Pushing IIoT Predictive Maintenance Forward: Two Challenges to Overcome
Pushing IIoT Predictive Maintenance Forward: Two Challenges to Overcome
by Amnon Shenfeld
There’s no doubt the Internet of Things (IoT) is moving quickly to the front lines of industrial maintenance reliability and asset management. Communication between machines and human technicians, enabled by wireless technology and connected devices, is fueling a shift from preventative to predictive maintenance. But while the Industrial Internet of Things (IIoT) groundwork has been laid, and it’s projected to be a $151 billion market by 2020, the revolution is still young.
Gartner’s special report, “Hype Cycle for Emerging Technologies,” points out that all new trends follow a similar growth pattern, and IIoT is no exception. While there’s a lot of excitement about the potential to apply data-driven algorithms to large data streams from industrial assets, IIoT is heading into the trough of disillusionment. Two major challenges must be overcome to push IIoT predictive maintenance technologies up the slope of enlightenment and spark mainstream adoption and success.
Figure 1: Hype cycle for emerging technologies
Poor Data Quality
Big data went through its own hype cycle, but is now more firmly grounded in the realization that merely collecting large amounts of data is insufficient to achieve meaningful insights. For IIoT predictive maintenance, the data challenges are twofold. Firstly, it’s difficult to obtain high quality, labeled data from industrial machines to begin with. Secondly, it’s even more challenging to then apply that data to provide human engineers and technicians with relevant and actionable condition-based maintenance insights.
Gathering large volumes of raw, unlabeled data is relatively easy, but when attempting to build learning algorithms for IIoT predictive maintenance platforms, the algorithm is only as good as the quality of data labeling (i.e., assigning each piece of data a useful tag or label that makes it somehow informative and useful). Building databases of high quality, labeled data is a much more technologically challenging and time-consuming endeavor.
For example, industrial machine engineers and technicians have used vibration testing and analysis for condition-based maintenance for ages. Vibration sensors, meters and related technologies have evolved and are now more advanced and affordable than ever before. However, an ongoing challenge with collecting large volumes of vibration data over time is that the data alone often isn’t enough to achieve deeper insights beyond the trivial, “it’s vibrating too much, I don’t know why without visiting this machine.” (Could be a loose part, a worn part, or something not aligned correctly.)
Fragmented Technologies and Human Operations
Because industrial maintenance software platforms, sensors and operations are currently highly fragmented, it’s a challenge to fuse sensor data (e.g., signals based on vibration, temperature, power consumption, etc.) with actual events or maintenance activities that humans carry out on machines.
Many existing condition-based maintenance solutions, such as vibration analysis via a handheld device, require sampling and diagnostics by human technicians going from machine to machine. These contact-based methods can fall victim to producing biased, one-sided results depending on the location of the sensor and the experience of the technician, and aren’t constantly monitoring and sending alerts in real time. Other non-handheld sensors with “smart” monitoring capabilities require complex integrations, training and retrofitting of old industrial assets.
IIoT is helping to change this, but so far in the hype phase, IIoT predictive maintenance solutions have mainly consisted of software to analyze data collected from sensors designed and manufactured by third parties. In many cases, users and implementers of such software solutions don’t control the sensors or the data origins. Therefore, they are very exposed to garbage in, garbage out scenarios where false-positive alerts rule and maintenance teams eventually ignore valuable alerts as they are trained to distrust the outputs of such systems. Industrial machine data will only be as good as its worst sensor and it’s impossible to identify which sensors are good and which are bad if they are not properly controlled, installed, or built in tandem with the software that’s processing the data inputs.
Reliability monitoring software also needs to be highly reliable. The challenge is to bridge the gap between human maintenance engineers, sensors and enterprise resource planning and monitoring software, especially when working within harsh industrial/manufacturing environments, such as steel plants or oil rigs, or with equipment spread across remote locations, such as energy generating turbines.
Much of the data quality challenges will be addressed by new, deep learning algorithms that mimic the learning faculties of the human brain and can be used to build more accurate predictive models. These deep learning models will be able to apply insights from previously labeled data to new, unlabeled data so both predictive and prescriptive analyses will become even more accurate over time. It’s only with optimal predictive models that any array of connected hardware devices can provide maximum return on investment (ROI) and benefit for decreasing human errors, reducing downtime and increasing average production.
To overcome the challenge of fragmented technologies and operations, maintenance engineers and technicians will need to start relying on classic signal outputs, such as vibration, temperature, power consumption, etc., as well as new smart sensors, such as deep learning, powered, airborne acoustics. Such sensor inputs will increasingly play a larger role in IIoT predictive maintenance. Engineers and technicians have, of course, always diagnosed machine problems simply by listening to them. However, humans can’t be physically next to every machine at all times during operation and also have a hard time filtering out other noise interference present in harsh industrial environments.
While vibrations are technically a form of acoustics, airborne acoustic monitoring allows maintenance engineers and technicians to listen to equipment and tap into the intuitive human capacity of sound-based diagnosis (looking at a vibration readout graph doesn’t trigger the same intuition regarding the machine’s actual problem). It also represents sensor fusion, as a machine working under different loads in different conditions will sound differently. Using signals like acoustics, which are intuitively meaningful to maintenance experts, will be a big step in bridging the gap, with a symbiotic relationship between the IIoT hardware, software and humans.
Additionally, airborne acoustics will help address the first challenge. Allowing a human to hear how a machine sounded at a specific moment in time will make it easier to label the data and speed up the herculean task of building high quality, labeled databases. This is analogous to how the CAPTCHA™ program works. Anyone who has ever bought concert or sports tickets online knows what CAPTCHA™ is. It’s that form during checkout where you’re asked to type some displayed words in order to verify you’re human and prevent spam and abuse by automated bots. It works because humans can read text like the ones in Figure 2, while computer programs currently cannot.
Figure 2: Example of a CAPTCHATM program
What you probably don’t know is that all the human input that goes into verifying all these words is, at the same time, being used to help digitize or translate books, newspapers and other texts that are too illegible to be scanned by computers. In both cases, leveraging human input helps facilitate ordinarily massive and laborious projects.
As industrial manufacturing and production become more automated, there will be an increased need in the future for predictive maintenance technology
Today, there’s a rising global demand for industrial automation systems as companies work to optimize operational efficiencies. As industrial manufacturing and production become more automated, there will be an increased need in the future for predictive maintenance technology – both hardware and software – that helps keep equipment running at optimal performance and identifies problems in real time before machine failure interrupts production and causes costly unplanned downtime and replacement of damaged parts.
IIoT and deep learning will play a big role in the advancement of predictive analytics and overcoming these two major challenges of data quality and the gap between humans and machines. IIoT and deep learning also will be critical to help get passed the upcoming phase of disillusionment and create more mainstream adoption of IIoT predictive maintenance solutions.