Like all new product releases, IBM Maximo Application Suite (MAS) 9.0 promises enhancements to existing features, intriguing new additions, and adjustments to support methods that may affect current users. As of writing, MAS 9.0 is slated for release in June 2024. However, the specifics discussed here are subject to change pending IBM’s final release. For accurate information, consult the official product documentation upon release.
Take an overview look at the new developments of SAP S/4HANNA Asset Management including: Phased Maintenance, Simplified Emergency Maintenance, Checklist Processes and Standard Resource Scheduling among others.
Effective understanding of the health of your equipment and prediction of what its future looks like is based on detecting anomalies sooner and being able to make real time decisions based on those anomalies.
By evaluating the type of system you are constructing and selecting the MAS components that your are implementing you will be able to accurately size your environment which now runs as containerized applications under Red Hat OpenShift.
TRM joins with Aspen Mtell to empower organizations to enhance asset performance through industrial artificial intelligence and machine learning along with other monitoring technologies.
This article describes the first few steps a person will take when using existing data sets and preparing them for use in AI/ML forecasting and anomaly detection. It introduces the reader to IBM Watson Studio by way of a problem statement and sample equipment data.
Industrial maintenance is a comprehensive process crucial to the reliable operation of various industrial plants, mines, and mills. It extends beyond simple repairs, involving a systematic approach to condition monitoring, fixed time maintenance, and corrective maintenance approaches for industrial equipment.
Tor Idhammar
President & CEO, IDCON, Inc. Reliability and Maintenance Consultant
IDCON is an Independent Subsidiary of TRM, Inc.
Measuring things that get done correctly and the results of this effort is an essential part of successful management, and is in your company’s best interests.
A key element of any approach to asset performance management (APM) are the tools to make use of the vast amounts of operational data coming from actual equipment sensors. Aspen Mtell is one of those tools that uses machine learning algorithms to analyze the data and generate credible alerts to impending failures.
It is important to understand what some of the cybersecurity standards and requirements are and how they may impact your adoption of cloud environments for your software solutions.
Anomaly detection (AD) is the art of discovering data points in a data set that deviate from what is considered normal or expected. Let’s try an example. Look at the chart below and ask a couple of questions: What appears to be the normal, or expected value for each day of the 16-day process? What appears to be the significant excursion(s) from that normal?
While the definition of APM may vary from one organization to another, there are several foundational elements that need to be considered to start down this path. APM is not a product nor even a framework but rather describes a set of activities that we have been doing to some degree or another for quite some time. Of course, there are software and other tools that can provide the necessary features and functions you need to “do,” APM.
