Modelling hydrogen production from biomass pyrolysis for energy systems using machine learning techniques.

In the context of Industry 4.0, hydrogen gas is becoming more significant to energy feedstocks in the world. The current work researches a novel artificial smart model for characterising hydrogen gas production (HGP) from biomass composition and the pyrolysis process based on an intriguing approach that uses support vector machines (SVMs) in conjunction with the artificial bee colony (ABC) optimiser. The main results are the significance of each physico-chemical parameter on the hydrogen gas production through innovative modelling and the foretelling of the HGP. Additionally, when this novel technique was employed on the observed dataset, a coefficient of determination and correlation coefficient equal to 0.9464 and 0.9751 were reached for the HGP estimate, respectively. The correspondence between observed data and the ABC/SVM-relied approximation showed the suitable effectiveness of this procedure.

Modelling energy performance using a new hybrid DE/MARS-based approach for fossil-fuel thermal power stations.

Despite their environmental impact, fossil-fuel power plants are still commonly used due to their high capacity and relatively low cost compared to renewable energy sources. The aim of this paper is to assess the performance of such energy systems as a key element within a fossil-fuel energy supply network. The methodology relies on fossil-fuel power plant modelling to define an optimal energy management level. However, it can be difficult to model the energy management of thermal power stations (TPS). Therefore, this paper shows an energy efficiency model found on a new hybrid algorithm that is a combination of multivariate adaptive regression splines (MARS) and differential evolution (DE) to estimate net annual electricity generation (NAEG) and carbon dioxide (CO2) emissions (CDE) from economic and performance variables in thermal power plants. This technique requires the DE optimisation of the MARS hyperparameters during the development of the training process. In addition to successfully forecast net annual electricity generation (NAEG) and carbon dioxide (CO2) emissions (CDE) (coefficients of determination with a value of 0.9803 and 0.9895, respectively), the mathematical model used in this work can determine the importance of each economic and energy parameter to characterize the behaviour of thermal power stations.

Evolution and forecasting of PM10 concentration at the Port of Gijon (Spain).

The name PM10 refers to small particles with a diameter of less than 10 microns. The present research analyses different models capable of predicting PM10 concentration using the previous values of PM10, SO2, NO, NO2, CO and O3 as input variables. The information for model training uses data from January 2010 to December 2017. The models trained were autoregressive integrated moving average (ARIMA), vector autoregressive moving average (VARMA), multilayer perceptron neural networks (MLP), support vector machines as regressor (SVMR) and multivariate adaptive regression splines. Predictions were performed from 1 to 6 months in advance. The performance of the different models was measured in terms of root mean squared errors (RMSE). For forecasting 1 month ahead, the best results were obtained with the help of a SVMR model of six variables that gave a RMSE of 4.2649, but MLP results were very close, with a RMSE value of 4.3402. In the case of forecasts 6 months in advance, the best results correspond to an MLP model of six variables with a RMSE of 6.0873 followed by a SVMR also with six variables that gave an RMSE result of 6.1010. For forecasts both 1 and 6 months ahead, ARIMA outperformed VARMA models.

Detection of outliers in pollutant emissions from the Soto de Ribera coal-fired power plant using functional data analysis: a case study in northern Spain.

For more than a century, air pollution has been one of the most important environmental problems in cities. Pollution is a threat to human health and is responsible for many deaths every year all over the world. This paper deals with the topic of functional outlier detection. Functional analysis is a novel mathematical tool employed for the recognition of outliers. This methodology is applied here to the emissions of a coal-fired power plant. This research uses two different methods, called functional high-density region (HDR) boxplot and functional bagplot. Please note that functional bagplots were developed using bivariate bagplots as a starting point. Indeed, they are applied to the first two robust principal component scores. Both methodologies were applied for the detection of outliers in the time pollutant emission curves that were built using, as inputs, the discrete information available from an air quality monitoring data record station and the subsequent smoothing of this dataset for each pollutant. In this research, both new methodologies are tested to detect outliers in pollutant emissions performed over a long period of time in an urban area. These pollutant emissions have been treated in order to use them as vectors whose components are pollutant concentration values for each observation made. Note that although the recording of pollutant emissions is made in a discrete way, these methodologies use pollutants as curves, identifying the outliers by a comparison of curves rather than vectors. Then, the concept of outlier goes from being a point to a curve that employs the functional depth as the indicator of curve distance. In this study, it is applied to the detection of outliers in pollutant emissions from a coal-fired power plant located on the outskirts of the city of Oviedo, located in the north of Spain and capital of the Principality of Asturias. Also, strengths of the functional methods are explained.

Cyanotoxin level prediction in a reservoir using gradient boosted regression trees: a case study.

