Industrial Gas Plant Control for Variable Renewable Power
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The variability and intermittency of renewable energy sources, such as wind, solar, and tidal power, pose challenges for industrial gas plants that require a constant power supply, particularly in ammonia production, where energy fluctuations affect efficiency and utilization.
Innovation Solution
A method utilizing machine learning models to predict available renewable power resources by training on historical environmental and operational data, allowing for optimized control of industrial gas plants and storage resources, such as battery, compressed air, and pumped hydroelectric storage, to maximize energy utilization and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If renewable energy sources (wind, solar, tidal) are used to power industrial gas plants, then environmental sustainability is improved, but power supply stability deteriorates due to natural variability and intermittency
Solution Approach 1:
The system performs preliminary actions by using machine learning models to predict future renewable power availability and plant operational characteristics before making control decisions. This advance prediction allows the system to proactively schedule operations and storage utilization to maximize renewable energy usage while maintaining plant reliability, rather than merely reacting to current conditions.
Solution Approach 2:
The control system dynamically adjusts operational parameters of industrial gas plants and storage resource utilization based on predicted power availability. The system continuously optimizes the balance between renewable energy input variability and constant power supply requirements by dynamically modifying plant operation schedules and storage discharge/charge patterns in response to predicted conditions.
2Productivity
If the operational schedule of industrial gas plants is adjusted to match variable renewable power supply, then energy utilization efficiency is improved, but production consistency deteriorates
Solution Approach 1:
The system schedules plant operations and storage resource utilization in advance based on predicted renewable power availability and plant operational characteristics. This preliminary scheduling allows the system to pre-coordinate production activities with expected energy supply patterns, maximizing renewable energy utilization while pre-planning to maintain production consistency through stored energy or adjusted schedules.
Solution Approach 2:
The system incorporates feedback mechanisms that continuously compare actual plant performance and power consumption against predicted values, using this information to refine future operational schedules. This feedback loop enables the system to learn from past deviations and improve the accuracy of future scheduling decisions, balancing energy efficiency with production consistency.
3Productivity
If machine learning models are used to predict power resources and optimize plant control, then energy utilization is improved, but system complexity increases
Solution Approach 1:
The system introduces machine learning prediction models as intermediary components that bridge the gap between variable renewable power supply and the control system. These models serve as mediators by translating complex environmental and operational data into simplified predictions of future power availability and plant characteristics, which then guide control decisions without requiring the control system itself to process the full complexity of raw data.
Data Source
AI summary
There is provided a method of controlling an industrial gas plant complex comprising a plurality of industrial gas plants powered by one or more renewable power sources, the method being executed by at least one hardware processor, the method comprising receiving time-dependent predicted power data for a pre-determined future time period from the one or more renewable power sources; receiving time-dependent predicted operational characteristic data for each industrial gas plant; utilizing the predicted power data and predicted characteristic data in an optimization model to generate a set of state variables for the plurality of industrial gas plants; utilizing the generated state variables to generate a set of control set points for the plurality of industrial gas plants; and sending the control set points to a control system to control the industrial gas plant complex by adjusting one or more control set points of the industrial gas plants.