Smart Manufacturing Use Case Series: Autonomous Maintenance Support
What is Autonomous Maintenance Support?
Autonomous Maintenance is one of the pillars of Total Productive Maintenance (TPM), but it doesn’t get the same level of attention as many other maintenance initiatives. In this program, the machine operators are responsible for the basic upkeep of the equipment they use every day. In theory, this empowers them to take ownership of the equipment and develop a greater sense of accountability for its upkeep.
Some of the key activities in this program include:
The benefits of autonomous maintenance can include reduced downtime, increased equipment reliability, improved safety, and greater operator engagement. By involving operators in the maintenance process, companies can create a proactive maintenance culture that leads to more efficient and effective operations
.
Who is Involved?
There are many people involved in this process. Let’s break that out into a SIPOC structure.
Suppliers:
The first set of suppliers to the process is the maintenance team. They can supply the existing list of PM tasks, the frequency, and the history of when they have been performed. They’ll also need to supply the work instructions in such a way that operators unfamiliar with the process can execute the tasks. They may even be called upon to provide some training to the operators.
Other suppliers could include engineering to work with maintenance on which tasks should be shifted to the operators. Even the equipment vendors could supply lists of recommended routine maintenance tasks and instructions.
Process:
This will be the operators in the manufacturing process. When the same operator is at a given machine each day, the shift to autonomous maintenance can be relatively straightforward. However, there are usually multiple shifts, rotating assignments, and more that raise the number of people involved in performing the tasks.
Customers:
The maintenance team is a customer in that they no longer have to perform the routine tasks and are freed up to focus on more value-added activities. The overall production team would be the other primary beneficiary. Hopefully the result of this project is better functioning equipment!
Other Stakeholders:
Other stakeholders would be people that benefit from improved shop floor performance such as management and finance.
Why is it Important?
The potential of the project is significant. From a functional perspective, this should have a direct impact on maintenance hours required. It will likely decrease the number of hours spent on preventive maintenance tasks, though that number can actually increase in situations where not enough PMs were currently being performed.
Because the tasks should be a higher priority for the operators than the maintenance team, it should help these tasks get performed on a more regular basis. This change should reduce the number of hours spent on reactive maintenance required due to unplanned downtime events. That is because the unplanned downtime events themselves should see a significant reduction. The reduction will then drive improvements to many KPI such as throughput, on time performance and schedule adherence.
This will also drive many financial benefits. The overall maintenance expense should decrease, but there will almost certainly be a decrease in maintenance overtime hours required when unexpected failures occur and must be immediately addressed. If throughput is increased, revenues should go up as well. If on time performance is improved, this could also lead to a reduction in customer penalties.
Other benefits could include improvements to product quality. When machines fail unexpectedly, the parts in process can often be damaged. In other environments such as a bakery, unplanned stops in the process can cause large portions of the in process material needing to be scrapped. Another soft benefit is that the quality of life at the job is higher for everyone involved when unplanned downtime decreases. The shift in responsibilities should also help to increase the feeling of ownership and autonomy on behalf of the operators.
Why is it Hard Today?
The shift to autonomous maintenance can be hard for many reasons.
This aspect is a bit out of scope here, but there needs to be a strong effort to help the workforce understand the reason for the change. Depending on how things have been run in the past, there can be a tendency to look at this as just one more thing being dumped on them. Be sure to emphasize that this is part of an overall effort to empower them, not just give them more busy work to get done.
领英推荐
There is also a likely need for additional data from the process. There needs to be a way to record when the tasks are performed, along with any data collection necessary when they are done. Additionally, the process then needs to track the calendar time, hours of production, or the number of pieces since the last time a given task was performed. That way, the solution can determine when the next instance of that task is required.
There are likely management changes that need to take place, as well. First off, it has to become an emphasis to empower the workers on the shop floor. If you are seeking for them to take more ownership of the equipment on the shop floor and the process results, then management must upgrade its treatment of employees. This means a review and alteration of the workforce KPIs and measurements, daily communication practices, and much more.
Finally, there is the hurdle of implementing the autonomous maintenance methods themselves. The overall practice may not be in place today, so it must be established. Then the detailed procedures for individual pieces of equipment must be established, documented and communicated. Then there needs to be mechanisms for the workers to know what they are supposed to do at what time, and also what they need to report back when the tasks are complete. The infrastructure for all of this is lacking in most operations today.
