Maintenance in the Age of IIoT
Published by : Industrial Automation
How Predictive Maintenance in the age of IIoT is reducing downtime and eliminating premature replacement of machinery and equipment.
Traditionally maintenance services have evolved with technology but there still remains them broad classification of reactive maintenance and proactive maintenance. Emergency maintenance, breakdown maintenance and corrective maintenance are examples of reactive maintenance. Proactive maintenance, on the other hand, comprises of preventive, condition- based and planned/scheduled types of maintenance. While larger companies with huge turnovers are likely to rely on more advanced types of proactive maintenance practices when compared to smaller ones relying on reactive maintenance, there is no such hard and fast rule. Essentially, a company may adopt different types of maintenance services based on the value of assets as well as the seriousness of the situation should a breakdown occur. Now in the age of Industrial Internet of Things (IIoT), predictive maintenance based on data analytics is increasingly talked about as the ideal solution. So how do companies decide their maintenance strategies?
“For any organisation, it is essential to follow a mix of maintenance practices. Reactive maintenance is adopted at the time of actual asset failure leading to a downtime and maintenance teams diagnose failure reason and get machine and lines functioning. Predictive maintenance helps providing reports and warning about failures even before they occur. Preventive maintenance is during planned shutdowns. Thus, a factory has to adopt a mix of all the above strategies to keep their machines and lines operational 24x7,” says Ninad Deshpande, Head of Marketing, B&R Industrial Automation. o read full response click here
“Being considered as a non-productive function, most of the companies do not have a proper strategy in place for maintenance. They may not even consider having a strategy for maintenance in the first place,” opines Shacheendra Bapat, Automotive and Manufacturing Industry Professional. “A good leader at the top, followed by leaders at department locations and then the working technicians (mechanical and electrical) on the machines is the most important dimension of maintenance strategy. The strategy should be in place at the time of erection of the plant. It should include the training plan, budget for spares, and maintainability of the equipment at the design stage,” he elaborates. To read full response click here
Sharad Dhumane, Metallurgist & Technical Freelancer compares industrial maintenance to flying an aircraft and says a well-resourced plant will fall to its knees, in absence of a competent maintenance crew. On the other hand, an ordinary plant with old machinery, can turn out a commendable performance, if the crew is competent and dedicated. “Somewhere in the last few decades, industries slowly woke up to the secret of effective Plant Maintenance. The well trained crew, stocks of spares, maintaining breakdown records to know what breaks down frequently. Most young companies can immediately hit the Preventive option. The Predictive technique would need a mature Data. So maybe after a couple of years, they can move into Predictive technique. If a good software is available, they can surely think of Prescriptive maintenance at that time,” he explains. To read full response click here
What makes companies still rely on corrective maintenance despite better options? One is of course the cost factor. “Despite developments in equipment and facilities most of the companies prefer sticking to conventional maintenance needs. The underlying problem with corrective maintenance is the cost implications, since no preventive actions are taken for medium or high priority assets. Thus, unplanned downtime and unexpected stoppage may lead to huge repair costs. Among firms currently experiencing a rapid decline in revenues and charting a recovery path, a data-derived condition monitoring generating alerts for bad trends and inspections would be more beneficial than other maintenance strategies,” says Titli Chatterjee, Manager – ER&D/Industry 4.0 Research, NASSCOM. To read full response click here
“Reactive or corrective maintenance is still witnessed in numerous factories across India. These practices usually look cost effective superficially but tend to be more expensive at the end,” asserts Ninad Deshpande, elaborating that if the fault is easy to diagnose the machine and line is brought back to production speeds instantly. However, this is usually not the case and the breakdown diagnosis usually takes a lot of time. “In the meantime the entire production line is stopped leading to loss in production, material and time,” he says about the consequences.
Shacheendra Bapat draws attention to the fact that companies do not want to spend money on the maintenance function as it is very difficult to quantify the benefits on the money spent. “For example, if the downtime is reduced, then the productivity increases. However, the time for which the machine availability is increased, cannot be justified in terms of money, as the electricity or manpower saved is difficult to quantify,” he says, pointing out that if a maintenance person proposes certain improvement, the question he hears is “The machine is running, no? Then why do you want to spend the money?” This management attitude discourages the maintenance person and the age old concept of corrective maintenance continues.
