The costs of machine downtime in most industries are significant leading to customers demanding higher up-time and more aggressive service level agreements (SLAs). Manufacturers and service providers are turning to Predictive Maintenance techniques that use accurate real-time machine data to determine the condition of a machine and when maintenance should be performed. This approach offers cost savings over routine or time-based preventive maintenance, because tasks are performed only when warranted.
The main value of Predictive Maintenance is to allow convenient scheduling of corrective maintenance and to prevent unexpected equipment failures. The key is "the right information in the right time". By knowing which equipment needs maintenance, maintenance work can be better planned. With a predictive maintenance solution based on your connected products, you can:
- Enable more timely maintenance to increase up-time
- Better plan maintenance work to reduce unnecessary field service calls
- Optimize spare parts replacement and management
- Reduce "unplanned stops" and move to shorter and fewer "planned stops"
- Improve machine performance
- Facilitate service compliance reporting
Many Axeda customers are connecting their products to analyze machine data and enable preventative maintenance. These customers are implementing business rules in Axeda and integrating Axeda alarms and alerts into their enterprise business systems to automate field service, spare part deployment and other preventative maintenance tasks. Machines are being instrumented with temperature, infrared, acoustic, vibration, battery-level and sound sensors to monitor conditions that can be early indicators for the need for maintenance. These sensors are inputs into sophisticated rules for determining service needs.
To drive their predictive maintenance programs, customers are using the Axeda Machine Cloud to collect and manage the machine data and visualization and analytics tools from partners like JackBe to analyze the data and make better decisions. For example, one Axeda customer is collecting hundreds of readings per minute on their machines to monitor early indicators of a potential failure and to pro-actively schedule maintenance or part replacement. Analysis of previous failures identified correlations between internal temperatures and conditions of bearings and eventual machine failures. This customer has reduced unnecessary field service calls and increased up-time significantly by enabling predictive maintenance.
Axeda and JackBe provide the platform and tools for real-time M2M analytics solutions with the following characteristics:
- Real-time Big Data visual exploration of M2M information
- Snapshots for instant visual event trending and insights from Key Performance Indicators
- Apps that visualize live and historical enterprise data mashed with M2M data
- Dashboards that business users can easily assemble quickly and share