A genetic algorithm-based artificial neural network model for the optimization of machining processes

Abstract

Artificial intelligent tools like genetic algorithm, artificial neural network (ANN) and fuzzy logic are found to be extremely useful in modeling reliable processes in the field of computer integrated manufacturing (for example, selecting optimal parameters during process planning, design and implementing the adaptive control systems). When knowledge about the relationship among the various parameters of manufacturing are found to be lacking, ANNs are used as process models, because they can handle strong nonlinearities, a large number of parameters and missing information. When the dependencies between parameters become noninvertible, the input and output configurations used in ANN strongly influence the accuracy. However, running of a neural network is found to be time consuming. If genetic algorithm-based ANNs are used to construct models, it can provide more accurate results in less time. This article proposes a genetic algorithm-based ANN model for the turning process in manufacturing Industry. This model is found to be a timesaving model that satisfies all the accuracy requirements.

Modeling of Surface Roughness during Conventional Turning using a Hybrid GA-ANN Based Model

“…al. "A genetic algorithm-based artificial neural network model for the optimization of machining processes, 2005" [7] made a GA based ANN model of the turning process, in which he used the genetic algorithm to find out the optimal connection weights, and compared it with a simple back propagation network model. He used a 5 -5 -4 neural network architecture and a real value encoding with 225-digit long chromosome, which represented the total 45 connection weights present in the architecture.…”

Prediction of compressive and tensile strength of Gaziantep basalts via neural networks and gene expression programming

“…The prediction ability of regression analyses may be limited for highly non-linear problems [16]. Neural Networks (NN) are also widely used in the literature due to their very high prediction performance [17]. The main disadvantage of neural networks is their black-box-like working characteristic.…”

“…A great variety of ANN architectures have been proposed and at least 50 different types are being explored in research for different applications [24,25]. Among those, Back propagation networks have quickly become the most widely encountered ANNs, particularly within the area of systems and control [17,26]. Many different resources are available in the literature for comprehensive explanations on neural networks.…”

Determination of Optimal Initial Weights of an Artificial Neural Network by Using the Harmony Search Algorithm: Application to Breakwater Armor Stones

“…Yam and Chow [16] proposed an algorithm based on least-squares methods to determine the optimal initial weights, showing that the algorithm can reduce the model's dependency on the initial weights. Recently, genetic algorithms have been applied to find the optimal initial weights of ANNs and to improve the model accuracy [17][18][19]. Ensemble methods have also been implemented to enhance the accuracy of the model.…”