• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.12
• /
• pp.48-55
• /
• 1997

A useful method to detect tool breakage suing neural network of cutting force signal is porposed and implemented in a basic cutting process. Cutting signal is gathered by tool dynamometer and normalized as a preprocessing. The cutting force signal level is continually monitored and compared with the predefined level. The neural network has been trained normalized sample data of the normal operation and cata-strophic tool failure using backpropagation learning process. The develop[ed system is verified to be very effective in real-time usage with minor modification in conventional cutting processes.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.1
• /
• pp.66-71
• /
• 2003

In the past, when there were few vehicles on the road, the T.O.D.(Time of Day) traffic signal worked very well. The T.O.D. signal operates on a preset signal cycling which cycles on the basis of the average number of average passenger cars in the memory device of an electric signal unit. Today, with increasing traffic and congested roads, the conventional traffic light creates startup-delay time and end lag time so that thirty to forty-five percent efficiency in traffic handling is lost, as well as adding to fuel costs. To solve this problem, this paper proposes a new concept of optimal green time algorithm, which reduces average vehicle waiting time while improving average vehicle speed using fuzzy rules and neural networks. Through computer simulation, this method has been proven to be much more efficient than fixed time interval signals. Fuzzy Neural Network will consistanly improve average waiting time, vehicle speed, and fuel consumption.

• Journal of Korea Multimedia Society
• /
• v.9 no.12
• /
• pp.1572-1579
• /
• 2006

An usual acoustic emission(AE) event has two widely characterized parameters in time domain, peak amplitude and event duration. But noise in AE measuring may disturb the signals with its parameters and aggrandize the signal incertitude. Experiment activity of detection of the nick inside of porcelain with AE was made and study on AE signal processing with statistic be presented in this paper in order to pick-up information expected from the signal with noise. Effort is concentrated on developing a novel arithmetic to improve extraction of the characteristic from stochastic signal and to enhance the voracity of detection. The main purpose discussed in this paper is to treat with signals on amplitudes with statistic mutuality and power density spectrum in frequency domain, and farther more to select samples for neural networks training by means of least-squares algorithm between real measuring signal and deterministic signals under laboratory condition. By seeking optimization with the algorithm, the parameters representing characteristic of the porcelain object are selected, while the stochastic interfere be weakened, then study for detection on neural networks is developed based on processing above.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.34S no.11
• /
• pp.148-155
• /
• 1997

Ths signal processing technqiue of FET type electrolyte sensors using the back propagation neural network was studied to reduce the interference effects of the different electrolytes. The FET-type electrolyte sensors, pH-ISFET, K-ISFET, and Ca-ISFET, were prepared to measure the pH, K, and Ca electrolytes. Neural network consisted of three layers was learned with 8 patterns and 9 patterns. The sensor output obtained with arbitrary concentrations was processed by the learned neural network. The errors obtained from calibration curve for pH, K, and Ca were .+-.0.039 pH, .+-.2.508 mmol/l, and .+-.1.807 mmol/l, respectively, without considering the interference effects. The errors of the network output for pH, K, and Ca were reduced to .+-.0.005 pH, .+-.0.436 mmol/l, and .+-.0.381 mmol/l in case of 9 patterns, respectively. the signal processing using the neural network can reduce the errors ofthe electrolyte sensor outputs caused by the interference effect, thereby providing effectiveness in the improvement of the sensor selectivity.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.271-276
• /
• 2003

In this study, we compared backpropagation neural network(BPNN) with probabilistic neural network(PNN) as shape recognition algorithm of welding flaws. For this purpose, variables are applied the same to two algorithm. Here, feature variable is composed of time domain signal itself and frequency domain signal itself, Through this process, we comfirmed advantages/disadvantages of two algorithms and identified application methods of two algorithms.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1020-1024
• /
• 2005

