Home Embedded Blog Predictive Maintenance case-studies from Railway, Energy, Oil & Minerals Industries: The Challenges and Benefits

Predictive Maintenance case-studies from Railway, Energy, Oil & Minerals Industries: The Challenges and Benefits

With the advent of Industry 4.0, predictive maintenance has been seen as the next technology frontier to unlock benefits of increased productivity and reduced costs.

This parameter based continuous monitoring helps in recognizing the failure point or behavioural anomalies. Thus, decision making can be done proactively by deploying the field technician or sending a patch fix remotely; prior to the actual breakdown.

To summarize, predictive maintenance is a culmination of condition based monitoring and data analytics.

However, for organizations this paradigm shift from preventive to predictive maintenance, though necessary, is challenging at various levels.

Such migration will need a re-framing of organizational process, investments in new technologies and training to the existing workforce.

PdM
Source: Deloitte
 
Learning from the Predictive Maintenance Case-Studies:

Despite the known and unknown challenges faced during migration to predictive maintenance. Many businesses have successfully made this change

We present to you a list of predictive maintenance implementations to serve as an inspiration for you.

  1. Industry – Railway

VR group is a state-owned railway company in Finland. VP of the maintenance at VR group, Kimmo Soini stated that transportation industry cannot afford to frustrate its passengers with unexpected delays.

Although admittedly, the VR group is the only passenger railway service in Finland still they are competing against other modes of transportation.

Therefore the company has always strived to make its operations fail-proof in order to keep its customer satisfied and engaged.

They eventually migrated their maintenance approach from a primitive reactive method to analytics and the Internet of Things (IoT) driven strategy.

This migration was confronted by following unique challenges:

  • Scale of operations:
  • VR group manages a fleet of 1500 trains running on rails. They all have a task of delivering a better, safer experience for its passengers.

    To migrate, large scale operations to Predictive Maintenance systems and processes requires robust planning, technology skills and investment of time and money

  • Operational hazards:
  • The trains undergo harsh weather conditions and hence are prone to unexpected breakdowns. This always resulted in draining of a sizeable amount of operational costs on maintenance activities

    While migrating to predictive maintenance, such operational hazards become a critical factor in designing of requisite hardware, sensors and other equipments.

Predictive Maintenance in action at VR Group:

They initiated the process by installing sensors to monitor fault points that can lead to failover.

But the sensor data is raw unless it is used in the real-time analytic engine. The VR group turned to SAAS Analytics to convert raw data into an actionable and decision aiding analytical report

SAAS data analytics has helped the company in many aspects including RCA (root cause analysis) of the failure points, improve the reliability of the trains and increase savings on unnecessary maintenance.

Data analytics has also helped the company to maximize the interval between maintenance events frequency at which planned maintenance needs to be executed.

Such planned maintenance events also add to the operations related costs. For example, turning wheels or the wheel-and-axle set replacement is one such planned maintenance activity.

If the date of turnings can be optimized, the trains will be functional on the rail for a longer time period. As indicated by Soini, this leads to cutting down on the maintenance work by one-third which is very cost effective for the business.
 

  1. Industry – Iron Ore

Advisian, a company within Worley Parsons Group implemented predictive maintenance model for one of its customers.

A large iron ore mining company in Australia partnered with Advisian, for a predictive maintenance project that required technology implementations at their mines, processing plants, logistics and other related functional segments.

The client’s vision was to develop a reliable and integrated asset management platform.

Objective of the platform was to support condition-based monitoring in order to keep in check the asset’s health, predict failure or breakdowns and ensure proactive maintenance decision-making on the basis of the historic data.

The implementation of this method of proactive maintenance was done by Advisian through specific software installation and configurations for condition-based monitoring.

Advisian successfully completed successful integration of SAP PM (predictive maintenance) which is a functional module to manage equipment on the production floor.

They also developed a maintenance strategy for their clients, which helped them achieve health and performance monitoring for critical mine processing equipment.

The evident outcomes resulted in a cost efficient predictive maintenance approach on the basis of analysis of field data and equipment data.

It also helped in significant reduction of equipment downtime, due to continuous monitoring technique.
 

  1. Industry – Wind Power

Roland Berger, which is a global consulting firm, has experience of working with several wind power operators and turbine OEMs for implementation of predictive maintenance strategies.

