Maintenance
Maintenance is a component of any system’s lifetime and it is critical to ensuring its adequate and safe functioning. However, maintenance costs time and money, and performing it may require restricting or interrupting a system’s functioning. Well-founded maintenance is an engineering practice, whereas unnecessary maintenance is not only a waste of resources, but it is also detrimental to the functioning of a system as a whole. Facility Management care about its Customer’s bottom line and therefore they are on the lookout for systems that contribute to such an endeavor. Condition Monitoring and Predictive Maintenance are those systems that often come up in the context of safety engineering and fit any Facility Manager’s goal.
Both Condition Monitoring and Predictive Maintenance systems are used to predict equipment or component maintenance, and to monitor corrosion, oil condition, arcing, bearing wear, overheating and other parameters that can lead to the breakdown of capital equipment. They incorporate technologies such as vibration measurement and analysis, infrared (IR) thermography, oil analysis and tribology, and motor current signature analysis (MCSA). Vibration analysis systems apply the principle that all moving bodies produce sound waves. By contrast, predictive maintenance and condition monitoring systems that use infrared thermography measure the emission of heat. Oil analysis and tribology systems are used to monitor the friction, lubrication and wear of interacting surfaces in relative motion. Motor current signature analysis (MCSA) systems provide information about electrical faults caused by excessive motor starts or overloading. Because rotor bar damage is difficult to detect with a vibration signature, MCSA systems are often used to prevent motor failure with mission-critical machinery.
Many predictive maintenance systems and condition monitoring systems use acoustic vibration monitoring (AVM) to identify vibrations which correspond to specific defects. There are several different AVM techniques. Low-frequency vibration measurement systems are used to indicate that a component is in advanced state of wear because of problems such as imbalance or misalignment. Service personnel can then repair machinery of equipment before component failure occurs. High-frequency vibration measurements also help to prevent downtime, but typically trigger alarms before a mechanical component enters a failure state. Exactly which parameters are monitored depends, of course, on application and equipment: they include, for example, temperature and vibration parameters for electrical drives, or Signal-to-noise ratio (abbreviated SNR or S/N) levels for communication equipment. Not only can these parameters indicate an impending failure, but they can also indicate which components are most likely to be at fault, thus enabling engineers to plan and target their maintenance operations with more accuracy.
Although predictive maintenance and condition monitoring systems vary in terms of features and cost, they consistently improve equipment reliability through the prediction and avoidance of costly failures. Predictive maintenance and condition monitoring systems also minimize downtime by enabling facilities to plan and schedule repairs. In turn, component life is maximized by avoiding conditions such as lubrication contamination and misalignment. Predictive Maintenance enables more efficient, longer-term planning for maintenance operations and makes it easier to define operational maintenance goals and to allocate maintenance resources. Consequently, in recent years, Predictive Maintenance has come to rely increasingly on Machine Learning techniques. Machine Learning refers to a set of statistical techniques, which enable computer systems to learn how to identify and classify patterns in large volumes of data and to make predictions based on it.