Fault diagnosis for MSF dynamic states using neural networks

Fault diagnosis for a MSF using neural networks

Fault diagnosis for MSF dynamic states using a SDG and fuzzy logic

We have shown previously that there is uncertainty associated with the output of artificial neural network (ANN) and we have now developed a new method to reduce this uncertainty by training ANNs with multiple target values. In conventional ANN training, binary target values are used to represent, e.g., benign and malignant cases. However, this method does not take into consideration the various histology subtypes. In this work, we used both simulated datasets and a mammography dataset to show that the conventional training method leads to larger uncertainty in the ANN output. Eight ANNs were trained by choosing different initial weights and ANN output variance was measured by the average standard deviation (SD) of the 8 ANNs' outputs for each test case. In the simulation, in addition to the conventional training method using binary target values, we also trained ANNs with multiple target values, and a set of continuous target values derived from a likelihood ratio of the underlying distributions. For the mammogram study, we assigned multiple target values based on histology subtypes. Both the simulation and mammogram studies showed that ANNs produce very close overall performance regardless the training methods. However, training neural networks with multiple target values demonstrated lower uncertainty in the ANN outputs.

This study presents the design of an artificial neural network (ANN) to evaluate and predict the viscosity behavior of Al2O3/10W40 nanofluid at different temperatures, shear rates, and volume fraction of nanoparticles. Nanofluid viscosity ({mu }_{nf}) is evaluated at volume fractions (varphi=0.25% to 2%) and temperature range of 5 to 55 °C. For modeling by ANN, a multilayer perceptron (MLP) network with the Levenberg–Marquardt algorithm (LMA) is used. The main purpose of this study is to model and predict the {mu }_{nf} of Al2O3/10W40 nanofluid through ANN, select the best ANN structure from the set of predicted structures and manage time and cost by predicting the ANN with the least error. To model the ANN, varphi, temperature, and shear rate are considered as input variables, and {mu }_{nf} is considered as output variable. From 400 different ANN structures for Al2O3/10W40 nanofluid, the optimal structure consisting of two hidden layers with the optimal structure of 6 neurons in the first layer and 4 neurons in the second layer is selected. Finally, the R regression coefficient and the MSE are 0.995838 and 4.14469E−08 for the optimal structure, respectively. According to all data, the margin of deviation (MOD) is in the range of less than 2% < MOD < + 2%. Comparison of the three data sets, namely laboratory data, correlation output, and ANN output, shows that the ANN estimates laboratory data more accurately.

In this study we developed an effective novel method for reducing the variability in the output of different artificial neural network (ANN) configurations that have the same overall performance as measured by the area under their receiver operating characteristic (ROC) curves. This variability can lead to inaccuracies in the interpretation of results when the outputs are employed as classification predictors. We extended a method previously proposed to reduce the variability in the performance of a classifier with data sets from different institutions to the outputs of ANN configurations. Our approach is based on histogram shaping of the outputs of all ANN configurations to resemble the output histogram of a baseline ANN configuration. We tested the effectiveness of the technique using synthetic data generated from two two-dimensional isotropic Gaussian distributions and 100 ANN configurations. The proposed output calibration technique significantly reduced the median standard deviation of the ANN outputs from 0.010 before calibration to 0.006 after calibration. The standard deviation of the sensitivity of the 100 ANN configurations at the same decision threshold reduced significantly from 0.005 before calibration to 0.003 after calibration. Similarly the standard deviation of their specificity values decreased significantly from 0.016 before calibration to 0.006 after calibration.

A retrospective analysis of the utility of an artificial neural network to predict ED volume

Position information in indoor environments can be procured using diverse approaches. Due to the ubiquitous presence of WLAN networks, positioning techniques in these environments are the scope of intense research. This paper explores two strategies for space partitioning when utilizing cascade-connected Artificial Neural Networks (ANNs) structures for indoor WLAN positioning. A set of cascade-connected ANN structures with different space partitioning strategies are compared mutually and to the single ANN structure. The benefits of using cascade-connected ANNs structures are shown and discussed in terms of the size of the environment, number of subspaces and partitioning strategy. The optimal cascade-connected ANN structures with space partitioning show up to 50% decrease in median error and up to 12% decrease in the average error with respect to the single ANN model. Finally, the single ANN and the optimal cascade-connected ANN model are compared against other well-known positioning techniques.

