Every day, maintenance planning faces the challenge of how to ensure the maximum availability of machines while simultaneously minimizing material consumption for maintenance and repairs – all with an eye to guaranteeing product quality.
This is a requirement that most existing maintenance concepts are unable to meet. But why? Frequently, the data is not yet intelligently evaluated across the various machines and processes, and the useful findings and information this would yield cannot be exploited.
In resistance spot welding, welding guns with copper-alloy electrode caps are used. The amount of wear and tear on these caps is one of the decisive factors for the quality of the spot weld. Usually, the caps are maintained according to fixed intervals. This entails milling the caps after a defined number of spot welds, and then replacing them once they have gone through a defined number of milling cycles. To avoid quality problems, this tends to be carried out earlier than required.
Using suitable machine learning algorithms, data analytics can help identify the optimum time for maintenance from the process data. This predictive maintenance provides several benefits for the welding process:
Cut costs. Minimize downtimes. Increase productivity. Detecting machine faults early on drives efficiency in your maintenance process and opens up completely new possibilities for your company:
Help yourself to new market opportunities: offer your customers supplementary services in the area of maintenance and resource optimization.
Effectively planned maintenance measures reduce costs, increase customer satisfaction, and differentiate your offering from the competition.
Smart Industry 4.0 approaches, such as Manufacturing Analytics and the Production Performance Manager, allow for integrated, smooth processes throughout the entire maintenance process and across all departments.
Making it easier to plan maintenance measures allows expensive downtimes to be avoided and keeps costs down when employing resources.
Together with our customers, we generally follow a comprehensive approach for realizing predictive maintenance projects. It covers all process steps, starting with the automated detection and early warning of process deviations and machine failures, through the planning of scheduled downtimes, all the way to transparent documentation.
Our portfolio is aimed at your requirements, existing data, and the IT infrastructure you have in place for maintenance purposes. We offer a variety of solutions and components that can be combined to suit your needs, implemented as stand-alone solutions, or extended at any time:
We develop predictive maintenance models that can be integrated into your existing infrastructure. Even after hand-off, our maintenance & support team continues to help further refine your automated algorithms, and retrain them as needed.
The Production Performance Manager facilitates intelligent repair and maintenance management. Based on machine reports, a central system records repair and maintenance tasks and assigns them to the appropriate operator.