• Written by Muhammed Abdulla NC, CEO

A maintenance log filled with unresolved issues and unactioned recommendations is a common sight in many organisations, and the introduction of AI is often seen as a solution to this problem. However, the failure to properly apply AI to maintenance can lead to a range of negative consequences, including wasted resources and decreased efficiency.

Automating a process nobody mapped

One of the most significant mistakes made when applying AI to maintenance is attempting to automate a process that has not been properly mapped. This can lead to a situation where the AI system is trying to optimise a process that is not fully understood, resulting in suboptimal performance and potential errors. A shift supervisor, for example, may try to use AI to automate the scheduling of maintenance tasks, but if the underlying process has not been properly documented, the AI system may not be able to make informed decisions.

A good example of this can be seen in a manufacturing plant, where a maintenance team may be using a range of different systems and processes to manage their work. If the AI system is not properly integrated with these systems, it may not be able to access the necessary data to make informed decisions, leading to a range of potential problems.

Treating work orders as complete when it is not

Another common mistake made when applying AI to maintenance is treating work orders as complete when they are not. This can happen when an AI system is used to automatically close work orders based on certain criteria, such as the completion of a specific task or the passage of a certain amount of time. However, if the work order is not actually complete, this can lead to a range of problems, including incomplete or inaccurate records and a lack of accountability.

This can be particularly problematic in a production environment, where the accurate tracking of work orders is critical to ensuring that maintenance tasks are properly completed and that equipment is functioning correctly. A category manager, for example, may need to track the status of work orders in order to ensure that maintenance tasks are being properly completed and that equipment is being properly maintained.

Giving the capability only to the analyst who already had it

Many organisations make the mistake of giving the capability to use AI for maintenance only to the analyst who already had it. This can limit the potential benefits of the AI system, as it may not be used by the people who need it most. A maintenance technician, for example, may be able to use the AI system to identify potential problems and schedule maintenance tasks, but if they do not have access to the system, they will not be able to take advantage of its capabilities.

This can be a particular problem in organisations where there is a lack of communication and collaboration between different teams and departments. By giving the capability to use AI for maintenance to a wider range of people, organisations can help to ensure that everyone is working together to achieve common goals.

Declaring success against a metric with no baseline

Declaring success against a metric with no baseline is another common mistake made when applying AI to maintenance. This can happen when an organisation implements an AI system and then declares it a success based on certain metrics, such as a reduction in maintenance costs or an increase in equipment uptime. However, if there is no baseline against which to measure these metrics, it can be difficult to determine whether the AI system is actually having a positive impact.

A good example of this can be seen in an organisation that implements an AI system to predict when equipment is likely to fail. If the organisation does not have a baseline against which to measure the accuracy of these predictions, it can be difficult to determine whether the AI system is actually improving maintenance outcomes. By establishing a baseline and tracking metrics over time, organisations can get a better sense of whether their AI system is actually having a positive impact.

When AI is not the right choice

Finally, it is worth considering when AI may not be the right choice for maintenance. In some cases, the use of AI may not be feasible or cost-effective, particularly in organisations with limited resources or where the potential benefits of AI are not clear. In these cases, organisations may need to consider alternative approaches to maintenance, such as the use of traditional maintenance scheduling systems or the implementation of condition-based maintenance programs.

Organisations that are considering the use of AI for maintenance should carefully evaluate their options and consider factors such as the potential benefits and costs of the system, as well as the potential risks and challenges. By doing so, they can help to ensure that they are making the best possible decision for their organisation. For more information on how to get started with AI for maintenance, please contact us.