking quantified optimal operation plans and effective adaptation to changes.
Innovation Solution
A method involving multiple algorithms (Latin hypercube sampling, decision tree, and roulette wheel selection) to generate and refine operation plans through distributed simulations across computing nodes, focusing on high-potential areas to derive an optimal operation plan with increased reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If user experience-based simulation is used to derive operation plans, then decision-making can be performed, but decision-making bias occurs and reliability decreases
Solution Approach 1:
The system performs self-evaluation by automatically assessing the potential of unobserved operation plans through algorithms, eliminating the need for user experience-based judgment and reducing decision-making bias while maintaining operational capability
Solution Approach 2:
The patent replaces human experience-based simulation with automated algorithms (second algorithm for potential evaluation, third algorithm for weight assignment) that objectively assess operation plans, substituting mechanical human judgment with computational evaluation to improve reliability
2Measurement precision
If comprehensive simulation is performed on all operation plans, then optimal plan accuracy improves, but simulation time and computational resources increase
Solution Approach 1:
The system applies different evaluation approaches to different regions of the operation plan space: observed plans are evaluated through comprehensive simulation while unobserved plans are assessed through potential evaluation algorithms, allowing focused computational resources on areas needing detailed analysis
Solution Approach 2:
The second algorithm performs preliminary evaluation of unobserved operation plans by assessing their potential before full simulation, and the third algorithm pre-assigns weights to areas based on this potential evaluation, enabling prioritized sampling that reduces overall simulation time while maintaining accuracy
3Reliability
If number of simulation iterations is increased, then optimal operation plan accuracy improves, but computational complexity and time increase
Solution Approach 1:
The system dynamically adjusts the sampling process by repeatedly performing simulation on additionally sampled operation plans based on weight assignments, allowing the simulation process to adapt and focus on high-potential areas rather than uniformly increasing iterations across all plans
Solution Approach 2:
The system uses feedback from potential evaluation results to guide additional sampling decisions, where the third algorithm assigns weights based on evaluated potential and the first algorithm uses these weights to determine which areas require additional sampling, creating a feedback loop that improves accuracy without uniformly increasing complexity
Data Source
AI summary
An operation plan derivation method includes outputting a plurality of initial operation plans by sampling a plurality of operation plans using a first algorithm. Each of the plurality of initial operation plans has an operation factor and a judgment factor corresponding to the operation factor. A simulation is performed on the plurality of initial operation plans. An optimal operation plan is output. The performing of the simulation includes evaluating a potential of an unobserved operation plan among the plurality of operation plans using a second algorithm. A plurality of areas is defined that includes the plurality of initial operation plans based on the evaluated potential. A weight is assigned according to the evaluated potential to each of the plurality of areas using a third algorithm. The plurality of operation plans is additionally sampled depending on the assigned weight using the first algorithm.