PurposeThe purpose of this paper is to present a degenerated simplex search method to optimize neural network error function. By repeatedly reflecting and expanding a simplex, the centroid property of the simplex changes the location of the simplex vertices. The proposed algorithm selects the location of the centroid of a simplex as the possible minimum point of an artificial neural network (ANN) error function. The algorithm continually changes the shape of the simplex to move multiple directions in error function space. Each movement of the simplex in search space generates local minimum. Simulating the simplex geometry, the algorithm generates random vertices to train ANN error function. It is easy to solve problems in lower dimension. The algorithm is reliable and locates minimum function value at the early stage of training. It is appropriate for classification, forecasting and optimization problems.Design/methodology/approachAdding more neurons in ANN structure, the terrain of the error function becomes complex and the Hessian matrix of the error function tends to be positive semi‐definite. As a result, derivative based training method faces convergence difficulty. If the error function contains several local minimum or if the error surface is almost flat, then the algorithm faces convergence difficulty. The proposed algorithm is an alternate method in such case. This paper presents a non‐degenerate simplex training algorithm. It improves convergence by maintaining irregular shape of the simplex geometry during degenerated stage. A randomized simplex geometry is introduced to maintain irregular contour of a degenerated simplex during training.FindingsSimulation results show that the new search is efficient and improves the function convergence. Classification and statistical time series problems in higher dimensions are solved. Experimental results show that the new algorithm (degenerated simplex algorithm, DSA) works better than the random simplex algorithm (RSM) and back propagation training method (BPM). Experimental results confirm algorithm's robust performance.Research limitations/implicationsThe algorithm is expected to face convergence complexity for optimization problems in higher dimensions. Good quality suboptimal solution is available at the early stage of training and the locally optimized function value is not far off the global optimal solution, determined by the algorithm.Practical implicationsTraditional simplex faces convergence difficulty to train ANN error function since during training simplex can't maintain irregular shape to avoid degeneracy. Simplex size becomes extremely small. Hence convergence difficulty is common. Steps are taken to redefine simplex so that the algorithm avoids the local minimum. The proposed ANN training method is derivative free. There is no demand for first order or second order derivative information hence making it simple to train ANN error function.Originality/valueThe algorithm optimizes ANN error function, when the Hessian matrix of error function is ill conditioned. Since no derivative information is necessary, the algorithm is appealing for instances where it is hard to find derivative information. It is robust and is considered a benchmark algorithm for unknown optimization problems.

Negative correlation learning has been proposed to create a set of negatively correlated artificial neural networks (ANNs) in a committee machine. In negative correlation learning, the error signals for each ANN on a given data are not only decided by the error differences between the output of ANN and the targets. Two terms are optimized at the same time. The first one is to minimize the error between the output of each ANN and the target output on the given data. The other one is to maximize the difference between the output of the ensemble and the output of each ANN on the given data. From the point of view on the bias-variance-covariance trade-off, the minimization of the first term would decrease the bias while the maximization of the second term would reduce the sum of bias and variance. In order to balance well among bias, variance and covariance, error signals in learning should be well adjusted. On one hand, when the learning would force itself to be closer to the ensemble, an individual ANN would choose to learn less so that the learning on that direction would be disencouraged. On the other hand, when the learning would help itself to be more different to the ensemble, an individual ANN would let itself to learn more so that the learning on that direction would be encouraged. A new version of negative correlation learning based on such error signal adjustment have been implemented in this paper. Experimental results were carried out to show how the error signal adjustment would help to achieve the better generalization.

