• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.45 no.3
• /
• pp.444-450
• /
• 1996

A digital hardware architecture for artificial neural network with learning capability is described in this paper. It is a modified hardware architecture known as HANNIBAL(Hardware Architecture for Neural Networks Implementing Back propagation Algorithm Learning). For implementing an efficient neural network hardware, we analyzed various type of multiplier which is major function block of neuro-processor cell. With this result, we design a efficient digital neural network hardware using serial/parallel multiplier, and test the operation. We also analyze the hardware efficiency with logic level simulation. (author). refs., figs., tabs.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.1
• /
• pp.58-66
• /
• 1992

This paper proposes a neuro-controller for position control of one-link flexible robot arm. Basically the controller consists of a multi-layer neural network and a conventional PD controller. Two controller are parallelly connected. Neural network is traind by the conventional error back propagation learning rules. During learning period, the weights of neural network are adjusted to minimize the position error between the desired hub angle and the actual one. Finally the effectiveness of the proposed approach will be demonstrated by computer simulation.

• The Transactions of the Korea Information Processing Society
• /
• v.5 no.11
• /
• pp.3010-3023
• /
• 1998

GA has a fast convergence speed in searching the one point around optimal value. But it's convergence time increase in searching the region around optimal value because it has no regional searching mechanism. BP has the tendency to converge the local minimum because it has global searching mechanism. To overcome these problems, a method in which a genetic algorithm and a back propagation are applied in turn is proposed in this paper. By using a genetic algorithm, we compute optimal synaptic strength and offset value. And then, these values are fed to the input of the back propagation. This proposed method is superior to each above method in improving the convergence speed.

• Journal of Power Electronics
• /
• v.8 no.4
• /
• pp.354-362
• /
• 2008

This paper presents neural load torque compensation method which is composed of a deadbeat load torque observer and gains compensation by a parameter estimator. As a result, the response of the PMSM (permanent magnet synchronous motor) obtains better precision position control. To reduce the noise effect, the post-filter is implemented by a MA (moving average) process. The parameter compensator with an RLSM (recursive least square method) parameter estimator is adopted to increase the performance of the load torque observer and main controller. The parameter estimator is combined with a high performance neural load torque observer to resolve problems. The neural network is trained in online phases and it is composed by a feed forward recall and error back-propagation training. During normal operation, the input-output response is sampled and the weighting value is trained multi-times by the error back-propagation method at each sample period to accommodate the possible variations in the parameters or load torque. As a result, the proposed control system has a robust and precise system against load torque and parameter variation. Stability and usefulness are verified by computer simulation and experiment.

• The Transactions of the Korean Institute of Electrical Engineers B
• /
• v.53 no.3
• /
• pp.188-195
• /
• 2004

This paper presents neural load torque observer that is used to deadbeat load torque observer and gain compensation by parameter estimator As a result, the response of the PMSM(permanent magnet synchronous motor) follows that nominal plant. The load torque compensation method is composed of a neural deadbeat observer To reduce the noise effect, the post-filter implemented by MA(moving average) process, is adopted. The parameter compensator with RLSM (recursive least square method) parameter estimator is adopted to increase the performance of the load torque observer and main controller The parameter estimator is combined with a high performance neural load torque observer to resolve the problems. The neural network is trained in on-line phases and it is composed by a feed forward recall and error back-propagation training. During the normal operation, the input-output response is sampled and the weighting value is trained multi-times by error back-propagation method at each sample period to accommodate the possible variations in the parameters or load torque. As a result, the proposed control system has a robust and precise system against the load torque and the Parameter variation. A stability and usefulness are verified by computer simulation and experiment.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.294-297
• /
• 2004

The purpose of this study was to develop landslide susceptibility analysis techniques using artificial neural networks and then to apply these to the selected study area of Janghung in Korea. We aimed to verify the effect of data selection on training sites. Landslide locations were identified from interpretation of satellite images and field survey data, and a spatial database of the topography, soil, forest, and land use was constructed. Thirteen landslide-related factors were extracted from the spatial database. Using these factors, landslide susceptibility was analyzed using an artificial neural network. The weights of each factor were determined by the back-propagation training method. Five different training datasets were applied to analyze and verify the effect of training. Then, the landslide susceptibility indices were calculated using the trained back-propagation weights and susceptibility maps were constructed from Geographic Information System (GIS) data for the five cases. The results of the landslide susceptibility maps were verified and compared using landslide location data. GIS data were used to efficiently analyze the large volume of data, and the artificial neural network proved to be an effective tool to analyze landslide susceptibility.

