With the improvement in wind turbine (WT) operation and maintenance (O&M) technologies and the rise of O&M cost, fault diagnostics in WTs based on a supervisory control and data acquisition (SCADA) system has become among the cheapest and easiest methods to detect faults in WTs.Hence, it is necessary to monitor the change in real-time parameters from the WT and maintenance action could be taken in advance before any major failures. Therefore, SCADA-driven fault diagnosis in WT based on machine learning algorithms has been proposed in this study by comparing the performance of three different machine learning algorithms, namely k-nearest neighbors (kNN) with a bagging regressor, extreme gradient boosting (XGBoost) and an artificial neural network (ANN) on condition monitoring of gearbox oil sump temperature. Further, this study also compared the performance of two different feature selection methods, namely the Pearson correlation coefficient (PCC) and principal component analysis (PCA), and three hyperparameter optimization methods on optimizing the performance of the models, namely a grid search, a random search and Bayesian optimization. A total of 3 years of SCADA data on WTs located in France have been used to verify the selected method. The results showed the kNN with a bagging regressor, with PCA and a grid search, provides the best R2 score, and the lowest root mean square error (RMSE). The trained model can detect the potential of WT faults at least 4 weeks in advance. However, the proposed kNN model in this study can be trained with the Support Vector Machine hybrid algorithm to improve its performance and reduce fault alarm.
Gas turbine (GT) modeling and optimization have been widely studied at the design level but still lacks focus on real-world operational cases. The concept of a digital twin (DT) allows for the interaction between operation data and the system dynamic performance. Among many DT studies, only a few focus on GT for thermal power plants. This study proposes a digital twin prototype framework including the following modules: process modeling, parameter estimation, and performance optimization. Provided with real-world power plant operational data, key performance parameters such as turbine inlet temperature (TIT) and specific fuel consumption (SFC) were initially unavailable, therefore necessitating further calculation using thermodynamic analysis. These parameters are then used as a target label for developing artificial neural networks (ANNs). Three ANN models with different structures are developed to predict TIT, SFC, and turbine power output (GTPO), achieving high R2 scores of 94.03%, 82.27%, and 97.59%, respectively. Physics-informed neural networks (PINNs) are then employed to estimate the values of the air–fuel ratio and combustion efficiency for each time index. The PINN-based estimation resulted in estimated values that align with the literature. Subsequently, an unconventional method of detecting alarms by using conformal prediction were also proposed, resulting in a significantly reduced number of alarms. The developed ANNs are then combined with particle swarm optimization (PSO) to carry out performance optimization in real time. GTPO and SFC are selected as the primary metrics for the optimization, with controllable parameters such as AFR and a fine-tuned inlet guide vane position. The results demonstrated that GTPO could be optimized with the application of conformal prediction when the true GTPO is detected to be higher than the upper range of GTPO obtained from the ANN model with a conformal prediction of a 95% confidence level. Multiple PSO variants were also compared and benchmarked to ensure an enhanced performance. The proposed PSO in this study has a lower mean loss compared to GEP. Furthermore, PSO has a lower computational cost compared to RS for hyperparameter tuning, as shown in this study. Ultimately, the proposed methods aim to enhance GT operations via a data-driven digital twin concept combination of deep learning and optimization algorithms.
Hydrogen offers a promising solution to reduce emissions in the energy sector with the growing need for decarbonisation. Despite its environmental benefits, the use of hydrogen presents significant challenges in storage and transport. Many studies have focused on the different types of hydrogen production and analysed the pros and cons of each technique for different applications. This study focuses on techno-economic analysis of onsite hydrogen production through ammonia decomposition by utilising the heat from exhaust gas generated by hydrogen-fuelled gas turbines. Aspen Plus simulation software and its economic evaluation system are used. The Siemens Energy SGT-400 gas turbine’s parameters are used as the baseline for the hydrogen gas turbine in this study, together with the economic parameters of the capital expenditure (CAPEX) and operating expenditure (OPEX) are considered. The levelised cost of hydrogen (LCOH) is found to be 5.64 USD/kg of hydrogen, which is 10.6% lower than that of the conventional method, where a furnace is used to increase the temperature of ammonia. A major contribution of the LCOH comes from the ammonia feed cost up to 99%. The price of ammonia is found to be the most sensitive parameter of the contribution to LCOH. The findings of this study show that the use of ammonia decomposition via heat recovery for onsite hydrogen production with ammonic recycling is economically viable and highlight the critical need to further reduce the prices of green ammonia and blue ammonia in the future.
This paper proposes a solution to address the challenges of high storage and transport costs associated with using hydrogen () as an energy source. It suggests utilizing ammonia () as a hydrogen carrier to produce onsite for hydrogen gas turbines. offers higher volumetric hydrogen density compared to liquid , potentially reducing shipping costs by 40%. The process involves pyrolysis, which utilizes the heat waste from exhaust gas generated by gas turbines to produce and nitrogen (). Numerical simulations were conducted to design and understand the behaviour of the heat recapture decomposition system. The design considerations included the concept of the number of transfer units and heat exchanger efficiency, achieving a heat recapture system efficiency of up to 91%. The simulation of decomposition was performed using ANSYS, a commercial simulation software, considering wall surface reactions, turbulent flow, and chemical reaction. Parameters such as activation energy and pre-exponential factor were provided by a study utilizing a nickel wire for decomposition experiments. The conversion of reached up to 94% via a nickel-based catalyst within a temperature range of 823 K to 923 K which is the exhaust gas temperature range. Various factors were considered to compare the efficiency of the system, including the mass flow of , operating gauge pressure, mass flow of exhaust gas, among others. Result showed that pressure would not affect the conversion of at temperatures above 800 K, thus a lower amount of energy is required for a compression purpose in this approach. The conversion is maintained at 94% to 97% when lower activation energy is applied via a ruthenium-based catalyst. Overall, this study showed the feasibility of utilizing convective heat transfer from exhaust gas in hydrogen production by pyrolysis, and this will further enhance the development of as the potential carrier for onsite production in hydrogen power generation.