In this paper, an approach to dynamic systems control is addressed based on exploiting the potential features of the new nonlinear neural oscillator. Neural oscillators have recently enabled robots to exhibit natural dynamics using their robustness and entrainment properties. To technically accomplish this objective, the neural oscillator should be connected to the robot joints under the sensory feedback. This also requires the neural oscillator to adapt to the non-periodic nature of arbitrary input patterns. However, even in the most widely-used Matsuoka oscillator, when an unknown quasi-periodic or non-periodic signal is applied, its output signal is not always closely entrained. Therefore, current neural oscillators may not be applied to the precise control of the dynamic systems response. We illustrate the enhanced entrainment properties of the new neural oscillator by numerical simulation and show the possibility for implementation to control a variety of dynamic systems. It is verified that the oscillator can produce rhythmic signals for generating actuator signals which can be naturally modified by incorporating sensory feedback to adapt to outer circumstances.

• Nuclear Engineering and Technology
• /
• v.32 no.5
• /
• pp.485-494
• /
• 2000

In this work, a fuzzy neural network is used to estimate the relevant sensor signal using other sensor signals. Noise components in input signals into the fuzzy neural network are removed through the wavelet denoising technique . Principal component analysis (PCA) is used to reduce the dimension of an input space without losing a significant amount of information. A lower dimensional input space will also usually reduce the time necessary to train a fuzzy-neural network. Also, the principal component analysis makes easy the selection of the input signals into the fuzzy neural network. The fuzzy neural network parameters are optimized by two learning methods. A genetic algorithm is used to optimize the antecedent parameters of the fuzzy neural network and a least-squares algorithm is used to solve the consequent parameters. The proposed algorithm was verified through the application to the pressurizer water level and the hot-leg flowrate measurements in pressurized water reactors.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.5
• /
• pp.576-581
• /
• 2003

Speech signal has the features of speakers. In this paper, we propose the speaker identification system which use the incremental learning based on neural network. Recorded speech signal through the Mic is passed the end detection and is divided voiced signal and unvoiced signal. The extracted 12 order cpestrum are used the input data for neural network. Incremental learning is the learning algorithm that the learned weights are remembered and only the new weights, that is created as adding new speaker, are trained. The architecture of neural network is extended with the number of speakers. So, this system can learn without the restricted number of speakers.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1034-1038
• /
• 2020

In order to effectively process target recognition using radar, accurate signal information for the target is required. However, such a target signal is usually mixed with noise, and this part of the study is continuously carried out. Especially, image processing, target signal processing and target recognition for the target are examples. Since the field of target recognition is important from a military point of view, this paper carried out research on target recognition of aircraft using a tree-structured fuzzy neural networks. Fuzzy neural networks are learned by using reflected signal data for an aircraft to optimize the model, and then test data for the target are used for the optimized model to perform an experiment on target recognition. The effectiveness of the proposed method is verified by the simulation results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4664-4681
• /
• 2020

Modulation recognition (MR) plays a key role in cognitive radar, cognitive radio, and some other civilian and military fields. While existing methods can identify the signal modulation type by extracting the signal characteristics, the quality of feature extraction has a serious impact on the recognition results. In this paper, an end-to-end MR method based on long short-term memory (LSTM) and the gated recurrent unit (GRU) is put forward, which can directly predict the modulation type from a sampled signal. Additionally, the sliding window method is applied to fast-changing mixed-modulation signals for which the signal modulation type changes over time. The recognition accuracy on training datasets in different SNR ranges and the proportion of each modulation method in misclassified samples are analyzed, and it is found to be reasonable to select the evenly-distributed and full range of SNR data as the training data. With the improvement of the SNR, the recognition accuracy increases rapidly. When the length of the training dataset increases, the neural network recognition effect is better. The loss function value of the neural network decreases with the increase of the training dataset length, and then tends to be stable. Moreover, when the fast-changing period is less than 20ms, the error rate is as high as 50%. As the fast-changing period is increased to 30ms, the error rates of the GRU and LSTM neural networks are less than 5%.