Estimation of concrete compressive strength using artificial neural network

The purpose of the research, the results of which are presented in this article, is to determine the possibility and evaluate the effectiveness of using a trained neural network in the diagnosis of ringworm. The article provides an analysis of the methods used for diagnosing dermatomycosis in veterinary practice. One of the actively developing areas at present is the use of artificial neural networks in the diagnosis of animal diseases. The authors have developed a method for diagnosing dermatophytosis using a trained neural network. To identify hair damaged by dermatophyte spores in cats, a trained artificial neural network YOLO v5 was used, based on the YOLO architecture (high-precision artificial neural network), which provides high accuracy and speed of object detection in images. Diagnostics was carried out in three stages. The first stage: the diagnosis of hair in cats damaged by dermatophyte spores was carried out using a trained artificial neural network. The second stage: microscopy by a veterinary specialist of the veterinary center. The third stage: comparison of the received data from the trained artificial neural network and veterinary specialists. Three comparative experiments were carried out on 20 depersonalized samples with different ratios from healthy and sick animals. As a result of testing the trichoscopy method using artificial neural networks for diagnosing spore-damaged hair dermatitis in cats, it was found that a trained artificial neural network of 60 studied samples diagnosed dermatophyte spore damage in 20 samples, a veterinarian - in 17. All positive results were confirmed by a mycological laboratory study. and identification of the pathogen. It has been established that the use of a trained artificial neural network increases the diagnostic efficiency by 15% and reduces the time to perform diagnostic microscopy by 60.3%. The application of the proposed method allows to reduce the time of microscopic examination, improve the accuracy of interpretation of the results, automate methods for identifying causative agents of ringworm in small animals and take timely measures to treat the animal.

In this paper, a computational intelligent technique genetic algorithm (GA) is implemented for the optimization of artificial neural network (ANN) architecture. The network structures are normally selected on the basis of the developer's prior knowledge or hit and trial approach is used for this purpose. ANN based models are frequently used for the prediction of future load, because of their learning and mapping ability to address the non linear nature of electrical load. The proposed technique provides a pathway to determine the best ANN architecture, prior to the training and learning process of neural network. Multi-objective algorithm is proposed in this research which optimizes the ANN architecture that leads to enhancement in load forecast accuracy and reduction in the computational cost. The results of several experiment conducted during this work, exhibits that forecast accuracy is considerably enhanced by using an optimized and reduced ANN structure.

