• Written by Sonali Subhadarsini, Product Manager

A shift supervisor in a printing and packaging plant often finds themselves waiting for a report to answer simple questions about maintenance, such as which machines are due for routine maintenance or what spare parts are currently in stock, and while they wait, production is delayed, and costs are incurred, which is why many maintenance teams are turning to AI for maintenance in printing and packaging to get the answers they need in real time.

The maintenance questions that currently wait on a report

For many maintenance teams, the wait for a report is a familiar frustration, as they try to plan their work around the availability of information, and it is not just the shift supervisor who is affected, as the category manager also needs to know what maintenance has been done on a particular machine in order to make informed decisions about purchasing spare parts or scheduling maintenance, and the maintenance manager needs to know which machines are most prone to breakdowns in order to prioritize their work.

These questions are not trivial, as they have a direct impact on the smooth running of the plant, and the ability to answer them quickly can make a significant difference to productivity and efficiency, and yet, many maintenance teams are still relying on manual systems and reports to get the information they need, which can be time-consuming and prone to error.

The data behind them: work orders, asset history, spare parts inventory, condition data where it exists

The data that maintenance teams need to answer their questions is often scattered across different systems and departments, making it difficult to access and analyze, and this is where AI for maintenance in printing and packaging can help, by providing a single platform for all maintenance-related data, including work orders, asset history, spare parts inventory, and condition data, where it exists, and allowing maintenance teams to query this data in real time, using natural language.

For example, a maintenance manager can ask what machines are currently undergoing maintenance, and what spare parts are required to complete the work, or a category manager can ask what maintenance has been done on a particular machine in the last quarter, and what spare parts have been used, and get an immediate answer, without having to wait for a report or manually search through different systems.

Sector constraints: setup and makeready losses and quoting accuracy

The printing and packaging sector has its own unique constraints, such as setup and makeready losses, which can have a significant impact on productivity and efficiency, and quoting accuracy, which can affect the profitability of jobs, and maintenance teams need to take these constraints into account when planning their work, and AI for maintenance in printing and packaging can help, by providing real-time data and analysis, and allowing maintenance teams to optimize their work around the needs of the plant.

For instance, a maintenance team can use AI to analyze data on setup and makeready losses, and identify areas where improvements can be made, such as reducing the time it takes to set up a machine, or minimizing the amount of waste generated during the makeready process, and they can also use AI to analyze data on quoting accuracy, and identify areas where improvements can be made, such as improving the accuracy of quotes, or reducing the time it takes to generate a quote, and production planning can also be optimized using AI.

What improvement looks like: planned versus reactive ratio, mean time between failures, spares availability

Improvement in maintenance can be measured in a number of ways, such as the planned versus reactive ratio, which shows the proportion of maintenance work that is planned, rather than reactive, and the mean time between failures, which shows how long machines are running without breaking down, and spares availability, which shows how quickly spare parts can be obtained when they are needed, and AI for maintenance in printing and packaging can help maintenance teams to improve these metrics, by providing real-time data and analysis, and allowing them to optimize their work.

For example, a maintenance team can use AI to analyze data on the planned versus reactive ratio, and identify areas where improvements can be made, such as increasing the amount of planned maintenance, or reducing the amount of reactive maintenance, and they can also use AI to analyze data on the mean time between failures, and identify areas where improvements can be made, such as improving the maintenance schedule, or reducing the amount of downtime, and contacting us can provide more information on how AI can be used to improve maintenance.

What this does not do, or when it is the wrong choice

While AI for maintenance in printing and packaging can be a powerful tool, it is not a solution to all maintenance problems, and there are some situations where it may not be the best choice, such as where the data is incomplete or inaccurate, or where the maintenance team is not familiar with the technology, and in these situations, other solutions may be more appropriate, such as manual systems or other types of software.

It is also important to note that AI for maintenance in printing and packaging is not a replacement for human judgment and expertise, but rather a tool to support and enhance it, and maintenance teams should always use their own expertise and experience when making decisions, rather than relying solely on the data and analysis provided by the AI system, and

• understanding the limitations of the technology
• having a clear understanding of the maintenance goals and objectives