Applied Mechanics and Materials Vols. 385-386

Abstract: In shallow sea the wave of ambient noise contains the information of environment acoustic field. In theory, vertical coherence, which is one of the numerous ambient noise field characters, can be used to invert geo-acoustic parameters because of its relative stability. The ambient noise data were collected in two different seasons using two vertical-laid hydrophones in shallow water. Then acoustic parameters of semi-infinite space seabed are inversed from the vertical coherence of measured ambient noise in the frequency range of 100Hz~3 kHz. The predicted vertical coherence curve of ambient noise, which is computed using inversed parameters, agrees with the measured curve by comparison. The experiment results show that geo-acoustic parameters can be inversed effectively by the vertical coherence of ambient noise.

Abstract: The design of a mechanical press slide bottom dead center measurement device which is based on the macro-micro adjustment is presented. This device has macro-micro adjustment function, which is also stable and credible in installation. The functions of press slide bottom dead center repeated positioning precision automatic measuring, analysis and display are implemented by using the technologies of eddy current sensor, PCI7422 data collection card, LED display and combine with the multi-parameter assessment from the system software, etc. It is small, portable, high precision and practical.

Abstract: This paper introduces the principles and methods of process performance of the compressor online test. The proposed monitoring system consisting of a computer and test analysis software, intuitive, real-time display the cylinder of transient pressure curve, and the curve real-time analysis of the performance of the machine and fault diagnosis.

Abstract: This document discusses the support vector machine (SVM) algorithm, then discusses least squares support vector machine (LS-SVM) algorithm, at the same time, the applications of SVM in the fault diagnosis of temperature signal of turbine blade being discussed, the least squares support vector machine algorithm being used in the research of fault diagnosis, being compared with LVQ neural network, experiments result show the operation speed of the least squares support vector machine algorithm is fast, its generalization ability is stronger, SVM can solve small sample learning problems as well as no-linear, high dimension and local minimization problems in the fault diagnosis of temperature signal of turbine blade.

Abstract: For an actual maneuvering target tracking system, the random change of system parameters and structure can often occur. So the whole system is dynamic, and there is uncertainty in system parameters and structure. In the paper, theory of system with random changing structures and technology of sensor management is introduced to build a tracking model with random changing structures. For the considering of random changing, the transient error brought by structure random changing is overcome.

Abstract: In order to improve the diagnosis rates of transformer fault, a research on application of RBF neural network is carried out. The structure and working principle of radial basis function (RBF) neural network are analyzed and a three layer RBF network is also designed for transformer fault diagnosis. It is proved by MATLAB experiment that RBF neural network is a strong classifier which is used to diagnose transformer fault effectively.

Abstract: In this paper, the principle of kernel-based possibilistic clustering algorithm and particle swarm optimization algorithm are introduced and the application of the algorithms in fault diagnosis of auxiliary inverter is studied. Several common fault types are simulated by MATALB software. By initializing clustering center of samples based on PSO algorithm, calculating the final membership matrix and the final clustering center matrix based on the KPCM algorithm, the fault samples can be classified finally. The simulation results show that the PSO-KPCM algorithm can be used in the field of fault diagnosis. The PSO-KPCM algorithm even has better results and faster convergence rate than FCM algorithm.

Abstract: A predictive maintenance approach of vacuum circuit breaker is based on the circuit breaker coil current signal. The method identifies the critical time instants in the close coil current, to be used for diagnostic analysis. Change points detection based automatic signal segmentation plays a significant role in recognition-oriented signal processing. In this paper, we addressed the algorithm of change points detection for applications in fault detection for a trip coil. The algorithm includes three parts which are data smoothing, extrema search and K-Means clustering. The experimental results show that this algorithm is effective.

Abstract: The information fusion method is introduced into the transformer fault diagnosis. Through the sensor acquire transformer in operation of each state parameter, using two parallel BP neural networks to local diagnosis, with D-S evidence theory to global fuse the local diagnostic results. It realized the accurate diagnosis when transformer comes out one or a variety of faults at the same time. The experiments demonstrate that the credibility of diagnosis results are improved significantly, uncertainties are obviously reduced, which fully shows that the method is effective.

Abstract: In recent years, with the development of the smart grid and high-voltage transmission technology, more and more attention has been paid online monitoring of high-voltage capacitive equipment. This paper developed a high-voltage capacitive equipment on-line monitoring system including hardware and software system. Hardware design takes DSP and precision AD as center including signal acquisition and conditioning unit, software part takes modular design including data processing and data query and acquisition control. The system uses zero flux micro-current sensors to collected signals and uses optical fiber to transmission signal, so, the phase measurement error can be control in and signal synchronous transmission can be guarantee. Field application shows that the system data accurate, reliable, stable operation.