5 key predictive maintenance tools

5 key predictive maintenance tools

Are you still using scheduled maintenance to keep your system critical machines running? Are you treating critical machines like a car, scheduling an oil change? Worse, are you waiting for your machines to show signs of damage before intervening?

In the near future, the internet of things will be the norm. Interconnectivity is so ubiquitous that it has become unremarkable. Connecting equipment to the internet of things has never been cheaper or easier. Data has never been easier to collect and analytics have never been easier to understand. Every year, more and more tech-savvy employees join the work force.

In short, implementing predictive maintenance is easy now and it will only get easier.

This is not about selling anyone on the merits of predictive maintenance. We have already covered predictive maintenance. We have also covered what kind of maintenance is best for you. Instead, we will cover what predictive maintenance tools are available right now. Implementation of these tools, systems and techniques are already available.

A refresher on maintenance

If you saw the links but chose not to click them, here is a brief primer on different maintenance approaches.

A common maintenance approach is conditional, or reactive, maintenance. With this system, maintenance is only performed when a machine slows or brakes. Until there is an issue, machines do not receive any maintenance. The upside to reactive maintenance is that a large staff is not required. Repairs are only performed when a machine breaks down. There are, however, serious risks to reactive maintenance. With no maintenance, machines might break, causing downtime. When machines break, they are expensive to repair. Repairs might take an extended period of time to perform.

The most common approach to maintenance is preventative, or scheduled, maintenance. At scheduled intervals, machines are either checked, maintained or repaired. The upside to this is a 12-18% decrease in maintenance costs. Preventative maintenance also reduces the risk of part failure while additionally extending a machines lifespan. There are downsides, however, as this is a labor intensive maintenance plan. Depending on conditional factors, machines may be over or under maintained. Finding the optimal maintenance schedule can take a lot of time and effort. It might take trial and error to maximize the repair schedules efficiency. A repair schedule in one environment might not be effective in another environment. Worse, the potential for total or catastrophic failure still exists.

Finally, there is predictive maintenance. Using sensors, software, data and analytics, connected equipment remains under constant supervision. Problems get addressed before they occur, not after. Maintenance is applied only as needed and not at scheduled intervals.

Predictive maintenance is very different than either of the other methods. Issues are only addressed when necessary, like reactive maintenance. Failures and poor performance is also avoided, like preventative maintenance.

By constantly monitoring equipment, streaming data and applying analytics, predictive maintenance uses the internet of things to drastically improve how equipment stays maintained.

There are many advantages to predictive maintenance. A component’s lifespan is best optimized when it is only replaced as necessary. Performed maintenance will still be proactive to avoid failure. Predictive maintenance can lead to significant reduction in downtime. Worker safety improves with decreased likelihood of equipment failure, leading to higher morale. Predictive maintenance delivers an estimated 8%-12% cost savings compared to scheduled maintenance.

There are, of course, drawbacks to this system. Hiring tech savvy employees or staff training will be a requirement. The capital investment in diagnostic tools can be prohibitively expensive. Finally, the cost savings may not be immediately obvious, especially considering the capital investment required.

Generally speaking, however, predictive maintenance can drive huge efficiency gains while reducing costs. Diagnostic tools are getting more sophisticated and less expensive. It has never been easier to implement a tech based approach to maintenance, and it will only get easier.

5 Predictive maintenance tools

1- Data storage

Start from the very beginning. Before you can use predictive maintenance, you have to have data. With data comes data storage requirements.

Before getting into staffing, there are two elements to consider: hardware and software. You will need physical equipment capable of data collection, data analysis and data storage. This will likely come in the form of highly sophisticated computer equipment. If you have the capital, you can have a bespoke system designed for you. If not, you will need to fit your criteria into an existing framework. There is no shortage of companies offering business to business tech expertise.

You will also need a staff capable of harnessing that information. How you choose to develop a predictive model depends on your specific equipment and needs. If you are monitoring multiple machines that are identical, it might be easy. If you are monitoring multiple machines that are different, it might be challenging. We covered these concepts in our article on predictive maintenance. You can find this specific section here.

It will not take long for you to find a variety of companies eager to help you set up your data and data storage or analytics. We have listed all vendors who can get you set up with accurate, effective analytical tools almost immediately.

2- Thermal Imagery

Increased heat is fantastic for soothing sore muscles or cooking a steak. Excessive heat is a death sentence for metals, composites and electronics.

