Search

Improving the reliability and performance of electric and rotating machines is crucial to many industrial applications. This will lead to improved robustness, efficiency, and eco-sustainability, as well as mitigate significant health and safety concerns regarding sudden catastrophic failure modes. Bearing degradation is the most significant cause of machine failure and has been reported to cause up to 75% of low-voltage machine failures. This paper introduces a low complexity machine learning (ML) approach to estimate the remaining useful life (RUL) of rolling element bearings using real vibration signals. This work explores different ML recipes using novel feature engineering coupled with various k-Nearest Neighbour (k-NN), and Support Vector Machines (SVM) kernel and weighting functions in order to optimise this RUL approach. Original non-linear wear state models and feature sets are investigated, the latter are derived from Short-time Fourier Transform (STFT) and Hilbert Marginal Spectrum (HMS). These feature sets incorporate one-third octave band filtering for low complexity multivariate feature subspace compression. Our proposed ML algorithm stage has employed two robust supervised ML approaches: weighted k-NN and SVM. Real vibration data were drawn from the Pronostia platform to test and validate this prognostic monitoring approach. The results clearly demonstrate the effectiveness of this approach, with classification accuracy results of up to 82.8% achieved. This work contributes to the field by introducing a robust and computationally inexpensive method for accurate monitoring of machine health using low-cost vibration-based sensing. [ABSTRACT FROM AUTHOR]

Environmental performance of ships is a critical factor in the shipping industry due to evolving climate change and the respective regulations imposed by authorities all over the world. As shipping moves towards digitization, a large amount of ships' environmental performance-related data, collected during ships' voyages, provide opportunities to develop and enhance data-driven performance models by using different machine learning algorithms. This paper introduces new indices of ships' environmental performance using machine learning techniques. The new indices are produced by combining clustering algorithms as well as principal component analysis. Based on the analysis of the data (14 variables with operational and design characteristics), the ships are divided into four clusters based on the new suggested indices. These clusters categorize the ships according to their physical dimensions, operating region, and operational environmental efficiency, offering insight into the distinctive traits of each cluster. [ABSTRACT FROM AUTHOR]

The study compares the prediction performance of alternative machine learning algorithms and time series econometric models for daily Turkish electricity prices and defines the determinants of electricity prices by considering seven global, national, and electricity-related variables as well as the COVID-19 pandemic. Daily data that consist of the pre-pandemic (15 February 2019–10 March 2020) and the pandemic (11 March 2020–31 March 2021) periods are included. Moreover, various time series econometric models and machine learning algorithms are applied. The findings reveal that (i) machine learning algorithms present higher prediction performance than time series models for both periods, (ii) renewable sources are the most influential factor for the electricity prices, and (iii) the COVID-19 pandemic caused a change in the importance order of influential factors on the electricity prices. Thus, the empirical results highlight the consideration of machine learning algorithms in electricity price prediction. Based on the empirical results obtained, potential policy implications are also discussed. [ABSTRACT FROM AUTHOR]

Electrical utilities performance is measured by various indicators, of which the most important are very dependent on the interruption time after a failure in the network has occurred, such as SAIDI. Therefore, they are constantly looking for new techniques to decrease the fault location and repair times. A possibility to innovate in this field is to estimate the failed network component when a fault occurs. This paper presents the conclusion of an analysis carried out by the authors with the aim to estimate failure types of underground MV networks based on observable indirect variables. The variables needed to carry out the analysis must be available shortly after the failure occurrence, which is facilitated by a smart-grid infrastructure, to allow for a quick estimation. This paper uses the groundwork already carried out by the authors on ambient variables, historical variables, and disturbance recordings to design an estimator to predict between four MV cable network failure types. The paper presents relevant analyses on the design and performance of various machine learning classification algorithms for estimation of the types of MV cable network failures using real-world data. Optimization of performance was carried out, resulting in an estimator with an overall 68% accuracy rate. Accuracy rates of 94% for cable failure, 63% for excavations, and 79% secondary busbar failures were achieved; as for cable joints, the accuracy was poor due to the difficulty to identify a feature that can be used to separate this failure type from cable failures. Future work to improve that accuracy is discussed. [ABSTRACT FROM AUTHOR]

