Making the decision to transition to automated condition monitoring shouldn’t be taken lightly. Far from a standalone maintenance project, automatic condition monitoring requires a shift in the entire organizational culture to support dramatic process, attitude and skillset changes. These changes can bring significant challenges, but by moving from manual to automatic condition monitoring, an organization can enable factory and organization-level scalability. A half-hearted or poorly planned implementation could see a substantial investment result in disappointing results.
So, how can an organization ready itself? We have put together a three-point checklist outlining the ideal groundwork.
1. Improving data acquisition and management
Data is the foundation of condition monitoring programs, so the correct sensors need to be in place on the right equipment to fuel the analysis engine. Acquiring data doesn’t need to be complicated or advanced (for example it doesn’t need to be full-scale vibration monitoring) but some level of monitoring such as thermocouples attached to PLCs or current monitoring of drives should exist.
You need to ask some key questions before taking the next step:
- What is the monetary value of improving our maintenance?
- How reliable do we need to be?
- Which are our critical assets?
- Are we collecting the correct data, in an appropriate format?
- Do we have the correct people to help us transition to predictive maintenance?
It is then important for this data to be accessible. Constant monitoring produces huge volumes of data and whilst direct internet connectivity on the shop floor may make things easy from an analysis point of view, careful consideration needs to be given to security. Effective mechanisms of separating IT and OT networks need to be employed but these don’t need to be painful – a simple IOLink interface could suffice or solutions like Siemens MindSphere can take all of the security and connectivity worries away.
If you have historic data in a compatible format – from an IoT middleware platform such as ThingWorx, Predix or MindSphere, or a more traditional factory Historian such as Kepware, Wonderware or OSI PI. Although you could start with something as simple as a CSV file regularly exported – this can fast-forward the path to meaningful diagnostic and prognostics.
Finally, as much information should be obtained on the monitored equipment as possible, such as any valuable nameplate information, equipment location, safety concerns and rotating speed. This can be used to identify specific faults in the monitored equipment and can greatly increase the accuracy of your analysis efforts. This information may be available from a variety of sources in your facility, such as the Computerized Maintenance Management System (CMMS), plant library, or various other resources.
2. Evolving your entire organizational (maintenance) culture
The move from manual to automatic condition monitoring isn’t just a technical one. It represents a shift in company culture which employees need to buy into. To achieve this, a planned communications programme should be established, outlining project goals and benefits and providing updates along the way. This should not only demonstrate the benefits to staff, but also help people to see the bigger picture during busier or more challenging periods. A strong project team from around the business can help with communication, feedback and keeping the project moving forwards, as well as carrying out any required training in their respective departments.
Security should be high on your priority list, with cyber threats in industry at an all-time high. Involving IT at the beginning of the process will make them a supporter rather than a road block later. Too often the biggest security threats such as the Meltdown and Spectre calamities are internal. Ensuring staff are mindful of security, updating passwords, ensuring antivirus software is up to date, encrypting data, keeping on top of permissions, maintaining a firewall; these are some of the areas which are critical in maintaining a secure network. However, any addition to a network carries additional risk and needs to be properly assessed. Solution providers should be able to provide security documentation, including third party audits, and answer any questions posed by your IT team. Your IT department may have valuable suggestions that can contribute to the overall success of the condition monitoring technology or may have concerns that must be addressed before implementation.
3. Additional short-term investment
Any significant business project requires an implementation budget; for staff training, sensors, data storage and infrastructure costs. Also, when moving from a preventative to proactive approach to maintenance, there is inevitably a cross-over ‘bulge’ period where existing scheduled maintenance is taking place alongside new preventative jobs/actions. As confidence in the predictive approach grows, the scheduled maintenance can be reduced. In the meantime, there is a bulge in the workload. Managing this requires flexible manpower planning and an upfront communications plan in place to avoid any nasty surprises and reassure maintenance teams.
Start with something manageable - try a pilot program. Identify known machine that requires a constant level of monitoring and set up a small test to continuously capture and analyse the data. This will help you to develop an appropriate workflow and build up the internal culture necessary to take advantage of this change in practise, before you scale it up to the entire factory.
See the bigger picture to realise the opportunity
Any project has ups and downs and the journey to automatic condition monitoring is no different. Amidst the day-to-day challenges, it is important to stay focused by reflecting on the reasons for the move to condition monitoring and the opportunities it presents for the organization (see our previous blog: Preventative vs Predictive Maintenance and why you need to get on board). The ability to automatically predict machine failure is a powerful tool and can bring benefits including reduced unplanned downtime, improved scheduling and a safer, more reliable environment. Longer term, it can lead to a complete shift in the way a business operates, such as moving to a servitization model. The future is opportunistic!
Want to see our easy-to-use diagnostics, prognostics and condition monitoring product Senseye in action and learn how it can save you downtime? Request a live demo here.