TRC-2018 Learning Zone 40:27
by Stuart Gillen, SparkCognition
Many organizations today are facing challenges in increasing reliability and uptime. Current industry solutions do not offer advanced notice for performing proactive, predictive maintenance. The use of intelligent edge devices to acquire asset sensory data, along with machine learning algorithms to predict when an asset will fail, is becoming more attractive to maintenance managers as they seek new methods to get maintenance costs under control. The use of this technology can augment or even supplement human subject matter experts while providing significant advanced notice of asset health issues by analyzing and learning from past asset health data. In this presentation, we will discuss practical ways in which utilities can get started today and see how others are implementing this technology.
TRC-2018 Learning Zone 42:20
by Randy Jones, Southern Company Generation
Everyone wants to achieve a connected plant and to leverage IoT, APR, predictive analytics, and other enhancements to improve business results. This presentation will discuss some practical steps to be considered and some basic foundational elements that will enable moving forward along this journey.
TRC-2018 Learning Zone 41:32
by David Shannon, Parker-Hannifin
Digital transformation is a journey in a large established company. One of the journeys surrounds packaging up an offer and figuring out how to sell it. These include technical issues and capabilities needed to simply connect and collect data from your product, notwithstanding the many forces that can make this effort challenging and potentially derail innovative ideas. Using the development and launch of the Parker-Hannifin’s Voice of the Machine™ IoT platform as a case study, David Shannon shares how Parker adopted a common set of standards and best practices for new business models and pricing across all its operating groups and technologies.
TRC-2018 Learning Zone 33:38
by Dave McCarthy, Bsquare
Traditional methods of equipment maintenance are often reactive – servicing equipment once it fails – or based on time intervals or hours of use. Reactive maintenance can represent expensive unplanned downtime and non-routine servicing that may be more costly. Time-based servicing may under- or over-service equipment, which can inflate maintenance costs and reduce asset longevity. This presentation will highlight how tailored maintenance schedules help eliminate over or under servicing to reduce downtime, improve asset longevity and the overall reliability of industrial assets.
A weekly collection of recommended articles and videos to boost your reliability journey. Right in your inbox
TRC-2018 Learning Zone 45:40
by Rudy Wodrich, IRISS
Online Monitoring and the use of IoT devices to facilitate easier data collection and collation can also be referred to as Critical Asset Surveillance Technologies (CAST). Traditional online monitoring techniques including Power Quality and Partial Discharge (PD) monitoring will be briefly examined. For industrial and commercial buildings, temperature monitoring may hold the most promise as a surveillance technique to catch problems early in the P-F curve. There are many options to consider when considering the implementation of online temperature monitoring. Keep in mind that the goal of temperature monitoring is to DETECT a potential, ANALYZE the data and determine criticality of further investigation, INSPECT the equipment in question to pinpoint the problem and finally to REPAIR the problem. With this in mind, we will weigh the technology options to be considered when choosing a temperature monitoring solution including:
Contact (point based) or non-contact (area based) monitoring
Wired or Wireless Communication
Wired or Battery Powered
CLOUD based or Firewalled Data
Data Collection Frequency
Stand-alone or part of Building Management System (BMS) or SCADA Platform
Let’s face it, people make mistakes – and some mistakes can be quite expensive. Mistakes made in a gearbox rebuild, for example, can cost a plant hundreds of thousands of dollars due to unplanned downtime and even workplace injuries resulting from a bad rebuild. Have you ever taken the time to audit your in-plant or outsourced rebuild facility? Do you require acceptance testing of the components that have been rebuilt to verify they are service ready?
The idea that smart factory technology will displace humans has generated considerable discussion. In a July 2016 report, McKinsey & Company estimates that “59 percent of all manufacturing activities could be automated.”1 In an article that can be applied to the field of industrial analytics, the MIT Technology Review2 suggests that unlike past experience, technologies are providing solutions that are more humanlike and could, therefore, eliminate jobs that so far have withstood automation.
Connected and integrated tools, sensors and software provide maximized uptime.
As industrial production rapidly transforms, the Industrial Internet of Things (IIoT) drives plant-wide changes and enhanced asset health and maintenance management. Facility managers, engineers and technicians must be able to rely on their equipment’s operation. Monitoring assets and assessing their health is of paramount concern to detect problems before catastrophic failures.
Deployment leverages Amazon Web Services (AWS) Internet of Things services to achieve the scale, availability, and security required in business-critical IoT systems
Chicago-based artificial technology company Uptake announced Monday that it has acquired Asset Performance Technologies, the Albuquerque-based technology company that provides industrial customers like power plants and oil companies with machine failure data.
IMC-2017 Panel Discussion - 39:45 by Mary Bunzel, Doug Cook, Sandra DiMatteo, Will Goetz, M. Mobeen Khan, John Murphy, Mike Poland, Heather Preu, Jagannath Rao
Machine learning and artificial intelligence is progressing at a rapid pace. According the Bureau of Labor Statistics, over 60% of maintenance tasks will be "machine" assisted by 2022. Join industry thought leaders at IMC-2017 for a vibrant panel discussion about human machine collaboration to advance reliability and asset management.
Equipcast utilizes Machine Learning and Predictive Analytics to provide the industry's leading Operational Health and Performance Optimization solution. We simplify and improve operational processes by discovering value from the complexity of equipment and maintenance data.
If you search the Internet for information on asset management, the Internet and Industrial Internet of Things, digitalization, business trends and business reengineering, you’ll find a considerable increase in the number of articles with headlines heralding or promising significant and “disruption” or “disruptive” change.
New scalability and ease of use features accelerate process manufacturing insights. Darcy Partners and CB Insights include Seeq in Advanced Analytics reports.
One of the goals of reliability is to identify and manage the risks around assets that could fail and cause unnecessary and expensive downtime. Organizations know it is important to identify areas of potential failures and rate them in terms of likelihood and consequence. They also have put in place good reliability strategies and have implemented proactive, condition-based maintenance programs. But now, machine learning is helping maintenance organizations get to an elevated level of situational intelligence to guide actions and provide early warnings of impending asset failure that previously remained undetected. Machine learning is paving the way for smarter and faster ways to make data-driven decisions in predictive maintenance (PdM).
Siemens AG and Software AG announced a partnership to strengthen the presence of the cloud-based open Internet of Things (IoT) operating system MindSphere across industries. MindSphere supports industrial companies in their digital transformation and offers a development platform to a broad customer base where companies can integrate their own applications and services to promote IoT innovations.