Enabling Condition Monitoring with Predictive Analytics

  • Mar 15, 2017

BUSINESS CHALLENGE

Every growing business aspires to strategically planning towards reducing operational expenditure (OPEX) and improve asset productivity through better understanding of asset usage and analysis. But, Growing Industry’s biggest challenges are productivity improvement, minimizing maintenance expenses, eliminate (if not reduce) the uncertainty in their plant / machinery / equipment reliability. Any unexpected equipment failure not only increases the cost of operations but also affects asset utilization levels adversely.

An Unplanned Downtime = 1.5 X Planned Down time. An Emergency Downtime = 5 X Planned Downtime.

Most industries primarily deploy preventive maintenance or corrective maintenance or both these approaches to enusre their business is in the growth path.

Corrective :

Equipment's are repaired on break down or when not performing up to the mark.

Cons :

Causes disruption in scheduling and production, as delays in sourcing spare parts, time taken to repair, and getting access to Service Engineers. High risk causing accidents and injury to operator, and failing safety standards.

Preventive :

Maintenance of equipment is on a fixed and periodic basis, depending on predetermined breakdown windows, which is decided based on the estimated rate of equipment wear and tear, acceptable maintenance costs, and general degradation rules. Most Industries today rely on preventive maintenance to ensure smooth operations.

Cons :

Equipment can be unpredictable, and even break down right after a scheduled maintenance. if not addressed proactively, can cause extensive business damage, apart from endangering the safety of workers.

PREDICTIVE ANALYTICS

As the Internet of Things (IoT) increasingly becomes mainstream across the industrial landscape, industries are exploring predictive maintenance, or condition based monitoring and maintenance. It is a new method of equipment care that analyses the real-time data collected from machines to forecast potential breakdowns. Continuous innovations in semiconductor manufacturing and digitization-enabled technological breakthroughs helping bring down the cost of sensors significantly, , making equipment digitisation cost-effective Condition Based Monitoring solutions that bundle both hardware and software viable for the industry. These connected sensors can monitor a wide range of functional equipment parameters – including temperature, acoustics, pressure, vibration and load – in real time, and generate an accurate and highly reliable predictive maintenance forecasting model.

SOLUTION

eHive a connected asset management Platform as a service provides a complete end-to-end solution for Industrial IoT adoption. The Platform’s Flexible architecture and configurable services reduces the time for deployment of solutions for OEM's & Dealer's.

eHive platform services includes preventive maintenance alerts, Equipment management, Machine operational event analysis and remote machine software distribution. eHive provides In-depth Insights of the machine analytics that enabled customers to plan and implement strategies to improve the overall equipment effectiveness and productivity. eHive’s Machine Learning capabilities provides predictive maintenance leading to early fault detection.

eHive determines Machine conditions based on three factors, Current consumption, Vibration and Temperature with the sensors that are capable of fast Fourier transform (FFT).

RESULTS

With eHive, OEM’s can offer customers value-added services, that can bring new revenue streams. It improves customer service and loyalty, reduce warranty and maintenance costs, and obtain real-time customer data and alerts.

OEM’s can use performance and usage insights from the field to improve product development.

For OEM’s customers, the services helps to improve machine productivity and customer satisfaction by minimizing machine outages through predictive maintenance and in-depth analytics.