Get Started

Understand the benefits of artificial intelligence in modern manufacturing today.

Get the ebook.
SCHEDULE A DEMO

Power Station Output Prediction

This case study showcases how using Vanti’s service, a leading Power Station can use proprietary sensor data in conjunction with public meteorological information to predict the projected power output 1-3 days in advance.

Background

A leading Power Station must declare 24 hours in advance what their generate power will be, in order to meet strict contractual requirements by the electric company.
  • The power station must predict it’s output power within tight tolerances. It is heavily penalized for not meeting the declared power, and incurs heavy costs for over production.
  • Time-series data from sensors installed in the equipment is being collected for each turbine in the plant.
  • In addition, public meteorological data is provided.

Challenges

  • Increase power prediction accuracy
  • Generate an on demand model, per turbine.
  • Deploy a model immune to the naturally recurring data drifts in this process.
  • Reduce costs associated with under / over-estimations

Challenge

  • Decrease overall cycle-time:
  • Reduce quality sampling time during the physical metrology inspection stage
  • Detect defective wafers early in the manufacturing process
  • Deploy a model immune to the naturally recurring data drifts in this process.

Solution process

  • Reduce the quality sampling time and detect defective wafers early:
  • This is achieved through training a model to predict the metrology test results based on data from the etching process.
  • Step 1: The user defined the desired acceptance criteria for Vanti’s model performance by MAPE and P95 error thresholds for the sampled areas on the wafer.
  • Step 1: Historical time-series data from the etching step alongside their corresponding quality test results for hundreds of wafers was used to train 13 regression models1.
  • Each model successfully complied to the pre-set success criteria and corresponded to a specific set of coordinates (X,Y) for each of the 13 sampled areas during metrology inspection.
  • The models provided real-time defect predictions of all sampled areas, thereby reducing the OEM’s dependency on physical metrology testing.

Solution process

  • Increase prediction accuracy and reduce estimation costs
  • This is achieved through training a model to predict the generated power based on sensor and meteorological data
  • Step 1: The user defined the desired acceptance criteria for Vanti’s model performance by RMSE
  • Step 2: Historical time-series data from the sensors alongside their corresponding public meteorological data was used to train a custom model per turbine.
  • The model successfully complied to the pre-set success criteria
  • The models provided real-time power predictions with significantly increased precision, thereby reducing the fines associated with over estimation, and energy consumption costs associated with under estimation
  • Deploy a model immune to naturally recurring data drifts:
  • Vanti’s service includes a proprietary drift-recovery mechanism. Once a drift is detected, production models can be automatically replaced within minutes with a new model.
  • Vanti continuously monitors the performance of deployed models to automatically improve performance over time.

Results

Using Vanti’s service the Power Station is now able to drastically minimize the costs associated with over and under estimation of the projected power output. Moreover, employing Vanti’s proprietary drift recovery mechanisms and auto-optimization of deployed models ensure a high quality of service at all times.
Book a Demo

Results

Using Vanti’s service the Power Station is now able to drastically minimize the costs associated with over and under estimation of the projected power output. Moreover, employing Vanti’s proprietary drift recovery mechanisms and auto-optimization of deployed models ensure a high quality of service at all times.
Book a Demo
Twitter Linkedin-in

Copyright © 2022 by Vanti.



Terms | Privacy

Want to learn more?