Introduction Atmospheric corrosion is the main cause of metallic heritage degradation when they are exposed to relative humidity, temperature cycle and air contaminants. Corrosivity maps are one of the preventive strategies for atmospheric corrosion mitigation, but they do not provide enough information about corrosion mechanism, besides that long experimentation periods are required [1]. Moreover, electrochemical techniques are alternatives to speed up results, but their relationship with constantly changing environmental variables is difficult to control.Currently, Artificial Intelligence has been introduced in corrosion engineering studies, because of its capability to make predictions based on big data. Also, experimental data of Electrochemical Impedance Spectroscopy had been used in Artificial Neural Network training to obtain Nyquist Diagrams [2]. The objective of this work is to obtain computational models of Artificial Neural Networks to predict atmospheric corrosion in Bronze with nanostructured patina with SiO2, in marine environments. Method Environmental parameters were taken from database previously reported [3,4], and from Civil Protection Secretariat of Veracruz. Whilst electrochemical evaluation consists in Polarization Resistance and Electrochemical Impedance Spectroscopy; they were carried out in a Gamry Interface 1000 Potentiostat with a Saturated Calomel Reference Electrode (SCE) and a graphite bar as counter electrode in an agar gelled cell. Meanwhile, working electrode was bronze with nanostructured patina with SiO2. Two patina were prepared, the first with CuSO4 solution (0.015 mol L-1) and the second applying a CuNO3 solution (20% wt).The 13 variables used in the database for Artificial Neural Networks (ANN) training were: exposure time, chloride concentration, sulfur compounds concentration, relative humidity, precipitation level, windspeed, temperature, nanocoating presence, corrosion potential, corrosion rate, frequency, real and imaginary component of impedance. The values of each variable were treated with measures of central tendency and dispersion, as well as correlation matrix and histograms, which allowed to find a relationship between variables, and choosing the inputs for ANN. The prediction models consisted in 5, 9, 10 and 12 neurons in the input layer (R5E, R9E, R10E and R12E, respectively), a hidden layer, and Zima as only neuron in the output layer. The number of neurons in hidden layer varied from 1 to 8 until the highest coefficient of determination was achieved. The computational model was performed using the toolbox in MATLAB with a feedforward ANN. It is worth mention that the hidden and output layers used a hyperbolic tangent and a linear transfer function, respectively, and a Levenberg-Marquardt algorithm as training function was used in the models. Results and Conclusions Figure 1 presents the coefficient of determination (R2) and root mean squared error (RMSE) with different ANN architectures. In the four models, the highest value was reached with 8 neurons in the hidden layer. Then, the linear regressions for R5E, R9E, R10E and R12E models and 8 neurons in the input layer were compared in Figure 2. In that sense, the Nyquist Diagrams in Figure 3 were simulated with the R9E and R12E models. Also, they were compared with experimental Nyquist Diagrams for Bronze with patina of CuSO4 and CuNO3, with and without SiO2 nanoparticles, at 56 days of exposure in marine atmospheres. The simulations demonstrated how an ANN model with 12 neurons in the input layer, 8 neurons in the hidden layer and 1 neuron in the output layer can be used as a corrosion prediction model of bronze with nanostructured patina with SiO2.

Energy consumption (kWh) is critical to the operation of electrical systems. Predictive modeling optimizes energy usage, increasing power system efficiency. This study created an artificial neural network (ANN) architecture to estimate energy consumption (kWh) for home users in Banda Aceh. The ANN topology consisted of 5 input layers, 5-25 hidden layers, and one output layer. This study used two scenarios: first, the ANN topology was trained using the logsig activation function, and then the tansig activation function was used for training. Based on training simulations, the ANN architecture with 5 input layers, 5 hidden layers, and 1 output layer has the lowest Mean Squared Error (MSE) of 0.00035. The next phase involved testing this ANN topology. The next stage is to analyze the ANN architecture with 5 input layers, 5 hidden layers, and 1 output layer using the testing technique. Based on the testing technique, the ANN architecture with 5 input layers, 5 hidden layers, and 1 output layer had a MAPE value of 3.34%.

Face recognition is one of the biometric methods that is used to identify any given face image using the main features of this face. In this research, a face recognition system was suggested based on four Artificial Neural Network (ANN) models separately: feed forward backpropagation neural network (FFBPNN), cascade forward backpropagation neural network (CFBPNN), function fitting neural network (FitNet) and pattern recognition neural network (PatternNet). Each model was constructed separately with 7 layers (input layer, 5 hidden layers each with 15 hidden units and output layer). Six ANN training algorithms (TRAINLM, TRAINBFG, TRAINBR, TRAINCGF, TRAINGD, and TRAINGD) were used to train each model separately. Many experiments were conducted for each one of the four models based on 6 different training algorithms. The performance results of these models were compared according to mean square error and recognition rate to identify the best ANN model. The results showed that the PatternNet model was the best model used. Finally, comparisons between the used training algorithms were performed. Comparison results showed that TrainLM was the best training algorithm for the face recognition system.

