Do you remember when a typical tire plant could confidently run the same tire types for days – or weeks? Changeovers could take hours. But because it was an occasional and predictable event, changeover did not dramatically impact productivity.
I don’t need to tell you those days are long gone. As a tire manufacturer, you must produce more SKU variations than ever to meet the evolving demands of automotive manufacturers. At the same time, the tire aftermarket expects minimal lead times – and reliable supply across your distribution network.
To boost production agility and meet contemporary challenges, tiremakers across the board are turning to digital technology. But exactly how to approach digitalization can be a daunting task for cost-conscious producers with an extensive installed base of legacy equipment.
There’s Not a Single Path to Digitalization
In my work as an automotive and tire industry consultant, I have learned that exactly how a particular tire manufacturer begins their digitalization journey is as unique as the challenges within their plants. Here are the key questions they are asking:
- Where are the bottlenecks?
- Where and how can digital initiatives make the biggest impact – given the ever-present constraints of time and available funding
When it comes to managing complexity – and responding to market demands – a manufacturing execution system (MES) checks all the boxes. An MES can orchestrate and manage your manufacturing process from raw materials to mixing, prep, assembly, curing, finish, test and warehousing.
When you install a platform MES, you can expect significant benefits throughout plant operations. An MES schedules and orchestrates the production of every tire – including the machine set-up and material requirements – based on each product’s engineering master data. An MES provides comprehensive control, sequencing, monitoring, traceability, alerts and documentation – throughout the entire manufacturing process. An MES enforces build standards and work instructions – and allows managers to make dynamic workforce assignments based on skillset and actual production needs.
This level of control and organization significantly reduces expired stock, work in progress, and scrap product in any given plant. And an MES across your entire manufacturing footprint improves overall agility and gives you the control to change production schedules quickly and efficiently to meet market demands and improve overall operating efficiency (OEE).
But while a platform MES is critical for sustainable end-to-end optimization, moving forward can prove to be a challenging decision for some tire manufacturers. Frankly, implementing a comprehensive MES requires an enterprise commitment to change – plus determination to break down organizational barriers and certain operational processes. It can be a significant investment, especially for existing plants that have developed and grown without consistent structure over time.
That’s why the path to digital tire often begins more simply – with initiatives focused on applying scalable Internet of Things (IoT) technology to optimize specific machine center performance.
Scalable IoT Technology Starts with Visualization & Analytics
Tire manufacturing is certainly a complex process. But with many similar machine types, tire manufacturers can gain significant incremental value from optimization efforts targeted on bottlenecks.
While people interacting with the machines day in and day out have good instinct into where those bottlenecks are, pinpointing issues is difficult when real-time machine performance visibility is limited. In addition, many machine centers are a combination of newer and legacy equipment – with varying levels of automation and performance visibility.
So how do you know which equipment is meeting designed cycle times – or which operators are falling behind? How can you view the operation of the machine center as a whole and determine where bottlenecks actually are – and how to optimize performance?
To improve process visibility, many tire manufacturers focus IoT initiatives first on scalable analytics software that can collect and consolidate data from many disparate sources and place it in meaningful context.
Basic analytics turns raw data into the kind of reporting and dashboards that can help you identify performance issues and make informed decisions. Specifically, this will help you answer the questions: “What happened?” and “Why did it happen?”
With a data science approach, you can extend these capabilities to predictive and prescriptive analytics – which help you answer the questions: “When will that happen again?” and “What can I do to avoid that?” These advanced analytics often use machine learning and artificial intelligence to deliver extraordinary insight – and performance gains:
- Predictive analytics recognize and learn patterns in the data that precede equipment failures or production anomalies – and can alert personnel to investigate or perform maintenance proactively.
- Prescriptive analytics not only predict a likely issue, but also prescribe actions to avoid downtime, improve cycle time or help ensure product quality.