Comparison between response surface models and artificial neural networks in hydrologic forecasting

Developing an efficient and accurate hydrologic forecasting model is crucial to managing water resources and flooding issues. In this study, response surface (RS) models including multiple linear regression (MLR), quadratic response surface (QRS), and nonlinear response surface (NRS) were applied to daily runoff (e.g., discharge and water level) prediction. Two catchments, one in southeast China and the other in western Canada, were used to demonstrate the applicability of the proposed models. Their performances were compared with artificial neural network (ANN) models, trained with the learning algorithms of the gradient descent with adaptive learning rate (ANN-GDA) and Levenberg-Marquardt (ANN-LM). The performances of both RS and ANN in relation to the lags used in the input data, the length of the training samples, long-term (monthly and yearly) predictions, and peak value predictions were also analyzed. The results indicate that the QRS and NRS were able to obtain equally good performance in runoff prediction, as compared with ANN-GDA and ANN-LM, but require lower computational efforts. The RS models bring practical benefits in their application to hydrologic forecasting, particularly in the cases of short-term flood forecasting (e.g., hourly) due to fast training capability, and could be considered as an alternative to ANN

Artificial neural network modeling of flow stress in hot rolling

In this study, an artificial neural network model is proposed to predict the flow stress variations during the hot rolling process. Optimization of the proposed neural network with respect to number of neurons within the hidden layer, different training methods and transfer functions of the neural network is performed. The results of the optimal network were compared with those of the conventional analytic method and it is shown that using an optimal neural network the mean calculated error is drastically reduced.

Development of a dynamic surface roughness monitoring system based on artificial neural networks (ANN) in milling operation

Dynamic surface roughness prediction during metal cutting operations plays an important role to enhance the productivity in manufacturing industries. Various machining parameters such as unwanted noises affect the surface roughness, whatever their effects have not been adequately quantified. In this study, a general dynamic surface roughness monitoring system in milling operations was developed. Based on the experimentally acquired data, the milling process of Al 7075 and St 52 parts was simulated. Cutting parameters (i.e., cutting speed, feed rate, and depth of cut), material type, coolant fluid, X and Z components of milling machine vibrations, and white noise were used as inputs. The original objective in the development of a dynamic monitoring system is to simulate wide ranges of machining conditions such as rough and finishing of several materials with and without cutting fluid. To achieve high accuracy of the resultant data, the full factorial design of experiment was used. To verify the accuracy of the proposed model, testing and recall/verification procedures have been carried out and results showed that the accuracy of 99.8 and 99.7 % were obtained for testing and recall processes.

Evolving an adaptive artificial neural network with a gravitational search algorithm

In this paper, a supervised fuzzy adaptive resonance theory neural network, i.e., Fuzzy ARTMAP (FAM), is integrated with a heuristic Gravitational Search Algorithm (GSA) that is inspired from the laws of Newtonian gravity. The proposed FAM-GSA model combines the unique features of both constituents to perform data classification. The classification performance of FAM-GSA is benchmarked against other state-of-art machine learning classifiers using an artificially generated data set and two real data sets from different domains. Comparatively, the empirical results indicate that FAM-GSA generally is able to achieve a better classification performance with a parsimonious network size, but with the expense of a higher computational load.

Intelligent animal fiber classification with artificial neural networks

Artificial neural networks (ANN) are increasingly used to solve many problems related to pattern recognition and object classification. In this paper, we report on a study using artificial neural networks to classify two kinds of animal fibers: merino and mohair. We have developed two different models, one extracting nine scale parameters with image processing, and the other using an unsupervised artificial neural network to extract features automatically, which are determined in accordance with the complexity of the scale structure and the accuracy of the model. Although the first model can achieve higher accuracy, it requires more effort for image processing and more prior knowledge, since the accuracy of the ANN largely depends on the parameters selected. The second model is more robust than the first, since only raw images are used. Because only ordinary optical images taken with a microscope are employed, we can use the approach for many textile applications without expensive equipment such as scanning electron microscopy.

Neural network training by hybrid accelerated cuckoo particle swarm optimization algorithm

Metaheuristic algorithm is one of the most popular methods in solving many optimization problems. This paper presents a new hybrid approach comprising of two natures inspired metaheuristic algorithms i.e. Cuckoo Search (CS) and Accelerated Particle Swarm Optimization (APSO) for training Artificial Neural Networks (ANN). In order to increase the probability of the egg’s survival, the cuckoo bird migrates by traversing more search space. It can successfully search better solutions by performing levy flight with APSO. In the proposed Hybrid Accelerated Cuckoo Particle Swarm Optimization (HACPSO) algorithm, the communication ability for the cuckoo birds have been provided by APSO, thus making cuckoo bird capable of searching for the best nest with better solution. Experimental results are carried-out on benchmarked datasets, and the performance of the proposed hybrid algorithm is compared with Artificial Bee Colony (ABC) and similar hybrid variants. The results show that the proposed HACPSO algorithm performs better than other algorithms in terms of convergence and accuracy.