This paper investigates the training performances of multilayer artificial neural network (ANN) architectures for the generation and prediction of Lorenz chaotic system. Given that the complexity of ANN architectures are at the same level, the training performances of ANN with only one hidden layer prevail over those of ANN with multiple hidden layers. The designed ANN model is used to simulate and analyze brain activities captured by Electroencephalogram (EEG). Previous research shows that EEG signals demonstrate chaotic patterns. Chaotic systems can be represented by a set of mathematical equations. The three differential equations of Lorenz chaotic system are used to generate the ANN training samples. The ANN training is carried out using MATLAB Neural Network Toolbox with three training algorithms and the Nonlinear autoregressive (NAR) model from the nonlinear time series tool ‘ntstool’. ANN architectures with two hidden layers combined with different number of hidden neurons and input delays are compared by measuring the training performance using the average mean square errors (MSE) of all training samples. The training results demonstrate that the training performance can not be improved simply by increasing the complexity of the ANN architecture in terms of the number of hidden layers and hidden neurons. The simplicity of ANN architecture will further benefit the hardware implementation in the application for the generation and prediction of chaotic systems time series to simulate EEG signals for brain research.

This study presents establishment of multiple input prediction model for automotive coil spring fatigue life estimation to shorten automotive suspension design process. Automotive suspension design is a lengthy work where any changes of the design lead to repetition of the entire process. It was hypothesised that the established model could be used to predict the spring design fatigue life without using any strain measurements. To initiate this model establishment, five sets of strain and acceleration measurement across different road conditions were collected and used for validations. To include spring stiffness as a parameter, a quarter car model was generated to obtain the force time histories from spring and vertical vibration of vehicle mass. In addition, artificial road profiles of road classes “A” to “D” were also generated for the quarter car simulation. Through adjusting the spring stiffness in the quarter car model, the spring and vehicle responses were varied. The simulated force time histories were used to predict springs’ fatigue life while acceleration time histories were used to calculate ISO 2631 ride-related vertical vibration. Subsequently, multiple linear regression approach was applied to determine the relationship between vehicle body frequency, ISO 2631 ride-related vertical vibration and spring fatigue life. The obtained regression had shown significance to the spring fatigue life with coefficient of determination of 0.8320. Reciprocally, multiple linear regression models were also used to predict the ISO 2631 ride-related vertical vibration with a coefficient of determination at 0.8810 and mean squared error values below 0.3430. To optimise the prediction results, artificial neural network was trained for the fatigue and vibration prediction purposes. The architectures of the artificial neural network were designed in terms of number of neurons and hidden layers to achieve a higher coefficient of determination of 0.9926 and lower mean squared error of 0.0824. For vibration prediction, the vehicle body frequency and spring fatigue life has shown a significant coefficient of determination to the ISO 2631 weighted vertical vibration, reaching 0.9579 with mean squared error of 0.0004. Based on the experimental strain and acceleration results, the predicted fatigue lives of multiple linear regression models were correlated well with the experimental results with coefficient of determination value of 0.9275. Meanwhile, the maximum difference of vibration prediction to experimental value using multiple linear regression models was only 18%. For artificial neural network predictions, the fatigue lives were mostly distributed within 1:2 or 2:1 life correlation and vibration prediction results were within 12%. For a good prediction, the target correlation value was above 0.80 to demonstrate a good fitted curve and the difference below 20%. The trained artificial neural network has shown outstanding capability in fatigue life or ride-related vertical vibration predictions. In this research, the main novelty was the trained artificial neural network for spring fatigue life or ride-related vertical vibration predictions which serve to reduce some procedures of automotive suspension design. The outcome of this study can be used to provide a new knowledge towards the field of fatigue research as well as vehicle ride dynamics. This research contributes to automotive industries especially in suspension spring design where the analysis of fatigue and ride-related vibration are provided.

