Improved Product Decisions with Machine Learning

November 22, 2016

By Jordan Reynolds, Senior Manager at Kalypso

Manufacturers seeking to gain and maintain a competitive edge have been implementing smart equipment to improve operations. Operational performance improvements such as reduced downtime, improved response times, and reduced human error translate to measurable improvements on the bottom line. As manufacturers have become increasingly connected, their connected systems, machines, sensors, and other devices are generating a wealth of new data. But this data is complex in nature, and given the sheer volume of data generated, isn’t easily gathered and analyzed. It is a challenge traditional manufacturing systems are not designed for – and manufacturers are missing out on valuable insights as a result.

Machine learning technology can help, when implemented in support of an IoT strategy and validated via a strategic experiment that proves the potential value. Manufacturers should take a comprehensive approach to machine learning and analytics, integrating equipment, systems and people into a highly collaborative environment that rapidly adapts to changing operational requirements and operates on a scale much larger than simple IoT applications.

Imagine a wind farm that has implemented smart, connected turbines using the ThingWorx Platform with the goals of gaining better insight into operational performance and making improvements for better outcomes. The farm has experienced problems stemming from repeated equipment failure, including lengthy and unplanned downtime and costly unplanned maintenance – which translates to bottom line losses and unhappy customers.

Each turbine generates millions of points of data. But the business lacks a system to properly gather and analyze it and currently monitors data manually. This is problematic for several reasons:

  1. Manpower resources are insufficient to monitor and process the high volumes of incoming data
  2. Employees monitoring data are not experts in the field of data science or mathematics
  3. The data is complex and in new and varying formats, making it difficult to manage with any traditional
    analytics tools
  4. Risk for error is high due to the volume, velocity, and variety of data

Without the ability to properly and effectively manage incoming data from the turbines, the business is unable to get the much-needed insights from its connected operations.  The wind farm seeks out an analytics solution that will monitor, manage, and analyze its data in order to:

  1. Identify performance patterns and trends
  2. Alert to anomalies in performance
  3. Predict unwanted events such as downtime or required maintenance
  4. Minimize human intervention and risk for error

In this example, the wind farm first uses ThingWorx Analytics to analyze historic data sets to understand what’s happening and what the conditions are when equipment failures have occurred. Then, ThingWorx Analytics is used for real-time usage monitoring to detect similar conditions and predictive analytics to identify when a failure is approaching. With the Machine Learning Quick Start services from Kalypso, organizations can rapidly create value from the ThingWorx Platform and ThingWorx Analytics. In a short period of time, companies can leverage these technologies to connect historical data to a predictive analytics engine.

Read the full case study