ICL, a multinational corporation based in Israel, faced challenges monitoring industrial equipment at their mining sites due to harsh conditions and costly manual monitoring. They partnered with AWS to develop in-house capabilities using machine learning for computer vision, leading to a successful prototype for monitoring mining screeners. This collaboration enabled ICL to build and deploy ML models on their own, with potential applications across various mining equipment. To learn more about building a production-scale prototype, readers are encouraged to reach out to their AWS account team. The authors of this post include Markus Bestehorn from AWS, David Abekasis from ICL Group, Ion Kleopas from AWS, and Miron Perel from Amazon Web Services.
“`html
ICL and AWS: Implementing Computer Vision for Mining Equipment Monitoring
About the Project
ICL, a multinational manufacturing and mining corporation, sought to improve efficiency and reduce waste in monitoring their mining equipment, which operates under harsh conditions. Their manual monitoring approach was not scalable and incurred high costs.
Developing In-House Capabilities
ICL developed in-house capabilities to use machine learning for computer vision to automatically monitor their mining machines. Due to limited internal resources with data science, CV, or ML skills, ICL approached AWS for support.
Building in-house capabilities through AWS Prototyping
ICL engaged in the AWS Prototyping program, which embeds specialists into customer development teams to build mission-critical use cases. This enabled ICL to develop a framework on AWS using Amazon SageMaker to build other use cases based on extracted vision from about 30 cameras, with the potential of scaling to thousands of such cameras on their production sites.
ICL’s Computer Vision Use Case
During the prototyping engagement, ICL selected the use case for monitoring their mining screeners. The solution involved using cameras and automatically processing their images while using CV, applicable to a wider range of mining equipment.
Monitoring Mining Screeners using CV Models with SageMaker
ICL utilized SageMaker for the complete lifecycle of an ML model, addressing tasks from labeling data to training, optimizing, and hosting ML models for production use. The solution involved using AWS Step Functions and AWS Lambda for automated model deployment and orchestration.
Conclusion
The collaboration between ICL and AWS resulted in the successful development of a computer vision approach for automated monitoring of mining equipment, showcasing the potential for other organizations facing similar challenges.
About the Authors
Markus Bestehorn, David Abekasis, Ion Kleopas, and Miron Perel are experts in AI, ML, and prototyping, leading the development of innovative solutions for challenging machine learning use cases.
Spotlight on a Practical AI Solution
Discover how AI can redefine your sales processes and customer engagement with the AI Sales Bot from itinai.com/aisalesbot, designed to automate customer engagement 24/7 and manage interactions across all customer journey stages.
“`
