Julio Fern'andez-Ceniceros

GA-PARSIMONY

Graphical abstractDisplay Omitted HighlightsGA-PARSIMONY combines feature selection and model parameter optimization.Selection of best parsimonious models according to cost and complexity separately.Lower number of features selected in 65% of 20 UCI and Statlib databases tested.GA-PARSIMONY proved useful in SVR control models for a hot dip galvanizing line. This article proposes a new genetic algorithm (GA) methodology to obtain parsimonious support vector regression (SVR) models capable of predicting highly precise setpoints in a continuous annealing furnace (GA-PARSIMONY). The proposal combines feature selection, model tuning, and parsimonious model selection in order to achieve robust SVR models. To this end, a novel GA selection procedure is introduced based on separate cost and complexity evaluations. The best individuals are initially sorted by an error fitness function, and afterwards, models with similar costs are rearranged according to model complexity measurement so as to foster models of lesser complexity. Therefore, the user-supplied penalty parameter, utilized to balance cost and complexity in other fitness functions, is rendered unnecessary. GA-PARSIMONY performed similarly to classical GA on twenty benchmark datasets from public repositories, but used a lower number of features in a striking 65% of models. Moreover, the performance of our proposal also proved useful in a real industrial process for predicting three temperature setpoints for a continuous annealing furnace. The results demonstrated that GA-PARSIMONY was able to generate more robust SVR models with less input features, as compared to classical GA.

Methodology based on genetic optimisation to develop overall parsimony models for predicting temperature settings on annealing furnace

Abstract Developing better prediction models is crucial for the steelmaking industry to improve the continuous hot dip galvanising line (HDGL). This paper presents a genetic based methodology whereby a wrapper based scheme is optimised to generate overall parsimony models for predicting temperature set points in a continuous annealing furnace on an HDGL. This optimisation includes a dynamic penalty function to control model complexity and an early stopping criterion during the optimisation phase. The resulting models (multilayer perceptron neural networks) were trained using a database obtained from an HDGL operating in the north of Spain. The number of neurons in the unique hidden layer, the inputs selected and the training parameters were adjusted to achieve the lowest validation and mean testing errors. Finally, a comparative evaluation is reported to highlight our proposal’s range of applicability, developing models with lower prediction errors, higher generalisation capacity and less complexity than a standard method.

Parsimonious Support Vector Machines Modelling for Set Points in Industrial Processes Based on Genetic Algorithm Optimization

An optimization based on genetic algorithms for both feature selection and model tuning is presented to improve the prediction of set points in industrial lines. The objective is the development of an automatic procedure that efficiently generates parsimonious prediction models with higher generalisation capacity. These models can achieve higher accuracy in predictions, maintaining the high quality of products while working with continual changes in the production cycle. The proposed method deals with three strict restrictions: few individuals per population, low number of holds and runs in model validation procedure and a reduced number of maximum generations. To fullfill these restrictions, we propose to include in the optimization the reranking of the individuals by their complexity when no significant difference is found between the values of their fitness functions. The method is applied to develop support vector machines for predicting three temperature set points in the annealing furnace of a continuous hot-dip galvanising line. The results demonstrate the rerank makes more efficiently and easily the process of obtaining parsimonious models without reducing performance.

Overall models based on ensemble methods for predicting continuous annealing furnace temperature settings

Abstract The prediction of the set points for continuous annealing furnaces on hot dip galvanising lines is essential if high product quality is to be maintained and energy consumption and related emissions into the atmosphere are to be reduced. Owing to the global and evolving nature of the galvanising industry, plant engineers are currently demanding better overall prediction models that maintain accuracy while working with continual changes in the production cycle. This paper presents three promising prediction models based on ensemble methods (additive regression, bagging and dagging) and compares them with models based on artificial intelligence to highlight how good ensembles are at creating overall models with lower generalisation errors. The models are trained using coil properties, chemical compositions of the steel and historical data from a galvanising process operating in Spain. The results show that the potential benefits from such ensemble models, once configured properly, include high performance in terms of both prediction and generalisation capacity, as well as reliability in prediction and a significant reduction in the difficulty of setting up the model.

Improving Hotel Room Demand Forecasting with a Hybrid GA-SVR Methodology Based on Skewed Data Transformation, Feature Selection and Parsimony Tuning

This paper presents a hybrid methodology, in which a KDD-scheme is optimized to build accurate parsimonious models. The methodology tries to find the best model by using genetic algorithms to optimize a KDD scheme formed with the following stages: feature selection, transformation of the skewed input and output data, parameter tuning, and parsimonious model selection. In this work, experiments demonstrated that optimization of these steps significantly improved the model generalization capabilities in some UCI databases. Finally, this methodology was applied to create room demand parsimonious models using booking databases from a hotel located in a region of Northern Spain. Results proved that the proposed method was useful to create models with higher generalization capacity and lower complexity to those obtained with classical KDD processes.

