• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.5
• /
• pp.55-60
• /
• 2021

We applied an artificial neural network (ANN) and evaluated surface roughness prediction in lateral milling using an endmill. The selected workpiece was AL6061-T4 to obtain data of surface roughness measurement based on the spindle speed, feed, and depth of cut. The Bayesian optimization algorithm was applied to the number of nodes and the learning rate of each hidden layer to optimize the neural network. Experimental results show that the neural network applied to optimize using the Expected Improvement(EI) algorithm showed the best performance. Additionally, the predicted values do not exactly match during the neural network evaluation; however, the predicted tendency does march. Moreover, it is found that the neural network can be used to predict the surface roughness in the milling of aluminum alloy.

• International conference on construction engineering and project management
• /
• 2005.10a
• /
• pp.913-916
• /
• 2005

This paper presents the development of Artificial Neural Network models for forecasting the cost and contract duration of school reconstruction projects to assist the planners' decision-making in the early stage of the projects. 132 schools reconstruction projects in central Taiwan, which received the most serious damage from the Chi-Chi Earthquake, were collected. The developed Artificial Neural Network prediction models demonstrate good prediction abilities with average error rates under 10% for school reconstruction projects. The analytical results indicate that the Artificial Neural Network model with back-propagation learning is a feasible method to produce accurate prediction results to assist planners' decision-making process.

• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.1
• /
• pp.101-107
• /
• 1997

Recently, as the raw water quality becomes to be polluted and the seasonal and local variation of water quality becomes to be severe, an exact control of coagulant dosing have been required in the water treat- ment plant. The amounts of coagulant is related to the raw water quality such as turbidity, alkalinity, water temperature, pH and edectrical conductivity. However the process of chemical reaction has not been clarified so far, so the dosing rate has been decided by jar-test, which is taken one or two hours. For the sake of this coagulant dosing control, fuzzy neural network to fuse fuzzy logic and neural network was proposed, and the scheme was applied to automatic determination of coagulant dosing rate. This controller can automatically identify the if-then rules and tune the membership functions by utilizing expert's cintrol data. It is shown that determination of coagulant dosing rate according to real time sensing of water quality is very effect.

• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.15-17
• /
• 2011

DVS 카메라는 인간의 눈을 모델링하여 만들어져서 화면의 변화에 반응하여 Address - Event - Representation 데이터를 생성하고 이 데이터는 jAER Viwer를 통해 확인할 수 있다. 이렇게 생성된 DVS 카메라의 데이터를 Spiking Neural Network의 입력으로 주기 위해 GPU를 이용한 Spiking Neural Network 시뮬레이터인 GPUSNN과 jAER 사이에 인터페이스가 필요하다. 이 인터페이스를 이용하면 GPUSNN을 통해 비전 알고리즘을 빠르고 효과적으로 Spiking Neural Network 시뮬레이션을 할 수 있을 것이다.

• Journal of Information Processing Systems
• /
• v.18 no.6
• /
• pp.755-762
• /
• 2022

The existing electrical engineering design method and the dynamic objective function in the application process of automatic control system fail to meet the unbounded condition, which affects the control tracking accuracy. In order to improve the tracking control accuracy, this paper studies the electrical engineering design method based on neural network and the application of automatic control system. This paper analyzes the structure and working mechanism of electrical engineering automation control system by an automation control model with main control objectives. Following the analysis, an optimal solution of controllability design and fault-tolerant control is figured out. The automatic control power coefficient is distributed based on an ideal control effect of system. According to the distribution results, an automatic control algorithm is based on neural network for accurate control. The experimental results show that the electrical automation control method based on neural network can significantly reduce the control following error to 3.62%, improve the accuracy of the electrical automation tracking control, thus meeting the actual production needs of electrical engineering automation control system.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.12
• /
• pp.120-129
• /
• 1995

This study introduces a tool wear monitoring technology in face milling operation comprised of an unsupervised neural network. The monitoring system employs two types of sensor signal such as cutting force and acceleration in sensory detection state. The RMS value and band frequency energy of the sensor signals are calculated for te input patterns of neural network. ART2 neural network, which is capable of self organizing without supervised learning, is used for clustering of tool wear states. The experimental results show that tool wear can be effectively detected under various cutting conditions without prior knowledge of cutting processes.

• Journal of the Korean Society for Precision Engineering
• /
• v.12 no.12
• /
• pp.100-108
• /
• 1995

The In-process minitoring of the chatter vibration is necessarily required to an automatic manufacturing system. In this study, we constructed a multi-sensing system using tool dynamoneter, accelerometer and AE(Acoustic Emission) sensor for a more credible detection of chatter vibration. And a new approach using a multiple neural network to extract the features of multi-sensor for the recognition chatter vibration is proposed. With the Back-propagation training process, the neural network memorize and classify the features of multi-sensor signals. As a result, it is shown by multiple neural network that the chatter vibration can be monitored accurately, and it can be widely used in practical unmanned system.

• Communications for Statistical Applications and Methods
• /
• v.31 no.1
• /
• pp.105-127
• /
• 2024

We propose recurrent neural network (RNN) methods for forecasting realized volatility (RV). The data are RVs of ten major stock price indices, four from the US, and six from the EU. Forecasts are made for relative ratio of adjacent RVs instead of the RV itself in order to avoid the out-of-scale issue. Forecasts of RV ratios distribution are first constructed from which those of RVs are computed which are shown to be better than forecasts constructed directly from RV. The apparent asymmetry of RV ratio is addressed by the Piecewise Min-max (PM) normalization. The serial dependence of the ratio data renders us to consider two architectures, long short-term memory (LSTM) and gated recurrent unit (GRU). The hyperparameters of LSTM and GRU are tuned by the nested cross validation. The RNN forecast with the PM normalization and ratio transformation is shown to outperform other forecasts by other RNN models and by benchmarking models of the AR model, the support vector machine (SVM), the deep neural network (DNN), and the convolutional neural network (CNN).

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.7
• /
• pp.1322-1331
• /
• 1992

The conventional neural networks are built without considering the underlying structure of the problems. Hence, they usually contain redundant weights and require excessive training time. A novel neural network structure is proposed for symmetric problems, which alleviate some of the aforementioned drawback of the conventional neural networks. This concept is expanded to that of the constrained neural network which may be applied to general structured problems. Because these neural networks can not be trained by the conventional training algorithm, which destroys the weight structure of the neural networks, a proper training algorithm is suggested. The illustrative examples are shown to demonstrate the applicability of the proposed idea.

• Journal of Digital Contents Society
• /
• v.18 no.5
• /
• pp.969-976
• /
• 2017

This paper proposes the learning method of an artificial neural network and a convolutional neural network using the WFSO algorithm developed as an optimization algorithm. Since the optimization algorithm searches based on a number of candidate solutions, it has a drawback in that it is generally slow, but it rarely falls into the local optimal solution and it is easy to parallelize. In addition, the artificial neural networks with non-differentiable activation functions can be trained and the structure and weights can be optimized at the same time. In this paper, we describe how to apply WFSO algorithm to artificial neural network learning and compare its performances with error back-propagation algorithm in multilayer artificial neural networks and convolutional neural networks.