A neural network-based preset generation tool for a steel tandem cold mill

This paper traces the development of a software tool, based oil a combination of artificial neural networks (ANN) and a few process equations. aiming to serve as a backup operation instrument in the reference generation for real-time controllers of a steel tandem cold mill By emulating the mathematical model responsible for generating presets under normal operational conditions, the system works as ail option to maintain plant operation in the event of a failure in the processing unit that executes the mathematical model. The system, built from the production data collected over six years of plant operation, steered to the replacement of the former backup operation mode (based oil a lookup table). which degraded both product quality and plant productivity. The study showed that ANN are appropriated tools for the intended purpose and that by this instrument it is possible to achieve nearly the totality of the presets needed by this land of process. The text characterizes the problem, relates the investigated options to solve it. justifies the choice of the ANN approach, describes the methodology and system implementation and, finally, shows and discusses the attained results. (C) 2009 Elsevier Ltd. All rights reserved

Particle Competition and Cooperation in Networks for Semi-Supervised Learning with Concept Drift

Concept drift is a problem of increasing importance in machine learning and data mining. Data sets under analysis are no longer only static databases, but also data streams in which concepts and data distributions may not be stable over time. However, most learning algorithms produced so far are based on the assumption that data comes from a fixed distribution, so they are not suitable to handle concept drifts. Moreover, some concept drifts applications requires fast response, which means an algorithm must always be (re) trained with the latest available data. But the process of labeling data is usually expensive and/or time consuming when compared to unlabeled data acquisition, thus only a small fraction of the incoming data may be effectively labeled. Semi-supervised learning methods may help in this scenario, as they use both labeled and unlabeled data in the training process. However, most of them are also based on the assumption that the data is static. Therefore, semi-supervised learning with concept drifts is still an open challenge in machine learning. Recently, a particle competition and cooperation approach was used to realize graph-based semi-supervised learning from static data. In this paper, we extend that approach to handle data streams and concept drift. The result is a passive algorithm using a single classifier, which naturally adapts to concept changes, without any explicit drift detection mechanism. Its built-in mechanisms provide a natural way of learning from new data, gradually forgetting older knowledge as older labeled data items became less influent on the classification of newer data items. Some computer simulation are presented, showing the effectiveness of the proposed method.

Optimization of Radial Basis Function neural network employed for prediction of surface roughness in hard turning process using Taguchi's orthogonal arrays

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Oriented texture classification based on self-organizing neural network and Hough transform

This paper presents a technique for oriented texture classification which is based on the Hough transform and Kohonen's neural network model. In this technique, oriented texture features are extracted from the Hough space by means of two distinct strategies. While the first operates on a non-uniformly sampled Hough space, the second concentrates on the peaks produced in the Hough space. The described technique gives good results for the classification of oriented textures, a common phenomenon in nature underlying an important class of images. Experimental results are presented to demonstrate the performance of the new technique in comparison, with an implemented technique based on Gabor filters.

Rede neural não supervisionada baseada em transformada Karhunen-Loève para processamento, compressão e reconhecimento de imagens

The merit of the Karhunen-Loève transform is well known. Since its basis is the eigenvector set of the covariance matrix, a statistical, not functional, representation of the variance in pattern ensembles is generated. By using the Karhunen-Loève transform coefficients as a natural feature representation of a character image, the eigenvector set can be regarded as an feature extractor for a classifier.

Automation in fault detection using neural network and model updating

In this article, an implementation of structural health monitoring process automation based on vibration measurements is proposed. The work presents an alternative approach which intent is to exploit the capability of model updating techniques associated to neural networks to be used in a process of automation of fault detection. The updating procedure supplies a reliable model which permits to simulate any damage condition in order to establish direct correlation between faults and deviation in the response of the model. The ability of the neural networks to recognize, at known signature, changes in the actual data of a model in real time are explored to investigate changes of the actual operation conditions of the system. The learning of the network is performed using a compressed spectrum signal created for each specific type of fault. Different fault conditions for a frame structure are evaluated using simulated data as well as measured experimental data.

Neural network detection of grinding burn from acoustic emission

An artificial neural network (ANN) approach is proposed for the detection of workpiece `burn', the undesirable change in metallurgical properties of the material produced by overly aggressive or otherwise inappropriate grinding. The grinding acoustic emission (AE) signals for 52100 bearing steel were collected and digested to extract feature vectors that appear to be suitable for ANN processing. Two feature vectors are represented: one concerning band power, kurtosis and skew; and the other autoregressive (AR) coefficients. The result (burn or no-burn) of the signals was identified on the basis of hardness and profile tests after grinding. The trained neural network works remarkably well for burn detection. Other signal-processing approaches are also discussed, and among them the constant false-alarm rate (CFAR) power law and the mean-value deviance (MVD) prove useful.

Projeto E análise de uma rede neural para resolver problemas de programação dinâmica

Systems based on artificial neural networks have high computational rates due to the use of a massive number of simple processing elements and the high degree of connectivity between these elements. Neural networks with feedback connections provide a computing model capable of solving a large class of optimization problems. This paper presents a novel approach for solving dynamic programming problems using artificial neural networks. More specifically, a modified Hopfield network is developed and its internal parameters are computed using the valid-subspace technique. These parameters guarantee the convergence of the network to the equilibrium points which represent solutions (not necessarily optimal) for the dynamic programming problem. Simulated examples are presented and compared with other neural networks. The results demonstrate that proposed method gives a significant improvement.

