Our Senior Data Analyst, Julianne Rhoads created a guide as a part of I2SL Best Practices. Best Practice Guides and Technical Bulletins provide information on the design, construction, and operation of specific technologies that contribute to energy efficiency and sustainability in laboratories. The guides include information from actual implementation of these technologies in various laboratory facilities by highlighting quantifiable performance goals and possible methods to achieve them.
The Predictive Maintenance Using Automatic Fault Detection and Diagnostics guide shows how the big data analytics revolution has enabled true predictive maintenance on a large scale. Users of predictive maintenance analytics can now reap the benefits of cost savings and reduction in greenhouse gas emissions, increased reliability, prolonged equipment life, and reduced risk of process disruptions. A future opportunity to further increase the effectiveness of predictive maintenance systems is integration with enterprise asset management systems. Although this may seem simple at first, there is currently a need for a human decision maker to add business insight as to what maintenance investments should be made.
Read the full paper:
In addition, multiple projects are underway in the industry to standardize building automation system point naming and metadata structuring and topology. Many exciting opportunities lie ahead, and we are just scratching the surface of what is possible with the physical world data analytics.
The field of automated building analytics has seen many advancements since it was introduced 20 years ago. Much of the discussion has focused on energy savings, but applications of big data analytics are not limited to this aspect. Lab owners and operators can use analytics not only to improve energy efficiency but also to facilitate predictive maintenance. Predictive maintenance results in increased equipment life, improved reliability, and power labor cost.
The goal of predictive maintenance is to save money and increase facility reliability. The risk of equipment failure can be reduced by continuous, automated analysis of equipment performance to identify faults before they become critical. Predictive maintenance was once limited to high-value capital assets, but modern automation systems allow for collection and storage of vast amounts of data, and low-cost computing power makes it possible to analyze that data.
A successful predictive maintenance program requires investing in a data-rich building automation system, configuration of that system to perform analytics, development of a process and workflow to manage the automatic fault detection and diagnostics (AFDD) results, and training of facilities personnel on the program. The result is a leaner, more efficient lab facility operation, helping to eliminate energy-wasting faults while freeing up funds and labor for other types of sustainability improvements.