• IEMEK Journal of Embedded Systems and Applications
• /
• v.16 no.1
• /
• pp.9-15
• /
• 2021

Recently, it is increasingly necessary to run high-end neural network applications with huge computation overhead on top of resource-constrained embedded systems, such as wearable devices. While the huge computational overhead can be alleviated by distributed neural networks running on multiple separate devices, existing distributed neural network techniques suffer from a large traffic between the devices; thus are very vulnerable to communication failures. These drawbacks make the distributed neural network techniques inapplicable to wearable devices, which are connected with each other through unstable and low data rate communication medium like human body communication. Therefore, in this paper, we propose a distributed neural network partitioning technique that is resilient to communication failures. Furthermore, we show that the proposed technique also improves the inference accuracy even in case of no communication failure, thanks to the improved network partitioning. We verify through comparative experiments with a real-life neural network application that the proposed technique outperforms the existing state-of-the-art distributed neural network technique in terms of accuracy and resiliency to communication failures.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1996.10a
• /
• pp.133-137
• /
• 1996

This paper presents a new approach to the design of neural control system using digital signal processors in order to improve the precision and robustness. Robotic manipulators have bevome increasingly important in the field of flexible automation. High speed and high-precision trajectory tracking arre indispensable capabilities for their versatile application. the need to meet demanding control requirement in increasingly complex dynamical control systems under sygnificant uncertainties leads toward design of implementing real time neural control to provide an enhanced motion control for robotic manipulators. In this control scheme the ntworks intrduced are neural nets with dynamic neurouns whose dynamics are distributed over all the network nodes. The nets are trained by the distributed dynamic are distributed over all the network nodes. The nets are trained by the distributed dynamic back propagation algorithm. The proposed neural network control scheme is simple in structure fast in computation and suitable for implementation of real-time control, Performance of the neural controller is illustrated by simulation and experimental results for a SCAEA robot.

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.430-438
• /
• 2023

The Modular Multilevel Converter (MMC) has emerged as a key component in HVDC systems due to its ability to efficiently transmit large amounts of power over long distances. In such systems, accurate estimation of the MMC capacitor voltage is of utmost importance for ensuring optimal system performance, stability, and reliability. Traditional methods for voltage estimation may face limitations in accuracy and robustness, prompting the need for innovative approaches. In this paper, we propose a novel distributed neural network observer specifically designed for MMC capacitor voltage estimation. Our observer harnesses the power of a multi-layer neural network architecture, which enables the observer to learn and adapt to the complex dynamics of the MMC system. By utilizing a distributed approach, we deploy multiple observers, each with its own set of neural network layers, to collectively estimate the capacitor voltage. This distributed configuration enhances the accuracy and robustness of the voltage estimation process. A crucial aspect of our observer's performance lies in the meticulous initialization of random weights within the neural network. This initialization process ensures that the observer starts with a solid foundation for efficient learning and accurate voltage estimation. The observer iteratively updates its weights based on the observed voltage and current values, continuously improving its estimation accuracy over time. The validity of proposed algorithm is verified by the result of estimated voltage at each observer in capacitor of MMC.

• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.120.2-120
• /
• 2002

In this paper auto-tuning scheme of weight function in the neural networks has been suggested by immune algorithm for nonlinear process. A number of structures of the neural networks are considered as learning methods for control system. A general view is provided that they are the special cases of either the membership functions or the modification of network structure in the neural networks. On the other hand, since the immune network system possesses a self organizing and distributed memory, it is thus adaptive to its external environment and allows a PDP (parallel distributed processing) network to complete patterns against the environmental situation. Also. It can provi..

