Predictive Maintenance

Predictive Maintenance
Predictive Maintenance
Predictive Maintenance
Predictive Maintenance
Predictive Maintenance
Predictive Maintenance
Predictive Maintenance
Predictive Maintenance
Predictive Maintenance
Feature New Record
DESCRIPTION
Condition-based Maintenance (CBM) or predictive maintenance is the science of maintaining physical assets over time, in order to maximize their return on those assets. It is enabled by sensors and data analytics that provide visibility into the current and future status of assets.
There are three ways that maintenance can be triggered, regardless of asset type or attributes. These are use-based maintenance (UBM), fail-based maintenance (FBM), and condition-based maintenance (CBM). Generally CBM is the preferred option but lack of visibility into asset condition often leads companies to rely on UBM or FBM policies. The value in leveraging IoT to improve CBM capabilities includes lower maintenance costs, lower asset lifecycle cost, greater asset availability, reliability, performance, and quality of output.

CBM focuses on identifying failures before they occur by incorporating inspections of equipment at predetermined intervals to determine system condition. These inspections could include continual data collection from equipment about the vibrations (sound), temperature, pressure, light, voltage, current, field strength and other variables. Depending on the outcome of a continual inspection, either a preventive or no maintenance activity is performed. Systems generally work by comparing current sensor or inspection data with standardized reference data.

Example of condition based maintenance:
Motor vehicles come with a manufacturer-recommended interval for oil replacements. These intervals are based on manufacturers’ analysis, years of performance data and experience. However, this interval is based on an average or best guess rather than the actual condition of the oil in any specific vehicle. The idea behind condition based maintenance is to replace the oil only when a replacement is needed, and not on a predetermined schedule.

In the example of industrial equipment, oil analysis can perform an additional function too. By looking at the type, size and shape of the metal particulates that are suspended in the oil, the health of the equipment it is lubricating can also be determined.

CBM = Cost Savings + Higher system reliability:
Condition based maintenance allows preventive and corrective actions to be scheduled at the optimal time, thus reducing the total cost of ownership. Today, improvements in technology are making it easier to gather, store and analyze data for CBM. In particular, CBM is highly effective where safety and reliability is the paramount concern such as the aircraft industry, semiconductor manufacturing, nuclear, oil and gas, et cetera.

Challenges of condition based maintenance:
- Condition based maintenance requires an investment in measuring equipment and staff up-skilling so the initial costs of implementation can be high.
- CBM introduces new techniques to do maintenance, which can be difficult to implement due to resistance within an organization.
- Older equipment can be difficult to retrofit with sensors and monitoring equipment, or can be difficult to access during production to spot measure.
- With CBM in place, it still requires competence to turn performance information from a system into actionable proactive maintenance items.

Benefits: Cost savings by ensuring machines are being kept healthy and being repaired when needed, while minimizing downtime
-OT CAPEX Reduction
-Customer Satisfaction Improvement

Key vendors: Bosch, GE, IBM, SAP
MARKET SIZE

The predictive maintenance market size is estimated to grow from USD 1,404.3 Million in 2016 to USD 4,904.0 Million by 2021, at a Compound Annual Growth Rate (CAGR) of 28.4% during the forecast period.

Source: markets and markets

 

Another Report indicates a USD 11 billion Predictive Maintenance market By 2022.

Source: Iot-Analytics

NEW USE CASE ALERT
Get notified when a New Use Case is published.