Industrial Supply Chain Optimization With Linked Node Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current supply chains in the petroleum and chemical industries operate independently within local decision envelopes, leading to sub-optimal management of material and energy streams between nodes, and there is a need for integrated decision-making solutions to optimize these chains.
Innovation Solution
A method is developed to generate equation-oriented models for each node in the supply chain, integrate them with a linking structure to form an optimization model, and solve this model using categorization of variables, allowing for optimal control of nodes and handling nonlinear constraints through linearization and iterative convergence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If nodes in the supply chain are operated independently within local decision envelopes, then operational simplicity and ease of control are maintained, but overall supply chain optimization and resource allocation efficiency deteriorate
Solution Approach 1:
The supply chain is segmented into multiple nodes, each with its own equation-oriented model representing local operations. These segmented models can be solved independently while being integrated through a linking structure that coordinates material and energy streams across nodes, achieving both local operational simplicity and global optimization.
Solution Approach 2:
Individual node models are merged into an integrated supply chain optimization model through a linking structure. This combining allows the system to achieve overall optimization by coordinating decisions across nodes while maintaining the ability to solve each node's operations efficiently.
2Ease of manufacture
If heuristic and myopic business rules are used to manage interfaces between nodes, then implementation simplicity is maintained, but material and energy stream management efficiency deteriorates
Solution Approach 1:
Traditional heuristic and myopic business rules are replaced with equation-oriented models that use systematic mathematical optimization. This substitution replaces simple but inefficient rule-based management with a more sophisticated optimization framework that improves material and energy stream management while maintaining implementation feasibility through structured modeling approaches.
3Productivity
If equation-oriented models are generated and integrated for each node, then supply chain optimization capability is improved, but model complexity and computational requirements increase
Solution Approach 1:
The complex supply chain optimization problem is segmented into individual equation-oriented models for each node. This segmentation allows the overall complex problem to be broken down into manageable sub-problems that can be solved independently and then integrated, reducing the computational burden compared to solving one monolithic model.
Solution Approach 2:
The optimization is performed in stages through iterative solving of individual node models rather than attempting to solve the entire supply chain model simultaneously. This partial action approach allows the system to achieve optimization incrementally, managing computational complexity while still improving overall supply chain performance.
4Productivity
If nonlinear constraints are handled through linearization and iterative solving, then solution computational efficiency is improved, but solution precision and convergence accuracy may deteriorate
Solution Approach 1:
The solution process uses periodic iterative solving where the optimization model is solved repeatedly with updated parameters and constraints. This periodic action allows the system to progressively refine the solution, improving precision through multiple iterations while maintaining computational efficiency by using linearized approximations in each iteration.
Solution Approach 2:
The system performs partial optimization by linearizing nonlinear constraints and solving iteratively rather than attempting exact nonlinear optimization. This approach trades some precision for computational efficiency, but through multiple iterative passes, the solution converges to an acceptably precise result while maintaining tractable computation times.
Data Source
AI summary
Embodiments control industrial supply chains. An embodiment controls a supply chain formed of multiple nodes by obtaining an input-output model for each node. In response, for each node in the supply chain an equation-oriented model is generated using the obtained input-output model corresponding to the node. The generated equation-oriented models of the multiple nodes are integrated with a linking structure to form an optimization model of the supply chain. The optimization model of the supply chain includes a plurality of variables, e.g., interface variables indicating relationships between the generated equation-oriented models for each node in the supply chain. To continue, the optimization model of the supply chain is solved using a categorization of each of the plurality of variables to determine a value for at least one variable of the plurality. In turn, the method outputs a signal indicating the determined value.