Optimum design of aerospace structural components using neural networks

ABSTRACTA back‐propagation neural network was applied to predicting the KIC values using tensile material data and investigating the effects of crack plane orientation and temperature. The 595 KIC data of structural steels were used for training and testing the neural network model. In the trained neural network model, yield stress has relatively the most effect on KIC value among tensile material properties and KIC value was more sensitive to KIC test temperature than to crack plane orientation valid in the range of material data covered in this study. The performance of the trained artificial neural network (ANN) was evaluated by comparing output of the ANN with results of a conventional least squares fit to an assumed shape. The conventional linear or nonlinear least squares fitting methods gave very poor fitting results but the results predicted by the trained neural network were considerably satisfactory. This study shows that the neural network can be a good tool to predict KIC values according to the variation of the temperature and the crack plane orientation using tensile test results.

Artificial neural networks (ANN) have been widely used in the field of data classification. Normally, training of neural network is applied with the traditional back propagation technique. As, this approach has various drawbacks, training of neural network is done with Particle Swarm Optimization (PSO). PSO has been widely used to solve the diverse kind of optimization problems. Population initialization performs a significant role in meta-heuristic algorithms. This paper describes a new initialization population approach Log Logistic termed as PSOLL-NN to create the initialization of the swarm. The proposed algorithm has been tested for weight optimization of feed forward neural network; and compared with back propagation Algorithm (BPA), standard PSO (PSO-NN), PSO initialized with Halton Sequence (PSOH-NN), Torus sequence (PSOT-NN) and Sobol sequence (PSOS-NN). The experimental results show that the proposed technique performed exceptionally better than the other traditional techniques. Moreover, the outcome of our work presents a foresight that how the proposed initialization technique can be used as an efficient alternative to standard training approaches for the data classification problems.

BACKGROUND: Currently, artificial intelligence in the form of artificial neural networks is being actively implemented in a number of areas of our lives, including medicine. In particular, in otorhinolaryngology, artificial neural networks are used to analyze images obtained during endoscopic examinations of patients (e.g., videolaryngoscopy) [1–3]. The interpretation of laryngoscopic images often presents significant difficulties for practicing physicians, which reduces the frequency of detection of precancerous laryngeal diseases and contributes to the increase in the number of patients with stage III–IV laryngeal cancer [4, 5]. This underscores the significance of prompt performance and accurate interpretation of the findings of endoscopic examinations of patients with laryngeal disorders. Artificial neural networks can be employed to analyze the results of videolaryngoscopy, furnishing the physician with supplementary information that can enhance diagnostic accuracy and diminish the probability of error [6, 7]. AIM: The study aims to develop and train an artificial neural network for recognizing characteristic features of laryngeal neoplasms and variants of laryngeal normality. MATERIALS AND METHODS: The study was conducted under the grant of the Moscow Center for Innovative Technologies in Healthcare (grant No. 2112-1/22) entitled “Using Neural Networks (Artificial Intelligence Algorithms) for Control and Improving the Quality of Diagnosis and Treatment of Diseases of Laryngeal and Ear Structures through Digital Technologies”.The following methods were used during the course of the study: data collection for the creation of a photobank (dataset) of medical images obtained during videolaryngoscopy; data partitioning for the formation of datasets for individual nosologies and groups of diseases; the method of consilium; analysis of the accuracy of recognition and classification of digital endoscopic images; and training of classification neural networks. Consequently, a dataset comprising 1,471 laryngeal images in digital formats (JPEG, BMP) was assembled, labelled, and uploaded for the purpose of training the artificial neural network. Of the total number of images, 410 were classified as pertaining to laryngeal formation, while 1061 were classified as variants of normality. Subsequently, the neural network was trained and tested to identify the signs of normal and laryngeal masses. RESULTS: The results of the testing of the artificial neural network indicated the formation of an inaccuracy matrix, the calculation of the value of recognition accuracy, the calculation of the quality indicators of the model performance, and the construction of the ROC curve. The developed and trained artificial neural network demonstrated an accuracy of 86% in recognizing the signs of laryngeal masses and norms. CONCLUSIONS: This study demonstrates that a trained artificial neural network can successfully distinguish between signs of normal and laryngeal masses in endoscopic photographs. With further training of the neural network and achievement of high accuracy, this technology can be used in clinical practice as an assistant in the interpretation of laryngoscopic images and early diagnosis of laryngeal masses. It can also be employed to control and improve the quality of diagnosis and treatment of diseases of the throat, nose, and ears by primary care physicians.