In order to solve the overlap link constraint, trapped movement, and computational cost problem in current IK model, this paper proposes a new coupled spiking neural network (CSNN) model which is combined with artificial neural network (ANN). Several references of end of effector's movement will be generated as training model of ANN. Current joint positions and angle values, movement direction and distance will be the input data. Angular velocity of every joint will be the output data. However, ANN structure and number of references will be minimized. As an alternative, CSNN will be implemented, where one joint angle is represented by a coupled neurons interconnected to each others. CSNN has feedback input from the current condition of arm robot, and its output will be combined with ANN's output. CSNN interconnection will be optimized using steady state evolutionary algorithm with several epoch. The proposed model is implemented to simulate multiple link planar robot. The result shows the effectiveness of the proposed model which succeeded in several trajectory tests with minimum computational cost.

The objective of this paper is to present a new approach to the problem of combustion engine efficiency characteristic development in dynamic working states. The artificial neural network (ANN) method was used to build a mathematical model of the engine comprising the following parameters: Engine speed, angular acceleration, engine torque, torque change intensity, and fuel mass flow, measured on a test bed on a spark ignition engine in static and dynamic working states. A detailed analysis of ANN design, data preparation, the training method, and the ANN model accuracy are described. The paper presents conducted calculations that clearly show the suitability of the approach in every aspect. Then, a simplified ANN was created, which allows a two dimensional characteristic in dynamic states, including 4 variables, to be determined.

In this paper we present a new artificial neural network (ANN) structure to compensate for the convergence problem associated with training the identification of a complex nonlinear flexible joint robot for trajectory tracking problem. The tracking control of a MIMO flexible joint robot with high velocity is complicated due to the joint flexibilities, nonlinearities, and couplings. Our scheme consists of three ANN structures. The neural network identification (NNI) is used to obtain a dynamic model of a flexible joint robot to be controlled. Once the NNI has not closely learned the dynamic model of a flexible joint robot, the other new ANN structure, called hidden control neural network identification (HCNNI), is designed to overcoming the identification convergence problem in this paper. This HCNNI allows learning to compensate for poor identification and external disturbance. A third ANN control is designed for tracking control of a flexible joint robot based upon the identification. These tasks are completed using the backpropagation neural network.

The goal for artificial neural networks (ANNs) in two-class classification problems is to predict the class membership accurately. Performance evaluation of ANNs focuses usually on the collective accuracy over a large number of cases in the prediction of the class membership, often measured by receiver operating characteristic (ROC) curve and area under the ROC curve (AUC). We show that with finite number of training cases, the output value of the ANN is a statistical random variable that exhibits uncertainty. We show that this uncertainty in the ANN output can be studied by training multiple ANNs of identical structure on a single set of training cases but with different random initialization, thereby causing the ANNs to arrive at not-necessarily-identical weight values at the conclusion of satisfactory training. We found that this variability in the ANN output is small but not negligible and that it can be important in CAD applications in which the ANN output is to be interpreted by a human observer rather than to be compared with a fixed threshold value in fully automated machine classification.

The authors propose a new training method for artificial neural networks (ANNs) in two-class classification tasks such as classifying breast lesions on a mammogram as malignant or benign. Whereas the conventional binary training method uses binary training target values based on the diagnostic truth of a lesion being malignant or benign, the authors use multiple training target values based on more detailed histological diagnosis that presumably are related to the posterior probability of a lesion being malignant. The authors performed Monte Carlo simulation studies in which training target values were assigned based on posterior probability, and they also performed a mammography study in which training target values were assigned according to histological subtypes. These studies showed that the multitarget training method produced less variability in the ANN outputs than the binary training method. The simulation studies also showed that except for when the number of training cases was extremely large, the multitarget training method produced improved overall classification performance over the binary training method. Therefore, the multitarget ANN training method is potentially useful for ANN applications in computer-aided diagnosis of breast cancer.

This paper presents the speed estimator for speed sensorless direct torque control of a three-phase induction motor based on constant voltage per frequency (V/F) control technique, using artificial neural network (ANN). The estimated stator current equation is derived and rearranged consistent with the control algorithm and ANN structure. For the speed estimation, a weight in ANN, which relates to the speed, is adjusted by using Widrow–Hoff learning rule to minimize the sum of squared errors between the measured stator current and the estimated stator current from ANN output. The consequence of using this method leads to the ability of online speed estimation and simple ANN structure. The simulation and experimental results in high- and low-speed regions have confirmed the validity of the proposed speed estimation method.