Edit This Guide Record
Guides IoT Index System of Intelligence: Building an IoT Learning Loop

System of Intelligence: Building an IoT Learning Loop

Published on 07/12/2017 | IoT Index

368 0

Marc Phillips

Director. Bright Wolf

IoT GUIDE

Why is your organization building a connected system? Whatever particular story fits your business, industrial investment in IoT is about value creation. It’s about collecting data from environments and assets, and transforming raw machine signals and external events into information used to improve performance. Greater reliability. Faster time to market. Reduced costs. Better customer relationships. Increased revenue. These outcomes are made possible when you know the state of your machines and the world around you at each moment in time. These are the outputs of the new Systems of Intelligence created by data-focused, flexible, secure, and scalable IoT solutions.

The Value is in the Data? 

Raw data is useless without collection and context, cleansing, and transformation into forms the engines of enterprise can put into action. Cars don’t run on pools of petroleum buried miles underground. Drilling, pumping, and refinement turns sludge into speed. Satellites in space aren’t powered by “the Sun.” Manufacturing and design turn solar energy into battery power and TV shows on demand. Similarly, data collected from “things” must be normalized, contextualized, and integrated with enterprise ERP, CRM, BI, and other systems to create value.

The Rise of the Resilient Learning System

IoT data enters your system at high velocity with amazing variety in incredible volume. Errors abound, ranging from the obviously corrupted to the well-formed but highly inaccurate. Aside from requested yet flawed input, unauthorized data and commands from malicious actors create additional risks to the system. How will you track data provenance and verify a chain of custody for all events? Will you capture all incoming data, and ensure only trusted events are injected into your enterprise systems, machine learning, analytics, and other tools? How are you keeping dirty data from polluting your enterprise?

Creating a Continuous Learning Loop

Data processing is just one step toward generating revenue. Organizations must also operationalize what they discover; to build upon each consecutive insight in a continuous learning loop. With a new breed of IoT data management services such as Bright Wolf’’s Strandz, you can ensure a reliable supply of clean, trusted data for building and training predictive models, turning these derived insights directly into improved system performance.

This system turns incoming data into consistent, immutable, and normalized records for your machine learning, analytics tools, and data scientists to process, then delivers intelligent, operationalized insights to your enterprise integrations and IoT applications.

To Re-Train or Not To Re-train?

This method of data management enables your intelligence tools and teams to train and validate models for machine learning. When outputs of real world integrated systems don’t match the predicted model, failure data is cycled back into the model re-training and validation process.

For many organizations, humans will remain the ultimate “grader” of the predictive system. Did the model predict an imminent failure and generate a service call for a machine the technician then found to be in perfect working order? When this occurs, the system enables external data sources (such as human observation) to either reinforce the model or invalidate it and trigger a re-training. Similarly, unexpected failures may invalidate the current model as well. 

To Scale is Human

The goal of (most) industrial IoT projects is not to remove humans from the system; rather they aim to enable enterprises to scale more effectively. Revenue, often capped by the number of machines in the field, is constrained by the capacity of the organization to monitor and maintain them. This in turn is limited by the the number of service technicians that can be employed as determined by the organization’s business model.

IoT learning loops and predictive models remove these constraints. By replacing “scheduled maintenance” with “likelihood of impending failure,” the same team can keep more machines running through elimination of unnecessary visits and emergency repair calls. Uptime increases, improving brand reputation and growing market share, enabling service teams to grow and deepen customer relationships even as the number of technicians needed per machine decreases.

The Future is Bright

Why is your organization building a connected system? To create value. To generate more opportunities to benefit your customers and shareholders. As management consultant and “Crossing the Chasm” author Geoffrey Moore explains:

“What in the world would cause business leaders to allocate another trillion dollars to enterprise IT in the next decade? Quite simply, the prospect of gaining ten trillion dollars by so doing.”

Will the IoT solution you invest in today deliver value over time as the world changes around you? That depends on whether your team assembles a monolithic application custom-built to match your requirements today, or instead layers a flexible interface atop a secure and scalable core of adaptable data management services not bound to specific machines, data types, or processing tools. Artificial intelligence and machine learning processes are improving at fantastic rates, faster than your internal systems and teams will be able to keep up. Your chosen architecture should provide a stable interface for your business and data layer while enabling your organization to reap the benefits from improvements in IoT analytics and infrastructure.

The prospect of extracting significant value over time from IoT requires a System of Intelligence that learns and evolves, enabling your organization to quickly adapt to new business opportunities and technologies. To learn more, visit us at brightwolf.com.

test test