The Lean Manufacturing approach identifies seven types of waste. These wastes can be directly applied to the maintenance segment.

1. Overproduction — performing maintenance when or where it is not needed.
2. Delay — waiting for spare parts or technicians due to poor scheduling or inventory.
3. Transportation — spare parts or technicians not where they need to be.
4. Processing — applying an incorrect standard or procedure for maintenance.
5. Inventory — holding too few, too many, or the wrong spare parts.
6. Motion — unnecessary steps in the maintenance process.
7. Defect — maintenance tasks carried out incorrectly.

Get smart

So how do you eliminate these wastes? Luckily, technology provides practical methods to optimize maintenance management and truly bring it under control.

Industry 4.0 has made the smart factory concept a reality. This concept is basically a highly digitized factory, with online equipment control and AI tools to interpret real-time data.

However, the answer is not to simply go digital with everything — a careful and pragmatic strategy needs to be in place. The areas of manufacturing that promise the most significant benefit from digitization need to be identified and prioritized.

A practical example of gaining efficiency from a digital approach is the automation of maintenance and inventory management. This is where a properly specified and entrenched CMMS (Computerized Maintenance Management System) is integrated into your ERP (Enterprise Resource Planning) software. It offers the following benefits:

• A log of technicians’ completed corrective procedures.
• Automatic inventory updates, allowing parts orders to be made on time.
• Highlights areas with a high failure rate.
• Indicates the best value in terms of spare parts vendors.

To progress further toward the smart factory concept, the priority areas that were identified should then be upgraded to include smart monitoring elements. Connected sensors at critical places — such as equipment bearings and conveyor drives — provide important data.

This online monitoring data is combined with other existing data sources, and processed via cloud computing, using the right software. By doing so, the wastes in your maintenance processes can be identified in real-time, allowing improvements to be deployed immediately.

Move towards predictive maintenance

With the maturing of Industry 4.0 and real-time data from IIoT, using artificial intelligence (AI) to remove waste is quickly becoming a reality. In order to assist in predictions, machine learning draws insights from large amounts of data generated from the production process and various electronic systems.

Currently, condition-based maintenance (using data provided by the equipment) is an excellent example of taking advantage of connected sensors (IIoT). However, moving forward to incorporate machine learning reduces the waste even more. Machine learning gathers these vast amounts of data and combines them with other data sources — such as maintenance logs and user inputs — to improve predictive maintenance targeting.

Predictive maintenance aims to decrease the 7 wastes by identifying the optimum time for the correct maintenance task to be carried out. That way resources can be planned beforehand, with the correct parts — and the best technicians — at the right place, at the right time. Predictive maintenance also allows a reduced stock of spare parts.

Augmentation: blending AI and human intelligence

AI processes the available data from various sources and highlights patterns, anomalies, and opportunities. This turns volumes of data into actionable insights, put in the hands of factory managers — assisting their decision-making.

As businesses grow in complexity, with an increased budget, resource limitations, and more variables such as supply chains and product specifications to manage and maintain, AI adds value in the following ways:

• Informs decisions — AI offers unbiased information based on facts, such as: which parts of the process are bottlenecks, or which ones are expensive to maintain.
• Cuts costs — as predictive maintenance is fine-tuned, the work is done in the right place and at the right time.
• Improves productivity — a well-maintained process means a lower failure rate, fewer interruptions, and increased output.

Simply put, predictive maintenance that uses AI leads to fewer maintenance work orders with better equipment uptime.

Conclusion

It really is possible to remove waste from your maintenance processes. To do so, you need modern, connected technology, and you need to embrace the smart factory concept. 

The value of eliminating waste by embracing an Industry 4.0 approach to processing equipment data is evident soon after deployment, even if you’re starting out small, with individual use cases.  Make your maintenance more targeted and efficient with the help of AI.