Modelling of porosity defects in high pressure die casting with a neural network

High Pressure Die Casting (HPDC) is a complex process that results in casting defects if configured improperly. However, finding out the optimal configuration is a non-trivial task as eliminating one of the casting defects (for example, porosity) can result in occurrence of other casting defects. The industry generally tries to eliminate the defects by trial and error which is an expensive and error -prone process. This paper aims to improve current modelling and understanding of defects formation in HPDC machines. We have conducted conventional die casting tests with a neural network model of HPDC machine and compared the obtained results with the current understanding of formation of porosity. While most of our findings correspond well to established knowledge in the field, some of our findings are in conflict with the previous studies of die casting.

Neural net device for IED gas identification

Most of the embedded systems that detect gases today are for specific types and indicate the levels of the gas present with their standard sensors. We introduce here an adaptable system that can detect and distinguish the type of gas in a volatile environment such as searching for Improvised Explosive Devices (IEDs). This is achieved with a small device mounted on a mobile robot through the use of an algorithm that is an Artificial Neural Network (ANN). The input layer to the ANN is an array of environmental and gas sensors. The small device, comprising of a multilayer circuit board with sensors in a rugged lightweight case, mounts on the mobile robot and communicates the gaseous data to the robot.

The ANN is implemented in the hardware of a FPGA with the control of the ANN being achieved through the configurable processor and memory. Calibration and testing of the device involves the training of device and the ANN with specific target gases. The Accuracy of the device is validated through lab testing against high-end gas test instruments with known concentrations of gases.

A mutation-based evolving neural network model and its application to condition monitoring

Data analysis using intelligent systems is a key solution to many industrial problems. In this paper, a mutation-based evolving artificial neural network, which is based on an integration of the Fuzzy ARTMAP (FAM) neural network and evolutionary programming (EP), is proposed. The proposed FAMEP model is applied to detect and classify possible faults from a number of sensory signals of a circulating water system in a power generation plant. The efficiency of FAM-EP is assessed and compared with that of the original FAM network in terms of classification accuracy as well as network complexity. In addition, the bootstrap method is used to quantify the performance statistically. The results positively demonstrate the usefulness of FAM-EP in tackling data classification problems.

Text-dependent speaker recognition using the Fuzzy ARTMAP neural network

Speaker recognition is the process of automatically recognizing the speaker by analyzing individual information contained in the speech waves. In this paper, we discuss the development of an intelligent system for text-dependent speaker recognition. The system comprises two main modules, a wavelet-based signal-processing module for feature extraction of speech waves, and an artificial-neural-network-based classifier module to identify and categorize the speakers. Wavelet is used in de-noising and in compressing the speech signals. The wavelet family that we used is the Daubechies Wavelets. After extracting the necessary features from the speech waves, the features were then fed to a neural-network-based classifier to identify the speakers. We have implemented the Fuzzy ARTMAP (FAM) network in the classifier module to categorize the de-noised and compressed signals. The proposed intelligent learning system has been applied to a case study of text-dependent speaker recognition problem.

An online pruning strategy for supervised ARTMAP-based neural networks

Identifying an appropriate architecture of an artificial neural network (ANN) for a given task is important because learning and generalisation of an ANN is affected by its structure. In this paper, an online pruning strategy is proposed to participate in the learning process of two constructive networks, i.e. fuzzy ARTMAP (FAM) and fuzzy ARTMAP with dynamic decay adjustment (FAMDDA), and the resulting hybrid networks are called FAM/FAMDDA with temporary nodes (i.e. FAM-T and FAMDDA-T, respectively). FAM-T and FAMDDA-T possess a capability of reducing the network complexity online by removing unrepresentative neurons. The performances of FAM-T and FAMDDA-T are evaluated and compared with those of FAM and FAMDDA using a total of 13 benchmark data sets. To demonstrate the applicability of FAM-T and FAMDDA-T, a real fault detection and diagnosis task in a power plant is tested. The results from both benchmark studies and real-world application show that FAMDDA-T and FAM-T are able to yield satisfactory classification performances, with the advantage of having parsimonious network structures.

Hybrid neural network—finite element river flow model

Results obtained from a hybrid neural network—finite element model are reported in this paper. The hybrid model incorporates artificial neural network (ANN) nodes into a numerical scheme, which solves the two-dimensional shallow water equations using finite elements (FE). First, numerical computations are carried out on the entire numerical model, using a larger mesh. The results from this computation are then used to train several preselected ANN nodes. The ANN nodes model the response for a part of the entire numerical model by transferring the system reaction to the location where both models are connected in real time. This allows a smaller mesh to be used in the hybrid ANN-FE model, resulting in savings in computation time. The hybrid model was developed for a river application, using the computational nodes located at the open boundaries to be the ANN nodes for the ANN-FE hybrid model. Real-time coupling between the ANN and FE models was achieved, and a reduction is CPU time of more than 25% was obtained.

Improvement of the prediction accuracy and efficiency of hot strength of austenitic steels with optimised ANN training schemes

The hot strength of austenitic steels of different carbon contents was modelled using an artificial neural network (ANN) model with optimum training data. As training data employed in a traditional neural network model were randomly selected from experimental data, they were not representative and the prediction accuracy and efficiency were therefore significantly affected. In this work, only representatively experimental data were used for training and during the procedure, one tenth of the training data extracted from experiment were used for testing the training model and terminating the modelling. The effects of the carbon con tent on flow stress, peak strains and peak stresses observed from the experiment for both training and test data were accurately represented with the ANN scheme reported in this work.