19 Jun 2020
Posted in Disruptor
AI-powered predictive maintenance game-changer for enterprises in costs savings, says GlobalData
Predictive maintenance systems powered by artificial intelligence (AI) technologies are helping enterprises to find patterns that can avoid machine failures more effectively. These systems, unlike the traditional business intelligence systems, can handle huge volumes of industrial internet of things (IIoT) data to maximize the economic benefits to enterprises, says GlobalData, a leading data analytics company.
Venkata Naveen, Disruptive Tech Analyst at GlobalData, comments: “Reactive maintenance costs enterprises billions each year in lost production. The ultimate goal is not to replace machines or parts too early but service them at the right time. This can be done optimally using AI-powered predictive maintenance leading to reduced downtime, extended equipment life, improved safety and increased return on investment.”
The Innovation Explorer database of GlobalData’s Disruptor Intelligence Center discloses how predictive maintenance is increasingly becoming useful to predict machine failures well in advance and save costs to enterprises across industries like automotive, manufacturing, oil & gas, mining, power and aerospace.
Mitsubishi Electric has developed an AI-based diagnostic technology that harnesses machine learning algorithms to analyze sensor data of machines and generate a model of the machine’s transition between different operational states. The model is then used to set optimal conditions for detecting abnormalities of a machine during each operational state, enabling operators to gauge signs of machinery failure before actual breakdowns.
American Family Insurance has collaborated with insurtech ‘Neos’ to offer a smart home insurance product for the US customers. The product consists of a smart water leak detector and cameras along with a mobile app connecting them. It leverages AI algorithms to analyze an individual’s water usage over a period of time establishing a pattern. Any changes in the water usage patterns can help Neos to predict issues with the pipelines. The Neos app alerts users on potential issues such as dripping taps and hidden leaks on pipes along with a live camera feed. Neos instantly connects customers with repair services through its platform, thereby significantly helpful to avoid any major issues.
Agnico Eagle Mines has partnered with Montreal’s Newtrax Technologies to predict mobile equipment maintenance issues in advance using AI algorithms to the data feed from IoT sensors. Newtrax helped to analyze an engine that has shown signs of a potential issue, which is estimated to have saved US$63,610 in repairs and replacement of the engine to the mining company.
Instead of building an AI-powered predictive maintenance system from the scratch, enterprises are partnering with startups to deploy their solutions off-the-shelf. Some of the popular technology providers in this space are C3.ai, Uptake Technologies, Maana, Sight Machines, Predictive-Sigma and Presenso.
Naveen concludes: “One of the critical challenges with predictive maintenance is to streamline the flow of data from machines to a central system with low levels of latency and high security. However, these issues can be addressed with upcoming technologies such as 5G and advanced security. Despite the stumbling blocks, AI-based predictive maintenance techniques are materially crucial for an enterprise to effectively predict operational breakdowns and thereby save costs.”