Connected Maintenance Solution Drive new insights and analytics from machine mounted sensors to help you better predict maintenance need and just-in-time repair priorities. What to look for Target this solution to companies, such as manufacturers or asset transporters, whose profitability is reliant on machine up-time. Architecture Solution and reference architectures
Connected Maintenance Lower operating and capital costs by proactive service and repair of assets, as well as more efficient use of repair resources. Key Benefits: Maximize productivity by predicting failures before they occur Focus repair resources on highest ROI priorities Use data insights drive R&D and future competitive advantage
What to look for Target this solution to companies, such as manufacturers or asset transporters, whose profitability is reliant on machine up-time. Machine mounted sensors provide a constant flow of data to Azure Power the most complex, low-latency, data-intensive scenarios and scale them with Service Fabric Ingest millions of events, as well as produce analytics to help you better understand patterns or trigger an action during real-time data streaming though Stream Analytics Captured data is evaluated based on expert knowledge or data from past events stored in SQL. Predictive capabilities are continuously improved using Machine Learning
Solution Architecture Business User An operations executive seeking to lower costs and maximize revenue by improving machine up-time. Solution goal Drive new insights and analytics from machine mounted sensors to help you better predict maintenance need and just-in-time repair priorities. Solution components This solution is built on the following Azure managed services: Azure IoT Hub, Event Hub, Stream Analytics, Service Fabric, Microservices, DocumentDB, SQL database, Machine Learning, Power BI. These services run in a high availability environment, patched and supported, allowing you to focus on your solution versus the environment to run them in.
Reference Architecture 3 4 Customer Azure subscription Customer Sites Node Node Device Management Event Hub Stream analytics SQL 1 7 Service Fabric Cluster Devices Tags IoT Hub DocumentDB Node Node Invoke Service SQL Commands 2 6 SQL Database Azure ML Anomaly Detection Micro-services SQL Portal (web app) 5 SQL DW Customer AAD Customer DC 1 Tags are sent over AMQP to IoT Hub 3 The packet is looked up in the device registry and forwarded onto the service layer 5 Data is scored using Azure ML anomaly detection algorithms 7 C&C is achieved through IoT Hub via service nodes 2 Deployed the Service Fabric 4 Initial anomaly detection is done in Stream Analytics 6 After data enrichment, it is written to a SQL Data Warehouse and a copy of the message is stored
Reference Architecture IoT hub A fully managed service that enables reliable and secure bidirectional communications between millions of IoT devices and a solution backend. Provides reliable device-to-cloud and cloud-to-device messaging at scale. Event hub A highly scalable publish-subscribe service that can ingest millions of events per second and stream them into multiple applications. Stream Analytics A fully managed, cost effective real-time event processing engine that helps to unlock data stream insights from devices, sensors, web sites, social media, applications, infrastructure systems, and more. Microservices A software architecture style in which complex applications are composed of small, independent processes communicating with each other using language-agnostic APIs. Service Fabric Cluster Service Fabric is an orchestrator of microservices across a cluster of machines. SQL Storage A relational database-as-a-service that delivers predictable performance, scalability, business continuity, data protection, and near-zero administration to cloud developers. DocumentDB Microsoft’s multi-tenant distributed database service for managing JSON documents at Internet scale. DocumentDB indexing enables automatic indexing of documents without requiring a schema or secondary indices. Machine Learning A cloud predictive analytics service that makes it possible to quickly create and deploy predictive models as analytics solutions.
Pricing Calculator To calculate an estimated price for this reference architecture, go to the Microsoft Azure Pricing Calculator. https://azure.microsoft.com/pricing/calculator/