Predictive Maintenance

Predictive Maintenance

“Information is the oil to the 21^st century and analytics is the combustion engine”: Peter Sondergaard

Human beings are generally curious to know about the future so that they can prepare themselves accordingly, especially if it is not favourable. Soothsayers (fortune-teller) predicts our future, marriage dates and even results of Football World cup! On TV channels, the weather forecast for the next few days are predicted and if it is not favourable (storm, rains etc.), government and individuals do take precautionary steps. Even a little cough or sneezing predicts our health and we take safety measures.

Something similar happens in a different type of industries wherein based on condition-based monitoring, organization/personnel decides possible actions to keep the machines in running condition with little or no loss.

Predictive Maintenance (PdM) is a proactive maintenance strategy that tries to predict when equipment might fail so that maintenance work can be performed just before that happens. These predictions are based on the condition of the equipment that is evaluated based on the data gathered through the use of various condition monitoring sensors and techniques. It’s no longer a case of “if it isn’t broken don’t touch it” but “fix it in time before it breaks.”

The basic form of predictive maintenance (PdM) happens when a mechanic put his ear to the handle of a screwdriver or touch the other end to a machine and pronounce that a bearing is going bad.

As per IATF 16949 clause 3.0, following are some of the key definitions

Predictive maintenance: An approach and set of techniques to evaluate the condition of in-service equipment by performing periodic or continuous monitoring of equipment conditions, to predict when maintenance should be performed.

Total productive maintenance: A system of maintaining and improving the integrity of production and quality systems through machines, equipment, processes, and employees that add value to the organization.

As per IATF 16949, Clause 8.5.1.5, one of the key maintenance activities is Predictive Maintenance (PdM).

Key objective of doing Predictive Maintenance (PdM):

• Monitoring of machines: Its purpose is to indicate when a problem exists. It must distinguish between good and bad condition, and if it is bad, it should indicate how bad it is.
• Protection of machines: It aims to prevent sudden failures. A machine is protected, when the values that indicate their status reach values considered dangerous, the machine automatically stops.
• Failure diagnosis: It aims to define the specific problem. Its objective is to estimate how much longer could operate the machine without the risk of sudden failure.

Where Predictive Maintenance (PdM) is relevant?

• High capital and operational expenditure (Construction and mining)
• Sensitive and very expensive equipment (oil and gas)
• High risks to human safety (Aviation)

Some of the industries that are at the forefront of using predictive maintenance include Manufacturing, Automotive and Aviation.

 5 Key Steps in Predictive Maintenance (PdM)

Step 1 – Identify critical equipment
Start by identifying critical equipment and systems to be included in the program. Assets with high repair/replacement costs that are critical to production are often the best candidates for a PdM program.

Step 2 – Establish a database
For the PdM program to be successful, another factor to consider is the presence of sufficient information that can offer actionable insights into machine behaviour. Historical data for each pilot equipment can be made available from sources like CMMS, maintenance records and charts, etc.

Step 3 – Analyze and establish failures modes
At this point, the organization will need to perform an analysis of the previously identified critical assets to establish their failure modes.

Step 4 – Make failure predictions
With the most critical equipment and failure modes identified, the next step is designing the right modelling approach that will form the basis for failure predictions.

The result of this stage is to deliver a fully automated system that:

• monitors operating conditions via installed sensors
• understands and predicts patterns created by data anomalies
• creates alerts when there is a deviation from established thresholds

Step 5 – Deploy to pilot equipment
This is where predictive modelling is put to test and validated by deploying the technology to a selected group of pilot equipment.

If the process is executed properly, there will be significant improvements to the company’s operations, even though noticeable impacts might take a few months to initiate, depending on the size and complexity of your organization.

How to do Predictive Maintenance?

Predictive maintenance (PdM) relies on condition-monitoring equipment to assess the performance of assets in real-time. By combining condition-based diagnostics with predictive formulas and with a little help from the Internet of Things (IoT), PdM creates an accurate tool for collecting and analyzing asset data. This data allows for the identification of any areas that need or will need attention.

These sensors measure different kinds of parameters depending on the type of machine. Most commonly, they measure vibration, noise, temperature, pressure, and oil levels.

Types of Predictive Maintenance:

Vibration analysis: Vibration sensors can be used to detect degradation in performance for equipment such as pumps and motors.

Infrared: Infrared cameras are often used to identify unusually high-temperature conditions.

Acoustic analysis: Acoustic analysis is performed with sonic or ultrasonic tests to find gas or liquid leaks.

Oil analysis: Oil analysis determines equipment wear by measuring an asset’s number and size of particles. Example: Hydraulic oil used in the moulding machine.

Key benefits of effective Predictive maintenance

• Return on Investment (ROI) improves
• Reduction in maintenance costs
• Elimination of sudden breakdowns
• Reduction in downtime
• Increase in production

The best predictive maintenance programs take time to develop, implement and perfect. The timeline to achieve gains varies depending upon the criticality and complexities of the equipment.

Predictive maintenance is not for every organization, especially those that have yet to implement planned maintenance activities. But for larger organizations that have outgrown traditional PMs and have additional budget, predictive maintenance can provide an ROI that turns the maintenance department into a source of cost-savings and higher profits

Possible Challenges:

• How often predictive maintenance is actually conducted and not on paper?
• How often top management is interested in knowing the effectiveness of predictive maintenance?
• How often maintenance personnel are competent enough to understand the condition-based monitoring tools (infrared, oil analysis, vibration analysis, acoustic analysis) and conduct PdM accordingly?

References:

ISO 9001: 2015

IATF 16949: 2016

This is the 70^th article of this Quality Management series. Every weekend, you will find useful information that will make your Management System journey Productive. Please share it with your colleagues too.

Your genuine feedback and response are extremely valuable. Please suggest topics for the coming weeks.