Predictive Maintenance

Industries at large face problem of unplanned downtime that causes them loss in term of man, machine, material, time and reputation. The downtime occurs due to various electrical and mechanical failures in machinery.
As of today, industries are having real time monitoring solution that is called condition monitoring, that is based on reactive maintenance i.e. after getting any part break down, maintenance team fixes it, that still hampers the production process for some time.
Instead the requirement is for predicting the possible fault at early stage and get is corrected before it breaks down any part. Under predictive maintenance, the machine is repaired when it is really needed. While preventive maintenance is done at fixed time interval.
The preventive maintenance objective was to keep the plant in a good operating condition components often had to be replaced with new one or refurbished parts to avoid major plant trips. However the approach was not adequate enough to improve the availability, operational excellence while minimizing maintenance cost.

Cost Analysis: Proactive, Predictive and Reactive Approach

Reactive

Cost to adjust and

Cost to repair component and

Cost to repair collateral dameageand

Cost of downtime

Cost of emergency OT

Cost of expediting parts

$3000

Predictive

Cost to repair component

and cost to align

$3000

Proactive

cost to align

$600

Predictive maintenance for rotating machinery is gaining prominence as plant operators embrace analytics and learn how to approach their operating benchmarks

Rotating machines, such as motors, compressors, pumps and turbines, are critically important components of plant operations, and must perform reliably and efficiently at all times. However, given the high pressures and harsh environments in which these machines operate, equipment failures are all too common

With vast computational power and the advent of low-cost sensors, preventive maintenance is transitioning into predictive maintenance. Predictive, or condition-based maintenance, as it is also called, identifies issues in equipment before they present serious risks to plant operations or personnel. In a predictive maintenance approach, plant managers use evidence-of-fault to determine how to maintain equipment or even when to replace it. Accurate information on equipment condition enables companies to minimize failure risks, reduce maintenance costs and maximize asset availability.

Because bearings are extremely critical components of rotating machines, sensors are frequently installed directly on the bearing to measure vibration and bearing surface temperature. Other sensors are installed on the machine housing to capture overall vibrations, and in the case of electrical motors, to measure critical electrical parameters, such as voltages and currents. Wired instrumentation also is used in less critical equipment, but this is uneconomical, so monitoring is often limited to high- and medium-criticality machines. Wiredsensors allow for continuous machine monitoring, while wireless sensors measure machine status periodically (for instance, once per hour). Wired instruments are better for protecting the machine, while wireless sensors are good for monitoring overall machine condition. Moreover, wired sensors can capture some types of signals and information not achievable wirelessly.

Vibration Analysis

For predictive maintenance, vibration analysis is used to:

Detect and monitor a chronic problem that cannot be repaired and will only get worse

Establish acceptance testing criteria to ensure that installation/repairs are properly conducted

Vibration analysis can be used as a troubleshooting tool to avoid failures.

Vibration analysis can be used to detect the fault in early stage so reduces maintenance costs and increases up-time.

Spectrum analysis is the most commonly used vibration analysis tool — the picks usually relate to components within the machine.

We look for changes in pattern to determine if the condition of the machine may have changed.

We look at the amplitude of the peaks to assess the severity of the fault condition.

We can use more analysis tools like time waveform analysis and phase analysis (we didn’t talk about it) to verify/confirm the diagnosis made with the spectrum.

Time waveform shows us what’s happening inside the machine from moment to moment.

Too few people utilize time waveform.

24/7 continuous vibration monitoring can be use to predict failures as part of a predictive maintenance program.

Motor Vibration Monitoring

Motors are likely to experience high vibration levels at some point during their lifetime. Performing predictive maintenance through motor vibration monitoring can prevent issues resulting from a variety of motor faults, including those often found in motor bearings, gearboxes and rotors:

Gearbox Vibration Monitoring

In gearboxes, impacting and friction can occur, and a single crack in a gear could cause a slight change in speed once the defective teeth are inside of the load zone. This will result in impacting, and if there is insufficient lubrication for the gear teeth, friction will also occur. Machine vibration monitoring can detect these instances of impacting and friction in predictive maintenance.

Bearing Condition Monitoring

Bearing defects are often the source of vibration in machinery, but bearing condition monitoring can help keep identify these defects and determine when repairs or replacements are needed. Bearing defects can include excessive loads, true or false brinelling, overheating, reverse loading, normal fatigue failure, corrosion, loose or tight fits, and misalignment, among other potential problems.

Rotor Vibration Monitoring

There are several causes of lateral vibrations in rotors, including instability and unbalance, along with other types of forces impacting the rotor. Cracks are often formed, frequently leading to reduced natural frequencies as a result of reduced rigidness. Rotor vibration analysis can monitor the rotor’s behavior to help locate a developed crack.

Our Solution

Uniconverge Technologies is leveraging the latest technologies like IoT, Machine Learning and Data analytics to predict the fault at early stages by monitoring key parameters. The predictive maintenance approach is currently widely used by the process industry today because it reduces unnecessary maintenance activities, improves stability and performance by providing an early detection of a decreasing reliability of plant equipment. This is accepted by the plants as the best available maintenance practice at a lower cost. Algorithm is highly flexible to take care of present monitored parameters as well as introduction of new parameters. A technology wise Predictive Maintenance approach promises cost savings and improvement in both stability and performance compared to a routine or time based Preventive Maintenance program.