Advanced Materials Research Vols. 341-342

Abstract: Study the retrieval algorithm based on shape feature and based on color features of image retrieval, to improve the accuracy of image retrieval, and to get results consisting with the shape feature and color feature ,this paper proposed new algorithm comprehensivly utilizing the two search algorithms. Through the image retrieval results show, new algorithm obtain results better than two algorithms, and can improve the retrieval precision.

Abstract: One of the most important application these days in Pattern Recognition (PR) is Optical Character recognition (OCR) which is a system used to convert scanned printed or handwritten image files into machine readable and editable format such as text documents. The main motivation behind this study is to build an OCR system for offline machine-printed Turkish characters to convert any image file into a readable and editable format. This OCR system started from preprocessing step to convert the image file into a binary format with less noise to be ready for recognition. The preprocessing step includes digitization, binarization, thresholding, and noise removal. Next, horizontal projection method is used for line detection and word allocation and 8-connected neighbors’ schema is used to extract characters as a set of connected components. Then, the Template matching method is utilized to implement the matching process between the segmented characters and the template set stored in OCR database in order to recognize the text. Unlike other approaches, template matching takes shorter time and does not require sample training but it is not able to recognize some letters with similar shape or combined letters, for this reason, this OCR system combines both the template matching and the size feature of the segmented characters to achieve accurate results. Finally, upon a successful implementation of the OCR, the recognized patterns are displayed in notepad as readable and editable text. The Turkish machine-printed database consists of a list of 630 names of cities in Turkey written by using Arial font with different sizes in uppercase, lowercase and capitalizes the first character for each word. The proposed OCR’s result show that the accuracy of the system is from 96% to 100%.

Abstract: For a cooperation imaging tracking system consisting of multiple moving platforms, time synchronization among these platforms was a critical demand. Based on the study of the hardware time model, the software Scheduling model, and data interaction & fusion process, a novel time synchronization method modified from RBS protocol was proposed. In the proposed method, firstly each platform used hardware to count the accurate sending period of the centre fusion node. Then the time error was extracted in each platform locally. Finally the extracted time error was used in the software time model to accomplish the time synchronization. The implementation structure and the precision of the proposed synchronization method were given in the paper.

Abstract: The project team has completed some research work in the earlier period. In this paper, the present mainstream intelligent network video monitoring system is compared and analyzed in details. Also, in accordance with the advantages and disadvantages of the multiple system architectures, a type of distributed system architecture is designed preliminarily. Thus, with regard to this architecture, the project team conducts a detailed design, segment many functional modules, puts forward specific design and implementation plans, and ultimately completes the construction of the model machine of the whole system.

Abstract: The objective of this paper is to analyze the closing time of fuel injector needle in electronic fuel injection system. The dynamics model and hydraulic simulation in AMESim software help to find the three critical parameters and the relationships between these three parameters and the needle closing time. Results show three directions to reduce the closing time of injector needle to meet the system requirements.

Abstract: In the paper, a computer-supported model of the innovation design is presented, which is based on the synergy of modular function deployment (MFD), theory of inventive problem solving (TIPS, TRIZ) and case-based reasoning (CBR) to assist designer to engage in modularized product design. This approach involves gathering all relevant information about the customer voice and applying this information to drive the design of products or modules. So, it is starting from the MFD-Diagrams and continuing through the technical contradictions matrix in TRIZ during the conceptual design stage of new modules or parts. A CBR system is then adopted to quickly search some similar design cases for the references of inventive problem solving. Last, two reasoning mechanism are fabricated based on Protege and JESS expert tool, and a particular case of bicycle part design is studied through the use of knowledge-based prototype system to prove the effectiveness/efficiency of the computer-supported model. However, it will greatly enhance the competitive capability of companies trying to rapid development of the innovation design.

Abstract: CNC machine tools, it is not only in aerospace, manufacturing, military and other fields are widely used, but also into cars, machine tools and other civilian machinery manufacturing industry. But the maintenance of CNC machine tools has become increasingly difficult to fault with the gradual application. This expert system using a series of advantages, designed a set of CNC machine tools based on expert system diagnosis system, in order to failure in the machine tools can be a quick diagnosis and repair. In the paper, elaborated on the principles of diagnosis system of CNC machine tools, given the specific design, in the final establishment of a specific experimental model.

Abstract: Automatic shop floor control system in distributed computing context is one of the most important links in Computer Integrated Manufacturing (or CIM) system. For most agent-based manufacturing control systems, a real-time product data available mechanism is not considered. In this paper, an integrated approach of RFID technology and multi-agent system of shot-floor control is presented. The proposed framework uses RFID for tracking products in the system and also for attaching product manufacturing information. This shift from off-line planning systems to on-line control systems will facilitate implementations of real-time scheduling requirement in autonomous manufacturing environment.

Abstract: Driving and control are key techniques to improving performance and application of ultrasonic motor. Based on ultrasonic motor’s special structure and principle in this paper, considering the issue that modulating frequency is not widely to traditional motor’s power, it is introduced to a digital power supply based on DDS technology; considering the difficulty that ultrasonic motor’s model can not be created precisely, a fuzzy PID compound controller is designed. Simulation results show that the DDS power supply is reliable, whose frequency can be modulated easily. Fuzzy PID compound controller has summed up advantages of fuzzy and PID, which is suitable for speed and position control of ultrasonic motor.

Abstract: This paper introducts the designing of a remote assessment information collection system based on fuzzy logic inference. The system has a 6-freedom double-eyes vision robot to catch vision information, and a group of wearable sensors to acquire biomechanical signals. Taking the speed of information collection system for example, analyses and designs the struct and the rule of fuzzy control. The remote auto control of the telerehabilitation information collection system was achieved. Rehabilitation professionals can semi-automatically practice an assessment program via Internet. The results show that the smart device, including the robot and the sensors, can improve the quality of remote assessment, and reduce the complexity of operation at a distance.