Digital Fault Recorders generate large volumes of data, but reviewing those records, classifying faults, and identifying their causes can still require significant engineering time.
In this webinar, Mark Diamond and David Cole from Qualitrol explore how artificial intelligence, machine learning, and pattern-matching techniques can transform fault analysis. Machine learning models trained on thousands of labeled DFR and FMS records can automatically identify fault categories and likely root causes, helping reduce manual analysis and improve the efficiency of fault investigation.
Mark and David will share insights from pilot projects, including what the models achieved, where they performed well, and where human engineering expertise remains essential.
In this webinar, you’ll hear about:
- How machine learning models are trained using thousands of labeled DFR and FMS records
- How AI and pattern matching can identify fault categories and likely root causes
- What the pilot projects found and how accurately the models performed
- Which parts of fault analysis can be automated and which still require an engineer
- How these technologies could be integrated into next-generation grid monitoring software
Product Manager at Qualitrol
Technical Application Specialist at Qualitrol
Mark Diamond is a Product Manager at Qualitrol with more than 21 years of experience in power grid monitoring and reliability solutions. A graduate of Queen’s University Belfast in Electrical and Electronic Engineering, Mark began his career at Qualitrol as an Application Engineer before moving into software testing and product management. He has worked with utility companies in more than 50 countries, holds two patents, and has authored numerous white papers on fault analysis, grid automation, and monitoring technologies.
David Cole is a Technical Application Specialist at Qualitrol, focusing on Grid Monitoring products. Over the past 40 years, he has worked across fault recorders, circuit breaker test sets, power quality devices, and travelling wave fault locators, in commercial, sales, product management, and technical roles. His earlier experience includes work with a UK distribution company, research into partial discharge location in cables, and application engineering in underground cable fault location. David is a member of the IET and CIGRE and has authored several technical papers.
If you work in protection, grid operations, reliability, or asset management, this session offers a practical look at how AI can support faster, more consistent fault analysis—and where human expertise remains critical.
