JICE 2016 February

JICE February 2016 academic PDFs

Showing 1–8 of 11 results

  • Design and Implementation of a Life Test System for the Train Driver Controller


    Abstract: The train driver controller is a main electric appliance for the train speed controlling and
    braking. Its reliability relates directly with the driving safety. The existing life-span test system of the
    train driver controller can only detect the mechanical life-span. A new life-span test system is
    developed which can detect not only the mechanical life-span, but also the life-span of the electrical components such as the internal cam contacts, potentiometers and so on. The new system is based on Labview. The modular design is applied and the system reliability is improved. Taking advantage ofLabview, it realizes more precious timing. The master-slave mode is applied to the network architecture of the system so as to test on multiple train driver controllers at the same time. Therefore the testing cost is reduced. The experiments show that the new life-span test system is an efficient workable platform which improves the productivity, reliability and maintainability of the train driver controller.
    Keywords: Train driver controller; Life-span test system; Modular design; Time division multipiexing

  • Design of an Intelligent Housekeeping Robot Based on IOT


    Abstract: This project has developed an IOT based indoor mobile robot, which is used for the
    housekeeping service and called as “smart housekeeper”. The robot is equipped with the crawler
    chassis structure and the head lifting machinery. It applies Cortex-M4 as the main controller, and
    communicates with the outer by WiFi. A smart mobile phone is used as its head. People can operate the robot remotely by another smart mobile phone at any time. It can realize remote video searching, home appliance control, and indoor security. The experiment shows that it works well with all the functions.
    Keywords: Housekeeping Robot; WiFi; Home Appliances Control; Video Transmission; Gas

  • The Application of a Driving Circuit Based on 1ED020I12-FTA in PMSM


    Abstract: A new driving circuit based on the IGBT driving chip 1ED020I12-FTA is designed to drive the controller of the high power brushless DC motor in this article. The article has introduced overall design, the driving circuit and the experiments. The experiment results show that the driving circuit is able to drive PMSM motor very well, and it works well with good anti-disturbance, desaturation, electromagnetic isolation, overcurrent and overvoltage protection, Miller active clamp, and so on.
    Keywords: high power driving; H bridge circuit; DC motor; pulse width modulation

  • Application of A* Algorithm and Its Optimization Method


    Abstract: Nowadays, the traffic congestion is becoming more and more serious. It is urgent to find a path planning algorithm with high efficiency. As a heuristic algorithm, A* algorithm can solve the
    problem of path planning with high efficiency, and the design of heuristic function is particularly
    important. By analyzing the problems of route planning, some improvements have been made in this paper: firstly, the evaluation function with two elements of distance and direction are considered; through the process of normalization, the problem of unified unit has been solved; secondly, use the smallest heap spatial to load the node information dynamically, and reduce the memory usage space.
    Keywords: Heuristic algorithm, A* algorithm, cost function, smallest heap

  • Novel Design of a Wheelchair with Stair Climbing Capabilities


    Abstract: Stair climbing wheelchairs were created to help disabled people overcome one of the most common architectural barrier, stairs. Many types of devices have been developed using tracked, leg, leg-wheel and hybrid wheels to climb stairs but they are expensive, thus, out of the reach of the neediest. This paper presents a stair climbing wheelchair with four “X”-shaped wheel that uses its legs to climb and descend stairs. This mechanism maintains contact with the stairs during climbing activity to perform better at the climbing task. The seat of the wheelchair provides 1 DOF so that the inclination angle can be changed in order to correct the position of the center of gravity to be close to the center of the supporting polygon. An inertial measurement unit (IMU) sensor is used to detect the angle of the seat in relation to the ground and by using a motor utilizing PID control, automatically balance the seat in the horizontal position. In order to climb stairs smoothly, the angular position of the wheels should be the same, thus a PD control was implemented to control the position of the wheel so that they will be synchronized, therefore, capable of performing the climbing task at the same time and at the same position. Simulation and experimental results demonstrate the effectiveness of this mechanism and wheelchair.
    Keywords: Disabled; stair; stairclimber; wheel-leg mechanism; wheelchair;

  • Control and Communication of a Multi-motor System based on LAN


    Abstract: This paper establishes a multi-motor control system based on the local area network. It
    introduces the control strategy and the master-slave network structure. It analyzes both the advantage and disadvantage of the traditional communication modes RS-422 and CAN. And based on the analysis, the paper puts forward a full-duplex communication method which combines the advantages of both RS-422 and CAN to achieve the network control for the multi-motor system.
    Keywords: multi motor; master-slave network structure; LAN control; full duplex bus communication

  • Emergence of Proto-Communication using Action Primitives Symbolized in Recurrent Q-Learning Agents


    Abstract: In this paper, we suppose the gesture theory that is one of the theories on the origin of
    language, which tries to establish that the speech originated from gestures. Based on the theory, we assume that “actions” having some purposes can be used as “symbols” in the communication through a learning process. The purpose of this study is to clarify what abilities of agents are necessary to acquire usages of the actions as the symbols. To achieve the purpose, we adopt a collision avoidance game and recurrent Q-learning (RQL) agents as the game players. Our simulations showed that the RQL agents can emerge a proto-communication to avoid collision with opponent by using visual information that the opponent turns its own eye away from the agent through the learning process. Further, we found that the RQL agents also obtain a rotational behavior to avoid collision by expanding the maximum number of learning iteration.
    Keywords: Collision Avoidance Game; Emergence of Proto-Communication; Neural Q-Learning
    (NQL) Agents; Recurrent Q-Learning (RQL) Agents; Symbolization of Action Primitives

  • Parameter Optimization of the SVM for Big Data


    Abstract:The traditional SVM parameter optimization use a wide range of traversal algorithm or some intelligent iterative algorithm, generally need to consume great deal of time, it is not applicable to optimization parameters of big data sets .To get around this ,This paper presents a strategy of stepwise optimize parameters based on the contour plots of cross-validation accuracy. Generate 25 parameter combinations uniformly, output the contour plots of cross-validation accuracy, then narrowing the optimal region of the parameters, proceeding stepwise optimizing parameter, until the optimal parameters were found. Finally, use a 13910*128 data set to verify the algorithm, compare with the traditional grid search algorithm, the new method not only greatly shorten the time of SVM parameters optimization, and it can find the better parameter than the traditional methods. This paper provides an effective solution to optimize SVM parameters especially for large data.
    Keywords: support vector machine, SVM , parameter optimization , big data