Providing essential asset health management and asset maintenance for any organization’s critical assets requires a fine balance. As you are aware, under-maintenance can result in low productivity, expedited costs and even safety risks. At the same time, excessive maintenance of assets can be wasteful – resulting in unnecessary downtime, higher labor costs, and could even create tension between line-managers and maintenance staff.
Over-investing in maintenance can be detrimental to operational and fiscal efficiency. By squandering precious resources – time, budget, and staff – you could be completing work which is not only unnecessary, but expensive as well. The dilemma begs the question: Is there an optimum balance between operations and maintenance, and, if so, how can it be achieved?
IoT-generated data can provide an in-depth view into asset health
The Internet of Things is proving to be one of the greatest technology catalysts for transformation. Through the use of sensors and instrumentation, it’s now possible to use real-time data analysis, cloud and edge computing to gain deeper insights into assets health and performance. By combining advanced analytics with new cognitive capabilities, organizations can now infuse intelligence into physical objects to gain deeper insights into assets health and performance.
Harness the power of preventive and predictive models
Most equipment manufactured today ships with a spectrum of built-in sensors designed to provide reams of real-time data to industrial control systems such as Supervisory Control and Data Acquisition (SCADA) systems, Building Management Systems (BMS) or Programmable Logic Controllers (PLCs). For older equipment, there are simple ways to retrofit assets with sensors too. As a result, operations teams can make use of streaming data from assets to monitor equipment performance and watch for early warning signs of failure – provided the right tools and dashboards are in place to turn that data into actionable insight.
Use case: reducing unnecessary preventive maintenance
As much as 70 percent of an organization’s investment in preventive maintenance has no effect on uptime metrics.
Operating routine maintenance without insight can be costly. Take the instance of a tier one automotive supplier operating a production line with 300 paint guns. In this particular shop, routine maintenance on paint guns is done on a time-based rotation – regardless of use or performance, a paint gun is taken off the line for maintenance every 900 hours.
In our example, the established rotation schedule for the PM is not based on any insight into the performance of the equipment – whether the pressure is off, or if the spray is uneven – it’s based solely on the number of hours the gun is used. In our scenario, the gun has never been run to failure. The conditions of that failure have not been measured. The data from the failure conditions is not being monitored, recorded, or modeled in any way that could help create a better maintenance program – one which kicks-in when a condition of failure is likely to occur. What if you could figure out when a paint gun is likely to fail, and only then have to take that piece of equipment off line for maintenance?
Breaking the digital blindness cycle
By running a piece of equipment to failure, you can establish benchmarks. By first establishing a base line, you are able to make more accurate assessments of when maintenance is actually needed, before a machine breaks.
Whatever the failure criteria is – less pressure, uneven spray – monitoring the data points surrounding these factors will help you see at failure what the readings are. From there, you can build this information into a calculation or model to identify what happens when the equipment reaches that point of failure – and, only at that time, do the PM.
This is a great example of what happens when things are done without insight. In this case, assuming the PM needs to be done without understanding the conditions of failure, your organization ends up wasting money on PMs that don’t need to happen. If you are operating a production line with 300 guns, taking a piece of equipment offline every 900 hours at a cost of 5K a PM means your organization is spending a lot of money unnecessarily.
Having visibility into the health of your assets will take you steps closer to operational efficiency. Understanding when maintenance is needed, for what duration, and at what impact to the organization are critical factors. Tapping advances in technology – analytics, IoT data, cognitive APIs like visual and voice recognition, combined with powerful computer processing – can help organizations gain better insight into their asset health.
Three ways to improve operational effectiveness and ROI
Here are three ways to improve operational efficiency and increase return-on-investment (ROI) using the data gathered from asset management solutions:
- Out-of-the-box technologies collect, filter and map real-time data from equipment and make it available to reliability engineers and maintenance professionals for optimizing preventive maintenance.
- Cloud technologies provide a cost-effective way to aggregate, store and use advanced analytics against massive amounts of data coming from equipment, in combination with other sources.
- Analytics technologies are more powerful in not only capturing tribal knowledge of engineers, but also for uncovering new, hidden patterns that can be used to predict failures. They are also becoming simpler to use, even by those without advanced statistical knowledge. Today’s flexible analytic technologies work with data from multiple sources and in different formats. They even make sense of non-traditional, unstructured data formats such as video.
For the first time, this new world of cutting-edge machine learning and real-time analytics is converging with leading enterprise asset management platforms like IBM Maximo. Together, IoT, EAM, and Analytics provide asset-intensive organizations a complete view of critical assets, enabling on-time maintenance with sharp analytics and cognitive capabilities that infuse intelligence to processes.
Try IBM Maximo Asset Health Insights solution for better insights for preventive maintenance
The IBM Maximo Asset Health Insights solution comprehensively manages asset health for an organization’s entire asset portfolio. The process begins by gathering data streaming from sensors using the Watson IoT Platform to illustrate real-time condition data. This data is then combined with historical data in IBM Maximo, where engineers can define baseline health for each asset or for a class of assets across their operations. The streaming asset health data is used to monitor the health of assets against the pre-defined rules. It is then scored and visualized to easily understand potential problem areas and accelerate preventive maintenance.
Read the paper to learn more about how technology is evolving to augment human intelligence and monitor asset health more accurately. Discover the benefits of asset health management, including greater ROI with IoT and cognitive capabilities for asset health insights.
- Gain operational effectiveness and ROI with the Internet of Things (IoT) and business analytics.
- Infuse your asset management system with new cognitive capabilities for immediate insight into asset health and optimal preventive maintenance scheduling.
- Manage your full asset portfolio with a single, integrated solution including Asset Health Insights, IBM Maximo and Watson IoT Platform.
Visit our website to further explore how you IBM enterprise asset management solutions can help you achieve greater operational efficiency.
The post Take advantage of preventive maintenance in the Cognitive Era appeared first on Internet of Things blog.