Papers by Author: Xue Jun Li

Abstract: KPCA is a commonly used method for feature extraction, for the problems of kernel function and its parameters have a great influence on performance of KPCA feature extraction but the optimal parameters are difficult to select. This paper applied the bacterial foraging algorithm on KPCA feature extraction and the method of KPCA feature extraction based on bacterial foraging algorithm was proposed. The experiment of bearing feature extraction shows that the method which proposed in this paper is effective.

Abstract: This paper aims to design the inverter control system of alternating current (AC) motors based on Advanced RISC Machines (ARM) and μC/OS-II. The system's hardware core is the LPC2131 in which processor successfully transplanted the μC/OS-II real-time operating system. In the form of task, each functional module of the system is achieved on the processor LPC2131. Testing and experiments show that the multi-task classify program is feasible on the embedded real-time operating system based on LPC2131 and μC/OS-II, it ensures the system's real-time, has good multi-task operating and transferring characteristics and improves the system stability and reliability.

Abstract: This paper described the theory which based on the spread spectrum communication system, a simulation model was designed based on MATLAB, and each module of the model was briefly introduced. In a particular simulation condition, ran the simulation program, and an expected result was obtained. Meanwhile, by design a spread spectrum communication system of two users, detect the bit error rate corresponding with the two users in different bit error rate (SNR), directly verified the validity of the model system.

Abstract: Wigner-Ville distribution (WVD) has the characteristics of very high-energy accumulation and excellent time-frequency resolution. It is a good way to extract fault feature of acoustic emission (AE) signals due to mechanical component broken. The characteristics of typical AE signals initiated by damages are analyzed. Based on the extracting principle of AE signals from damaged components, the WVD analysis method of AE signal is developed. WVD method is employed to the fault diagnosis of rolling bearings with AE technique. The fault features reading from experimental data analysis are clear, accurate and intuitionistic, meantime, the validity and accuracy of WVD method proposed are nice from the experimental results. Therefore, WVD method is useful for condition monitoring and fault diagnosis in conjunction with AE technique.

Abstract: Aiming at inaccurately and inefficiently fault feature of early crack by the vibration method in the environment of strong noise, the acoustic emission signal (AE) is used to cracks defect with the advantages of sensitive. The Pseudo Wigner-Ville Distribution (PWVD) is introduced to extract the amplitude and frequency of AE signal as feature vector, which combines with support vector machine (SVM) to achieve prediction and diagnosis of fault types of different rotor cracks depth. It is shown by experiment that the proposed method have the features of obvious frequency characteristic, early prediction of fault time, accurate and reliable diagnosis results of early cracks fault diagnosis.

Abstract: From the basic theory of fracture mechanics and combining the fatigue mechanism of rotor crack propagation, energy theory and power relationship, the stress analysis and deformation of the rotor are discussed, and the acoustic emission mathematical model of the rotor crack propagation is deduced, which will provide the theoretical basis for the further study of the acoustic emission in the rotor crack fault detection.

Abstract: The real-time respondent speed and the reliability play a deciding role on the performance of the digital monitoring for mine hoist. Differs to the traditional monitoring for mine hoist , it is possible to improve the signal respondent speed during upgrading of mine hoist by two methods, one is to adopt the quick microprocessor and another is the embedded real-time multi-task operating system. The Advanced Reduced Instruction Set Computer Machines (ARM) is particularly suitable to work as the controller of the digital monitoring for mine hoist with its merits as high running speed and complete peripheral equipments. The micro C/OS-Ⅱcan both improve the respondent speed against various signals from mining enterprises fields and the reliability of the controlling software as an embedded real-time operating system.The principle of task allocation is an important one of the highest priority related to the stability of mine hoist and functional tasks. To avoid multiple tasks simultaneously access the same shared resources, two semaphores are introduced to determine the access mechanism of the shared resource. Application of real-time operating system is the future of digital development of mine hoist.

Abstract: Based on analysis of submerged arc welding arc heat source model and droplet heat inputting uniform distribution, ANSYS parametric design language was applied to develop sub-program for loading moving heat sources. ANSYS software was used to calculate the temperature fields. In the same welding conditions, weld seam width and depth value of experiments and simulation are contrasted, the biggest error was below 5%. The influence of different welding speed to molten pool temperature of twin-arc submerged arc welding was analyzed, it obtained results that temperature field distribution of twin-arc submerged arc welding changes more gentle than single arc submerged arc welding in condition of increased welding speed, it was helpful to the further analysis of molten pool dynamic behavior and weld seam shape factors of twin-arc high speed submerged arc welding.

Abstract: The parameter optimization is the key to study of support vector machine (SVM). With strong global search capability of bacterial foraging algorithm(BFA), the optimization method—support vector machine parameters optimization based on bacterial foraging algorithm was proposed, which can achieve the dynamic optimization of the parameters C andγ,and overcomes the problem of inefficiency for selecting reasonable parameters according to the experience in the traditional fault diagnosis. Compared with other methods, the BFA is simpler and easier for programming, and the optimization SVM model become smaller. The rolling bearing fault diagnosis results show that bacterial foraging algorithm is suitable for support vector machine parameter optimization.

Abstract: Manufacturing execution system is the link in the process of enterprise implementation information integration.The application of Radio Frequency Identification technology is important to implement the data collection function of MES. Speculation against the low efficiency, poor in real time, and low security function for data acquisition in a motor manufacturer, established data acquisition system in MES based on RFID,discussed the data collection process, designed structure of the system in detail，analyzed the function requirements,provide anti-collision algorithm to avoid data collection of the label which may be used in the system implementation,finally discussed the principle of coding.