Surrogate Process Modeling for Green Hydrogen Plant 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 difficulty in determining optimal electrolyzer and storage device numbers and locations.
Innovation Solution
A computer-implemented method using physics-informed machine learning models and rigorous dynamic process models to create a surrogate process model, which includes multi-objective design optimization algorithms, addressing intermittent power supply and optimizing electrolyzer and storage device configurations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If large-scale green hydrogen production plants utilize intermittent renewable energy sources, then renewable energy utilization is improved, but operational stability deteriorates due to unpredictable power supply
Solution Approach 1:
The system performs preliminary actions by using historical power profile data to generate representative power profiles that capture seasonal and diurnal variations. These pre-generated profiles are used in the optimization algorithm to anticipate intermittent power supply patterns and pre-determine optimal electrolyzer configurations and storage device sizes before actual operation, thereby maintaining operational stability while utilizing renewable energy
Solution Approach 2:
The system creates a simplified surrogate process model that copies the essential behavior of the complex hydrogen production process. This surrogate model, trained on simulation data from the rigorous dynamic process model, replicates key process characteristics while being computationally efficient, allowing the optimization algorithm to evaluate multiple configurations quickly and find optimal designs that handle intermittent power supply
2Productivity
If the number of electrolyzers and storage devices is increased to meet hydrogen demand, then hydrogen production capacity is improved, but system complexity and cost increase
Solution Approach 1:
The optimization algorithm determines the optimal number of electrolyzers and storage devices by evaluating whether full capacity installation is necessary. It identifies that excessive electrolyzers may operate inefficiently during low renewable power periods, and calculates the precise number needed to meet hydrogen demand when combined with storage devices, avoiding both under-capacity and over-capacity scenarios
Solution Approach 2:
The system designs a multi-functional configuration where electrolyzers serve primary hydrogen production during high renewable power periods, while storage devices provide both hydrogen storage and load balancing functions. This universal approach allows the same set of devices to handle multiple objectives: meeting demand, managing intermittency, and optimizing cost, thereby reducing overall system complexity
3Measurement precision
If traditional dynamic process models are used for optimization, then model accuracy is improved, but computational time increases significantly
Solution Approach 1:
The system creates a simplified surrogate process model that copies the essential behavior of the complex hydrogen production process. This surrogate model, trained on simulation data from the rigorous dynamic process model, replicates key process characteristics while being computationally efficient, allowing the optimization algorithm to evaluate multiple configurations quickly
Solution Approach 2:
The system substitutes the computationally intensive rigorous dynamic process model with a machine learning-based surrogate model. This replacement uses algorithms to predict process behavior based on input parameters, achieving comparable accuracy for optimization purposes while reducing computational time from hours to minutes, enabling practical application of multi-objective optimization
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables efficient and cost-effective hydrogen production by minimizing levelized cost of hydrogen while ensuring demand is met, with the ability to handle intermittent renewable energy sources and optimize plant location.
Implementation Method 1
the one or more target assets comprise one or more electrolyzers
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Embodiments of the present disclosure provide an optimal conceptual design framework. A surrogate process model may be generated based on one or more physicsinformed machine learning models and a rigorous dynamic process model. The surrogate process model may comprise a representation of a plant 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. An optimal conceptual design for the process may be generated by executing an optimization model based on the surrogate process model and the design optimization algorithm.