Predictive Maintenance (PdM)

PdM techniques are designed to help determine the condition of in-service equipment in order to predict when maintenance intervention should be performed. This approach promises cost savings over routine or time-based preventive maintenance, because tasks are performed only when warranted.

The main promise of Predicted Maintenance is to allow convenient scheduling of corrective maintenance, and to prevent unexpected equipment failures. The key is “the right information in the right time”. By knowing which equipment needs maintenance, maintenance schedules can be optimised and intervention work can be better planned (spare parts, people, etc.). “Unplanned shutdowns” are transformed to shorter and fewer “planned shut downs”, thus increasing plant availability. Other potential advantages of PdM include extended equipment lifetime, increased plant safety, fewer incidents with negative impact on the environment, and personnel, and optimisation of spare parts handling and system reliability.

PdM attempts to evaluate the condition of equipment by performing periodic or continuous (online) condition monitoring. The ultimate goal of PdM is to perform scheduled maintenance intervention when the maintenance activity is most cost-effective and prior to the equipment performance falling below a pre-defined threshold. This is in contrast to a time- and/or operation count-based maintenance program, where a piece of equipment gets maintained whether it needs it or not. Time-based maintenance is labor intensive, ineffective in identifying problems that develop between scheduled inspections, and is not cost-effective.

Most PdM inspections are performed while equipment is in service, which minimises disruption of normal system operations whilst having little or no impact on asset availability. Adoption of PdM can result in substantial cost savings and higher system reliability.

Reliability-centered maintenance, or RCM, emphasizes the use of predictive maintenance (PdM) techniques in addition to traditional preventive measures. When properly implemented, RCM provides companies with a tool for achieving lowest asset Net Present Costs (NPC) for a given level of performance and risk.

Differences Between Predictive and Preventive Maintenance

Predictive maintenance tends to include direct measurement of the equipment parameters and condition. Example, an infrared picture of a circuit board to determine hot spots while Preventive Maintenance includes the evaluation of particles in suspension in a lubricant, sound and vibration analysis of a machine.


An individual bought an incandescent light bulb. The manufacturing company mentioned that the life span of the bulb is 3 years. Just before the 3 years, the individual decided to replace the bulb with a new one. This is called preventive maintenance.

– On the other hand, the individual has the opportunity to observe the bulb operation daily. After two years, the bulb starts flickering. The individual predicts at that time that the bulb is going to fail very soon and decides to change it for a new one. This is called predictive maintenance.

– The individual ignores the flickering bulb and only goes out to buy another replacement light bulb when the current one fails. This is called corrective maintenance.

Predictive Maintenance Technologies

To evaluate equipment condition, predictive maintenance utilises nondestructive testing technologies such as infrared, acoustic (partial discharge and airborne ultrasonic), vibration analysis, sound level measurements, oil analysis, and other specific online tests. New methods in this area utilise measurements on the actual equipment in combination with measurement of process performance.

Vibration analysis (VA) is most productive on high-speed rotating equipment. When performed properly, VA allows the user to evaluate the condition of equipment and reduce the likelihood of failures.

Acoustical analysis can be done on a sonic or ultrasonic level. New ultrasonic techniques for condition monitoring make it possible to “hear” friction and stress in rotating machinery, which can predict deterioration earlier than conventional techniques. Ultrasonic technology is sensitive to high-frequency sounds that are inaudible to the human ear and distinguishes them from lower-frequency sounds and mechanical vibration. Machine friction and stress waves produce distinctive sounds in the upper ultrasonic range. Changes in these friction and stress waves can suggest deteriorating conditions much earlier than technologies such as vibration or oil analysis. With proper ultrasonic measurement and analysis, it’s possible to differentiate normal wear from abnormal wear, physical damage, imbalance conditions, and lubrication problems based on a direct relationship between asset and operating conditions.

Infrared monitoring and analysis has the widest range of application (from high- to low-speed equipment), and it can be effective for spotting both mechanical and electrical failures; some consider it to currently be the most cost-effective technology.

Oil analysis is a long-term program that, where relevant, can eventually be more predictive than any of the other technologies. Analytical techniques performed on oil samples can be classified in to two categories: used oil analysis and wear particle analysis. Used oil analysis determines the condition of the lubricant itself, determines the quality of the lubricant, and checks its suitability for continued use. Wear particle analysis determines the mechanical condition of machine components that are lubricated. Through wear particle analysis, you can identify the composition of the solid material present and evaluate particle type, size, concentration, distribution, and morphology. Wear particle analysis can be a useful tool for identification of which machine components are degrading, and the rate of degradation of the components.