Product Blending Sequencing for Layered Silo Order Fulfillment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional manual methods for blending products with varying characteristics in storage units are inefficient and often result in sub-optimal outcomes due to complexity and resource underutilization, particularly in scenarios involving multiple silos with layered materials and customer-specific quality requirements.
Innovation Solution
An automated product blending process using mixed integer linear programming and machine learning models optimizes the blending of product layers in storage units, considering constraints like FIFO and LIFO access, to achieve desired quality parameters and minimize resource use.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual methods are used for blending products in storage units, then operational simplicity is maintained, but blending efficiency and resource utilization deteriorate due to complexity and sub-optimal outcomes
Solution Approach 1:
The patent replaces manual mechanical blending operations with an automated computer-implemented system that uses optimization algorithms and machine learning models to determine blending sequences and proportions, thereby improving efficiency while managing complexity through software-based control
Solution Approach 2:
The system enables self-service blending optimization by automatically analyzing storage unit configurations, product characteristics, and customer orders to generate optimal blending plans without requiring manual intervention for each blending decision
2Manufacturing precision
If automated optimization systems are implemented, then blending precision and resource utilization improve, but system complexity increases
Solution Approach 1:
The patent replaces manual blending decision-making with automated optimization algorithms and machine learning models that precisely calculate blending sequences and proportions based on product characteristics and customer specifications, achieving high manufacturing precision through computational methods
Solution Approach 2:
The system incorporates feedback mechanisms where the optimization algorithm continuously evaluates blending outcomes against target quality parameters and adjusts subsequent blending decisions to maintain precision, using real-time data from storage units and customer orders
3Productivity
If complex blending scenarios with multiple silos and layered materials are handled manually, then operational flexibility is maintained, but resource utilization and order fulfillment deteriorate
Solution Approach 1:
The system automatically handles complex storage unit configurations by analyzing silo arrangements, layered material structures, and access constraints to generate feasible blending sequences that maximize resource utilization and order fulfillment without manual intervention
Solution Approach 2:
The optimization system dynamically adapts blending plans based on real-time storage unit states, customer order requirements, and product characteristics, adjusting blending sequences and proportions to handle complex scenarios efficiently while maintaining operational flexibility
Data Source
AI summary
Disclosed are various embodiments for product blending optimization. In one embodiment, inventory data is received that represents a plurality of product layers stored in a plurality of storage units. The inventory data indicates a product quantity for each of the product layers and a set of characteristics for each of the product layers. Order data is received that represents a plurality of orders for a blended product. Each of the orders specifies a respective set of target characteristics for the blended product and a respective quantity. Based on the inventory data and the order data, an optimal sequence of the plurality of orders for fulfillment is automatically generated, along with an optimal sequence for dispensing product from the storage units for the blended product of each respective order.