Presented By O’Reilly and Cloudera
Make Data Work
September 11, 2018: Training & Tutorials
September 12–13, 2018: Keynotes & Sessions
New York, NY

How Komatsu is improving mining efficiencies using the IoT and machine learning

Shawn Terry (Komatsu Mining Corp)
1:10pm–1:50pm Thursday, 09/13/2018
Data engineering and architecture
Location: 1E 09 Level: Non-technical
Secondary topics:  Transportation and Logistics
Average rating: ****.
(4.50, 2 ratings)

Who is this presentation for?

  • Solution architects, big data professionals, data analysts and IoT leads, and line of business managers who are thinking about deploying IoT use cases

Prerequisite knowledge

  • A basic understanding of the big data analytics space and technologies and the IoT landscape and use cases

What you'll learn

  • Learn how Komatsu is bringing in data from connected mining equipment in near real time to monitor performance and utilization in real time and how Komatsu is using machine learning and analytics on terabytes of IoT data to improve operational efficiencies
  • Explore Komatsu’s data management and analytics architecture and roadmap, best practices for deploying real-time, streaming, and IoT use cases, and lessons learned from Komatsu’s journey deploying IoT use cases


Komatsu Mining Corp (formerly Joy Global) is one of the leading global mining equipment and services providers specializing in solutions for the excavation of energy, industrial, and hard rock minerals. Komatsu Mining is committed to helping its customers improve the safety, productivity and cost of their mining operations. The company offers an industrial internet of things (IIoT)-based service, JoySmart Solutions, which helps customers optimize machine performance using real-time data and analytics obtained from its smart, connected devices and assets. Devices and assets in this application include some of the largest mobile mining equipment used in surface and underground mining, including longwall mining systems, electric mining shovels, continuous miners, and wheel loaders, among others.

Originally, the company’s legacy data warehouse supported this IIoT service. However, as customer demand grew and more machines were connected, staff found they needed a new approach. Data growth is anticipated to reach 30 TB per month, and the old environment was limited in its ability to scale and grow.

Shawn Terry walks you through Komatsu’s data and analytics journey to build a next-generation data platform for the industrial IoT. He also delves into how Komatsu is using advanced analytics and predictive modeling capabilities to drive insights on terabytes of data from connected mining equipment in order to improve utilization and drive efficiencies.

JoySmart teams partnered with Cloudera and Microsoft to create a cloud-based IIoT analytics platform that provides scalability, performance, and flexibility to support global service teams. The platform ingests, stores, and processes a wide variety of data collected from mining equipment operating around the globe, often at very remote locations in harsh conditions. This data includes time series data—machine pressures, temperatures, currents, voltages and other sensor data—alarm and event data, and other data from third-party systems. A single machine can have thousands of data metrics and can generate 30,000 to 50,000 unique time-stamped records in one minute. The team plans to integrate more closely with customers’ onsite systems and other data sources to better contextualize machine operations.

With a unified data management platform, JoySmart teams can now more easily analyze data from the company’s P&H and Joy-branded mining machines, as well as from third-party programmable logic controller (PLC)-based equipment, to get a systems view of mining operations. The company’s data scientists can also produce machine learning models and better results faster than was previously possible.

A more complete picture of machine health and operations in each mine enables Komatsu teams to partner with their customers to identify ways to improve equipment safety, productivity, and operating costs. In one instance, they were able to make recommendations with a large coal mining company that enabled them to double the daily utilization of their longwall mining system. And because Komatsu Mining engineering staff can easily access and analyze the data, they are able to gain valuable insights to help them improve their current products and design the next generation of mining equipment.

Photo of Shawn Terry

Shawn Terry

Komatsu Mining Corp

Shawn Terry is lead architect for Joy Global Analytics.