CEO Insights: How to get the most of your old machines leveraging Predictive Maintenance
There is an enormous amount of buzz about predictive maintenance and how it can save money for manufacturers, but it’s often difficult to figure out what is and isn’t hype. Also, there are a lot of questions about Predictive Maintenance in a moment when things become connected everyday. In this interview, Amnon Shenfeld, CEO of 3DSignals, will explain how Predictive Maintenance can save time, old equipment and money.
Lucian Fogoros: Why do you think Industry 4.0 is a game changer from your POV?
Amnon Shenfeld: Similarly to how the e-commerce revolution forever changed retail, the industry 4.0 revolution is about to disrupt conservative manufacturing industries.
By some estimates there are 60 million machines in factories throughout the world and 90% are not connected. Meanwhile, 70% of the machines are more than 15 years old.
Such assets lacking proper visibility for maximizing operational and maintenance procedure efficiency.
Industry 4.0 which from our perspective brings rich yet easy to deploy data visibility, accessibility and connectivity stands to fast-track manufacturing operations into a new era of safety, efficiency and profitability.
Lucian Fogoros: There are four primary technologies behind Predictive Maintenance: vibration analysis, ultrasound, oil analysis and infrared thermography. Which one is the best for manufacturing? Why?
Amnon Shenfeld: Each of these methods excels in specific scenarios, however in the sense of sensor economics there is only one method that allows for coverage of a wide variety of equipment with a small number of cheap sensors and that method is airborne sound monitoring.
Condition monitoring via acoustics has three main advantages over other sensing techniques:
Early detection – As changes begin to occur in rotating, mechanical equipment, the subtle nature of ultrasound allows these potential warning signals to be detected early, before actual failure, often before they are detected by vibration, temperature and audible means. In addition, if we zoom out from the individual component out to an entire machine, a single acoustic sensor can detect anomalies in sequence of components operation, where sensors such as vibration are more discrete in nature, isolating each individual component hence missing the “big picture”.
Ease of installation – Acoustic sensors, being external to the equipment, are agnostic and non-destructive. Installation of 3DSignals equipment takes one day, without taking any machine down, and even without requiring a network access in order to get access remotely. In addition, acoustic sensors are more economical as a single sensor can cover anywhere from a single component to an “orchestra” of machines, compared with multiple sometimes tens of sensors per each piece of equipment.
Sound is intuitive – plant workers are not data scientists, and often getting their buy-in turns out to be a hurdle, perhaps larger than the technology itself. Sound however is intuitive to everyone. Listening to the sound the machine made minutes before it broke, compared to last week’s sound, makes acoustics an effective and friendly root cause analysis method for plant maintenance staff.
Lucian Fogoros: Can you describe your data connection to the equipment you monitor? How is the data transmitted?
Amnon Shenfeld: We’ve created client-friendly data retention and data transmission policies that help us to onboard clients very fast in a scalable manner. Our proprietary sensors harvest data from the factory without affecting the factory production line, and sends the raw data to Edge devices that are installed on-premise. Our Edge devices have both storage and computational capability and we’re able to process data both on-premise or send the data to our secured cloud. Our data hub architecture is of course able to analyze additional external data sources in a timely fashion and clients can benefit from a scalable approach that also meets their security and IT concerns, while getting access to our deep learning neural network and analysis platform when analyzing machine deterioration processes of machine anomalies.
Our platform facilitates smooth and seamless access to a new data source: Sound; and we offer both industry standard methods to analyze this signal such as FFT and feature extraction in the frequency or time domains as well as innovative deep learning algorithms that learn to recognize and alert on specific acoustic signatures which identify various failure states such as bearing friction, shaft misalignment, blocked filters, lack of lubrication, etc.
Lucian Fogoros: Can you describe your approach to Cyber Security for the transmission of machine data?
Amnon Shenfeld: 3DSignals does not collect or transmit sensitive machine data. We rely purely on the sound which is emitted from machines to the air around them.
Sound is not considered data which carries any cyber security implications.
On top of this, there is no physical contact between our sensors and monitored equipment or communication networks. We rely on a separate (encrypted) cellular data link which carries the sound data directly to secured cloud storage for processing.
Lucian Fogoros: How can sound-based predictive maintenance save money?
Amnon Shenfeld: Global demand for manufactured products is growing at a snail’s pace. Output is expected to increase just 3.1 percent in 2016 and 3.4 percent in 2017, according to the International Monetary Fund. In a slow-growth environment such as this, productivity gains are paramount, where IoT Predictive Maintenance is expected to bring 10-40% savings (McKinsey). That said, digitization is an expensive business, especially if the factory uses good old machinery that doesn’t come with state of the art IOT capabilities. This is where acoustics come to play. With just a single day of installation, no single drilling or taking any machine down, the whole factory can get digitized. From productivity perspective, acoustic monitoring early fault detection in any rotating machinery allows reducing failure rates, reduce raw material scrap, increase overall production pace and increase maintenance staff efficiency.
Lucian Fogoros: How do you see the future of Predictive Maintenance?
Amnon Shenfeld: According to industry research, the predictive maintenance market will reach $11 billion by 2022, driven largely by IoT technology. Within this framework, there is massive opportunity to apply industry 4.0 capabilities both to brownfield assets by retrofitting, as well as for manufacturers of industrial machines and equipment to integrate Predictive Maintenance technology directly into new systems. We seek to democratize sound as a meaningful tool serving both predictive maintenance needs, as well as operational efficiency and safety applications.