In the past, a machine or industrial plant had to literally break down before it was repaired. Today, predictive maintenance systems promise to detect a possible breakdown before it happens. This way, it is possible to reduce downtime and in turn, save expenses.
Systems for predictive maintenance are of course based on a pro-active approach. The current state of the system is measured and assessed. Together with the appropriate model for a prognosis, it is possible to predict quite accurately how and when incidents or downtime are likely to occur. This contributes to the quality of the operation of the machine and increases its life span. Wear and tear costs are additionally reduced and production is optimized.
The successful implementation of predictive maintenance technology depends entirely on the quality of the sensor data. In some industries, such as wind-power producers, it has been possible to achieve great successes in recent years. Vibration analysis has made it possible to accurately predict fallout which could then be prevented with the timely installation of replacement parts.
On the other hand, we have machine tool manufacturers who still find it difficult to come to terms with predictive maintenance. Due to the complexity of their equipment – with their vast variety, complicated assemblies, different mechanical, hydraulic, and often hidden units that have to be precisely matched – the collection of measurable data for use in predictive models is extremely difficult.
At the same time, their customers who use the machines expect great innovations in the field of maintenance and servicing. The goal is to reduce downtime, operating costs, and time spent on services. The manufacturers in turn expect these innovations to lead to new business models, repeat revenues, and competitive advantages over their competitors.
There are many options to give customers tools that reduce downtime and operating costs. The introduction of digital tools that provide maintenance personnel easy access to all critical information is a good start along the route to the self-servicing machine.
Such a tool would be apps for the smartphone and tablet where packing notes, machine files and documentation, and a variety of other pieces of information can be linked. The employees can record incidents, identify defective parts through image recognition, and immediately place an order.
At the same time you – as the manufacturer – can collect important data:
All these pieces of information are useful when developing predictive data models that can (hopefully) prevent disruptions. In the meantime, maintenance personnel already have access to digital tools that have proven extremely helpful – and that bring added revenue to machine manufacturers.
Would you like to know more about our solutions for the identification of replacement parts and our approach to the introduction of digital tools in maintenance and repairs?
We are looking forward to hearing from you!