The algorithm to train artificial neural networks for intelligent decision support systems has been constructed. A distinctive feature of the proposed algorithm is that it conducts training not only for synaptic weights of an artificial neural network, but also for the type and parameters of membership function. In case of inability to ensure the assigned quality of functioning of artificial neural networks due to training of parameters of artificial neural network, the architecture of artificial neural networks is trained. The choice of the architecture, type and parameters of membership function occurs taking into consideration the computation resources of the facility and taking into consideration the type and the amount of information entering the input of an artificial neural network. In addition, when using the proposed algorithm, there is no accumulation of an error of artificial neural networks training as a result of processing the information entering the input of artificial neural networks.Development of the proposed algorithm was predetermined by the need to train artificial neural networks for intelligent decision support systems in order to process more information given the unambiguity of decisions being made. The research results revealed that the specified training algorithm provides on average 16–23 % higher the efficiency of training artificial neural networks training that is on average by 16–23 % higher and does not accumulate errors in the course of training. The specified algorithm will make it possible to conduct training of artificial neural networks; to determine effective measures to enhance the efficiency of functioning of artificial neural networks. The developed algorithm will also enable the improvement of the efficiency of functioning of artificial neural networks due to training the parameters and the architecture of artificial neural networks. The proposed algorithm reduces the use of computational resources of decision support systems. The application of the developed algorithm makes it possible to work out the measures aimed at improving the effectiveness of training artificial neural networks and to increase the efficiency of information processing

A set of training methods for artificial neural networks of intelligent decision-making support systems has been developed. A distinctive feature of the proposed methods is that not only the synaptic weights of the artificial neural network, but also the type and parameters of the membership function are trained. If it is impossible to ensure the specified quality of functioning of artificial neural networks due to learning the parameters of the artificial neural network, the learning of the architecture of artificial neural networks takes place. The choice of the architecture, type and parameters of the membership function takes place taking into account the computing resources of the tool and taking into account the type and amount of information entering the input of the artificial neural network. Due to the use of the proposed methods, there is no accumulation of learning errors of artificial neural networks as a result of processing information received at the input of artificial neural networks. Also, a distinctive feature of the developed methods is that no preliminary calculation data is required for data calculation. The development of the proposed methods is due to the need to train artificial neural networks for intelligent decision-making support systems, with the aim of processing a larger amount of information, with the unambiguity of the decisions being made. According to the results of the research, it was established that the specified training methods provide an average of 10‒18% higher training efficiency of artificial neural networks and do not accumulate errors during training. These methods will make it possible to conduct training of artificial neural networks, to determine effective measures to increase the efficiency of the functioning of artificial neural networks. The use of the specified methods will allow to increase the efficiency of the functioning of artificial neural networks due to the learning of the parameters and architecture of artificial neural networks, to reduce the use of computing resources of decision-making support systems. The developed methods will make it possible to develop measures aimed at increasing the effectiveness of learning artificial neural networks; increase the efficiency of information processing in artificial neural networks.

Crude oil fractions are essential products which are major sources of income that influence the economic growth. However, the complex nature of crude oil is calling for manufacturing innovation that will ease its process monitoring. Thus, there is need to design the crude distillation unit (CDU) operation to meet customers’ demand for the crude oil fractions. In this study, artificial neural network was applied for the process design and monitoring of a CDU in a petroleum refinery. A total of 230 data sets was used as experimental data (comprising controllable and uncontrollable variables) from which 88%, 6% and 6% were used for training, validation and testing of neural network respectively. The architectures for the CDU unit design and its neural network controller were 14 inputs, one hidden layer and seven outputs (14-1-7) and; 13 inputs, one hidden layer and six outputs (13-1-6) respectively. Logistic sigmoid transfer function was used as the activation function for the neural network training in the algorithms. The mean absolute error (MAE) and the mean square error (MSE) were used to test the accuracy of the model. After iteration numbers of 396 and 786 for CDU design and its neural network controller respectively, convergence was attained with training error of less than 10 −6 . For CDU design, the minimum values of MSE and MAE were 0.0055 and 0.0568 while their maximum values were 0.3517 and 0.4139 between the testing data and experimental data respectively. For the CDU neural network controller, the minimum values of MSE and MAE were 0.0000 and 0.000 while their maximum values were 0.1412 and 0.2922 between the testing data and experimental data respectively. In conclusion, artificial neural network could effectively be used as a machine learning tool for process monitoring of CDU in a petroleum refinery.

