A demand for predictive models for on-line estimation of variables is increasing in industry. As industrial processes are timevarying, on-line learning algorithms should be adaptive to capture process changes. On-line ensemble methods have been shown to provide better generalization performance than single models in changing environments. However, most on-line ensembles do not include and exclude models during on-line operation. As a result, the ensembles have limited adaptation capability. Moreover, a higher performance can be obtained by combining a selected set of most relevant models of the ensemble for the current situation, rather than combining all the models. This paper proposes a new on-line learning ensemble of regressor models using an ordered aggregation (OA) technique which is able to provide on-line predictions of variables in changing environments. OA dynamically selects an optimal size and composition of a subset of models based on the minimization of the ensemble error on the newest sample. The proposed strategy overcomes the problem of defining the optimal ensemble size, and in most cases it obtains better performance than aggregating all the models. Models are added or removed for assuring adaptation of the ensemble in changing environments. Furthermore, this paper proposes and integrates a new on-line Extreme Learning Machine (ELM) neural network model with variable forgetting factor (FF) using the directional FF method which shows superior performance in industrial applications when compared to the well-known On-line Sequential ELM (OS-ELM) algorithm. Experiments are reported to demonstrate the performance and effectiveness of the proposed methods.
a b s t r a c tThis work introduces a new information-theoretic methodology for choosing variables and their time lags in a prediction setting, particularly when neural networks are used in non-linear modeling. The first contribution of this work is the Cross Entropy Function (XEF) proposed to select input variables and their lags in order to compose the input vector of black-box prediction models. The proposed XEF method is more appropriate than the usually applied Cross Correlation Function (XCF) when the relationship among the input and output signals comes from a non-linear dynamic system. The second contribution is a method that minimizes the Joint Conditional Entropy (JCE) between the input and output variables by means of a Genetic Algorithm (GA). The aim is to take into account the dependence among the input variables when selecting the most appropriate set of inputs for a prediction problem. In short, theses methods can be used to assist the selection of input training data that have the necessary information to predict the target data. The proposed methods are applied to a petroleum engineering problem; predicting oil production. Experimental results obtained with a real-world dataset are presented demonstrating the feasibility and effectiveness of the method.
Highlights• A fuzzy logic model for modeling regenerative braking systems is presented.• Model output is the ratio of regenerative braking force to the total braking force.• Model can be adapted to be used in traffic simulators like the SUMO simulator.• Real data was gathered from short and long-distance field tests with a Nissan LEAF.• Results were compared with real-world data obtained with a Nissan LEAF in road tests.
AbstractR2Q3 This paper presents a fuzzy logic model of regenerative braking (FLmRB) for modeling EVs' regenerative braking systems (RBS). The model has the vehicle's acceleration and jerk, and the road inclination as input variables, and the output of the FLmRB is the regeneration factor, i.e. the ratio of regenerative braking force to total braking force. The regeneration factor expresses the percentage of energy recovered to the battery from braking. The purpose of the FLmRB development is to create realistic EV models using as least as possible manufacturers intellectual property data, and avoiding the use of EV on-board sensors. To tune the model, real data was gathered from short and long-distance field tests with a Nissan LEAF and compared with two types of simulations, one using the proposed FLmRB, and the other considering that all the braking force/energy is converted to electric current and returned back to charge the battery (100% regeneration). The results show that the FLmRB can successfully infer the regenerative braking factor from the measured EV acceleration and jerk, and road inclination, without any knowledge about the EV brake control strategy.
This paper proposes two new training algorithms for multilayer perceptrons based on evolutionary computation, regularization, and transduction. Regularization is a commonly used technique for preventing the learning algorithm from overfitting the training data. In this context, this work introduces and analyzes a novel regularization scheme for neural networks (NN) named eigenvalue decay, which aims at improving the classification margin. The introduction of eigenvalue decay led to the development of a new training method based on the same principles of SVM, and so named Support Vector NN (SVNN). Finally, by analogy with the transductive SVM (TSVM), it is proposed a transductive NN (TNN), by exploiting SVNN in order to address transductive learning. The effectiveness of the proposed algorithms is evaluated on seven benchmark datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.