• International Journal of Concrete Structures and Materials
• /
• v.2 no.2
• /
• pp.91-98
• /
• 2008

Curved bridges are important components of a highway transportation network for connecting local roads and highways, but very few data have been collected in terms of their field performance. This paper presents two-years monitoring and system identification results of a curved concrete box-girder bridge, the West St. On-Ramp, under ambient traffic excitations. The authors permanently installed accelerometers on the bridge from the beginning of the bridge life. From the ambient vibration data sets collected over the two years, the element stiffness correction factors for the columns, the girder, and boundary springs were identified using the back-propagation neural network. The results showed that the element stiffness values were nearly 10% different from the initial design values. It was also observed that the traffic conditions heavily influence the dynamic characteristics of this curved bridge. Furthermore, a probability distribution model of the element stiffness was established for long-term monitoring and analysis of the bridge stiffness change.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.21 no.5
• /
• pp.828-834
• /
• 1997

The knowledge of material stress-strain behavior is an essential requirement for design and analysis of deformation processes. Empirical stress-strain relationship and constitutive equations describing material behavior during deformation are being widely used, despite suffering some drawbacks in terms of ease of development, accuracy and speed. In the present study, back-propagation neural networks are used to model and predict the flow stresses of a HSLA steel under conditions of constant strain, strain rate and temperature. The performance of the network model is comparedto those of statistical models on rate equations. Well-trained network model provides fast and accurate results, making it superior to statistical models.

• International Journal of Control, Automation, and Systems
• /
• v.2 no.2
• /
• pp.256-262
• /
• 2004

Conventionally, profile non-uniformity has been characterized by relying on approximated profile with angle or anisotropy. In this study, a new non-uniformity model for etch profile is presented by applying a discrete wavelet to the image obtained from a scanning electron microscopy (SEM). Prediction models for wavelet-transformed data are then constructed using a back-propagation neural network. The proposed method was applied to the data collected from the etching of tungsten material. Additionally, 7 experiments were conducted to obtain test data. Model performance was evaluated in terms of the average prediction accuracy (APA) and the best prediction accuracy (BPA). To take into account randomness in initial weights, two hundred models were generated for a given set of training factors. Behaviors of the APA and BPA were investigated as a function of training factors, including training tolerance, hidden neuron, initial weight distribution, and two slopes for bipolar sig-moid and linear function. For all variations in training factors, the APA was not consistent with the BPA. The prediction accuracy was optimized using three approaches, the best model based approach, the average model based approach and the combined model based approach. Despite the largest APA of the first approach, its BPA was smallest compared to the other two approaches.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.18 no.2
• /
• pp.170-177
• /
• 2009

The objective of this study is to evaluate an acoustic emission (AE) source characterization and fracture behavior of the SM45C steel by using back-propagation neural network (BPN). In previous research Ref. [8] about k-nearest neighbor classifier (k-NNC) continuity, we used K-means clustering method as an unsupervised learning method for obtaining multi-variate AE main data sets, such as AE counts, energy, amplitude, risetime, duration and counts to peak. Similarly, we applied k-NNC and BPN as a supervised learning method for obtaining multi-variate AE working data sets. According to the error of convergence for determinant criterion Wilk's ${\lambda}$, heuristic criteria D&B(Rij) and Tou values are discussed. As a result, in k-NNC before fracture signal is detected or when fracture signal is detected, showed that produce some empty classes in BPN. And we confirmed that could save trouble in AE signal processing if suitable error of convergence or acceptable encoding error give to BPN.