This paper details the selection of machine learning models for predicting the effectiveness of a heat pipe system in a concentric tube exchanger. Heat exchanger experiments with methanol as the working fluid were conducted. The value of the angle varied from 0° to 90°, values of temperature varied from 50 °C to 70 °C, and the flow rate varied from 40 to 120 litres per min. Multiple experiments were conducted at different combinations of the input parameters and the effectiveness was measured for each trial. Multiple machine learning algorithms were taken into consideration for prediction. Experimental data were divided into subsets and the performance of the machine learning model was analysed for each of the subsets. For the overall analysis, which included all the three parameters, the random forest algorithm returned the best results with a mean average error of 1.176 and root-mean-square-error of 1.542. [ABSTRACT FROM AUTHOR]

Accurate prediction of building energy need plays a fundamental role in building design, despite the high computational cost to search for optimal energy saving solutions. An important advancement in the reduction of computational time could come from the application of machine learning models to circumvent energy simulations. With the goal of drastically limiting the number of simulations, in this paper we investigate the regression performance of different machine learning models, i.e., Support Vector Machine, Random Forest, and Extreme Gradient Boosting, trained on a small data-set of energy simulations performed on a case study building. Among the XX algorithms, the tree-based Extreme Gradient Boosting showed the best performance. Overall, we find that machine learning methods offer efficient and interpretable solutions, that could help academics and professionals in shaping better design strategies, informed by feature importance. [ABSTRACT FROM AUTHOR]

Condition monitoring, diagnostics, and prognostics are key factors in today's competitive industrial sector. Equipment digitalisation has increased the amount of available data throughout the industrial process, and the development of new and more advanced techniques has significantly improved the performance of industrial machines. This publication focuses on surveying the last decade of evolution of condition monitoring, diagnostic, and prognostic techniques using machine-learning (ML)-based models for the improvement of the operational performance of gas turbines. A comprehensive review of the literature led to a performance assessment of ML models and their applications to gas turbines, as well as a discussion of the major challenges and opportunities for the research on these kind of engines. This paper further concludes that the combination of the available information captured through the collectors and the ML techniques shows promising results in increasing the accuracy, robustness, precision, and generalisation of industrial gas turbine equipment. [ABSTRACT FROM AUTHOR]

A main challenge for integrating the intermittent photovoltaic (PV) power generation remains the accuracy of day-ahead forecasts and the establishment of robust performing methods. The purpose of this work is to address these technological challenges by evaluating the day-ahead PV production forecasting performance of different machine learning models under different supervised learning regimes and minimal input features. Specifically, the day-ahead forecasting capability of Bayesian neural network (BNN), support vector regression (SVR), and regression tree (RT) models was investigated by employing the same dataset for training and performance verification, thus enabling a valid comparison. The training regime analysis demonstrated that the performance of the investigated models was strongly dependent on the timeframe of the train set, training data sequence, and application of irradiance condition filters. Furthermore, accurate results were obtained utilizing only the measured power output and other calculated parameters for training. Consequently, useful information is provided for establishing a robust day-ahead forecasting methodology that utilizes calculated input parameters and an optimal supervised learning approach. Finally, the obtained results demonstrated that the optimally constructed BNN outperformed all other machine learning models achieving forecasting accuracies lower than 5%. [ABSTRACT FROM AUTHOR]

Driven by climatic processes, wind power generation is inherently variable. Long-term simulated wind power time series are therefore an essential component for understanding the temporal availability of wind power and its integration into future renewable energy systems. In the recent past, mainly power curve-based models such as Renewables.ninja (RN) have been used for deriving synthetic time series for wind power generation, despite their need for accurate location information and bias correction, as well as their insufficient replication of extreme events and short-term power ramps. In this paper, we assessed how time series generated by machine learning models (MLMs) compare to RN in terms of their ability to replicate the characteristics of observed nationally aggregated wind power generation for Germany. Hence, we applied neural networks to one wind speed input dataset derived from MERRA2 reanalysis with no location information and two with additional location information. The resulting time series and RN time series were compared with actual generation. All MLM time series feature an equal or even better time series quality than RN, depending on the characteristics considered. We conclude that MLM models show a similar performance to RN, even when information on turbine locations and turbine types is unavailable. [ABSTRACT FROM AUTHOR]