• Journal of Sensor Science and Technology
• /
• v.31 no.2
• /
• pp.96-101
• /
• 2022

As the elderly population gradually increases, the risk of fatal fall accidents among the elderly is increasing. One way to cope with a fall accident is to determine the fall direction before impact using a wearable inertial measurement unit (IMU). In this context, a previous study proposed a method of classifying fall directions using a support vector machine with sensor velocity, acceleration, and tilt angle as input parameters. However, in this method, the IMU signals are processed through several processes, including a Kalman filter and the integration of acceleration, which involves a large amount of computation and error factors. Therefore, this paper proposes a machine learning-based method that classifies the fall direction before impact using IMU raw signals rather than processed data. In this study, we investigated the effects of the following two factors on the classification performance: (1) the usage of processed/raw signals and (2) the selection of machine learning techniques. First, as a result of comparing the processed/raw signals, the difference in sensitivities between the two methods was within 5%, indicating an equivalent level of classification performance. Second, as a result of comparing six machine learning techniques, K-nearest neighbor and naive Bayes exhibited excellent performance with a sensitivity of 86.0% and 84.1%, respectively.

• International Journal of Precision Engineering and Manufacturing
• /
• v.7 no.1
• /
• pp.18-23
• /
• 2006

Cutting by a high speed laser cutting machine is one of most effective technologies to improve productivity. This paper has presented the cutting characteristics and optimal cutting conditions in a high speed feeding type laser cutting machine by using Tacuchi method in the design of experiment. An L9(34) orthogonal array is adopted to study the effect of adjustment parameters. The adjustment parameters consist of cutting speed, laser power, laser output duty and assistant gas pressure. The surface roughness of sheet metal is regarded as a quality feature. Analysis of variance is performed in order to evaluate the effect of adjustment parameters on the quality feature of laser cutting process.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.25 no.9
• /
• pp.1359-1367
• /
• 2001

Improvement of machine tool accuracy is an essential part of quality control in manufacturing process. Among of all the errors of a particular machine tool, the thermal errors of the spindle have a notably significant effect on machining accuracy and have a direct influence upon both the surface finish and geometric shape of the finished workpiece. Therefore, this paper proposed new measurement method for thermal errors of the spindle in machine tools. The thermal errors are measured by a ball bar system instead of capacitance sensor system. The novel measurement method using ball bar system is more efficient, easier to use than conventional measurement system. And also the ball bar system is possible to measure both geometric errors and thermal errors at the same time.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.2 no.1
• /
• pp.75-84
• /
• 2003

In this paper, a new nano/micro-mechanical processing test machine was developed. This new test machine, which is based on the principle of the scanning force controlled probe microscope, can realize nano/micro-mechanical machining and in-process profile measurement. Experimental results of nano/micro indentation and scratching show that the controllable cutting depth of the test machine can be controlled by PZT actuator. Profile measurement of the machined surface has also been performed by using the test machine and a conventional AFM(Atomic Force Microscopy). A good agreement of the two measurement results have been achieved.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.575-579
• /
• 2005

In this paper, the development of an IMM(Injection Molding Machine) controller is discussed. Presently, the Mold Close and Open Control Method of a toggle-type IMM is open-loop control. Through the development, a PC based control system was built instead of an existing controller and a closed-loop control replaced the previous control method by using PC based PLC. To control the nonlinear system of toggle type clamping unit, a fuzzy PI control algorithm was selected and it was programmed by an IL(Instruction List) and a LD(Ladder Diagram) on a PC based PLC. The application of fuzzy algorithm as the control method was also considered to change a control object like a mold replacement or an additional apparatus. For the development of an IMM controller, PC based PLC of PCI card type, distributed I/O modules with CANopen and Industrial PC and HMI (Human Machine Interface) software were used.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1922-1927
• /
• 2005

This paper describes the mechanism of a new biped machine capable of doing human-robot cooperation work. The biped machine, WABIAN-2 is made of two seven degrees of freedom (DOF) legs, a two DOF waist and no DOF trunk. Its leg system consists of two three DOF ankles, two one DOF knees and two three DOF hips to deal with various walk motions. Its height is about 1.2[m], and its weight is 40[kg]. It is designed with large movable range as a human. Also, a knee stretch walk pattern generation for the biped machine to perform natural walk like a human is discussed in this paper. Its leg motion is compensated by using the motion of its waist. Basic knee stretch walk experiments using WABIAN-2 are conducted on the plane, and the validity of its mechanism and walk pattern generator is verified.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.9
• /
• pp.2358-2367
• /
• 1994

This paper presents techniques for evaluation and compensation of total measuring errors in a commercial CMM. The probe errors as well as the machine geometric errors are assessed from probing of the mechanical artefacts such as shpere, step, and rings. For the error compensation, the integrated volumetric error equations are considered, including the probe error adn the machine geometric error. The error compensation is performed on the absolute scale coordinate system, in order to overcome the redundant degree of freedom in the CMM with multi-axis probe. A interface box and corresponding software driver are developed for data intercepting/correction between the machine controller and machine, thus the volumetric errors can be compensated in real time with minimum interference to the operating software and hardware of a commercial CMM. The developed system applied to a practical CMM installed on the shop floor, and demonstrated its performance.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.12
• /
• pp.2899-2908
• /
• 2000

Methodology of volumetric error identification is presented to improve the accuracy of NC machine tools by using a reference artifact and a touch trigger probe. Homogeneous transformation matrix and kinematic chain are used for modeling the geometric and thermal errors of a three-axis vertical machining center. The reference artifact is designed and fabricated to identify the model parameters by machine tool metrology. Parameters in the error model are able to be identified and updated by direct measurement of the reference artifact on the machine tool under the actual conditions which include the thermal interactions of error sources. The proposed method can speed up and simplify volumetric error identification processes.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2006.05a
• /
• pp.281-282
• /
• 2006

Tension control performance is very important in high-speed printing machine. One of the major factors that effect to tension control performance is the process of roll changing. Even if the turret arm moves during roll changing process and the span length of the unwinding system varies, it is customary to neglect it in motion and tension control and to consider it as a disturbance. In this paper, its effect is modeled nonlinearly and compared with linear model, and an effect of an infeeder dancer is analyzed under the condition with no unwinder dancer. We verify the performance of the proposed method via simulation in the high-speed printing machine.

• Proceedings of the KIPE Conference
• /
• 2005.07a
• /
• pp.479-482
• /
• 2005

본 연구는 알루미늄 단조 라인의 가열로 컨베이어에 적용된 6관절 이송용 로봇에 Machine Vision System을 구축 한 것으로 이송용 로봇이 작업 대상물을 적재하기 위한 위치정보를 획득하고 재처리하여 로봇 컨트롤러에 제공하는 비주얼가이던스 기법을 연구하여 이를 적용하였다. 적용된 Machine Vision System이 실제 구동에 있어서 안정함을 확인하였다. Machine Vision System에 적용된 CCD 센서로는 Sony사의 XC-HR50이 적용되었으며 Frame Grabber는 Matrox Meter II 카드가 적용되었다. Machine Vision System 제어기로는 범용PC(2.4Ghz, Windows 2000)를 사용하였으며 제어Software는 Microsoft 사의 Visual Basic 6.0 version을 사용하였다.