• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 2003.10a
• /
• pp.137-142
• /
• 2003

A fundamental study for developing a system of fault diagnosis of a pump is performed by using neural network. The acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The signals were obtained in various driving frequencies in order to obtain many types of data from a limited number of pumps. The acoustic data in frequency domain were managed to multiples of real driving frequency with the aim of easy comparison. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer, Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. The results showed neural network trained by acoustic signals can be used as a simple method far a detection of machine malfunction or fault diagnosis.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.13 no.5
• /
• pp.81-86
• /
• 2004

A fundamental study for developing a system of fault diagnosis of a pump is performed by using neural network. The acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The signals were obtained in various driving frequencies in order to obtain many types of data from a limited number of pumps. The acoustic data in frequency domain were managed to multiples of real driving frequency with the aim of easy comparison. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer. Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. The results showed neural network trained by acoustic signals can be used as a simple method for a detection of machine malfuction or fault diagnosis.

• Journal of Mechanical Science and Technology
• /
• v.20 no.12
• /
• pp.2079-2086
• /
• 2006

A fundamental study for developing a fault diagnosis system of a pump is performed by using neural network. Acoustic signals were obtained and converted to frequency domain for normal products and artificially deformed products. The neural network model used in this study was 3-layer type composed of input, hidden, and output layer. The normalized amplitudes at the multiples of real driving frequency were chosen as units of input layer. And the codes of pump malfunctions were selected as units of output layer. Various sets of teach signals made from original data by eliminating some random cases were used in the training. The average errors were approximately proportional to the number of untaught data. Neural network trained by acoustic signals can detect malfunction or diagnose fault of a given machine from the results.

• The Journal of Korea Robotics Society
• /
• v.3 no.1
• /
• pp.9-15
• /
• 2008

Unlike robotic systems, humans excel at a variety of tasks by utilizing their intrinsic impedance, force sensation, and tactile contact clues. By examining human strategy in arm impedance control, we may be able to teach robotic manipulators human''s superior motor skills in contact tasks. This paper develops a novel method for estimating and predicting the human joint impedance using the electromyogram(EMG) signals and limb position measurements. The EMG signal is the summation of MUAPs (motor unit action potentials). Determination of the relationship between the EMG signals and joint stiffness is difficult, due to irregularities and uncertainties of the EMG signals. In this research, an artificial neural network(ANN) model was developed to model the relation between the EMG and joint stiffness. The proposed method estimates and predicts the multi joint stiffness without complex calculation and specialized apparatus. The feasibility of the developed model was confirmed by experiments and simulations.

• 전기의세계
• /
• v.29 no.7
• /
• pp.460-470
• /
• 1980

The design of a control unit for a playback-type industrial robot is studied. Implemented for the cylindrical-coordinate type industrial robot with 5 degrees of freedom, the control unit constructed for the study consists of (i) z-80 .mu.p-based .mu.-computer control system (ii) Teach-Box for work command, and (iii) various softwares for generating signals for servo driving unit and operating the robot as playback-type. Softwares are developed by using high level Basic Language and low level z-80 Assembly Language for ease of programming and speed of program execution. To show the effectiveness, and example is included.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.25 no.4
• /
• pp.271-280
• /
• 2016

Predicting cutting forces in machine tools is essential to productivity improvement and process control in the manufacturing field. Furthermore, milling machining is more complicated than turning machining. Therefore, several studies have been conducted previously to simulate milling forces; this study aims to simulate the cutting forces in milling machines using multi-layered neural networks. In the experiments, the number of layers in these networks was 3 and 4 and the number of neurons in the hidden layers was varied from 20 to 200. The root mean square errors of simulated cutting force components were obtained from taught and untaught data for the various neural networks. Results show that the error trends for untaught data were non-uniform because of the complex nature of the cutting force components, which was caused by different cutting factors and nonlinear characteristics coming into play. However, trends for taught data showed a very good coincidence.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.19 no.4
• /
• pp.54-63
• /
• 2011

An educational network system based on CAN protocol internal to a passenger ground vehicle has been developed. The developed network system has been applied to a commercial plug-in electrical vehicle and verified the educational applicability. To apply this in-vehicle network technology based on CAN, a suitable electric vehicle has been chosen and a CAN network structure has been designed, developed and manufactured. Since the commercial electric vehicle chosen as a test bed has its own proprietary electric network, we explain how the original electric network has been utilized and how the new network system has been designed. The developed network system on a real vehicle has been tested to show the applicability and the performance. Finally, the system has been applied at few classrooms to demonstrate how the in-vehicle network system works and to teach how to analyse the CAN signals. The developed system proven to be effective for educational purpose.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.14 no.5
• /
• pp.179-186
• /
• 2010

When a structure is damaged, its dynamic responses (natural frequency, acceleration, strain) are found to be changed. The ANN(Artificial Neural Network) damage-assesment method is that some measured dynamic signals from the structural changing dynamic responses are applied to ANN to assess the structural damage. Although there have been some studies on a certain typical cases so far, it is rare to find studies about the characteristics of the ANN damage-assesment method or about its applicability, its strength and weakness. So this study researches on the characteristics of ANN damage assesment method and on a problem in application of the various dynamic responses to ANN. What the ANN damage assessment method usually does in past researches is to teach an ANN by using some response signals obtained from damaged structures under one kind of excitations and to identify the locations and the extents of damage of same structures under the same excitations. However, the excitations inflicted on the structures are not always the same. Thus this study experiments whether a ANN which is trained using the same excitations is able to identify the damage when different excitations inflict. All response signals are obtained from experimental models.