NOVEL STAGING TOOL FOR LOCALIZED PROSTATE CANCER: A PILOT STUDY USING GENETIC ADAPTIVE NEURAL NETWORKS

PurposeThis paper aims to investigate the use of artificial neural networks (ANN) to predict the sewing performance of fabrics. The purpose of this study is to verify the ANN techniques that could be emulated as human decision in the prediction of sewing performance of fabrics.Design/methodology/approachIn order to verify the ANN techniques that could be emulated as human decision in the prediction of sewing performance of fabrics, 109 data sets of fabrics were tested by using fabric assurance by simple testing system and the sewing performance of each fabric's specimen was assessed by the domain experts. Of these 109 input‐output data pairs, 94 were used to train the proposed backpropagation (BP) neural network for the prediction of the unknown sewing performance of a given fabric, and 15 were used to test the proposed BP neural network.FindingsAfter 10,000 iterations of training of BP neural network, the neural network converged to the minimum error level. The experimental results reveal the great potential of the proposed approach in predicting the sewing performance of fabrics for apparel production.Originality/valueGenerally, the fabric's performance in the manufacturing process is judged subjectively by the operators and/or their supervisors. Current methodologies of acquiring fabric property information and predicting fabric sewing performance are still incapable of providing a means for efficient planning and control for the sewing operation. Further, development of techniques to predict the sewing performance of fabric is essential for the current apparel production environment. In this paper, the use of ANN to predict the sewing performance of fabrics in garment manufacturing is investigated.

Predicting impact strength of perforated targets using artificial neural networks trained on FEM-generated datasets

Artificial neural network enabled accurate geometrical design and optimisation of thermoelectric generator

In the present work, an effort has been made to explore the potentialities of application of regression analysis and artificial neural network (ANN) in milling process. Optimum setting of horizontal and vertical cutting forces for a particular tool-work piece combination is found using three levels of speed, feed and depth of cut. The parameter combination is worked out using full factorial design of experiment methods (DOE). Experiments are conducted for all the combinations and forces are measured using a milling tool dynamometer. Based on the observations, regression equations are derived. The present investigation was further extended with the application of ANN using an architecture consisting of three input and two output nodes and a hidden layer. The network training is carried out and then trained network is tested with few experimental results, which are not used during training. The results obtained during the study are critically discussed and reported.

Development and application of reservoir models and artificial neural networks for optimizing ventilation air requirements in development mining of coal seams

Samaria Tertiary field in southeastern Mexico produces extra-heavy to medium grade oil (5 to 23° API) from sand-shale sequences. It is well known that the nuclear magnetic resonance (NMR) logging application can provide the total and effective porosity values, as well as free and related fluids independent of mineralogy. When the NMR logging tool is run in heavy oil deposits, oils of varying viscosities can be distinguished qualitatively. Unfortunately, however, in the presence of heavy oils, this measurement process underestimates the total porosity and effective porosity, and overestimates the bulk volume irreducible water (a key parameter for estimating permeability). Although the literature specifies methods that can correct this porosity and fluid volume bias by using fundamental magnetic resonance principles and conventional borehole information, they are only effective when the drilling fluid used is water-based mud. The artificial neural networks (ANN) have traditionally been used to correct well log data corrupted by tension pulls on the tool or degraded by poor borehole conditions. They have also been used for cases in which it is not feasible to obtain a traditional set of openhole well log data. In such cases, a neural network is used to generate synthetic openhole data from pulsed neutron logging data. In this application of ANN, the data is first manually interpreted to delineate uncorrupted zones of the data. This interpretation will correspond to zones in which there is no hydrocarbon or the hydrocarbon type is not heavy oil. The aggregate of such zones is used to define a training set. The remaining data is used to define the application data set. Traditional openhole data (such as resistivity, neutron, bulk density, and thorium) is used to train a neural network to predict NMR fluid volumes. The network obtained is then applied to the application data set, and it is shown that the resulting predicted NMR fluid volumes have been corrected for heavy oil effects in the presence of oil-based mud. This paper demonstrates the effectiveness of this approach and discusses the results obtained. It also demonstrates how the process can be automated.

Artificial neural network (ANN) is a simplified model of the biological nervous system consisting of nerve cells or neurons. The application of ANN to food process engineering is relatively novel. ANN had been employed in diverse applications like food safety and quality analyses, food image analysis, and modeling of various thermal and non-thermal food-processing operations. ANN has the ability to map nonlinear relationships without any prior knowledge and predicts responses even with incomplete information. Every neural network possesses data in the form of connection weights interconnecting lines between the input to hidden layer neurons and weights of hidden to output layer neurons, which has a significant role in predicting the output data. The applications of ANN in different unit operations in food processing were described that includes theoretical developments using intelligent characteristics for adaptability, automatic learning, classification, and prediction. The parallel architecture of ANN resulted in a fast response and low computational time making it suitable for application in real-time systems of different food process operations. The predicted responses obtained by the ANN model exhibited high accuracy due to lower relative deviation and root mean squared error and higher correlation coefficient. This paper presented the various applications of ANN for modeling nonlinear food engineering problems. The application of ANN in the modeling of the processes such as extraction, extrusion, drying, filtration, canning, fermentation, baking, dairy processing, and quality evaluation was reviewed. HIGHLIGHTS 1. This paper discusses application of ANN in different emerging trends in food process. 2. Application of ANN to develop non-linear multivariate modeling is illustrated. 3. ANNs have been shown to be useful tool for prediction of outcomes with high accuracy. 4. ANN resulted in fast response making it suitable for application in real time systems.