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.953-958
• /
• 1993

We develop a neural network control algorithm for the ACS (Advanced Control System). The ACS is an extended version of the DCS (Distributed Control System) to which functions of fault detection and diagnosis and advanced control algorithms are added such as neural networks, fuzzy logics, and so on. In spite of its usefulness proven by computer simulations, the neural network control algorithm, as far as we know, has no tool which makes it applicable to process control. It is necessary that the neural network controller should be turned into the function code for its application to the ACS. So we develop a general method to implement the neural network control systems for the ACS. By simulations using the simulator for the boiler of 'Seoul fire power plant unit 4', the methodology proposed in this paper is validated to have the applicability to process control.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2003.05a
• /
• pp.473-476
• /
• 2003

Nowaday, Internet is doing the role of a large distributed information service tenter and various information and database servers managing it are in distributed network environment. However, the we have several difficulties in deciding the server to disposal input data depending on data properties. In this paper, we designed server mining mechanism and Intellectual data mining system architecture for the best efficiently dealing with input data pattern by using neural network among the various data in distributed environment. As a result, the new input data pattern could be operated after deciding the destination server according to dynamic binding method implemented by neural network. This mechanism can be applied Datawarehous, telecommunication and load pattern analysis, population census analysis and medical data analysis.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1999.10a
• /
• pp.113-118
• /
• 1999

This paper presents a new approach to the design of neural control system using digital signal processors in order to improve the precision and robustness. Robotic manipulators have become increasingly important n the field of flexible automation. High speed and high-precision trajectory tracking are indispensable capabilities for their versatile application. The need to meet demanding control requirement in increasingly complex dynamical control systems under significant uncertainties, leads toward design of intelligent manipulation robots. The TMS320C31 is used in implementing real time neural control to provide an enhanced motion control for robotic manipulators. In this control scheme, the networks introduced are neural nets with dynamic neurons, whose dynamics are distributed over all the network nodes. The nets are trained by the distributed dynamic back propagation algorithm. The proposed neural network control scheme is simple in structure, fast in computation, and suitable for implementation of real-time control. Performance of the neural controller is illustrated by simulation and experimental results for a SCARA robot.

• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2001.04a
• /
• pp.255-260
• /
• 2001

This paper presents a new approach to the design of neural control system using digital signal processors in order to improve the precision and robustness. Robotic manipulators have become increasingly important in the field of flexible automation. High speed and high-precision trajectory tracking are indispensable capabilities for their versatile application. The need to meet demanding control requirement in increasingly complex dynamical control systems under significant uncertainties, leads toward design of intelligent manipulation robots. The TMS320C31 is used in implementing real time neural control to provide an enhanced motion control for robotic manipulators. In this control scheme, the networks introduced are neural nets with dynamic neurons, whose dynamics are distributed over all the network nodes. The nets are trained by the distributed dynamic back propagation algorithm. The proposed neural network control scheme is simple in structure, fast in computation, and suitable for implementation of real-time control. Performance of the neural controller is illustrated by simulation and experimental results for a SCARA robot.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.45 no.4
• /
• pp.574-581
• /
• 1996

The neural network approach has been shown to be a general scheme for nonlinear dynamical system identification. Unfortunately the error surface of a Multilayer Neural Networks(MNN) that widely used is often highly complex. This is a disadvantage and potential traps may exist in the identification procedure. The objective of this paper is to identify a nonlinear dynamical systems based on Self-Organized Distributed Networks (SODN). The learning with the SODN is fast and precise. Such properties are caused from the local learning mechanism. Each local network learns only data in a subregion. This paper also discusses neural network as identifier of nonlinear dynamical systems. The structure of nonlinear system identification employs series-parallel model. The identification procedure is based on a discrete-time formulation. Through extensive simulation, SODN is shown to be effective for identification of nonlinear dynamical systems. (author). 13 refs., 7 figs., 2 tabs.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.3
• /
• pp.1-8
• /
• 1998

In this paper, we propose a Neural Call Admission Control (CAC) method using a Sparse Distributed Memory(SDM). CAC is a key technology of TM network traffic control. It should be adaptable to the rapid and various changes of the ATM network environment. conventional approach to the ATM CAC requires network analysis in all cases. So, the optimal implementation is said to be very difficult. Therefore, neural approach have recently been employed. However, it does not mett the adaptability requirements. because it requires additional learning data tables and learning phase during CAC operation. We have proposed a neural network CAC method based on SDM that is more actural than conventioal approach to apply it to CAC. We compared it with previous neural network CAC method. It provides CAC with good adaptability to manage changes. Experimenatal results show that it has rapid adaptability and stability without additional learning table or learning phase.