Search

The current energy scenario requires that gas turbines (GTs) operate at their maximum efficiency and highest reliability. Trip is one of the most disrupting events that reduces GT availability and increases maintenance costs. To tackle the challenge of GT trip prediction, this paper presents a methodology that has the goal of monitoring the early warnings raised during GT operation and trigger an alert to avoid trip occurrence. The methodology makes use of an auto-encoder (prediction model) and a three-stage criterion (detection procedure). The auto-encoder is first trained to reconstruct safe operation data and subsequently tested on new data collected before trip occurrence. The trip detection criterion checks whether the individually tested data points should be classified as normal or anomalous (first stage), provides a warning if the anomaly score over a given time frame exceeds a threshold (second stage), and, finally, combines consecutive warnings to trigger a trip alert in advance (third stage). The methodology is applied to a real-world case study composed of a collection of trips, of which the causes may be different, gathered from various GTs in operation during several years. Historical observations of gas path measurements taken during three days of GT operation before trip occurrence are employed for the analysis. Once optimally tuned, the methodology provides a trip alert with a reliability equal to 75% at least 10 h in advance before trip occurrence. [ABSTRACT FROM AUTHOR]

A Pump as Turbine (PAT) is a renewable energy technology that can be a cost-effective and reliable alternative to hydraulic turbines in micro and small hydropower plants. In order to further favour PAT exploitation, a general procedure that allows the identification of the most suitable turbomachine to install is required. To this purpose, this paper develops a novel methodology aimed at selecting the best PAT that, among several alternatives, maximizes energy production. The methodology comprises two steps, which only require the knowledge of the best efficiency point of the considered pump and the hydraulic parameters of the site. The novel methodology is validated in this paper by calculating the electrical energy production of a simulated water distribution network coupled with several PATs, whose performance curves, both in direct and reverse modes, are taken from the literature. For the sake of generality, the considered turbomachines account for different geometrical characteristics, rotational speeds and operating ranges.

The exploitation of fossil fuels is undoubtedly responsible of environmental problems such as global warming and sea level rise. Unlike energy plants based on fossil fuels, energy plants based on renewable energy sources may be sustainable and reduce greenhouse gas emissions. However, they are unpredictable because of the intermittent nature of environmental conditions. For this reason, energy storage technologies are needed to meet peak energy demands thanks to the stored energy. Moreover, the renewable energy systems composing the plant must be optimally designed and operated. Therefore, this paper investigates the challenge of the optimal design and energy management of a grid connected renewable energy plant composed of a solar thermal collector, photovoltaic system, ground source heat pump, battery, one short-term thermal energy storage and one seasonal thermal energy storage. To this aim, this paper develops a methodology based on a genetic algorithm that optimally designs a 100% renewable energy plant with the aim of minimizing the electrical energy taken from the grid. The load profiles of thermal, cooling and electrical energy during a whole year are taken into account for the case study of the Campus of the University of Parma (Italy).