• Written by Azhar Aliyar, Director

A production manager at a manufacturing plant is deciding whether to adjust the production schedule for the upcoming week, and currently bases this decision on manual checks of the maintenance log and scrap reports, but with the introduction of AsscherAi, they will be able to query the plant's data in real time to inform their decision.

Field-level meaning and why column names are not documentation

The success of AsscherAi in providing accurate answers to production-related questions depends on the quality of the data foundations, specifically the field-level meaning of the data stored in the production database. Column names such as "status" or "quantity" are not sufficient documentation, as they do not provide enough context about what these fields represent in the production process. For example, a shift supervisor checking the production schedule may not understand what "status" refers to without additional context.

Most people get wrong the idea that column names are enough to understand the data, but they are wrong. The meaning of each field must be clearly defined and documented, so that when a question is asked, the system can accurately retrieve the relevant data. This requires a thorough understanding of the production process and the data that supports it.

The systems that get left out of scope and the partial answers that follow

When implementing AsscherAi, it is common for certain systems to be left out of scope, such as the quality control system or the maintenance management system. This can lead to partial answers, as the system may not have access to all the relevant data. For instance, a question about the causes of scrap may not be fully answerable if the quality control system is not integrated.

This can be particularly problematic in production, where data from multiple systems is often required to get a complete picture. The production manager may need to manually check multiple systems to get the information they need, which can be time-consuming and prone to errors.

The production data this depends on: output against plan, cycle times, scrap and quality records, maintenance history

The production data that AsscherAi depends on includes output against plan, cycle times, scrap and quality records, and maintenance history. This data is critical to understanding the production process and identifying areas for improvement. For example, a category manager comparing two suppliers may want to know the cycle times for each supplier to determine which one is more efficient.

The maintenance history is also crucial, as it can help identify patterns of equipment failure or downtime, which can inform decisions about maintenance scheduling and resource allocation. By analyzing this data, the production manager can optimize the production schedule and reduce the risk of unplanned downtime.

What it changes about: unplanned downtime and stock cover against the plan

AsscherAi can help production managers make more informed decisions about unplanned downtime and stock cover against the plan. By analyzing data from the production database, the system can identify patterns and trends that may indicate a higher risk of unplanned downtime, allowing the production manager to take proactive measures to mitigate this risk.

For example, if the system identifies a pattern of equipment failure during a particular shift, the production manager can schedule additional maintenance during that shift to reduce the risk of downtime. This can help to minimize the impact of unplanned downtime on production and reduce the need for stock cover against the plan. To learn more about how AsscherAi can support production planning, visit our production page.

Measured with: OEE, unplanned downtime hours, scrap rate

The effectiveness of AsscherAi in production can be measured using key performance indicators such as Overall Equipment Effectiveness (OEE), unplanned downtime hours, and scrap rate. These metrics provide a clear picture of the production process and can help identify areas for improvement.

By tracking these metrics, the production manager can see the impact of AsscherAi on the production process and make adjustments as needed. For instance, if the OEE is lower than expected, the production manager may need to investigate the causes of equipment downtime or inefficiency. If you have questions about how to implement AsscherAi in your production environment, please contact us for more information.

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

AsscherAi is not a replacement for human judgment and expertise in production. While the system can provide valuable insights and data-driven answers, it is not a substitute for the experience and knowledge of production managers and supervisors.

In situations where the production process is highly complex or dynamic, AsscherAi may not be the best solution. For example, in a highly customized production environment, the system may struggle to provide accurate answers due to the unique nature of each product. In these cases, other solutions may be more effective, such as manual data analysis or specialized production planning software.