Computer systems based on artificial neural networks, often known as neural networks or neural nets, are modeled after the organic neural networks seen in animal brains. Artificial neurons are a group of interconnected units or nodes that serve as the foundation of an ANN and are meant to approximate the function of biological brain neurons. This article contains a survey of practical uses for neural networks. It offers a taxonomy of Artificial Neural Networks (ANNs), in-forms the reader of recent and upcoming developments in ANN applications research, and highlights research areas of interest. This paper also discusses the difficulties, contributions, comparative effectiveness, and important methodologies in ANN applications. The study examines a wide range of ANN applications in numerous disciplines, including computing, science, engineering, medicine, the environment, agriculture, mining, technology, climate, business, and the arts similar to nanotechnology. This study analyses performance assesses ANN contributions and criticizes techniques. The study discovered that artificial neural networks with feedforward and feedback propagation do well when applied to solving human problems. Therefore, based on data analysis characteristics such as accuracy, processing speed, latency, fault tolerance, volume, scalability, convergence, and efficiency, we presented feed-forward and feedback propagation ANN models for research centers. A computational model known as an artificial neural network (ANN) is composed of many processing elements that accept inputs and produce outputs by their specified activation functions. This article will make other articles in this computer magazine easier to grasp for those who know little or nothing about ANNs. We go over the reasons for creating ANNs, the fundamentals of a biological neuron and an artificial computer model, network designs, learning mechanisms, and some of the most widely used ANN models. A successful ANN character recognition application brings us to a close. EDAS Evaluation Based on Distance from Average Solution method for Notebook(n1), Notebook(n2), Notebook(n3), Notebook(n4), Notebook(n5). Notebook (n1), Notebook (n2), Notebook (n3), Notebook (n4), Notebook (n5). Speed (MHz), RAM (Mbytes), Display (inches), Price (Euro). Notebook (n5) has the highest rank whereas Notebook (n1) has the lowest rank. The need for hybrid systems, Optical Neural Networks, EDAS Method.

A novel method using artificial neural network with back-propagation algorithm to detect and separate LFM signal is proposed. This method trains the network by LFM signal mixed with Gauss noise. Simulation result shows the trained BP neural network can eliminate noise effectively. In addition, if the learning sample is a multicomponent LFM signal, the trained network can separate the LFM signal component conveniently. Theoretical analysis and simulation results show that the proposed method has low computational complexity and good performance

This article discusses the applications of Artificial Neural Network (ANN) and Fuzzy Logic Control (FLC) strategies in a control context of a grid connected Wind Energy Conversion System (WECS), using a Doubly-Fed Induction Generator (DFIG). To rigorously explore the performance of the controllers, a systemic approach based on an ideal model and a nominal model of the wind turbine is used for the comparative analysis between PI, FLC and ANN. It turns out that the PI is less efficient than ANN and FLC. It turns out that the PI is less efficient than ANN and FLC. Whereas, for a high level of control, the FLC has better performance than the ANN. For a low level, the performance of the ANN is very slightly superior to the FLC. In addition, one notes a good rejection of disturbance and a good robustness with the FLC compared to the ANN. The latter has a Total Harmonic Distortion (THD) and cos ϕ ≈ 1 slightly better than the FLC. In short, the ANN and FLC present great advantages for the WECS and the results obtained are satisfactory. The platform used for modeling and simulation studies is MATLAB/Simulink.KeywordsWind Energy Conversion SystemFuzzy Logic Control (FLC)Artificial Neural Network (ANN)DFIGPower grid

Development and application of artificial neural network (ANN) pedotransfer functions for estimating soil hydraulic properties (SHP) have become popular in the last two decades. However, limited availability of SHP training data often constrains the full potential of improved SHP estimation with ANN in many practical situations. In many situations, SHP data are limited and could be biased by samples from a restricted portion of the data population. Artificial neural network pedotransfer functions developed under such situations are likely to yield biased estimates. We proposed a direct approach to minimize mean estimation errors (bias) in such situations and developed a regularized ANN algorithm. The new algorithm revised the ANN error function and its gradients with respect to neural network outputs. We applied the new algorithm to synthetically generated SHP data representing different data availability situations and found that the newly developed algorithms were effective in reducing bias. Training with both the new and conventional mean square error functions resulted in equally good results in test phases when ANN models were trained with randomly sampled unbiased data. However, when ANN was trained with and applied to SHP data with respectively different means (biased sample), the proposed regularized ANN was highly effective in minimizing the bias when compared with ANN with the conventional mean square error function.