Packaging Efficiency via MILP and Clustering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated packaging systems face inefficiencies across multiple packaging levels, with average fill-rate efficiencies ranging from 30% to 51%, as they primarily focus on individual levels rather than optimizing the entire end-to-end process.
Innovation Solution
A method and system that utilize clustering techniques and Mixed Integer Linear Programming (MILP) optimization models to standardize secondary package dimensions, maximize space utilization in tertiary packaging, and feedback to optimize primary package placement, thereby enhancing packing efficiency across all levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If existing automated packaging processes focus on only one level (commonly tertiary level), then the packing efficiency at that specific level may be improved, but the overall end-to-end packaging efficiency remains suboptimal (30-51%)
Solution Approach 1:
The packaging process is divided into three distinct levels (primary, secondary, tertiary) with dedicated optimization strategies for each level. Clustering techniques are applied separately to group primary packages, then secondary packages are optimized within clusters, and finally tertiary packages are optimized using MILP. This segmented approach allows each level to be optimized independently while maintaining overall system efficiency.
Solution Approach 2:
The invention merges the optimization of all three packaging levels into a unified end-to-end process. By combining clustering for secondary packages with MILP for tertiary packages and coordinating both levels simultaneously, the system achieves overall efficiency improvement (70-77%) that exceeds what single-level optimization could achieve alone.
2Productivity
If standard secondary package dimensions are used, then the packing process becomes simpler and faster, but space utilization efficiency decreases
Solution Approach 1:
The invention changes the parameters of secondary packages by creating multiple standardized size categories (small, medium, large, extra-large) based on clustering analysis of primary package dimensions. This allows the system to select the most appropriate standardized size for each cluster, balancing between process simplicity and space utilization. The MILP optimizer further adjusts tertiary package parameters to maximize space utilization while maintaining standardized secondary packages.
Solution Approach 2:
Different standardized secondary package dimensions are assigned to different clusters of primary packages based on their specific size characteristics. Instead of using a single universal standard, the system applies local optimization by matching secondary package sizes to the specific needs of each cluster, thereby improving overall space utilization while maintaining standardization benefits.
3Ease of manufacture
If clustering techniques are applied to group primary packages, then secondary package standardization is achieved, but the complexity of determining optimal groupings increases
Solution Approach 1:
The clustering process uses dimensional parameters (length, width, height) of primary packages to automatically group them into clusters with similar size characteristics. By transforming the raw dimensional data into cluster assignments, the system achieves standardization without manual intervention. The clustering algorithms process the dimensional parameters to create standardized groupings that simplify subsequent packaging operations.
4Volume of moving object
If MILP optimization is used for tertiary packaging, then space utilization is maximized, but computational processing time increases
Solution Approach 1:
The system performs preliminary clustering of primary packages into secondary packages before applying MILP optimization to tertiary packaging. This preliminary organization reduces the complexity of the subsequent MILP problem by pre-grouping items, allowing the optimization algorithm to work with fewer, larger units rather than individual small packages, thereby reducing computational time while maintaining high space utilization.
Solution Approach 2:
The tertiary packaging problem is segmented by treating each standardized secondary package as a single unit for MILP optimization, rather than optimizing individual primary packages. This segmentation reduces the number of decision variables in the MILP model, making the computational problem more tractable while still achieving high space utilization through optimized arrangement of secondary packages within tertiary containers.
Data Source
AI summary
This disclosure relates generally to automated packing of objects, and, more particularly, to a method and system for packing products with increased efficiency across packaging levels. While conventional methods of improving packaging efficiency focus on only one of the multiple levels in the packaging process, most commonly the tertiary level, the present disclosure attempts increasing packaging efficiency across packaging levels. Embodiments of present disclosure achieves increased efficiency across packaging levels by identifying standard size of secondary packages for packing a plurality of primary packages, packing the secondary packages within tertiary packages using a Mixed Integer Linear Programming (MILP) optimization model based on packing heuristics, and providing a feedback between tertiary and secondary packaging levels to identify standard secondary packages which can pack the primary packages with higher packing efficiency.