Register to our upcoming webinars!
[SYP Webinar] Optimized Pulse Patterns for High-Power Converter: From Offline to Online Computation
Tuesday 26 May 2026 at 2:00 PM CET, 8:00 AM ET, 10:00 PM AET By Tobias Geyer (ABB Switzerland), and Ellis Tsekouras (Sydney University of Technology) Register now using the link below: https://attendee.gotowebinar.com/register/5329242054774405213 Abstract: Optimized pulse patterns (OPP) are the modulation method of choice to maximize the hardware capability of high-power converters and drives. OPPs achieve inverter-friendly operation by constraining the semiconductor junction temperatures and load-friendly operation by meeting harmonic grid codes or minimizing motor losses. Model predictive control methods, such as model predictive pulse pattern control (MP3C), achieve closed-loop control of OPPs with superior dynamic performance. Traditionally, OPPs have been computed offline based on assumptions of the operating conditions. Particularly when operating grid-connected converters, the harmonics present at the point of common-coupling are unknown. These unknown grid voltage harmonics often deteriorate the harmonic performance of the converter. The next frontier in OPPs is, therefore, the online computation of tailor-made OPPs to the operating conditions at hand. This webinar will introduce high-power converters and their applications, discuss traditional OPPs and MP3C and showcase a breakthrough in online computed OPPs. As an example, real-time OPPs (RT-OPPs) that account for unknown and time-varying grid voltage harmonic disturbances will be presented. Presenters’ ...
[WiE Webinar] Signal-to-Semantics: LLM-Powered Time Series Understanding for Explainable Industrial Fault Diagnosis Paradigm
Friday 28 May 2026 at 7:00 PM CST, 1:00 PM CET, 7:00 AM ET By Chunhui Zhao (College of Control Science and Engineering, Zhejiang University, Hangzhou, China) Extraordinary Women-in-IES Webinar Register now using the link below: https://attendee.gotowebinar.com/register/4914301759458674779 Abstract: Fault diagnosis is a critical link in ensuring the safe operation of industrial systems. Traditional time-series data diagnosis models typically output abstract results, such as anomaly scores or fault categories, but they cannot answer key questions like "why the fault occurred" or "how to perform maintenance." Although large language models (LLMs) show great potential for fault diagnosis, they face the challenge of a semantic gap when processing time-series industrial signals; that is, continuous temporal data are difficult to encode into discrete tokens that language models can effectively process. Differing from the traditional "signal-to-category" paradigm in fault diagnosis, we propose a novel explainable fault diagnosis framework, namely the "Signal-to-Semantics" (S2S) fault diagnosis framework. Our research replaces the original paradigm of mapping abstract time-series data to abstract diagnostic results, and instead outputs reasoning processes and diagnostic texts that are comprehensible and verifiable by human experts, establishing a new generation of intelligent diagnosis frameworks for industrial equipment. Presenter’s bio: Chunhui Zhao, Qiushi Distinguished Professor, ...