Optimization of neural classifiers based on bayesian decision boundaries and idle neurons pruning

In this article we describe a feature extraction algorithm for pattern classification based on Bayesian Decision Boundaries and Pruning techniques. The proposed method is capable of optimizing MLP neural classifiers by retaining those neurons in the hidden layer that realy contribute to correct classification. Also in this article we proposed a method which defines a plausible number of neurons in the hidden layer based on the stem-and-leaf graphics of training samples. Experimental investigation reveals the efficiency of the proposed method. © 2002 IEEE.

Effects of simvastatin on bone regeneration in the mandibles of ovariectomized rats and on blood cholesterol levels.

The purpose of this study was to evaluate the effects of simvastatin on guided bone regeneration in the mandibles of ovariectomized rats, and to observe their blood cholesterol levels. Seventy female rats were divided into two groups: control and treated, both groups containing normal and ovariectomized rats. A month after ovariectomy a bone defect was created in the mandible, and was covered by a polytetrafluoroethylene membrane. The treated groups received simvastatin orally for 15 or 30 days. The rats were sacrificed 15, 30 or 60 days after surgery, at which time a blood sample was extracted for blood cholesterol level analysis and the mandible was extracted for densitometric, histological and morphometric analysis. All specimens underwent analysis of variance. The ovariectomized animals had higher cholesterol levels than the treated normal animals, and no significant difference was found between the different treatment periods and the sacrifice times. The densitometric, histological and morphometric analysis showed that the treated ovariectomized animals developed more new bone than the control ovariectomized rats, but no significant difference was observed between the treatment periods. It can be concluded that the deficiency of estrogen increased the level of blood cholesterol and that the simvastatin aided new bone formation in the ovariectomized animals.

Transient stability analysis of electrical power systems using a neural network based on fuzzy ARTMAP

This work presents a methodology to analyze transient stability for electric energy systems using artificial neural networks based on fuzzy ARTMAP architecture. This architecture seeks exploring similarity with computational concepts on fuzzy set theory and ART (Adaptive Resonance Theory) neural network. The ART architectures show plasticity and stability characteristics, which are essential qualities to provide the training and to execute the analysis. Therefore, it is used a very fast training, when compared to the conventional backpropagation algorithm formulation. Consequently, the analysis becomes more competitive, compared to the principal methods found in the specialized literature. Results considering a system composed of 45 buses, 72 transmission lines and 10 synchronous machines are presented. © 2003 IEEE.

Influence of age on combined effects of cyclosporin and nifedipine on rat alveolar bone

Background: There is some evidence showing that cyclosporin A (CsA) and nifedipine (NIF) affect bone metabolism. The purpose of this work was to study the effects of CsA and NIF, given alone or concurrently, on alveolar bone of rats of different ages. Methods: Rats 15, 30, 60, and 90 days old were treated daily with 10 mg/kg body weight of CsA subcutaneously injected and/or 50 mg/kg body weight of NIF/day given orally for 60 days. Alveolar bone of the first lower molars was morphologically and stereologically evaluated in serial 5 μm bucco-lingual paraffin sections, stained with hematoxylin and eosin. Serum calcium and alkaline phosphatase levels were measured in all animals at the end of the experimental period. Results: Rats treated with CsA or NIF alone or CsA and NIF concurrently showed decreased alveolar bone density. CsA was more effective than NIF. A significant decrease in serum calcium was found only in animals treated with CsA or CsA/NIF. The results were similar regardless of age. Conclusions: These results indicate that the decrease in the alveolar bone volume in rats caused by CsA and NIF alone or concurrently is not age dependent. Furthermore, NIF (50 mg/kg) did not further increase the loss of alveolar bone volume induced by CsA (10 mg/kg).

Bone mineralization among male adolescents: Critical years for bone mass gain

Objective: To verify the behavior of the mineral bone content and density in male adolescents according to age and secondary sexual characters. Methods: 47 healthy adolescents between 10 and 19 years old were assessed according to weight, height, body mass index, puberty stage, calcium intake, bone mineral density and content in the lumbar spine and in the proximal femur. The bone mass was measured through bone densitometries. The intake of calcium was calculated through a 3-day diet. The BMI (body mass index) was calculated with the Quetelet Index and the puberty stage was defined according to Tanner's criteria. The analysis used descriptive statistics such as average and standard deviation, and variance estimates to compare the different age groups. Moreover, the Tukey test was used to determine the significant differences. Results: It was evident that the calcium intake in the different ages assessed has not reached the minimum value of 800 mg. The bone mineral density and content showed an increase after the age of 14, as well as when the teenagers reached the sexual maturation stage G4. The mineralization parameters showed a high level when the teenagers were in the G3 stage, however, without statistical significance. Conclusion: The results indicate an important level of bone mineralization during adolescence. Maturation levels superior to G3 have shown more mineralization. This study proves that the critical years for bone mass gain start after the 14-15 years old or older. Copyright © 2004 by Sociedade Brasileira de Pediatria.

Recurrent neural network for induction motor speed estimation in industry applications

Many electronic drivers for the induction motor control are based on sensorless technologies. The proposal of this work Is to present an alternative approach of speed estimation, from transient to steady state, using artificial neural networks. The inputs of the network are the RMS voltage, current and speed estimated of the induction motor feedback to the input with a delay of n samples. Simulation results are also presented to validate the proposed approach. © 2006 IEEE.