The company extended its partnership towards two of the Wind power operators, for providing Predictive maintenance service.

The Operators faced business challenges, in operation and maintenance of the wind turbines. The factors like, rough environmental conditions and installations in remote geographical locations are the major concerns.

Since Predictive Maintenance (PdM) supports remote surveillance, it has emerged as an effective method of monitoring wind turbines.

In the wind power industry, the estimated revenue that goes towards maintenance is estimated to be 20% of the total production cost.

The wind power plant operators have reported PdM to be more efficient method to reduce operational and maintenance costs and increase production revenues. It has even delivered ROI within 6 months in some cases.

A global wind plant operator has been quoted mentioning that for a medium sized wind farm, the company was able to save quarter of a million dollars on adopting a predictive maintenance software system.

As testified by another wind power operator, effective asset tracking is also one primary benefit of predictive maintenance technique.

The operator implemented the predictive maintenance solution and analyzed the assets through an asset tracking software. They discovered that one of their wind turbines was not performing optimally.

predictive maintenance solution
Source: Blog tieto
 

The RCA (Root Cause Analysis) of the situation gave an insight on the operational limit of the turbine system which led to such under performance.

This analysis helped the operator to select a right functional threshold for the equipment.

Such proactive approach helped them to manage their turbines and its health condition before any breakdown thus avoiding any significant loss in business due to downtime.
 

  1. Industry – Petrochemical

The IoT-powered predictive maintenance solutions have also made an indispensable impact on oil refining and petrochemical companies.

The major challenge faced by oil refineries is that, the physical inspection of the equipment located at deep ocean floor is very dangerous and inefficient process.

Therefore oil refining industry has always been in need of the better method not only for predictive maintenance, to identify potential failure, but also for better asset tracking.

Oil fields generally have assets fitted with sensors, to assimilate the vast amount of data. But most of these data is never utilized.

Mckinsey estimated that, certain oil field production platforms contain data tags as large as 40,000, though not much data is being used.

Dyogram, an IoT service provider for Industrial, Retail, Manufacturing and Logistics, helped one of its oil and gas industry customers, to implement the predictive maintenance solution and big data analytics.

Advanced predictive maintenance solutions helped mitigate the challenges associated with huge volume of data generated by Oil refining and petrochemical companies.

The big data analytics ensures huge volume of data is managed in a scalable and cost-effective way thus shooting down the maintenance cost

These advanced solutions also incorporate methods like, data storage in the central repository and efficient remote monitoring.

The solution was designed to compare the real-time data with historical failure rate models and identifying potential equipment failure.

This helped in efficient resource maintenance, without the need for equipment replacement due to permanent damage.

Predictive Maintenance (PdM) is omnipresent:

All these implementations prove the relevance of Predictive Maintenance and its positive impacts across various industries.

Stay tuned with us for more information regarding PdM. In the meantime, do checkout our other posts related to predictive maintenance

This entry was posted in Embedded Blog, Blog by Embitel. Bookmark the permalink

Jun 21 2017
Related Posts

ASK OUR EXPERTS

captcha

 I agree to allow this website to store my submitted data. This data can be used only for responding to my query and/or send related information about technology services and solutions.

FEATURED WHITEPAPER

12 design strategies to develop an "In-Vehicle Infotainment " system

RELATED SERVICES
 

Car HUD (Heads-up Display)

Go-to-market in 6 months with our automotive grade hardware and software design


Automotive Control Units

Electronic Control Units (ECU) development services for Body Control Modules (BCM), Powertrain, Chassis and Infotainment


AUTOSAR Software Services

AUTOSAR MCAL development, RTE and BSW integration, Application Layer development, Tools configuration and code generation


CUSTOMER SUCCESS STORIES
 
J1939-stack

J1939 Stack for advanced EPS system

Find out how J1939 stack resolved on-chip memory issue for an Automotive Tier-I supplier


connected-car

Software re-engineering | Telematics applications

Modular architecture re-design across fleet management product lines - GPS fleet security, vehicle and trailer tracking


IoT

IoT based Home Automation system

Design and development – Sensor Networks, Custom IoT gateway, Cloud and Mobile App