Green Hydrogen Site Selection Using Surrogate Process Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Designing large-scale green hydrogen production plants that utilize intermittent renewable energy sources poses challenges due to unpredictable power supply, leading to inefficient operation, high costs, and potential electrolyzer degradation, with traditional methods failing to optimize electrolyzer numbers, sizes, and site locations effectively.
Innovation Solution
A computer-implemented method using physics-informed machine learning models and rigorous dynamic process models to create a surrogate process model, enabling multi-objective design optimization that considers site selection variables and constraints, optimizing electrolyzer numbers, power storage, and renewable energy site locations to achieve stable hydrogen production at minimal cost.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional design methods are used for green hydrogen production plants, then the design process is simpler, but the optimization of electrolyzer numbers, sizes, and site locations is ineffective, leading to high costs and unstable operation
Solution Approach 1:
The patent creates a digital twin (surrogate model) that replicates the complex physics-informed process model. This digital copy enables rapid optimization iterations without requiring repeated execution of the computationally intensive physics model, thus improving productivity while managing design complexity
Solution Approach 2:
The patent performs preliminary optimization studies using the surrogate model to identify optimal electrolyzer configurations and site locations before finalizing the design. This preliminary action allows multiple design scenarios to be evaluated efficiently, leading to optimized hydrogen production without excessive complexity in the final implementation
2Object-affected harmful factors
If intermittent renewable energy sources are used, then the environmental benefits are improved, but the power supply becomes unpredictable, leading to electrolyzer degradation and unstable operation
Solution Approach 1:
The patent employs dynamic optimization that adapts electrolyzer operation parameters in response to varying renewable energy input. The physics-informed model captures transient behavior and degradation mechanisms, allowing the system to dynamically adjust operation to maintain stability and prevent degradation while utilizing intermittent renewable energy
Solution Approach 2:
The patent incorporates feedback mechanisms where the surrogate model predicts electrolyzer performance and degradation based on historical operation data and renewable energy patterns. This feedback enables proactive adjustment of operation parameters to prevent degradation before it occurs, maintaining reliability while using renewable energy
3Reliability
If the number of electrolyzers and power storage devices is increased to ensure stable operation, then operation stability is improved, but the levelized cost of hydrogen increases
Solution Approach 1:
The patent optimizes key parameters including electrolyzer size, number of units, and power storage capacity to achieve the minimum configuration required for stable operation. By carefully tuning these parameters rather than over-provisioning, the system maintains reliability while minimizing the levelized cost of hydrogen through optimized capital and operational expenditures
4Productivity
If site selection is not optimized, then the deployment process is faster, but the renewable energy utilization is suboptimal, leading to higher costs and reduced efficiency
Solution Approach 1:
The patent uses a surrogate model that replicates the physics-informed process to rapidly evaluate multiple site locations and renewable energy configurations. This digital copying approach allows comprehensive site optimization without the time-consuming iterative simulations that would otherwise be required, achieving optimal renewable energy utilization efficiently
Data Source
AI summary
Embodiments of the present disclosure provide optimal site selection framework. A surrogate process model may be generated based on one or more physics-informed machine learning models and a rigorous dynamic process model. The surrogate process model may comprise a representation of a process including one or more target assets and one or more secondary assets. The process input for the one or more target assets may comprise power output from a renewable energy source. A design optimization algorithm representative of a multi-objective design optimization problem may be generated. The design optimization algorithm may comprise one or more site selection variables and one or more site selection constraints. One or more outputs may be generated by executing an optimization model based on the surrogate process model and the design optimization algorithm. The one or more outputs may comprise predicted optimal sites and an optimal conceptual design for the process.