Field-tested solutions
with proven results

Discover a variety of solutions for energy, process, and production optimization, created in collaboration with our leading industry partners.

Partner Ecosystem

The Kelvin partner network unites industry leaders to drive autonomous operations by leveraging Kelvin technology to enhance asset optimization, workflow automation, and operational efficiency, ultimately boosting productivity and profits across industries.

Performance Optimization in Process Compressors

Edit Content

Performance Optimization in Process Compressors

Challenge

  • Unplanned downtimes lead to reactive and time-based maintenance which can be costly and inefficient

  • Difficult to quantify metrics that correlate to valve health

Solution

  • Use first principles to predict the efficiency and power in real-time

  • Develop ML model to predict the anomalies in real-time leading to sub-optimal operations

  • Email notifications for real-time deviations

  • Recommendations to close the loop for optimal operations

Result

  • 2-5% reduction in energy consumption

  • 45-50% Reduction in unplanned downtimes

Performance Optimization in Air Compressors

Edit Content

Performance Optimization in Air Compressors

Challenge

  • More than required energy consumption due to sub-optimal operations

 

  • Unnoticed deviations and losses in the compressed air network leading to excessive energy consumption

Solution

  • Predicting the Performance and Health score of the compressors with early warnings
  • Using process and mechanical parameters to predict the Ideal energy consumption against the actual consumption
  • Email notifications for real-time deviations
  • Recommendations to close the loop for optimal operations

Result

  • 2-3 % reduction in energy consumption
  • Reduction in GHG emissions by ~ 150 Tonnes of CO2/year

Performance Optimization for Heat Exchanges

Edit Content

Performance Optimization for Heat Exchanges

Challenge

  • Fluid with dissolved impurities upon reaching saturation deposit on the inner tubes causing scaling
  • Scaling was leading to corrosion and improper heat transfer

Solution

  • Using ML to create a PdM model to allow personnel to take necessary action before reaching impurities saturation
  • Parameter creation of Overall Heat transfer Coefficient(U) that varies with time
  • Employing physics-based features to predict fouling

Result

  • Reduction in unplanned downtimes by >50%

 

  • Savings of around $1M

Multi-effective Evaporator – Steam Optimization

Edit Content

Multi-effective Evaporator – Steam Optimization

Challenge

  • Includes frequent thermal breakdowns due to fouling

 

  • More than required steam consumption leading to sub-optimal operations

Solution

  • Create a soft sensor for overall heat transfer coefficient and set alarm limits
  • Benchmark and compare the real-time steam consumption with respect to the ideal consumption

Result

  • Steam optimization by ~ 15-20%

 

  • Reduction in unplanned maintenance by 55-60%

 

  • Reduction in cost of maintenance by 12-15%

Productivity Improvement Blast Furnace Operations

Edit Content

Productivity Improvement Blast Furnace Operations

Challenge

  • Complex and dynamic conditions with various parameters makes it difficult to detect hanging incidents in real-time
  • Difficult to monitor Silicon content of the molten iron which is an important indicator of the furnace temperature variations

Solution

  • ML based models to predict the deviations in the furnace operations – correlated with hanging
  • Predict silicon content in real time using the historical data

Result

  • 2-3% Increase in blast furnace productivity

 

  • ~ 450-600k Savings annually

Feed Strategy Optimization in Aluminum Smelters

Edit Content

Feed Strategy Optimization in Aluminum Smelters

Challenge

  • Difficult to maintain the bath temperature and excess ALF3 in the specified range
  • Shift engineer experience driving ALF3 addition directly impact the performance of the smelters productivity

Solution

  • Advanced Conditioning for identifying the deviations in the bath temperature and excess ALF3
  • Used historical data to model the required ALF3 feed to be added for optimal operations

Result

  • 6-10% decrease in unplanned downtime

 

  • Reduction in process variability by 35-40%

Furnace Efficiency Prediction

Edit Content

Furnace Efficiency Prediction

Challenge

  • Ethylene furnaces coke (foul) during cracking operations resulting in a loss of efficiency
  • Improper decoking resulting in equipment damage and lost production time

Solution

  • Identify different phases of decoke operation and excessive hold times
  • Predict decoke effectiveness with KPIs like temperature recovery and run time between decokes

Result

  • Tracking decoke effectiveness metrics identified procedural inefficiencies and inconsistency in execution
  • Optimization of decoke procedures reducing hold time and dead time has resulted in an additional $250k/y in production.

Distillation Column Efficiency

Edit Content

Distillation Column Efficiency

Challenge

  • Changes in feed quality impact the efficiency of columns
  • Frequent vacuum pumps/ reboilers and condenser failure causes operational upsets

Solution

  • ML-algorithm based PdM model for vacuum pump and reboiler
  • Employing Data Analysis to understand trends and create indicators to drive predictions
  • Employing first-principle based equations to understand status of machine

Result

  • 23% decrease in downtime

 

  • Increase in efficiency by 8-10%

 

  • ~ 250k Savings annually

Boiler Efficiency Prediction

Edit Content

Boiler Efficiency Prediction

Challenge

  • High variations in fuel quality and feed leads to operational challenges in maximizing the steam generation

 

  • Degradation of boiler efficiency leading to suboptimal combustion strategies

Solution

  • Maintaining enthalpy balance in boilers for incoming streams and generated steam to track the efficiency in real-time

 

  • Predicting the efficiency degradation and recommending the corrections to counter impact the fuel quality variations

Result

  • Optimal Steam to fuel ratio

 

  • 4-7 % energy savings/ year

 

  • Reduction in greenhouse gas emissions of 200 tonnes of CO2 per year

Cooling Tower Health Monitoring

Edit Content

Cooling Tower Health Monitoring

Challenge

  • Impact of seasonality and load requirements are unknown

 

  • More than required energy consumption in fan, water losses

Solution

  • Predict the energy requirements using advanced modeling to regulate the fan RPM

 

  • Monitor and track the losses – evaporative, drift and blowdown of the water stream

Result

  • Timely and effective maintenance for cooling towers

 

  • Increased efficiency by 12-16%

Need a custom solution?

Please reach out if you need more details on a custom solution tailored to your specific needs. We collaborate with leading industry partners who have extensive experience developing with Kelvin for real-world applications.

Contact us