Design and Implementation of a Flexible Manufacturing Control System Using Neural Network

Design and implementation of a sequential controller based on the concept of artificial neural networks for a flexible manufacturing system are presented. The recurrent neural network (RNN) type is used for such a purpose. Contrary to the programmable controller, an RNN-based sequential controller is based on a definite mathematical model rather than depending on experience and trial and error techniques. The proposed controller is also more flexible because it is not limited by the restrictions of the finite state automata theory. Adequate guidelines of how to construct an RNN-based sequential controller are presented. These guidelines are applied to different case studies. The proposed controller is tested by simulations and real-time experiments. These tests prove the successfulness of the proposed controller performances. Theoretical as well as experimental results are presented and discussed indicating that the proposed design procedure using Elman's RNN can be effective in designing a sequential controller for event-based type manufacturing systems. In addition, the simulation results assure the effectiveness of the proposed controller to outperform the effect of noisy inputs.     

Structural Characterization of Different Asphaltenes of Kuwaiti Origin

Asphaltenes obtained by precipitation from crude Kuwaiti oils have been analyzed by proton magnetic resonance (¹H-NMR), carbon-13 nuclear magnetic resonance (¹³C-NMR) and Infrared (IR) spectral techniques. The molecular weight and elemental analysis were also determined. These combined analytical data were used for the characterization of these Kuwaiti oils. The asphaltenes molecular weights range from approximately 4200-6500 with an H/C ratio of 0.91-1.1 with an average 45-71% aromatic carbons. The average side chain length was of 4-6 carbons. It can also be concluded that the asphaltenes under investigation contain 5-9 sets of condensed aromatic rings joined together by bridges of alkyl chains or other hetero atoms and the average number of each of these sets of condensed aromatic rings is nearly 7. There are a number of alicyclic rings and condensed alicyclic rings in asphaltene. The IR spectra showed main molecular groups including OH, NH, SH, C=O and aliphatic and aromatic C-H's.     

Recognizing arabic handwritten characters using deep learning and genetic algorithms

Automated techniques for Arabic content recognition are at a beginning period contrasted with their partners for the Latin and Chinese contents recognition. There is a bulk of handwritten Arabic archives available in libraries, data centers, historical centers, and workplaces. Digitization of these documents facilitates (1) to preserve and transfer the country’s history electronically, (2) to save the physical storage space, (3) to proper handling of the documents, and (4) to enhance the retrieval of information through the Internet and other mediums. Arabic handwritten character recognition (AHCR) systems face several challenges including the unlimited variations in human handwriting and the leakage of large and public databases. In the current study, the segmentation and recognition phases are addressed. The text segmentation challenges and a set of solutions for each challenge are presented. The convolutional neural network (CNN), deep learning approach, is used in the recognition phase. The usage of CNN leads to significant improvements across different machine learning classification algorithms. It facilitates the automatic feature extraction of images. 14 different native CNN architectures are proposed after a set of try-and-error trials. They are trained and tested on the HMBD database that contains 54,115 of the handwritten Arabic characters. Experiments are performed on the native CNN architectures and the best-reported testing accuracy is 91.96%. A transfer learning (TF) and genetic algorithm (GA) approach named “HMB-AHCR-DLGA” is suggested to optimize the training parameters and hyperparameters in the recognition phase. The pre-trained CNN models (VGG16, VGG19, and MobileNetV2) are used in the later approach. Five optimization experiments are performed and the best combinations are reported. The highest reported testing accuracy is 92.88%.

     

Effect of matrix/reinforcement particle size ratio (PSR) on the mechanical properties of extruded Al–SiC composites

This paper studied the combined effects of matrix-to-reinforcement particle size ratio (PSR) and SiC volume fraction on the mechanical properties of extruded Al–SiC composites. A powder metallurgy technique (PM) of cold pressing at 500 MPa followed by hot extrusion at 580 °C was adopted to produce Al/SiC composite. Aluminum powder of size 60 μm and silicon carbide with different sizes, i.e., 50, 20, and 8 μm, were used. Three different volume fractions of SiC were employed, i.e., 5, 10, and 15 %, for each investigated size using a constant extrusion ratio of 14.36. The effect of matrix-to-reinforcement PSR on the reinforcement spatial distribution, fabricability, and resulting mechanical properties of a PM-processed Al/SiC composite were investigated. It has been shown that small ratio between matrix to reinforcement particle size resulted in more uniform distribution of the SiC particles in the matrix. As the PSR increases, the agglomerations and voids increase and the reinforcement particulates seem to have nonuniform distribution. In addition, the agglomerations increased as the volume fraction of the SiC increased. It has also been shown that homogenous distribution of the SiC particles resulted in higher yield strength, ultimate tensile strength, and elongation. Yield strength and ultimate tensile strength of the composite reinforced by PSR (1.2) are higher than those of composite reinforced by PSR (7.5), while the elongation shows opposite trend with yield strength and ultimate tensile strength.     

