Industrial Gas Plant Monitoring for Renewable Power Deviations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Industrial gas plant complexes face challenges in maintaining steady-state operations due to unexpected failures and efficiency losses, leading to undesirable downtime and reduced production rates, especially when relying on intermittent renewable power sources.
Innovation Solution
A method and system utilizing machine learning models to predict available power resources from renewable sources, incorporating historical environmental and operational data to optimize power usage and storage resource management, allowing for proactive control of industrial gas plants to maximize power utilization and minimize downtime.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If renewable power sources are used to power industrial gas plants, then environmental sustainability is improved, but power availability becomes intermittent and unpredictable
Solution Approach 1:
The system performs preliminary actions by training machine learning models on historical environmental and operational data to predict future power availability from renewable sources. This advance prediction enables the plant to prepare and adjust operations before power shortages occur, resolving the contradiction between using renewable energy and maintaining reliable power supply.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring actual power output from renewable sources, comparing it with predicted values, and using this information to refine predictions and adjust plant operations. This closed-loop approach maintains reliability while sustaining environmental benefits of renewable power usage.
2Productivity
If machine learning models are deployed to predict power availability and operational characteristics, then power utilization is optimized, but system complexity increases
Solution Approach 1:
The machine learning models serve multiple functions simultaneously: predicting power availability from renewable sources, forecasting operational characteristics of plant equipment, identifying maintenance requirements, and optimizing production scheduling. This multi-functionality justifies the added complexity by delivering comprehensive optimization across multiple dimensions of plant operation.
Solution Approach 2:
The system employs self-service mechanisms where the machine learning models automatically learn from historical data, continuously improve their predictions, and generate operational recommendations without requiring extensive manual intervention. This autonomy reduces the operational burden despite the initial complexity of deploying advanced predictive systems.
3Reliability
If proactive control measures are implemented based on predictions, then downtime is reduced, but real-time data processing requirements increase
Solution Approach 1:
The system performs preliminary analysis by training machine learning models on historical data to establish predictive relationships before real-time operation. This advance preparation enables the system to process real-time data more efficiently, reducing the computational burden during critical decision-making moments while maintaining the ability to proactively prevent downtime.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
There is provided a method of monitoring operational characteristics of an industrial gas plant complex comprising a plurality of industrial gas plants. The method being executed by at least one hardware processor and comprising: assigning a machine learning model to each of the industrial gas plants forming the industrial gas plant complex; training the respective machine learning model for each industrial gas plant based on received historical time-dependent operational characteristic data for the respective industrial gas plant; executing the trained machine learning model for each industrial gas plant to predict operational characteristics for each respective industrial gas plant for a pre-determined future time period; and comparing predicted operational characteristic data for each respective industrial gas plant for a pre-determined future time period with measured operational characteristic data for the corresponding time period to identify deviations in industrial gas plant performance.