How Can We Do It Better?
Fortunately, technology solutions can make the shift to Autonomous Maintenance much easier. Here are some key steps to making the transition in your company.
The first step is to determine the tasks to be performed by the operators. This involves an initial analysis of the existing preventive maintenance routines to determine which of those can and should be performed by the operators. It is important for these tasks to then be fully documented with a system of record such as a Maintenance Management System (MMS). This should include work instructions as well as the proper interval for the task or condition under which it should be performed. This analysis should be a periodic effort, also. Ideally, there would be a quarterly review of both preventive and autonomous maintenance tasks to measure their effectiveness and optimize the overall task list, as well as the balance between PM and AM.
Training should also be a significant part of the plan for the transition to Autonomous Maintenance. The team may need assistance on how to perform the analysis on which taks to transfer from preventive to autonomous. They may also need some assistance in how to create the master data around the new processes within the system of record. Additionally, there may need to be some training for the operators from the maintenance team on how to perform the actual tasks. Whether this type of training is required or not depends on the complexity of the tasks, the existing skill sets, how often operators rotate across different jobs, etc.
There are a couple of key technologies to facilitate this shift. There are multiple ways to go support the change, but this is the approach with the fewest moving parts involved. The first key solution is the Maintenance Management System mentioned above. This system is important because it will be the system of record for the maintenance activities, it will own the work instructions for the tasks, the additional details about each task such as the trigger or interval, and the history for all of the completed tasks. The second key piece of the puzzle is an IoT Platform (Internet of Things). There are other approaches, but they would all involve multiple components whereas the IoT system can do all of the following on its own.
The IoT system would be responsible for providing an interface for the operators at the work station. This interface would be used to prompt the operators when tasks need to be performed, provide the instructions for those tasks, and collect any desired (or required) information about the task when it is completed. Additionally, the IoT system would be used to collect information from the process itself to determine when the tasks need to be performed. This may be based on runtime for that machine since the last task instance, number of pieces produced, or a condition-based metric such as oil temperature. Two-way integration between these two systems is also critical to facilitating the overall process.
AI systems can also play a big role in easing the transition to Autonomous Maintenance. There are efforts underway to pilot utilizing Generative AI to produce work instructions for tasks that do not currently have them. At this time, that output would still require review from people that know the details of that process, but the promise is there to save a tremendous amount of time and reduce a big barrier to moving forward.
Additionally, AI could be used to provide an ongoing analysis of the impact of the preventive / autonomous maintenance tasks themselves. This can help to reduce costs and/or increase performance by eliminating tasks that are not providing real value, increase the frequency of tasks that provide an impact but are seeing machine failures between task instances, or decrease frequency of tasks that provide an impact but are never seeing any failures between PM/AM tasks.
There are a few dependencies on other initiatives. Primarily, this refers to the MMS and IoT systems. But there also needs to be some infrastructure in place to make this work. First, there needs to be a reliable network on the shop floor. Then there also needs to be a computer, tablet or other screen at each of the machines where the autonomous maintenance tasks will be performed.
Key Data Sources
The key data sources are straightforward. The maintenance management system needs to supply the task list, along with the frequencies of the tasks and when the tasks were created. The history of when those tasks have been done in the past can also be very helpful.
The shop floor data systems will provide information about the machines. They should provide the downtime history, the failure reasons for those downtime events, as well as other performance information.
Case Study
Many companies recognize the benefits of an autonomous maintenance program but struggle to implement one. This can be for a variety of reasons, such as high job rotations among operators. High attrition rates among direct employees since covid has also made these programs much more difficult to put in place or maintain.
In this case, the crew rotated jobs frequently. This meant that operators would need to know how to perform the autonomous maintenance tasks across a high number of machines. There would also need to be some way for them to know what tasks would need to be performed that day. These issues (and more) made it impractical for the company to have the operator take on more of the routine maintenance tasks.
However, since they were already implementing an IoT system across their shop floor, it presented an opportunity to use technology to knock down the roadblocks.
There were three main steps to facilitating the transition:
With these changes in place, the company began to roll out the program across the floor one station at a time. Over the course of a few months, all of the primary operations were covered by the initiative.
(This case study was for a fictional company, but it has its basis in projects performed over the years)
Summary
That’s it for today!
If you have questions or would like to talk about how to apply these concepts within your company, please reach out to us at VDI.