Micorsoft iot

10
Azure Inter net Of Thin gs Mariner has a customer whose business model is rooted in IoT (Internet of Things). They monitor the sensors of critical devices to provide predictive maintenance services. The sensors, located on the shop floors of our customer’s customers, stream data to local servers where it is subsequently streamed to collector servers in Microsoft’s Azure cloud.

Transcript of Micorsoft iot

Page 1: Micorsoft iot

Azure Internet Of Things

Mariner has a customer whose business model is rooted in IoT (Internet of Things). They monitor the sensors of critical devices to provide predictive maintenance services. The sensors, located on the shop floors of our customer’s customers, stream data to local servers where it is subsequently streamed to collector servers in Microsoft’s Azure cloud.

Page 2: Micorsoft iot

Predictive Maintenance Iot

An Internet of Things (IoT) strategy for predictive maintenance (PdM) need not be that different from any other operational technology strategy, or for that fact, any business-related strategy or implementation plan. These are the basic building blocks, stock phrases and truisms one finds in most of the business strategy literature. They are legitimate, unoriginal pieces of advice. None of it is contradictory or controversial, and these behaviors have been cited by those declaring success.

Page 3: Micorsoft iot

Micorsoft IotThere are numerous hurdles to overcome. For example, the lack of standard protocols resulting in too many regional dialects between devices and security concerns. What types of devices will succeed? Are we going to have “weak devices strongly connected” or “strong devices weakly connected?”

Who knows – it’s still the Wild West!

That said, vendors across the technology spectrum are gearing up to, “sell shovels for the gold rush.” Service providers like PwC have provided architectural patterns like the “thing stack.” Microsoft recently announced Azure Internet of Things (IoT) and Azure Machine Language (ML) to facilitate emerging IoT scenarios. Cisco, Google and Apple are all betting big. The image below, courtesy Microsoft, shows how “eventually everything connects.”

Page 4: Micorsoft iot

Predictive Maintenance Internet Of Things

These are the crucial things to consider as you plan your foray into IoT-based predictive maintenance:

Obtain C-level buy-in before you start

Think globally, act locally

Go for low-hanging fruit to obtain the success and enthusiasm needed to obtain approval to achieve more expensive goals

Remember that no one vendor can do it all; pick those that have a track record or commitment to working together

Understand the value PdM will bring before you start

Always include change management activities into your plans

Understand which equipment is worth a predictive maintenance investment

Understand which equipment failures can be forecasted versus those that cannot

Page 5: Micorsoft iot

Microsoft Internet Of Things

Mariner worked with the customer to develop a predictive maintenance solution to handle its customers’ motive power needs . This IoT solution, deployed completely in Azure, enables the motive power company to reduce its customers’ power spend while improving productivity levels.The company had a vision to become the market leader by automating decisions generally made by engineering staff and account managers. A key roadblock to this goal was the time involved in monitoring the devices and manually analyzing the data to implement engineered solutions.

Page 6: Micorsoft iot

Azure Internet Of Things

Our solution is a heavily modified version of a system described by Alan K Fish, in his book Knowledge Automation. The technologies used in our example include Microsoft Azure Machine Learning (ML), Azure Intelligent Systems Service (ISS), HDInsight, and Sparkling Logic’s SMARTS Decision Management service.

We’ve applied our expertise in predictive maintenance (PdM), decision management, analytics, machine learning and cloud to create the conceptual architecture

Page 7: Micorsoft iot

Predictive Maintenance Iot

At the cost of oversimplification, here is the flow:

Data is generated by various devices and sensors.

Azure ISS is used to provide a secure connection and help with the management of devices and collection of data. Once the data is in the cloud we store it in a “data lake” built using HDInsight.

Next we apply Azure ML’s machine learning algorithms to uncover patterns and gain predictive insight.

Finally, the enriched data set can be fed to a decision management service, like SMARTS, which fires off decisions.

Page 8: Micorsoft iot

MICORSOFT IOT

In short, the architecture above siphons data in, makes sense of it and churns decisions out – with limited human involvement! While many details are missing, conceptually this represents a predictive, “decisioning,” cloud service that can be re-used for multiple scenarios.

Using the pattern described above, or something similar, we can help your business become a more intelligent and scalable digital business.

Page 9: Micorsoft iot

Predictive Maintenance Internet Of Things To overcome this,  we helped them design a system

to read events from the monitoring devices attached to their managed assets, and make decisions regarding the appropriate action to take in response to those events. The solution helps the company:

  Use a common syntax for all events Resolve issues faster Improve customer service Identify opportunities to reduce costs and increase

revenue