Automated stockpile volume measurement

Global Steel Recycler Saves Over 40+ Man-Days Annually with Stockpile Volume Measurement

Ripik AI's Volumetric Estimation using LIDAR has transformed stockpile management, achieving over 95% measurement accuracy, eliminating 100% of safety hazards, and saving over 40 man-days annually, driving efficiency, safety, and precision in operations.

stockpile volume measurement

World’s Largest Steel Recycler Committed to Sustainability

Client Overview

A global leader in steel recycling, the client is the world’s largest recycler, processing over 27 million tons of steel annually. Committed to sustainability, they are targeting net-zero carbon emissions by 2050 to reduce environmental impact and contribute to a more sustainable future for the steel sector.

Problem Statement

Inaccurate Manual Stockpile Volume Estimations Leading to Poor Supply Planning and Safety Hazards

The client struggled with manual stockpile volume estimation, leading to inconsistencies in inventory planning and material management. Outdated measurement methods resulted in unreliable data, affecting supply chain efficiency. Additionally, the process required workers to climb stockpiles, exposing them to significant safety hazards such as slips and falls. The reliance on skilled personnel further increased the risk of human errors, making the need for an automated, accurate, and safer solution essential.

Manual stockpile estimation

Manual estimation leads to significant errors in volume calculations

Volumetric estimation done manually by climbing the piles to measure the base and height, resulting in a 15% error due to inconsistencies and unaccounted surface deformations.​

Workers Safety hazards

Climbing onto piles for measurements poses safety risks, with chances of slipping and accidents.​

Climbing onto piles for measurements poses safety risks, with chances of slipping and accidents.​

Incorrect supply planning

No continuous/unplanned tracking results leads to wastage or shortages

Measurement variations lead to inaccurate procurement of materials, affecting supply planning.​

Reactive Adjustments

Without continuous monitoring, adjustments to supply planning are reactive rather than proactive

Conventional methods require extensive human effort, which slows down operations. Without continuous monitoring, adjustments to supply planning become reactive rather than proactive.

Solution​

Ripik AI leverages LiDAR technology to accurately compute volume of stockpiles

  • Real-Time Stockpile Monitoring Using LIDAR Ripik.ai utilized a combination of LiDAR and IP cameras to precisely measure the volumes of piles in bins, ensuring improved accuracy and efficiency in the estimation process.​
  • 3D map of the material The IP Camera would be used for segmentation of the material based on their color and the LiDAR would be used to create a 3D map of the material.​
  • Automated Data Collection Fixed or mobile LiDAR units scan stockpiles at scheduled intervals, reducing the need for manual intervention.
  • Seamless Integration LiDAR-based measurements integrate with ERP and material tracking systems, providing automated reporting and analytics.
stockpile volume measurement

Results and Impact

Accurate Stockpile Measurements, Improved Safety, and Operational Efficiency

Our AI-driven volumetric estimation solution significantly enhanced the accuracy of stockpile measurements, eliminating manual errors. This improvement boosted operational efficiency and also reduced safety hazards for workers, ultimately optimizing supply planning and increasing overall productivity for the client.

95%+

Measurement accuracy​

Achieved a consistent accuracy of 95%, with initial accuracy of 93.4% in October and current accuracy at 98.4%, significantly reducing estimation errors​.

100%​

Reduction in safety hazards

Eliminated the need for manual climbing on piles, thereby removing health and safety hazards for personnel.

40​+

Man-Days saved annually

Automated volume estimation process reduced manual effort and saved time, improving operational efficiency