Helios’ new failure prediction capabilities allow you to predict machine performance in real time.
There’s nothing worse than playing catch-up after something goes wrong unexpectedly. Unplanned downtime costs industrial manufacturers an estimated $50 billion per year, and the problem is particularly urgent in the corrugated business, where producers are pushing equipment to their limits to meet increased demand.
Fortunately, Helios’ new failure prediction capabilities offer corrugated manufacturers the ability to not only monitor machine performance in real time, but to view an ongoing assessment of the likelihood of failure or interruption within a 30-minute window. This new machine learning algorithm provides operators with actionable insight into the well-being of their equipment that can help them forecast future problems and reroute production to prioritize critical projects and avoid delays.
A revolution in predictive analytics
Helios is a machine-learning IIoT (Industrial Internet of Things) platform that provides critical insight into corrugated machine performance. Our algorithms are OEM-agnostic and can be seamlessly retrofitted to existing equipment. Customers who subscribe to the full suite of advanced machine learning features now have access to something new: advanced predictive analytics with real time prediction of component failures and required maintenance.
This new feature harnesses current sensor information along with historical downtime data in order to provide not just an up-to-date picture of the state of your equipment, but actionable information about future functioning so operators can make proactive decisions about their machines. The algorithms are no longer simply providing diagnostic information about past machine performance: they’re providing a picture of ongoing and future performance, legibly displayed through dials and gauges. An initial case study found that 74% of machine breakdowns were accurately forecasted within a 30-minute window using this new technology.
This gives operators the chance to make decisions in advance before a possible interruption occurs. With just a 20% reduction in downtime, the average box plant can expect to save $122,000 per year per machine. If a machine is operating at high risk of failure, operators can stop it in advance to investigate the cause before a disruption. Managers can also reroute work ahead of time for high priority projects or alter production schedules accordingly to avoid a break-down. This information empowers plant leadership to make better decisions about the reliability and efficiency of their equipment.
Harnessing real time and historical data
The ability to provide these kinds of advanced predictions was previously only theoretical. But now these machine learning models are fully operational and live on the platform for select Helios customers. Early adopters of this powerful new technology are already reducing maintenance costs by 30% and eliminating equipment breakdowns by 70%.
In order to generate these predictive models, Helios needs two distinct sets of data. The first is the ongoing raw information provided by sensors on the equipment as it’s operating. The second is historical downtime data, listing the start and end times of previous unplanned disruptions along with explanations and descriptions of the problems that were encountered.
Ideally there should be at least eight to twelve weeks’ worth of data for the machine learning to function optimally. Helios’ data scientists work with customers to input this information in order to get the predictive algorithm fully operational. And once the systems are in place, the predictive power of Helios’ machine learning only gets more refined.
While the initial study predicted 74% of machine breakdowns, that number is only a starting point: it will improve as Helios’ algorithms gather more information about ongoing machine performance, providing operators with increasingly sophisticated forecasts within a 15 minute window. Over time, these progressive solutions allow for increasingly accurate downtime predictions, more advanced warning, and in turn, improve uptime and ROI.
Helios has changed the game
The rise of e-commerce has brought rapid growth to the corrugated industry, and increased demand means it’s more important than ever to make sure equipment is operating as efficiently as possible. But optimizing machine performance is a delicate balancing act coordinating dozens of different machines, each with its own output rates and maintenance schedules. Historically the industry has relied on the knowledge and experience of a generation of operators, many of whom are now retiring – and a skills gap has meant that there are fewer people to take their place.
Consequently it’s more important than ever to leverage IIoT solutions to harness the power of information. Machine learning is revolutionizing how box plants understand, predict, and maintain their corrugated converting equipment, and Helios’ new failure prediction capabilities place it at the forefront of the industry.