Search results for "NEURAL NETWORK"

Surrogate models for the compressive strength mapping of cement mortar materials

2021

Despite the extensive use of mortar materials in constructions over the last decades, there is not yet a robust quantitative method available in the literature, which can reliably predict their strength based on the mix components. This limitation is attributed to the highly nonlinear relation between the mortar’s compressive strength and the mixed components. In this paper, the application of artificial intelligence techniques for predicting the compressive strength of mortars is investigated. Specifically, Levenberg–Marquardt, biogeography-based optimization, and invasive weed optimization algorithms are used for this purpose (based on experimental data available in the literature). The c…

Adaptive Neural Control of MIMO Nonstrict-Feedback Nonlinear Systems with Time Delay

2016

In this paper, an adaptive neural output-feedback tracking controller is designed for a class of multiple-input and multiple-output nonstrict-feedback nonlinear systems with time delay. The system coefficient and uncertain functions of our considered systems are both unknown. By employing neural networks to approximate the unknown function entries, and constructing a new input-driven filter, a backstepping design method of tracking controller is developed for the systems under consideration. The proposed controller can guarantee that all the signals in the closed-loop systems are ultimately bounded, and the time-varying target signal can be tracked within a small error as well. The main con…

Multiple Fault Diagnosis of Electric Powertrains Under Variable Speeds Using Convolutional Neural Networks

2018

Electric powertrains are widely used in automotive and renewable energy industries. Reliable diagnosis for defects in the critical components such as bearings, gears and stator windings, is important to prevent failures and enhance the system reliability and power availability. Most of existing fault diagnosis methods are based on specific characteristic frequencies to single faults at constant speed operations. Once multiple faults occur in the system, such a method may not detect the faults effectively and may give false alarms. Furthermore, variable speed operations render a challenge of analysing nonstationary signals. In this work, a deep learning-based fault diagnosis method is propos…

Weld quality prediction in linear friction welding of AA6082-T6 through an integrated numerical tool

2016

Abstract A numerical and an experimental campaign were carried out with varying oscillation frequency and interface pressure. The local values of the main field variables at the contact interface between the specimens were predicted by a Lagrangian, implicit, thermo-mechanical FEM model and used as input of a dedicated Neural Network (NN). The NN, integrated in the FEM environment, was designed in order to calculate both a Boolean output, indicating the occurrence of welding, and a continuous output, indicating the quality of the obtained solid state weld. The analysis of the obtained results allowed three different levels of bonding quality, i.e., no weld, sound weld and excess of heat, to…

Neural modelling of friction material cold performance

2008

The complex and highly non-linear phenomena involved during braking are primarily caused by friction materials’ characteristics. The final friction materials' characteristics are determined by their compositions, manufacturing, and the brake's operating conditions. Analytical models of friction materials' behaviour are difficult, even impossible, to obtain for the case of different brakes' operating conditions. That is why, in this paper, all relevant influences on the friction materials' cold performance have been integrated by means of artificial neural networks. The influences of 26 input parameters, defined by the friction materials' composition (18 ingredients), manufacturing (five pa…

Online fitted policy iteration based on extreme learning machines

2016

Reinforcement learning (RL) is a learning paradigm that can be useful in a wide variety of real-world applications. However, its applicability to complex problems remains problematic due to different causes. Particularly important among these are the high quantity of data required by the agent to learn useful policies and the poor scalability to high-dimensional problems due to the use of local approximators. This paper presents a novel RL algorithm, called online fitted policy iteration (OFPI), that steps forward in both directions. OFPI is based on a semi-batch scheme that increases the convergence speed by reusing data and enables the use of global approximators by reformulating the valu…

Modeling and control of uncertain nonlinear systems

2018

A survey of the methodologies associated with the modeling and control of uncertain nonlinear systems has been given due importance in this paper. The basic criteria that highlights the work is relied on the various patterns of techniques incorporated for the solutions of fuzzy equations that corresponds to fuzzy controllability subject. The solutions which are generated by these equations are considered to be the controllers. Currently, numerical techniques have come out as superior techniques in order to solve these types of problems. The implementation of neural networks technique is contributed in the complex way of dealing the appropriate coefficients and solutions of the fuzzy systems.

2021

Classification approaches that allow to extract logical rules such as decision trees are often considered to be more interpretable than neural networks. Also, logical rules are comparatively easy to verify with any possible input. This is an important part in systems that aim to ensure correct operation of a given model. However, for high-dimensional input data such as images, the individual symbols, i.e. pixels, are not easily interpretable. Therefore, rule-based approaches are not typically used for this kind of high-dimensional data. We introduce the concept of first-order convolutional rules, which are logical rules that can be extracted using a convolutional neural network (CNN), and w…

Model-based Engineering for the Integration of Manufacturing Systems with Advanced Analytics

2016

To employ data analytics effectively and efficiently on manufacturing systems, engineers and data scientists need to collaborate closely to bring their domain knowledge together. In this paper, we introduce a domain-specific modeling approach to integrate a manufacturing system model with advanced analytics, in particular neural networks, to model predictions. Our approach combines a set of meta-models and transformation rules based on the domain knowledge of manufacturing engineers and data scientists. Our approach uses a model of a manufacturing process and its associated data as inputs, and generates a trained neural network model as an output to predict a quantity of interest. This pape…

Extreme Learning Machines for Data Classification Tuning by Improved Bat Algorithm

2018

Single hidden layer feed forward neural networks are widely used for various practical problems. However, the training process for determining synaptic weights of such neural networks can be computationally very expensive. In this paper we propose a new learning algorithm for learning the synaptic weights of the single hidden layer feedforward neural networks in order to reduce the learning time. We propose combining the upgraded bat algorithm with the extreme learning machine. The proposed approach reduces the number of evaluations needed to train a neural network and efficiently finds optimal input weights and the hidden biases. The proposed algorithm was tested on standard benchmark clas…