Page 22 - An Introduction To Predictive Maintenance

12 An Introduction to Predictive Maintenance

company must provide sufficient training to ensure maximum return on its investment.
This training should focus on process or operating dynamics for each of the critical
production systems in the plant. It should include comprehensive process design, oper-
ating envelope, operating methods, and process diagnostics training that will form the
foundation for the reliability group’s ability to optimize performance.

The second approach is to hire professional reliability engineers. This approach may
sound easier, but it is not because there are very few fully qualified reliability pro-
fessionals available, and they are very, very expensive. Most of these professionals
prefer to offer their services as short-term consultants rather than become a long-term
employee. If you try to hire rather than staff internally, use extreme caution. Résumés
may sound great, but real knowledge is hard to find. For example, we recently inter-
viewed 150 “qualified” predictive engineers but found only 5 with the basic knowl-
edge we required. Even then, these five candidates required extensive training before
they could provide acceptable levels of performance.

1.2.2 Proper Use of Predictive Technologies
System components, such as pumps, gearboxes, and so on, are an integral part of the
system and must operate within their design envelope before the system can meet its
designed performance levels. Why then, do most predictive programs treat these com-
ponents as isolated machine-trains and not as part of an integrated system? Instead of
evaluating a centrifugal pump or gearbox as part of the total machine, most predic-
tive analysts limit technology use to simple diagnostics of the mechanical condition
of that individual component. As a result, no effort is made to determine the influence
of system variables, like load, speed, product, or instability on the individual compo-
nent. These variations in process variables are often the root-cause of the observed
mechanical problem in the pump or gearbox. Unless analysts consider these variables,
they will not be able to determine the true root-cause. Instead, they will make rec-
ommendations to correct the symptom (e.g., damaged bearing, misalignment), rather
than the real problem.

The converse is also true. When diagnostics are limited to individual components,
system problems cannot be detected, isolated, and resolved. The system, not the indi-
vidual components of that system, generates capacity, revenue, and bottom-line profit
for the plant. Therefore, the system must be the primary focus of analysis.

When one thinks of predictive maintenance, vibration monitoring, thermography, or
tribology is the normal vision. These are powerful tools, but they are not the panacea
for plant problems. Used individually or in combination, these three cornerstones of
predictive technologies cannot provide all of the diagnostics required to achieve and
sustain world-class performance levels. To gain maximum benefit from predictive
technologies, the following changes are needed: Process parameters, such as flow
rates, retention time, temperatures, and others, are absolute requirements in all pre-
dictive maintenance and process optimization programs. These parameters define the
operating envelope of the process and are essential requirements for system operation.
In many cases, these data are readily available.