Multilayer-Perceptron network ensemble modeling with genetic algorithms for the capacity of bolted lap joint

The assessment of failure force in bolted lap joints is a critical parameter in the design of steel structures. This kind of bolted joint shows a highly nonlinear behaviour so traditional analytical models are not very reliable. By contrast, other classical technique like finite element analysis provides a powerful tool to solve nonlinearities but usually with a high computational cost. In this article, we propose a data-driven approach based on multilayer-perceptron network ensemble model for failure force prediction, using a data set generated via finite element simulations of different bolted lap joints. Numeric ensemble methods combine multiple predictors to obtain a single output through average. Moreover, a procedure based on genetic algorithms is used to optimize the ensemble parameters. Results show greater generalization capacity than single prediction model. The resulting ensemble includes the advantages of finite element method whereas reduces the complexity and requires less computation.

Hotel Reservation Forecasting Using Flexible Soft Computing Techniques: A Case of Study in a Spanish Hotel

Room demand estimation models are crucial in the performance of hotel revenue management systems. The advent of websites for online room booking has produced a decrease in the accuracy of prediction models due to the complex customers’ patterns. A reduction that has been particularly dramatic due to last-minute reservations. We propose the use of parsimonious models for improving room demand forecasting. The creation of the models is carried out by using a flexible methodology based on genetic algorithms whereby a wrapper-based scheme is optimized. The methodology includes not only an automated model parameter optimization but also the selection of most relevant inputs and the transformation of the skewed room demand distribution. The effectiveness of our proposal was evaluated using the historical room booking data from a hotel located at La Rioja region in northern Spain. The dataset also included sociological and meteorological information, and the list of local and regional festivities. Nine types of regression models were tuned using the optimization scheme proposed and grid search as the reference method. Models were compared showing that our proposal generated more parsimonious models, which in turn led to higher overall accuracy and better generalization performance. Finally, the applicability of the methodology was demonstrated through the creation of a six-month calendar with the estimated room demand.

The Application of Metamodels Based on Soft Computing to Reproduce the Behaviour of Bolted Lap Joints in Steel Structures

A promising field of research in steel structures regarding their preliminary design and optimization is the replacement of expensive computational finite element models with more efficient techniques. Without a significant loss of accuracy, new proposals should be able to consider not only the ideal load-displacement response but also relevant failure mechanisms and imprecisions in material properties. The article proposes the use of metamodels based on soft computing as an overall approximation system for structures analysis. This approach has been applied in several fields but, till nowadays, its implementation on structural analysis in early esign seems quite limited to a few theoretical cases. Taking advantage of artificial neural network as global approximation technique, the parameters for more realistic and informative load-displacement curve including nonlinear effects (damage mechanics) are estimated for bolted steel lap joints. Our results demonstrate the accuracy of the metamodel implemented can be close to simulations and also real experimental tests.

Stacking ensemble with parsimonious base models to improve generalization capability in the characterization of steel bolted components

Abstract This study presents a new soft computing method to create an accurate and reliable model capable of determining three key points of the comprehensive force–displacement curve of bolted components in steel structures. To this end, a database with the results of a set of finite element (FE) simulations, which represent real responses of bolted components, is utilized to create a stacking ensemble model that combines the predictions of different parsimonious base models. The innovative proposal of this study is using GA-PARSIMONY, a previously published GA-method which searches parsimonious models by optimizing feature selection and hyperparameter optimization processes. Therefore, parsimonious solutions created with a variety of machine learning methods are combined by means of a nested cross-validation scheme in a unique meta-learner in order to increase diversity and minimize the generalization error rate. The results reveal that efficiently combining parsimonious models provides more accurate and reliable predictions as compared to other methods. Thus, the informational model is able to replace costly FE simulations without significantly comprising accuracy and could be implemented in structural analysis software.

Innovative Modular Building Manufactured Using Structural Black Poplar Plywood Panels

This article presents a small prefabricated building with constructive systems not usually utilized in Spain, together with the structural checking needed before its construction. The principal material is the black poplar plywood panel. These wood-derived panels may enhance building sustainability and lighten their weight, showing new business opportunities because of the possibility of mass production. This also allows companies to respond to large orders in shorter periods of time, such as critical situations after some recent catastrophes. The construction has to table with the worst environmental conditions in Spain, which are defined by the Spanish Building Technical Code (CTE). For that reason, the national standard mentioned and other recommendations from the American Engineered Wood Association were used in design and structural checking processes. Another important requirement is that the construction has also to be easy to set up by non-qualified workers. Its constructive solution consisted of a bearing wall that supports a roof with two slopes. A wide inner bearing wall supports the weight of the tile roof. Maximum moments and displacements generated were obtained using the Navier and Levy models based on plate’s theory. These calculations allowed us to demonstrate the significant resistance of the construction proposed.