Manufacturers collect large amounts of data, but when it comes to getting real value from that data, many companies often fall short. One area where manufacturing operations could particularly benefit from data is machine health and performance. Keeping a close watch on how your production machinery is working can lead directly to better business decisions and increases in operating income. Keep reading to learn more about how you can leverage machine condition monitoring in your operations to power efficiency and profitability.
From data-driven machine insight to condition-based maintenance
So far, the strategic use of data from manufacturers’ machines and production lines connected to the industrial internet of things (IIoT) to assess their actual condition is mostly seen in larger, leading and more forward-looking manufacturing businesses.
Many companies are looking for ways to capitalize on the IIoT, but they are also grappling with security concerns or unsure of what their strategy should be.
There are real benefits to monitoring the condition of your machinery and equipment. Most importantly, it can enable condition-based maintenance and help you produce better business outcomes from your assets.
To do this, you need to find a way to extract intelligence from the masses of data generated in your operation. If you apply meaningful measurements, such as performance or dependability, you soon get a better sense of how well your industrial assets are supporting your goals.
If you take a step further and subject real-time data to an analysis of metrics that matter, you can act when you can make a real difference, improving the business results from your machines and production resources.
To accomplish this you can apply, for example, Overall Equipment Effectiveness (OEE), which comprises assessments of the performance, availability and quality produced by your machinery into a single compound value.
Once you know the OEE values in your operation, you can improve them, keeping an eye on the data evidence to verify that your actions create the results you want.
In OEE, lean manufacturing meets the IoT
OEE was originally developed in the discipline of lean manufacturing, and lean practitioners have created best practices to take effective action to improve your OEE results and avoid distraction from data overload.
In one approach, you first need to identify the constraint – the machine or process action that determines the output more than any other element – and then treat it as a priority. You determine what quality faults, performance losses or breakdowns occur, identify the steps to correct them and capture the results.
Then you refine your approach or move on to the next-urgent IIoT finding that highlights a need for improvement.
You can find on industry websites various descriptions of this common-sense method, often referred to as IDA, which stands for “information, decision, action.” When you follow it to review and act promptly on real-time data, you can boost OEE.
Several desirable outcomes can then happen. For instance, you might run at full capacity, avoid unplanned breakdowns, minimize waste and maintain a steady flow of production. Those, in turn, have a direct impact on the quality you provide to customers, the timeliness of your delivery and your ability to run a profitable operation.
Large payoffs in condition-based monitoring
Improving OEE by as little as 10% can improve a manufacturer’s bottom line by 20% or more. On average, machinery runs at between 35% and 45% OEE, which means many companies could do much better and are not currently enjoying the benefit of immediately actionable improvement opportunities.
Frequently, part of the reason is that they are not looking at all the data they should consider or do so with a delay, when poor quality or slow production have already harmed the customer experience.
Keep in mind that OEE improvements are not the sole reason for condition-based monitoring. You can use innius IoT data to review how well machines withstand their workloads, anticipating and avoiding possible machine slowdowns and breakdowns before they impact your production.
Alerts sent to the right people when IoT sensor data cross certain thresholds help them jump into action by getting a technician to the machine to replace a part, for instance, or adjusting the flow of raw materials.
Some manufacturers also collaborate with customers and help them make more effective use of their machines, improve operator training or optimize parts design and functionality.