• Design & Manufacturing
• /
• v.15 no.3
• /
• pp.1-6
• /
• 2021

An artificial neural network model based on a deep learning algorithm is known to be more accurate than humans in image classification, but there is still a limit in the sense that there needs to be a lot of training data that can be called big data. Therefore, various techniques are being studied to build an artificial neural network model with high precision, even with small data. The transfer learning technique is assessed as an excellent alternative. As a result, the purpose of this study is to develop an artificial neural network system that can classify burr images of light guide plate products with 99% accuracy using transfer learning technique. Specifically, for the light guide plate product, 150 images of the normal product and the burr were taken at various angles, heights, positions, etc., respectively. Then, after the preprocessing of images such as thresholding and image augmentation, for a total of 3,300 images were generated. 2,970 images were separated for training, while the remaining 330 images were separated for model accuracy testing. For the transfer learning, a base model was developed using the NASNet-Large model that pre-trained 14 million ImageNet data. According to the final model accuracy test, the 99% accuracy in the image classification for training and test images was confirmed. Consequently, based on the results of this study, it is expected to help develop an integrated AI production management system by training not only the burr but also various defective images.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.49 no.3
• /
• pp.197-204
• /
• 2021

If a failure or an abnormal maneuver occurs during the flight test of a missile, the missile is deliberately self-destructed so as not to continue the flight. At this time, debris are produced and it is important to estimate the impact area in real-time whether it is out of the safety area. In this paper, we propose a method to estimate the debris dispersion area and falling time in real-time using a Fully-Connected Neural Network (FCNN). We applied the Unscented Transform (UT) to generate a large amount of training data. UT parameters were selected by comparing with Monte-Carlo (MC) simulation to secure reliability. Also, we analyzed the performance of the proposed method by comparing the estimation result of MC.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.6
• /
• pp.2128-2147
• /
• 2021

Cognitive radio systems are being implemented recently to tackle spectrum underutilization problems and aid efficient data traffic. Spectrum sensing is the crucial step in cognitive applications in which cognitive user detects the presence of primary user (PU) in a particular channel thereby switching to another channel for continuous transmission. In cognitive radio systems, the capacity to precisely identify the primary user's signal is essential to secondary user so as to use idle licensed spectrum. Based on the inherent capability, a new spectrum sensing technique is proposed in this paper to identify all types of primary user signals in a cognitive radio condition. Hence, a spectrum sensing algorithm using improved convolutional neural network and long short-term memory (CNN-LSTM) is presented. The principle used in our approach is simulated annealing that discovers reasonable number of neurons for each layer of a completely associated deep neural network to tackle the streamlining issue. The probability of detection is considered as the determining parameter to find the efficiency of the proposed algorithm. Experiments are carried under different signal to noise ratio to indicate better performance of the proposed algorithm. The PU signal will have an associated modulation format and hence identifying the presence of a modulation format itself establishes the presence of PU signal.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2356-2376
• /
• 2021

In this paper, we proposed a novel modulation recognition method based on quantum elephant herding algorithm (QEHA) evolving neural network under impulse noise environment. We use the adaptive weight myriad filter to preprocess the received digital modulation signals which passing through the impulsive noise channel, and then the instantaneous characteristics and high order cumulant features of digital modulation signals are extracted as classification feature set, finally, the BP neural network (BPNN) model as a classifier for automatic digital modulation recognition. Besides, based on the elephant herding optimization (EHO) algorithm and quantum computing mechanism, we design a quantum elephant herding algorithm (QEHA) to optimize the initial thresholds and weights of the BPNN, which solves the problem that traditional BPNN is easy into local minimum values and poor robustness. The experimental results prove that the adaptive weight myriad filter we used can remove the impulsive noise effectively, and the proposed QEHA-BPNN classifier has better recognition performance than other conventional pattern recognition classifiers. Compared with other global optimization algorithms, the QEHA designed in this paper has a faster convergence speed and higher convergence accuracy. Furthermore, the effect of symbol shape has been considered, which can satisfy the need for engineering.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.107-114
• /
• 2021

Recently artificial intelligence technology has been introduced in various fields and various machine learning models have been operated in various frameworks as academic interest has increased. However, these frameworks have different data formats, which lack interoperability, and to overcome this, the open neural network exchange format, ONNX, has been proposed. In this paper we describe how to transform multiple machine learning models to ONNX, and propose algorithms and inference systems that can determine machine learning techniques in an integrated ONNX format. Furthermore we compare the inference results of the models before and after the ONNX transformation, showing that there is no loss or performance degradation of the learning results between the ONNX transformation.

