• Written by Sonali Subhadarsini, Product Manager

In theory, a production team in the automotive sector should be able to ask their data anything, from the current output against plan to the maintenance history of a specific machine, and get immediate answers. However, in practice, many of these questions currently wait on a report, which can take days or even weeks to materialise, by which time the information is often outdated and less useful for making timely decisions.

The production questions that currently wait on a report

The shift supervisor, for instance, may want to know the current production levels, or the category manager may need to compare the performance of different suppliers. These questions are critical to the smooth operation of the production line, but the answers are often stuck in a report that is only generated at the end of the week or month. This can lead to delays and inefficiencies, as decisions are made based on outdated information. The production team may also want to ask more complex questions, such as what is the impact of a specific engineering change on the production schedule, or how does the current scrap rate compare to the same period last year.

A closer look at the types of questions that are currently waiting on a report reveals that many of them are related to the daily operations of the production line. For example, the production manager may want to know the current status of the production schedule, or the maintenance team may need to check the maintenance history of a specific machine. These questions are essential to the efficient operation of the production line, but the answers are often not readily available.

The data behind them: output against plan, cycle times, scrap and quality records, maintenance history

The data that underlies these questions is complex and multifaceted. It includes output against plan, which shows how the current production levels compare to the planned levels. It also includes cycle times, which show how long each production step takes, as well as scrap and quality records, which show the number of defective products and the quality of the products being produced. Additionally, the data includes maintenance history, which shows when each machine was last maintained and what maintenance was performed. This data is critical to understanding the current state of the production line and making informed decisions about how to improve it.

The data is often stored in different systems, such as enterprise resource planning (ERP) systems, manufacturing execution systems (MES), and computerised maintenance management systems (CMMS). This can make it difficult to access and analyse the data, as it requires integrating data from multiple systems. However, with the right tools and technology, it is possible to bring this data together and provide the production team with the insights they need to make informed decisions.

Sector constraints: supplier escalations and engineering change propagation

The automotive sector has a number of unique constraints that can impact the production process. One of these is the tiered supply chain, where multiple suppliers provide components to the production line. This can lead to supplier escalations, where a problem with one supplier has a ripple effect throughout the entire supply chain. Another constraint is the long programmes, where production runs for extended periods with minimal changes. This can make it difficult to implement changes or improvements to the production process, as it requires coordinating with multiple stakeholders and suppliers.

Engineering change propagation is another constraint that can impact the production process. When a change is made to the design or production process, it can have a ripple effect throughout the entire production line, requiring updates to multiple systems and processes. This can be time-consuming and costly, and requires careful planning and coordination to implement successfully. The production team must be able to ask questions about the impact of these changes and get immediate answers in order to make informed decisions.

What improvement looks like: OEE, unplanned downtime hours, scrap rate

Improvement in the production process can be measured in a number of ways, including overall equipment effectiveness (OEE), unplanned downtime hours, and scrap rate. OEE measures the percentage of time that the production line is running at full capacity, producing high-quality products. Unplanned downtime hours measure the amount of time that the production line is down due to unexpected problems or maintenance. Scrap rate measures the percentage of defective products being produced. By reducing unplanned downtime hours and scrap rate, and increasing OEE, the production team can improve the efficiency and effectiveness of the production line.

For example, a production team may use production data to identify areas where they can improve OEE, such as by reducing setup times or improving machine reliability. They may also use this data to identify the root causes of unplanned downtime hours, such as equipment failures or maintenance issues, and take steps to address these problems. By asking the right questions and getting immediate answers, the production team can make informed decisions and drive improvement in the production process.

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

While AI for production in automotive can provide valuable insights and improvements to the production process, it is not a silver bullet. It is not a replacement for human judgment and expertise, and it should not be relied upon as the sole source of decision-making. Additionally, it may not be the right choice for every production team, particularly those with very simple or low-volume production processes. In these cases, the benefits of AI for production may not outweigh the costs and complexity of implementation. If you are considering implementing AI for production in your organisation, you can contact us to discuss your specific needs and determine whether it is the right choice for you.