Feature spotlights

Asset maintenance status

IBM’s Design Thinking is applied to provide a user experience that incorporates the concept of “cards”, which represent individual assets. It allows reliability engineers to easily access information to determine which assets are being over-, under- or well-maintained and use this prescriptive analysis to optimize maintenance practices and resources. The user experience supports analysis and reporting on all assets, classes of assets, or filters for properties common to a set of assets.

Drivers and risk factors

At the most granular level, reliability personnel gain an understanding of individual drivers and factors that affect asset performance, as well as detailed attributes of the asset, predicted time to failure, and maintenance logs. This information provides as complete a context as possible for assessing past, present, and future asset performance that can be used to recommend or prescribe practices or procedures to improve maintenance strategies.

Compare asset performance

To further explore why certain assets may be performing better or worse than others, a reliability engineer can chronologically compare drivers and risk factors such as hours of operation, failure frequency, AND cycles for a specific asset. This level of detail can help a reliability engineer visually correlate factors that are positively and negatively influencing asset performance in context of historical failure data and maintenance and replacement activities.

Machine learning

Apply machine learning, using principles of math, science, and engineering to identify correlations between maintenance data and operating data along with any other data that may contain clues about equipment usage and degradation. In some instances, analysis may indicate current asset maintenance schedules and practices are ideal and no changes need be made. For others, analysis will prescribe maintenance be preponed to avoid asset failure or postponed to avoid unnecessary maintenance.

How customers use it

  • Identify risks to operations using operational data

    Identify risks to operations using operational data

    Problem

    Instrumented, connected assets generate volumes of operational data - structured and unstructured - that can be used to identify risks if the organizations have analytic tools to convey this insight to personnel responsible for asset operations.

    Solution

    IBM Prescriptive Maintenance on Cloud enables organizations to apply machine learning and analytics to operational data generated by critical assets and visualizes this analysis to provide a better understanding factors affecting asset performance .

  • Optimize maintenance resources to reduce overall costs

    Optimize maintenance resources to reduce overall costs

    Problem

    Without careful analysis of asset operational data and factors affecting asset performance it is difficult to determine the how to best allocate maintenance resources and schedules so as to optimize asset availability and reduce maintenance costs.

    Solution

    Determine which assets are being over-, under- or well-maintained by analyzing maintenance records, timing, performance metrics, and event data to prescribe optimum asset maintenance schedules, allocate resources, and reduce maintenance costs.

Technical details

Software requirements

A workstation that runs one of the supported web browsers.

    Hardware requirements

    This solution is hosted in IBM's secure, cloud data centers.

      See how it works