The Benefits of Predictive Maintenance versus Preventative Maintenance to Lower Maintenance Costs

You’ve fine-tuned your plant’s many integrated processes to produce products planned to meet your customer’s requirements – and then it happens! One piece of equipment fails, bringing your whole line down. Decisions are fast and difficult, considering the impact to your business is immediate and costly including changes to customer delivery schedules, alternate routings, expedited replacement parts, maintenance overtime, and equipment vendor support.

Could you have predicted this failure and completed maintenance in a controlled manner? Could you have scheduled machine downtime, spare parts readily available, mechanics on standby, coordinated vendor support? The answer is “YES”, using predictive maintenance.

What is Predictive Maintenance?

According to Wikipedia, predictive maintenance (PdM), is a technique designed to help determine the condition on in-service equipment in order to predict when maintenance should be performed. The approach promises cost savings over routine or time-based preventative maintenance, because tasks are performed only when warranted.

The main promise of predictive maintenance is to allow convenient scheduling of corrective maintenance, and to prevent unexpected equipment failures. The key is “the right information in the right time”. By knowing which equipment needs maintenance, maintenance work can be better planned (spare parts, people, etc.) and what would have been “unplanned stops” are transformed to shorter and fewer “planned stops”, thus increasing plant availability. Other potential advantages include increased equipment lifetime, increased plant safety, few accidents with negative impact on environment, and optimized spare parts handling.

Predictive maintenance differs from its cousin preventative maintenance because it relies on the actual condition of equipment, rather than average or expected life statistics, to predict when maintenance will be required.

Applying Predictive Analytic Techniques to Equipment Maintenance

Equipment failure has a root cause that is manifested over time and usage. The goal of predictive maintenance is to be able to anticipate failure occurrence and address the problem in a controlled scenario. How can this be done? Gathering equipment sensor data and other process inputs provide a window into equipment performance. Machinery often has the option of coming equipped with sensors, or they can be added later to monitor equipment performance in real time. These could include bearing temperature, shaft revolutions per minute (RPM), coolant temperature, coolant chemical composition, output quantity, impression count, viscosity, turbidity, and vibration.

By correlating the sensor data to the equipment performance, predictions can be made as to the timing of the failure, and sensor involved. It takes process engineers to translate the sensor data to the actual root cause, but predicting the failure can allow the business to provide maintenance in a controlled environment.

What’s needed for Predictive Maintenance?

The main tools supporting this approach are: a data historian capable of storing large amounts of data, and applying business rules such as data sampling, summarization, and preparing the output of data based on your business rules.

SAP offers Plant Maintenance to track equipment and maintenance records; Manufacturing Integration and Intelligence (MII) which provides; business logic, visualization tools, quality, KPI metrics and data services. For more complex analysis, SAP Predictive Analytics with its data correlation and time series algorithms, can combine the data with models to predict failure time.

The solution is not “plug and play”, but the payback is substantial and increases the level of plant performance and customer delivery well into the future. What’s required is some process equipment expertise, industrial engineering, JAVA programming, and SAP Application knowledge. Often projects pay for themselves within months – predicting the first failure with costs often exceeding $10,000 per hour of downtime.

Getting Started

Move from reactive to proactive maintenance and service by analyzing large volumes of operational data along with business data using the SAP Predictive Maintenance and Service solution. Apply deep insight into asset history and trends for predicting maintenance and service needs.

NTT DATA Business Solutions offers a full range of services supporting SAP Predictive Maintenance and Service solutions.