Has predictive maintenance become easier to implement in the IIoT era? It has, says Sharad Dhumane, who feels Smart sensors placed at critical positions of the machine keep sending critical machine condition information to your computer/mobile. “So vibrations, noise, temperature data keeps coming round the clock. Smart charts let you know how these are trending and also alert you for an imminent failure. You truly can sit in a chair and know the Plant Machinery health in a glance,” he explains.
“With the emergence of IIoT, blend of huge data volume and analytics enable improved maintenance strategies to progress along the maturity continuum. Predictive maintenance is one such application which helps in detecting advanced warnings before failure. IIoT enabled monitoring combines different datasets or small data from a device with algorithms to monitor the condition of a machine and raise an alert. This also works on virtual equipment (digital twins) that help in saving a great deal of cost,” says Titli Chatterjee. Ninad Deshpande too shares this assessment and says data mining techniques are used to examine historical data to uncover previously unrecognised – and often very complex – correlations. “In combination with manufacturer data and information from measuring transducers, it becomes possible to make very precise predictions about when components are likely to fail. This knowledge can be used to make more informed maintenance decisions, such as deferring tasks of lower importance to allow for prompt replacement of components where failure is imminent,” he emphasises.
How important is inventory management for a successful maintenance strategy? According to Shacheendra Bapat, Spare Parts Inventory Management is extremely important aspect of Maintenance that requires a lot of foresight and experience. “Lack of critical spares may jeopardise production and unnecessary stocking may lock revenue and space. The managements should leave the decision on the purchase of spares to the maintenance managers. What best can be done is to fix a budget depending upon the financial condition of the company. The Maintenance Manager can identify which part is needed the most. Usability of a part in multiple machines, lead time of procurement, shelf life, in-house reparability and frequency of failure are some of the key deciding factors,” he stresses.
While inventory management is important, predictive maintenance can actually help feels Sharad Dhumane. “If the Prediction is trustworthy, then surely the Inventory Management can be diluted to a large extent. You just stock highly critical parts, which take long time to reach the Plant. Cost of the Inventory, amount of Management time it takes, space the inventory takes up in the Plant … everything gets reduced to a miniature level. Being able to work with a miniature inventory can be looked upon as an indicator of strong Predictive Maintenance capability of the Plant,” he opines.
With emerging technologies like AI & ML now coming into play, is Zero Downtime now with sight? “AI/ML will have a huge impact on manufacturing and unleash a significant part of disruption, says Titli Chatterjee. “This will gradually help to provide prescriptive solutions to production issues, addressing zero waste concerns and least amount of time would help in suggesting what’s possible. However, a robust data infrastructure needs to be at place to obtain real AI/ML. It also leaves the manufacturers confused on the right adoption of technology exactly aligned to the pain-points,” she adds.
“Zero downtime is technically not possible,” states Ninad Deshpande. Artificial intelligence or machine learning surely will help and take manufacturing units to the next level. However, zero downtime is currently a dream or a vision for any organisation. These are similar to terms are zero defects, zero rejection, which are a requirement for any manufacturing to be successful, but very difficult to practically achieve. In my opinion, with these emerging technologies together with existing technologies manufacturing will definitely get a boost reducing downtime and increasing machine availability,” he elaborates.
Will the Maintenance Strategies change post Covid-19? “Yes, it will definitely call for some changes in the strategy in industries running for 24 hours and 365 days a year, which may severely face the shortage of skilled manpower, availability of spares parts at the right time and unavailability of requisite vendors due to long shut down periods,” expresses Shacheendra Bapat, who, speaking from his own experience in manufacturing industry, feels certain steps like keeping power in On condition on machines could help mitigate issues of breakdown. “When we started our production after a gap of 48 days, we did not face a single start up related breakdown. Keeping the electric power On was the key to achieve this,” he says.
“Covid-19, after its pandemic run is over, will become another run-of-the-mill virus. Its sting will no longer bite. When a vaccine gets on board, the Covid-19 will truly become a history and the world will get back on its feet. So it seems unlikely, given the way technology has progressed, that Covid-19 will become a long time hurdle,” sums up Sharad Dhumane.
(Note: The responses of various experts featured in this story are their personal views and not necessarily of the companies or organisations they represent. The full interviews are hosted online at https://www.iedcommunications.com/interviews)