Use MCO.ai to predict Moisture Carryover more accurately than you ever thought possible
MCO.ai A prediction platform for MCO in BWRs
MCO.ai predictions enable visibility into moisture carryover, reduce exposure risk, ensure long-term viability of key plant assets, enhance core efficiency, and reduce reload fuel costs.
NEW METHODOLOGY
Blue Wave AI Labs is pioneering MCO prediction capability with the creation of MCO.ai to address MCO uncertainty and peer inside the ‘black box’ of MCO to meet the demands of current and future core designs. Our proprietary physics-constrained approach uses artificial intelligence (AI) coupled with machine learning (ML) to leverage historical fuel cycle data, outputs from core simulators, and past MCO measurements.
By using AI and ML, we construct a neural representation of MCO dynamics, yielding high-value results in the form of powerful predictive capability. Through feature engineering and a physical understanding of the underlying mechanisms, we transform the datasets into a “canonical set” of key drivers of MCO. This enables the development of high-fidelity models with parameters that core designers and operators can control, giving the models not only predictive power but, just as important, corrective power.
By using AI and ML, we construct a neural representation of MCO dynamics, yielding high-value results in the form of powerful predictive capability. Through feature engineering and a physical understanding of the underlying mechanisms, we transform the datasets into a “canonical set” of key drivers of MCO. This enables the development of high-fidelity models with parameters that core designers and operators can control, giving the models not only predictive power but, just as important, corrective power.
DATA REQUIREMENTS
A number of techniques have been employed to enhance the datasets, including data augmentation for maintaining representative distributions, interpolation of training targets, and transfer learning to take maximum advantage of information from multiple sites. These techniques have made it possible to extend the development of highly accurate models to reactors possessing less data than would otherwise be required. Typical situations require approximately three fuel cycles worth of data for a given reactor unit.
SYSTEM REQUIREMENTS
MCO.ai is accessed via a web browser and is available for all standard computing platforms with a high-speed Internet connection, running most modern 32- and 64-bit operating systems and mobile operating systems: Linux, Windows, macOS, Android, iOS, and UNIX architectures are all acceptable environments for MCO.ai.
FEATURES
• Upload historical data in multiple formats (.zip, .dat or HDF5) for model evolution and training, resulting in powerful predictive capabilities.
• Upload cycle depletions in multiple formats for prediction reports and scenario planning.
• Generate, delete, download, and email MCO projection reports in multiple formats.
• Graph and view historical cycle data for trending and comparisons.
• Filter and sort data tables quickly and seamlessly.
• Create ‘Design’ or ‘Operating’ scenarios to mitigate MCO levels during design or manage MCO during operation.
• Store and archive historical cycle data, design files, and MCO projection reports.
Enable visibility, reduce exposure risk, ensure long-term viability, enhance core efficiency, and reduce reload fuel costs with MCO.ai.
Cycle Exposure (MWd/ST)
The above diagram depicts how our predictions lead to millions of dollars in savings per fuel cycle by: 1) more efficient fuel arrangements, 2) reduce risks of derating due to exceeding limits, 3) Increase safety and 4) protect downstream assets.
“HOW DOES IT WORK?
MCO.ai uses historical fuel cycle data, core simulator outputs, and past MCO measurements to create a neural representation of MCO dynamics. It doesn’t just predict—it identifies the key drivers of moisture carryover, so you have visibility into both the ‘why’ and ‘what next.’
BUT HOW DOES THAT TRANSLATE INTO ACTUAL SAVINGS?
With accurate MCO predictions, you can optimize your core designs to prevent unnecessary fuel costs. For example, some of our clients have saved millions of dollars per fuel cycle by avoiding overloading fuel or mitigating high MCO levels before they escalate. Plus, it helps protect your plant assets from erosion and reduces exposure risks tied to soluble contaminants.
HOW COMPLEX IS IT TO INTEGRATE INTO OUR EXISTING PROCESSES?
Surprisingly simple. MCO.ai is designed to seamlessly integrate with your current workflows. It’s compatible with most nuclear fuel analysis tools and is delivered as a web-based solution, so there’s no heavy infrastructure or disruptive implementation process.
Oh, and did we mention that our team provides full support during setup?
BUT CAN YOU PROVE IT?
It’s already proven itself at multiple BWRs. Since its deployment, clients have seen an average prediction error of just ±0.018% MCO—far better than traditional methods. That precision has enabled them to make smarter, more cost-effective decisions.
ARE YOU CURRENTLY CONFIDENT IN YOUR TEAM’S ABILITY TO ACCURATELY PREDICT MOISTURE CARRYOVER LEVELS?
Has it seemed to be a bit of a frustrating guessing game lately?
That uncertainty can lead to costly decisions, right? Either you overcompensate with larger reload batch sizes, increasing fuel costs, or risk pushing your steam separators too far, potentially causing operational and maintenance headaches.
That’s where MCO.ai takes a revolutionary leap. Up until recently, there has been no reliable method to forecast future MCO levels prior to or during a new fuel cycle. By combining AI and machine learning with physics-based models, it predicts moisture carryover levels with incredible accuracy. You’ll no longer need to over-design or second-guess—you’ll have precise data to make informed decisions.
Our MCO predictions yield visibility into core efficiency
The Problem:
Elevated levels of Moisture Carry Over (MCO) can lead to increased Cobalt-60 exposure to plant personel, component failure, unexpected downtime, elevated maintenance costs, and/or lost revenue.
Designing and managing a fuel cycle with accurate MCO predictions avoids the following adverse effects:
For MCO > 0.3%, accelerated rate of erosion of internal surfaces of the Main Steam Isolation Valves (MSIVs) occurs.
For MCO > 0.1%, accelerated rate of erosion of the rotor and stationary elements of the main turbine takes place.
Increased Exposure Risk – Co-60 carryover and dose levels increase as MCO increases, which can lead to increased exposure risk for plant personnel in the steam dependent areas and elevated dose rates in the water-steam cycle.
Increased Maintenance Costs – Elevated MCO levels requires increased testing and inspection of MSIV internal surfaces main turbine, which can lead to costly repairs if MSIVs or main turbine is damaged.
Reduction in Electrical Power Output – Small reduction in power output due to error in calculating thermal power.
The Significance:
Moisture Carry Over is a byproduct of nuclear power generation, thus predicting it and mitigating its impact on key plant assets is crucial not only to the safety of key plant assets and driving down the reload batch size but to the viabiity and reliability of the plant itself.
