With the automation of production lines in the manufacturing industry, the importance of real-time fault diagnosis of facility is increasing. In this paper, we propose a fault diagnosis algorithm of LM (Linear Motion)-guide based on deep learning using vibration signals. Generally, in order to guarantee the performance of the deep learning, it is necessary to have a sufficient amount of data, but in a manufacturing industry, it is often difficult to obtain enough data due to physical and time constraints. To solve this problem, we propose a convolutional neural networks (CNN) model based on transfer learning. In addition, the spectrogram image is input to the CNN to reflect the frequency characteristic of the vibration signals with time. The performance of fault diagnosis according to various load condition and transfer learning method was compared and evaluated by experiments. The results showed that the proposed algorithm exhibited an excellent performance.

The smart product market is growing year by year and is being used in many areas. There are various ways of interacting with smart products and users by inputting voice recognition, touch and finger movements. It is most important to detect an accurate hand region as a whole step to recognize hand movement. In this paper, we propose a method to detect accurate hand region in real time in various environments. A conventional method of detecting a hand region includes a method using depth information of a multi-sensor camera, a method of detecting a hand through machine learning, and a method of detecting a hand region using a color model. Among these methods, a method using a multi-sensor camera or a method using a machine learning requires a large amount of calculation and a high-performance PC is essential. Many computations are not suitable for embedded systems, and high-end PCs increase or decrease the price of smart products. The algorithm proposed in this paper detects the hand region using the color model, corrects the problems of the existing hand detection algorithm, and detects the accurate hand region based on various experimental environments.

Finite field operations have played an important role in error correcting codes and cryptosystems. Recently, the necessity of efficient computation processing is increasing for security in cyber physics systems. Therefore, efficient implementation of finite field arithmetics is more urgently needed. These operations include addition, multiplication, division and inversion. Addition is very simple and can be implemented with XOR operation. The others are somewhat more complicated than addition. Among these operations, multiplication is the most important, since time-consuming operations, such as exponentiation, division, and computing multiplicative inverse, can be performed through iterative multiplications. In this paper, we propose a multiplexer based parallel computation algorithm that performs Montgomery multiplication over finite field using redundant basis. Then we propose an efficient multiplexer based semi-systolic multiplier over finite field using redundant basis. The proposed multiplier has less area-time (AT) complexity than related multipliers. In detail, the AT complexity of the proposed multiplier is improved by approximately 19% and 65% compared to the multipliers of Kim-Han and Choi-Lee, respectively. Therefore, our multiplier is suitable for VLSI implementation and can be easily applied as the basic building block for various applications.

Spectral Beam Combining (SBC) is used for a high-power fiber laser in order to overcome the power limitation of single fiber laser. In SBC, several laser bwams with different wavelengths are combined to obtain a single-aperture beam by diffraction grating. The combining efficiency is dependent on a linewidth, beam quality and specific wavelength of each beam among others. In this paper, we consider the method of a wavelength monitoring and a feedback control of laser diodes used as seeds of laser beams to obtain optimum combining conditions. In order to measure the wavelengths of multi-beam, we use the high resolution camera and diffraction grating with 1,800l/mm. The experiment results show the possibility of feedback control of a current and temperature of multi-seed laser diodes to obtain optimum wavelengths for SBC.

Today's embedded software (SW) developments are mostly preceded by composing Software Requirement Specification (SRS). In particular, in the domain of weapon systems, it is essential to have a systematic method for the verification of the SW functionality. To be more specific, it is crucial to check if the SW functionality is implemented as described in SRS, so-called SW suitability verification. Unfortunately, existing static or dynamic SW testing methods are not sufficient to evaluate suitability with SRS since those testings only verify the robustness of the SW codes. In this paper, we propose an automatic embedded SW suitability verification framework which is based on a structured SRS. The major challenge in the automation of this verification framework is how to get rid of ambiguities in SRS. In order to overcome this challenge, we propose a structured SRS description framework and the supporting toolchain for that. We show how the proposed framework is applied to an actual SRS of a weapon system.

Multi-axis servo systems are widely used in various fields such as industiral systems for improving production efficiency, robotics and complex systems where many mechanical devices and sensor systems are connected. Such a servo system requires that the servo control technique to realize the synchronization of the drive shaft in the steady state and transient conditions and to control so as to follow the target track in order to improve product precision and production efficiency. In addition, embedded type hardware is required for smooth control of the entire multi-axis system. Therefore, this paper uses hardware based on FPGA which is widely used in digital signal processing field and various control system because hardware design change is easy and parallel processing is possible. In addition, Labview based servo motor control program was studied that can control the servo motor by ensuring the performance and flexibility of the FPGA and follow the target trajectory according to various speed processing and accurate timing synchronization.

Electric-hydraulic sever cylinders are used in many offshore applications such as wind energy farms, solar farms and plants. Jack-up barges are often used for these offshore system operations. Jack-up barge control is up/down by hydraulic cylinder position control. Working in harsh environments can lead to changes in internal parameters. This nonlinearity makes precise control difficult. In order to overcome the problems, we proposed a method of unknown-parameter estimation algorithm based on measurements obtained by system. In this paper, we employee Unscented Kalman filter (UKF) to estimate states and unknown-parameter from augmented nonlinear equation. Performance of estimation results is verified in simulation on an environments of Matlab. The estimation results of the state and unknown-parameter show that the estimation error of unknown-parameter is reduced according to decreasing the state estimation error.