• Nuclear Engineering and Technology
• /
• v.54 no.8
• /
• pp.2859-2870
• /
• 2022

Because nuclear power plants (NPPs) are safety-critical infrastructure, it is essential to increase their safety and minimize risk. To reduce human error and support decision-making by operators, several artificial-intelligence-based diagnosis methods have been proposed. However, because of the nature of data-driven methods, conventional artificial intelligence requires large amount of measurement values to train and achieve enough diagnosis resolution. We propose a graph neural network (GNN) based accident diagnosis algorithm to achieve high diagnosis resolution with limited measurements. The proposed algorithm is trained with both the knowledge about physical correlation between components and measurement values. To validate the proposed methodology has a sufficiently high diagnostic resolution with limited measurement values, the diagnosis of multiple accidents was performed with limited measurement values and also, the performance was compared with convolution neural network (CNN). In case of the experiment that requires low diagnostic resolution, both CNN and GNN showed good results. However, for the tests that requires high diagnostic resolution, GNN greatly outperformed the CNN.

• Nuclear Engineering and Technology
• /
• v.54 no.1
• /
• pp.310-317
• /
• 2022

The mass attenuation coefficient is the primary physical parameter to model narrow beam gamma-ray attenuation. A new machine learning based approach is proposed to model gamma-ray shielding behavior of composites alternative to theoretical calculations. Two fuzzy logic algorithms and a neural network algorithm were trained and tested with different mixture ratios of vanadium slag/epoxy resin/antimony in the 0.05 MeV-2 MeV energy range. Two of the algorithms showed excellent agreement with testing data after optimizing adjustable parameters, with root mean squared error (RMSE) values down to 0.0001. Those results are remarkable because mass attenuation coefficients are often presented with four significant figures. Different training data sizes were tried to determine the least number of data points required to train sufficient models. Data set size more than 1000 is seen to be required to model in above 0.05 MeV energy. Below this energy, more data points with finer energy resolution might be required. Neuro-fuzzy models were three times faster to train than neural network models, while neural network models depicted low RMSE. Fuzzy logic algorithms are overlooked in complex function approximation, yet grid partitioned fuzzy algorithms showed excellent calculation efficiency and good convergence in predicting mass attenuation coefficient.

• Structural Engineering and Mechanics
• /
• v.83 no.3
• /
• pp.401-413
• /
• 2022

The collapse of civil infrastructure due to natural disasters results in financial losses and many casualties. In particular, the recent increase in earthquake activities has highlighted on the importance of assessing the seismic performance and predicting the seismic risk of a structure. However, the nonlinear behavior of a structure and the uncertainty in ground motion complicate the accurate seismic response prediction of a structure. Artificial intelligence can overcome these limitations to reasonably predict the nonlinear behavior of structures. In this study, a deep learning-based algorithm was developed to estimate the time-history seismic response of bridge structures. The proposed deep neural network was trained using structural and ground motion parameters. The performance of the seismic response prediction algorithm showed the similar phase and magnitude to those of the time-history analysis in a single-degree-of-freedom system that exhibits nonlinear behavior as a main structural element. Then, the proposed algorithm was expanded to predict the seismic response and fragility prediction of a bridge system. The proposed deep neural network reasonably predicted the nonlinear seismic behavior of piers and bearings for approximately 93% and 87% of the test dataset, respectively. The results of the study also demonstrated that the proposed algorithm can be utilized to assess the seismic fragility of bridge components and system.

• Current Optics and Photonics
• /
• v.6 no.5
• /
• pp.479-488
• /
• 2022

To account for the internal thermal effects of solid-state lasers, a method using a back propagation (BP) neural network integrated with a particle swarm optimization (PSO) algorithm is developed, which is a new wavefront distortion correction technique. In particular, by using a slab laser model, a series of fiber pumped sources are employed to form a controlled array to pump the gain medium, allowing the internal temperature field of the gain medium to be designed by altering the power of each pump source. Furthermore, the BP artificial neural network is employed to construct a nonlinear mapping relationship between the power matrix of the pump array and the thermally induced wavefront aberration. Lastly, the suppression of thermally induced wavefront distortion can be achieved by changing the power matrix of the pump array and obtaining the optimal pump light intensity distribution combined using the PSO algorithm. The minimal beam quality β can be obtained by optimally distributing the pumping light. Compared with the method of designing uniform pumping light into the gain medium, the theoretically computed single pass beam quality β value is optimized from 5.34 to 1.28. In this numerical analysis, experiments are conducted to validate the relationship between the thermally generated wavefront and certain pumping light distributions.

• Nuclear Engineering and Technology
• /
• v.54 no.3
• /
• pp.834-841
• /
• 2022

System thermal-hydraulic (STH) code is adopted for nuclear safety analysis. The critical flow model (CFM) is significant for the accuracy of STH simulation. To overcome the defects of current CFMs (low precision or long calculation time), a CFM based on a genetic neural network (GNN) has been developed in this work. To build a powerful model, besides the critical mass flux, the critical pressure and critical quality were also considered in this model, which was seldom considered before. Comparing with the traditional homogeneous equilibrium model (HEM) and the Moody model, the GNN model can predict the critical mass flux with a higher accuracy (approximately 80% of results are within the ±20% error limit); comparing with the Leung model and the Shannak model for critical pressure prediction, the GNN model achieved the best results (more than 80% prediction results within the ±20% error limit). For the critical quality, similar precision is achieved. The GNN-based CFM in this work is meaningful for the STH code CFM development.