• Written by Sonali Subhadarsini, Product Manager

A typical Monday morning for a logistics maintenance team begins with a review of the weekend's activities, checking the maintenance log to see what work was completed and what still needs attention, and this is where the shift supervisor often realises that some questions about the team's performance will have to wait for the weekly report to be generated, which can be frustrating when trying to plan for the day ahead.

The maintenance questions that currently wait on a report

The maintenance team in a logistics organisation often finds itself waiting for reports to be generated before it can answer questions about its own performance, such as which assets are due for maintenance, what the current spare parts inventory levels are, and what the mean time between failures is for a particular type of equipment, and this waiting can lead to delays in planning and decision making.

For instance, the shift supervisor may need to know which drivers are available to take on extra work, or which vehicles are currently in the workshop, but this information is not readily available without waiting for the report, and even then, it may not be up to date, and this is where having access to real-time data can make a big difference, as it allows the team to respond quickly to changing circumstances, such as a sudden increase in demand or an unexpected equipment failure.

This is particularly relevant in logistics, where the ability to respond quickly to changing circumstances can make a big difference to the overall efficiency of the operation, and where having access to real-time data can help the maintenance team to plan and prioritise its work more effectively, and to make better decisions about how to allocate its resources, which can be critical in a sector where cost and service are constantly trading off against each other.

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

The data that the maintenance team needs to answer its questions is typically stored in a variety of different systems, including the maintenance management system, the enterprise resource planning system, and the fleet management system, and this can make it difficult to get a complete picture of what is going on, as the data is often fragmented and not easily accessible.

For example, the work order system may contain information about what maintenance has been carried out, and when, but it may not be linked to the asset history, which contains information about the asset's overall condition and maintenance record, and the spare parts inventory system may be separate again, making it difficult to get a complete picture of what is available and what is needed, and this is where a system like AsscherAi can help, by providing a way to query the data in natural language and get answers in real time, which can be particularly useful for teams that are used to working with production systems.

Sector constraints: carrier performance variance and dwell and detention

Logistics is a sector that is subject to a variety of constraints, including carrier performance variance, and dwell and detention, which can all impact on the maintenance team's ability to plan and prioritise its work, and where having access to real-time data can help to mitigate some of these risks, by allowing the team to respond quickly to changing circumstances, such as a change in carrier performance, or an increase in dwell and detention times.

For instance, if a carrier is experiencing problems with its fleet, this can impact on the maintenance team's ability to get vehicles in for maintenance, and if dwell and detention times are increasing, this can impact on the team's ability to get vehicles back on the road quickly, and this is where having access to real-time data can help, by allowing the team to plan and prioritise its work more effectively, and to make better decisions about how to allocate its resources, which can be critical in a sector where cost and service are constantly trading off against each other.

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

Improvement in maintenance can be measured in a variety of ways, including the planned versus reactive ratio, the mean time between failures, and spares availability, and where having access to real-time data can help the maintenance team to track its performance and identify areas for improvement, which can be critical in a sector where cost and service are constantly trading off against each other.

For example, the category manager may want to know what the current planned versus reactive ratio is, in order to identify areas where the team can improve its planning and prioritisation, and the mean time between failures can help to identify areas where the team can improve its maintenance procedures, and spares availability can help to identify areas where the team can improve its inventory management, and this is where a system like AsscherAi can help, by providing a way to query the data in natural language and get answers in real time, which can be particularly useful for teams that are looking to improve their performance and get in touch with experts who can help.

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

While a system like AsscherAi can be very useful for maintenance teams in logistics, it is not a replacement for other systems, such as maintenance management systems, or enterprise resource planning systems, and it is not suitable for all types of data, such as unstructured data, or data that is not well organised, and this is where the maintenance team needs to be careful about what it is trying to achieve, and to make sure that it is using the right tool for the job.

Most people get wrong the idea that AI for maintenance in logistics is about replacing human decision making with automated decision making, but this is not the case, as the goal of a system like AsscherAi is to provide the maintenance team with the data it needs to make better decisions, not to make the decisions for it, and this is where the team needs to be careful about how it is using the system, and to make sure that it is not relying too heavily on automation, but is instead using the system to support its decision making, which can be critical in a sector where cost and service are constantly trading off against each other.