Neural network based design of fault-tolerant controllers for automated sequential manufacturing systems

This paper presents a novel application of recurrent neural network (RRN) to fault-tolerant control (FTC) of automated sequential manufacturing systems (ASMS) subject to sensor faults. Two RRNs are employed: the first one acts as an I/O relations recognizer and is able to detect faulty sensors and the latter is used as an inverse model of the AMSM to compute the desired control action in a faulty case according to nominal specifications. The learning process of these networks is carried out based on training data generated from the healthy manufacturing system controlled by a programmable logic controller (PLC). Design of the proposed fault-tolerant control system (FTCS) scheme is based on utilizing the two RNNs, a reconfigurable controller and a fault decision subsystem. The design procedure of the proposed FTCS is introduced. The proposed FTCS has been implemented and tested experimentally for a benchmark industrial ASMS subject to single or multiple faulty sensors. Experimental results show the effectiveness of the procedure for a real simple plant. In addition, the results prove these features of the proposed FTCS: (a) effectively improving the faulty control system behaviors, (b) accomplishing its proper functionality in handling single and multiple sensor faults, (c) identifying the sensor faults, and (d) being advantageous in reducing the complexity of the hardware redundancy.     

Metaheuristic Optimization of Time Series Models for Predicting NetworksTraffic

Traffic prediction of wireless networks attracted many researchers and practitioners during the past decades. However, wireless traffic frequently exhibits strong nonlinearities and complicated patterns, which makes it challenging to be predicted accurately. Many of the existing approaches for predicting wireless network traffic are unable to produce accurate predictions because they lack the ability to describe the dynamic spatial-temporal correlations of wireless network traffic data. In this paper, we proposed a novel meta-heuristic optimization approach based on fitness grey wolf and dipper throated optimization algorithms for boosting the prediction accuracy of traffic volume. The proposed algorithm is employed to optimize the hyper-parameters of long short-term memory (LSTM) network as an efficient time series modeling approach which is widely used in sequence prediction tasks. To prove the superiority of the proposed algorithm, four other optimization algorithms were employed to optimize LSTM, and the results were compared. The evaluation results confirmed the effectiveness of the proposed approach in predicting the traffic of wireless networks accurately. On the other hand, a statistical analysis is performed to emphasize the stability of the proposed approach.     

Network Intrusion Detection Based on Feature Selection and Hybrid Metaheuristic Optimization

Applications of internet-of-things (IoT) are increasingly being used in many facets of our daily life, which results in an enormous volume of data. Cloud computing and fog computing, two of the most common technologies used in IoT applications, have led to major security concerns. Cyberattacks are on the rise as a result of the usage of these technologies since present security measures are insufficient. Several artificial intelligence (AI) based security solutions, such as intrusion detection systems (IDS), have been proposed in recent years. Intelligent technologies that require data preprocessing and machine learning algorithm-performance augmentation require the use of feature selection (FS) techniques to increase classification accuracy by minimizing the number of features selected. On the other hand, metaheuristic optimization algorithms have been widely used in feature selection in recent decades. In this paper, we proposed a hybrid optimization algorithm for feature selection in IDS. The proposed algorithm is based on grey wolf (GW), and dipper throated optimization (DTO) algorithms and is referred to as GWDTO. The proposed algorithm has a better balance between the exploration and exploitation steps of the optimization process and thus could achieve better performance. On the employed IoT-IDS dataset, the performance of the proposed GWDTO algorithm was assessed using a set of evaluation metrics and compared to other optimization approaches in the literature to validate its superiority. In addition, a statistical analysis is performed to assess the stability and effectiveness of the proposed approach. Experimental results confirmed the superiority of the proposed approach in boosting the classification accuracy of the intrusion in IoT-based networks.     

Optimization of Electrocardiogram Classification Using Dipper Throated Algorithm and Differential Evolution

Electrocardiogram (ECG) signal is a measure of the heart’s electrical activity. Recently, ECG detection and classification have benefited from the use of computer-aided systems by cardiologists. The goal of this paper is to improve the accuracy of ECG classification by combining the Dipper Throated Optimization (DTO) and Differential Evolution Algorithm (DEA) into a unified algorithm to optimize the hyperparameters of neural network (NN) for boosting the ECG classification accuracy. In addition, we proposed a new feature selection method for selecting the significant feature that can improve the overall performance. To prove the superiority of the proposed approach, several experiments were conducted to compare the results achieved by the proposed approach and other competing approaches. Moreover, statistical analysis is performed to study the significance and stability of the proposed approach using Wilcoxon and ANOVA tests. Experimental results confirmed the superiority and effectiveness of the proposed approach. The classification accuracy achieved by the proposed approach is (99.98%).