Predictive maintenance is no longer something that is reserved for big multinationals active in very specific industries. Rapid developments in sensor technology, artificial intelligence and IOT have made predictive maintenance cheaper and easier to implement, making it accessible for every kind of company in every kind of industry. The consequence of this is huge: according to a study conducted by McKinsey, predictive maintenance typically reduces machine downtime by 30 to 50 percent and increases machine life by 20 to 40 percent. This means that if your competitors have already made the move to predictive maintenance, you can not stay behind because it won’t be long before they start to use these efficiency gains to drive you out of the market.
Oil and gas industry
The oil and gas industry was one of the early adopters of predictive maintenance. The reason why the oil industry was one of the pioneers in this field is simple. Every hour of downtime is costing them enormous sums of money. In that McKinsey article, the authors are mentioning the story of an oil producer who consistently faced problems with the compressors on its offshore production platforms. If one of those compressors broke down, it stopped the entire production which was costing the company between one and two million US dollars a day. The company had been looking into the source of the failure for years, but couldn’t figure out its root cause. It’s only once they developed an algorithm based on hundreds of sensors with information on a thousand different parameters that they were able to predict in advance that a compressor was about to break down.
An industry in which we gathered quite some experience is offshore wind. Setting up an offshore wind farm requires an enormous investment, so an operational life of 20 to 25 years is the bare minimum that is needed to generate an attractive return on investment. Therefore, all measures are taken during the design phase to ensure the structure will reach its lifetime, but in practice the real state of health of the structures still comes with a degree of uncertainty. New concepts, assumptions regarding soil conditions and loads as well as unforeseen events all have an influence on how the structure or some of its key components degrade. Which means that the actual evolution of the health of your windfarm is hard to predict.
By equipping the wind farm with a smart, multi-sensor monitoring solution, you get a continuous insight into the health of your wind farm, you are alarmed when certain components have degraded to critical levels and you are told which maintenance activities are really needed and which activities can easily be postponed for a couple of months. As a result our Wind Turbine Doctor platform helped our clients lower their maintenance costs by 30% and significantly extended the lifetime of their wind farm.
Yet another sector that started to embrace predictive maintenance is the sector of large civil infrastructure projects. Civil infrastructure is erected with a long-term focus. Predictions over 25 years or more are however difficult to make with high accuracy. A dedicated, sensor-based follow-up allows the owner / operator to significantly de-risk the operational life of structures such as bridges, tunnels, roads, dams… and lowers their operational costs by more than twenty percent.
One of the sectors that is typically slower to pick up and act on new trends is the manufacturing industry. Companies in this industry get their competitive edge from their plants’ efficiency, so once they’ve optimized their setup they prefer making only incremental changes to their plants and production processes. But the fourth industrial revolution is a trend that they can’t ignore. Those players that embraced predictive maintenance managed to limit unexpected mechanical failures to a minimum and significantly lowered their maintenance costs, making their plants extremely efficient. ArcelorMittal is one of the companies we worked with in this industry. By equipping their overhead cranes with the right sensors, gathering and analyzing the data that they produce and turning that complex data into clear and easy-to-understand insights about the cranes’ health, we managed to help them significantly reduce unexpected downtime of these production-critical assets.
The number of industries picking up predictive maintenance keeps increasing every year, which is something we should all be excited about. It boosts productivity and therefore drives economic growth, it improves the durability of assets and helps us move to a more sustainable future and it is boosting innovation in IOT, artificial intelligence, big data… creating new opportunities way beyond the maintenance sphere.