Excessive heat is a major threat to electric motorsExcessive heat is a primary maintenance concern for telecom companies. Dangerous working conditions and castrophic delays can occur due to something as simple as a poorly lubricated set of bearings.

In short, unchecked heat is a killer of industry.

An easy solution is thermal imagery. Thermal imagery utilizes infrared images to show the temperature of interacting machine parts. Seeing the temperature of interacting parts can help identify potential issues.

Simple thermal imagery equipment is easy to get and easy to operate. In its simplest form, technicians can take mobile readings with a handheld device. There is no downtime required for a simple handheld thermal image scan. The positives to this sort of predictive system are simplicity and ease. The downside is that constant observation is likely impossible with a handheld device.

A more sophisticated and accurate system would need diagnostic thermal tools with connectivity. Compared with baseline data, this equipment would show abnormal temperature ranges. These sensors would track the machines for potential deviations from acceptable temperatures. Once relayed, that information would alert technicians to any issues. This system would need greater capital investment and a technologically competent staff.

Monitoring temperatures makes avoiding failures much easier. Setting up a comprehensive temperature monitoring system is also easy to achieve, provided you have the equipment and staff available.

3- Vibration, Sonic and Ultrasonic Analysis:

Unexpected vibrations can be fatal to a machine. In the highly technical sport of Formula One, for example, Honda’s engines faced unexpected vibration issues. These issues were so severe that the engines would literally shake themselves to death, failing (often spectacularly) in the middle of a competition.

Your business is likely not on the world stage. You are unlikely to face the sneering scrutiny of the British tabloids. Vibration related failures will still cause downtime, however. A sneering press is likely preferable to a snarling customer.

Predictive maintenance offers solutions to vibration, sonic and ultrasonic issues.

Vibrations can occur due to any number of factors. A machine’s bearings or brackets might start to lose their tactile strength. A component may be nearing the end of its lifespan. Anything is possible.

Sensors will feed information back to the systems connected to them. Once calibrated, a system will notice any unusual vibrations. Once analyzed, technicians or learning machines will determine the appropriate course of action.

This equipment does not just exist: it is already sophisticated and advanced. Fast Furrier Transform analyzers, for example, can detect minute vibrations that were previously undetectable. Similar systems exist that can detect sonic and ultrasonic vibrations.

Infralogix has ultrasonic sensors that can detect sound waves beyond what the human ear can hear. This information can help technicians find vacuum seal failures, as well as air and gas leaks.

4- Oil and lubricant analysis

Oil analysis can determine many factors of your machine performance. Actual oil viscosity versus expected viscosity can show how your machine is preventing oxidation, dilution, moisture, etc. Metal shards in the oil can alert technicians to parts grinding that might slow or break a machine. Sensors that calculate fluid dynamics might help expose a leak or faulty connector.

Oil analytics systems have been around for a while. Most modern cars have them integrated into the central computer system. Your car checking oil quality is a practical example of predictive maintenance.

These systems are not difficult to integrate into existing machines. You should have guidance from your lubricant provider on acceptable temperatures, viscosity, etc. You could cross-reference your actual results against the expected results. Analytic systems are commonly designed to detect impurities in oil. Metal, dirt and sludge will be easily found. Moisture is easily detected, even in trace amounts. Your system will calculate any aspect of the oil which could cause failure.

5- Scheduling Tools

The internet of things (IOT) and Industry 4.0 make predictive maintenance possible. The sensors and analytics are one part of the equation, of course, but so is the maintenance.

Software leaders like IBM, SAP and SAS all create full range technology suites. These suites combine machine learning and the sensor data to compile maintenance plans.

Remember that predictive maintenance is about monitoring equipment and acting only when necessary. Technology programs designed for industry are honing in on when, precisely, action is required.

These available systems will automate much of the maintenance analysis. Your computer system will not be able to change parts, but it will be able to alert technicians of a pending issue. The programs will not create maintenance schedules, but rather, proactive behavior when a component faces the end of its life cycle. Even better, these systems can request maintenance long before a machine faces failure. When a machine starts to decrease in productivity or output, proactive maintenance can occur.

Again, all of this is already in work. A recent IBM commercial demonstrates this concept perfectly. Watson, IBM’s proprietary AI, calls a technician before the elevator is set to break in two days. It is not just a commercial: it is happening. You can improve your maintenance systems by getting in on the ground floor of this revolution.

Leave a Reply

Your email address will not be published. Required fields are marked *