Data-Driven Recirculating Aquaculture Control for Nitrate Removal
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional recirculating aquaculture systems (RAS) face challenges in maintaining optimal water quality and species health due to nitrate accumulation, equipment intensity, high energy costs, and sensitivity to disturbances, with clearwater RAS being equipment-intensive and biofloc systems requiring close monitoring and high energy input.
Innovation Solution
A data-driven recirculating aquaculture system (RAS) incorporating a main tank, an anoxic batch reactor, and a moving bed biofilm reactor (MBBR), controlled by a data-driven controller that adjusts feed and biofloc levels using sensors and machine learning to maintain desired system states, reducing nitrate and optimizing water quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If clearwater RAS are used to maintain reliable and easy control, then equipment intensity and nitrate accumulation increase
Solution Approach 1:
The system divides the treatment process into separate functional modules: an anoxic reactor for denitrification, an aerobic reactor for nitrification and biofloc production, and a settling tank. This segmentation allows each component to perform its specific function efficiently, reducing the complexity of any single piece of equipment while maintaining overall system reliability
Solution Approach 2:
Biofloc acts as an intermediary substance that mediates between waste nitrogen and the cultured species. The biofloc incorporates nitrogen into biomass that can be consumed by omnivorous species, providing a natural treatment mechanism that reduces equipment intensity while maintaining control reliability
2Device complexity
If biofloc systems are used to reduce equipment and water usage, then energy costs and monitoring requirements increase
Solution Approach 1:
The system uses periodic batch operation in the anoxic reactor rather than continuous operation. The reactor alternates between filling with nitrate-rich water, treating for a set period, and emptying to the settling tank. This periodic action reduces energy consumption compared to continuous aeration while maintaining effective denitrification
Solution Approach 2:
The system dynamically adjusts operational parameters such as aeration rates, pump speeds, and reactor timing based on real-time sensor feedback from dissolved oxygen, pH, and turbidity sensors. This dynamic control optimizes energy usage by applying aeration only when and where needed, rather than continuous operation
3Loss of substance
If biofloc systems operate without water exchange to reduce water usage, then nitrate accumulation and system stability worsen
Solution Approach 1:
The system incorporates multiple sensors (dissolved oxygen, pH, turbidity, temperature) that continuously monitor water quality parameters and provide feedback to the control system. This feedback enables real-time adjustments to aeration, pumping, and reactor operation, maintaining system stability without requiring water exchange. The control system can detect and respond to changes in nitrate levels, preventing harmful accumulation
Solution Approach 2:
The system uses the cultured species themselves and naturally occurring microorganisms to maintain water quality. Omnivorous species consume biofloc, removing nitrogen from the system biologically. The microorganisms in the biofilter continuously process ammonia and nitrate, providing self-sustaining water quality management without external water exchange
4Extent of automation
If data-driven control is implemented to reduce human supervision, then measurement precision and sensor requirements increase
Solution Approach 1:
The control system is designed to handle multiple functions with a unified platform: monitoring water quality parameters, controlling pumps and aerators, managing reactor operations, and providing alerts. This multi-functional approach consolidates sensor requirements and data processing, achieving high-level automation without requiring excessively precise specialized sensors for each function
Solution Approach 2:
The system monitors more parameters than strictly necessary (including temperature, pH, dissolved oxygen, and turbidity) but uses machine learning to identify which parameters are most critical at any given time. This partial monitoring approach with intelligent filtering achieves reliable automation while tolerating moderate sensor precision, as the system can compensate for less precise measurements through multiple data points and predictive algorithms
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
The system achieves efficient waste removal, minimizes water consumption, reduces feed requirements, and enhances species growth and system robustness, allowing for semi-autonomous operation with minimal human supervision.
Implementation Method 1
nitrate reduction happens much more efficiently in an anoxic environment—one without dissolved oxygen
Implementation Method 2
ammonia is oxidized to nitrite and oxidized again to nitrate
Implementation Method 3
The data-driven controller may include sensors to detect one or more of pH, dissolved oxygen, ammonia, nitrite, and nitrate levels
Implementation Method 4
The data-driven controller may include sensors to detect one or more of pH, dissolved oxygen, ammonia, nitrite, and nitrate levels
Implementation Method 5
solids that can settle to the bottom within 30 minutes are classified as settleable, while the remaining solids are classified as suspended solids
Data Source
AI summary
A recirculating aquaculture system (RAS) is disclosed, which includes a main tank, in which fish or shellfish are farmed; a first reactor fluidically connected to the main tank, wherein the first reactor is a batch reactor that operates under anoxic conditions; a second reactor fluidically connected to the main tank, wherein the second reactor is a moving bed biofilm reactor (MBBR); a feed stream fluidically connected to the main tank; and a data-driven controller operably connected to the first reactor, the second reactor, and the feed stream, wherein the data-driven controller is configured to bring and maintain the system (RAS) at a desired state.