This paper investigates the training performances of multilayer artificial neural network (ANN) architectures for the implementation of chaotic systems. The designed ANN models can be employed for pattern recognition and prediction of dynamic chaotic systems, in order to simulate and analyze brain activities captured by Electroencephalogram (EEG). Previous research shows that EEG signals demonstrate chaotic features. Chaotic systems can be represented by a set of mathematical equations, which can be used to generate the target outputs for training ANN. In this research, the Henon map is selected as an example for ANN-based chaotic system design. The optimization of ANN architecture is important for improving the performance of hardware implementation. ANN architectures with up to 3 hidden layers combined with different number of hidden neurons are compared by measuring the training performance using the mean square errors (MSE). The ANN training are carried out using three training algorithms: Levenberg-Marquardt, Bayesian Regulation and Scaled Conjugated Gradient. Nonlinear autoregressive (NAR) model is used for ANN architectures design. The training results demonstrate that the training performance can not be improved simply by increasing the complexity of the ANN architecture in terms of the number of hidden layers and hidden neurons. It is therefore necessary to optimize the ANN architecture on a case-by-case basis in order to improve the efficiency of the ANN implementation for specified applications.

A multitude of problems in the contemporary literature are addressed using machine learning models, the most widespread of which are artificial neural networks. Furthermore, in recent years, evolutionary techniques have emerged that identify both the architecture of artificial neural networks and their corresponding parameters. Among these techniques, one can also identify the artificial neural networks being constructed, in which the structure and parameters of the neural network are effectively identified using Grammatical Evolution. In this work, a pre-training stage is introduced in which an artificial neural network with a fixed number of parameters is trained using some optimization technique such as the genetic algorithms used here. The final result of this additional phase is a trained artificial neural network, which is introduced into the genetic population used by Grammatical Evolution in the second phase. In this way, finding the overall minimum of the error function will be significantly accelerated, making the second phase method more efficient. The current work was applied to many classification and regression problems found in the related literature, and it was compared against other methods used for neural network training as well as against the original method used to construct neural networks.

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.

The proposed architecture of a binary artificial neural network is inspired by the structure and function of the major parts of the brain. Consequently it is divided into an input module that resemble the sensory (stimuli) area and an output module similar to the motor (responses) area. These two modules are single layer feed forward neural networks and have fixed weights to transform input patterns into a simple code and then to convert this code back to output patterns. All possible input and output patterns are stored in the weights of these two modules. Each output pattern can be produced by a single neuron of the output module asserted high. Similarly each input pattern produces a single input module neuron at binary 1. The training of this neural network is confined to connecting one output neuron of the input module at binary 1 that represents a code for the input pattern and one input neuron of the output module that produces the desired associated output pattern. Thus fast and accurate association between input and output pattern pairs can be achieved. These connections can be implemented by a crossbar switch. This crossbar switch acts similar to the thalamus in the brain which is considered to be a relay center. The role of the crossbar switch is generalized to an electric field in the gap between input and output modules and it is postulated that this field may be considered as a bridge between the brain and mental states. The input module encoder is preceded by the extended input circuit which ensures that the inverse of the input matrix exists and at the same time to make the derivation of this inverse of any order a simple task. This circuit mimics the processing function of the region in the brain that process input signals before sending them to the sensory region. Some applications of this neural network are: logical relations, mathematical operations, as a memory device and for pattern association. The number of input neurons can be increased (increased dimensionality) by multiplexing those inputs and using latches and multi-input AND gates. It is concluded that by emulating the major structures of the brain using artificial neural networks the performance of these networks can be enhanced greatly by increasing their speed, increasing their memory capacities and by performing a wide range of applications.

The paper deals with the neural identification of the compressive strength of concrete on the basis of non‐destructively determined parameters. Basic information on artificial neural networks and the types of artificial neural networks most suitable for the analysis of experimental results are given. A set of experimental data for the training and testing of neural networks is described. The data set covers a concrete compressive strength ranging from 24 to 105 MPa. The methodology of the neural identification of compressive strength is presented. Results of such identification are reported. The results show that artificial neural networks are highly suitable for assessing the compressive strength of concrete. The neural identification of the compressive strength of concrete has been verified in situ.