Cyanotoxins are a type of cyanobacteria that is poisonous and poses a health threat in waters that could be used for drinking or recreational purposes. Thus, it is necessary to predict their presence to avoid risks. This paper presents a nonparametric machine learning approach using a gradient boosted regression tree model (GBRT) for prediction of cyanotoxin contents from cyanobacterial concentrations determined experimentally in a reservoir located in the north of Spain. GBRT models seek and obtain good predictions in highly nonlinear problems, like the one treated here, where the studied variable presents low concentrations of cyanotoxins mixed with high concentration peaks. Two types of results have been obtained: firstly, the model allows the ranking or the dependent variables according to its importance in the model. Finally, the high performance and the simplicity of the model make the gradient boosted tree method attractive compared to conventional forecasting techniques.

Hard-Rock Stability Analysis for Span Design in Entry-Type Excavations with Learning Classifiers.

The mining industry relies heavily on empirical analysis for design and prediction. An empirical design method, called the critical span graph, was developed specifically for rock stability analysis in entry-type excavations, based on an extensive case-history database of cut and fill mining in Canada. This empirical span design chart plots the critical span against rock mass rating for the observed case histories and has been accepted by many mining operations for the initial span design of cut and fill stopes. Different types of analysis have been used to classify the observed cases into stable, potentially unstable and unstable groups. The main purpose of this paper is to present a new method for defining rock stability areas of the critical span graph, which applies machine learning classifiers (support vector machine and extreme learning machine). The results show a reasonable correlation with previous guidelines. These machine learning methods are good tools for developing empirical methods, since they make no assumptions about the regression function. With this software, it is easy to add new field observations to a previous database, improving prediction output with the addition of data that consider the local conditions for each mine.

Hybrid ABC Optimized MARS-Based Modeling of the Milling Tool Wear from Milling Run Experimental Data.

Milling cutters are important cutting tools used in milling machines to perform milling operations, which are prone to wear and subsequent failure. In this paper, a practical new hybrid model to predict the milling tool wear in a regular cut, as well as entry cut and exit cut, of a milling tool is proposed. The model was based on the optimization tool termed artificial bee colony (ABC) in combination with multivariate adaptive regression splines (MARS) technique. This optimization mechanism involved the parameter setting in the MARS training procedure, which significantly influences the regression accuracy. Therefore, an ABC-MARS-based model was successfully used here to predict the milling tool flank wear (output variable) as a function of the following input variables: the time duration of experiment, depth of cut, feed, type of material, etc. Regression with optimal hyperparameters was performed and a determination coefficient of 0.94 was obtained. The ABC-MARS-based model's goodness of fit to experimental data confirmed the good performance of this model. This new model also allowed us to ascertain the most influential parameters on the milling tool flank wear with a view to proposing milling machine's improvements. Finally, conclusions of this study are exposed.

A hybrid PCA-CART-MARS-based prognostic approach of the remaining useful life for aircraft engines.

Prognostics is an engineering discipline that predicts the future health of a system. In this research work, a data-driven approach for prognostics is proposed. Indeed, the present paper describes a data-driven hybrid model for the successful prediction of the remaining useful life of aircraft engines. The approach combines the multivariate adaptive regression splines (MARS) technique with the principal component analysis (PCA), dendrograms and classification and regression trees (CARTs). Elements extracted from sensor signals are used to train this hybrid model, representing different levels of health for aircraft engines. In this way, this hybrid algorithm is used to predict the trends of these elements. Based on this fitting, one can determine the future health state of a system and estimate its remaining useful life (RUL) with accuracy. To evaluate the proposed approach, a test was carried out using aircraft engine signals collected from physical sensors (temperature, pressure, speed, fuel flow, etc.). Simulation results show that the PCA-CART-MARS-based approach can forecast faults long before they occur and can predict the RUL. The proposed hybrid model presents as its main advantage the fact that it does not require information about the previous operation states of the input variables of the engine. The performance of this model was compared with those obtained by other benchmark models (multivariate linear regression and artificial neural networks) also applied in recent years for the modeling of remaining useful life. Therefore, the PCA-CART-MARS-based approach is very promising in the field of prognostics of the RUL for aircraft engines.

Study of a Steel's Energy Absorption System for Heavy Quadricycles and Nonlinear Explicit Dynamic Analysis of its Behavior under Impact by FEM.

Current knowledge of the behavior of heavy quadricycles under impact is still very poor. One of the most significant causes is the lack of energy absorption in the vehicle frame or its steel chassis structure. For this reason, special steels (with yield stresses equal to or greater than 350 MPa) are commonly used in the automotive industry due to their great strain hardening properties along the plastic zone, which allows good energy absorption under impact. This paper presents a proposal for a steel quadricycle energy absorption system which meets the percentages of energy absorption for conventional vehicles systems. This proposal is validated by explicit dynamics simulation, which will define the whole problem mathematically and verify behavior under impact at speeds of 40 km/h and 56 km/h using the finite element method (FEM). One of the main consequences of this study is that this FEM-based methodology can tackle high nonlinear problems like this one with success, avoiding the need to carry out experimental tests, with consequent economical savings since experimental tests are very expensive. Finally, the conclusions from this innovative research work are given.