Predictive maintenance & AI
Equipment failure is the cause of 42% of unplanned downtime costing industrial manufacturers an estimated $50 Billion per year, a joint Wall Street Journal and Emerson study found out recently.
So what can we do to prevent this collossal loss?
- Employ a more efficient equipment maintenance strategy.
Speaking about different types of maintenance, two main types come to mind: corrective maintenance (reactive and periodic) and preventive maintenance. Meantime a third type, known as predictice has proven benefits that will surprise you:
Reduction in maintenance costs - can be reduced by more than 50%
Reduction in machine failures – 55% reduction of unexpected and catastrophic equipment failures with projections indicating that reductions of 90% can be achieved.
Reduced downtime for repairs – 60% reduction of mean time to repair
Reduced stock of spare parts – average reduction of 30%
Increased service life of parts - in average plus 30%
Increased production – plus 30% based strictly on machine availability and does not include improved process returns.
Improved operator safety – reduction of risks of destructive failures, which can lead tp personal injuries
Leveraging artificial intelligence (AI) into a predictive maintenance models to identify anomalous behavior turns equipment sensor data into meaningful, actionable insights for proactive asset maintenance. This intelligence forecasts when or if functional equipment will fail so its maintenance and repair can be scheduled before the failure occurs.
Source: Sundhama Vemuri, Digital DoughNut
We know 3 classes of predictive maintenance tools
- sensors generate data
- analytics & monitoring tools help clean and analyze that data
- scheduling tools coordinate teams in the field and guiding them to carry out maintenance activities
Big data, analytics and cloud data storage are enabling more equipment to share condition-based data with a centralized server, making fault detection easier, more practical and more direct.
For manufacturers and other industrial organizations, finding the best way to minimize waste and inefficiency can have a major impact on the bottom line of their business. When working together correctly, these tools act in a complementary manner – enabling the success of one to aid in the success of another. However, any decision made with regards to predictive maintenance should include inputs from employees and other relevant parties throughout the business to ensure that the functionalities required are the ones that are obtained.
A positive example of predictive maintenance had been achieved by ProRail, which is the organization responsible for performing maintenance on the Dutch national railway network. Using a network of high-tech sensors, ProRail has been able to reduce the number of failures in its switches, overpasses, sign-posts and detection systems by a quarter over the past few years. The sensors enable ProRail to predict 80% of failures for a particular group of switches. As a result, the percentage of trains that run on schedule has increased by 3%, to 92.9%.
Predictive maintenance solutions are expected at a compound annual growth rate (CAGR) of 24% through 2022. Key players include Bosch, GE, Hitachi, Honeywell and Rockwell Automation.