Papers by Author: Fu Zhou Feng

Abstract: Ultrasonic infrared thermography is a novel nondestructive detection technique, which combines a short ultrasonic pulse excitation and infrared imaging to detect defects, such as crack, in materials and structures. A simplified one-dimension heat-conduction model excited by ultrasonic pulses is put forward in this paper. Based on this model, a serial of image processing methods for recognition and reconstruction of cracks were presented. Results obtained show that the proposed method is creditable and applicable.

Abstract: Ultrasonic Infrared Imaging is a novel NDE technique, which performs well on material internal defect detection, such as metal fatigue crack, composite material impact damage and adhesion and so on. Traditional defect identification often depends on eyes and professional experience, which can’t give a clear conclusion of defect information. The identification algorithm based on time sequence images is low-level. Therefore, taking the crack detection in Ultrasonic IR Imaging as an example, after contrastive analysis of shape characters and gray distribution between crack region and normal region, characteristic parameters for different regions was creatively extracted in this paper. An automatic recognition algorithm based on Weighted Support Vector Machines is put forward for crack recognition. Subsequently, the correctness of the algorithm was validated by experiments.

Abstract: The application based on Backpropagation (BP) Algorithm network is conducted on identifying the categories and numbers of mechanical equipments by acoustic signal in battlefield targets. Collected signal was pre-processed and extracted the power spectrum feature of acoustic signal as input vectors of neural networks, then classified by neural networks and pattern recognition theorem. We employ the acoustic signals of six kinds of normal equipments as training samples to train the network. The experiment shows that the ratio of recognition of the acoustic signal processing system based on neural networks proposed is better than the conventional methods.

Abstract: Reliability of equipment has long been considered as an important quality characteristic. Traditional methods of equipment reliability assessment are based on lifetime data. With equipment being much more reliable and the growing need for developing new equipments within shorter period and at lower cost, we can hardly get enough lifetime data in many cases. Performance degradation data can also be used for reliability assessment. This paper is mainly researched on reliability of a certain diesel engine. Through analyzing the failure mode and failure mechanism, performance degradation parameters of the diesel engine is selected as compression pressure in a cylinder while driven by an electrical motor. Based on a long time accumulation on performance degradation data, two methods of degradation path fitting and degradation value distribution are tried in this paper to evaluate reliability of the diesel engine. Besides, the regulation of the reliability variation is given by the results of the assessment.

Abstract: A genetic algorithm-support vector regression model (GA-SVR) is proposed for machine performance degradation prediction. The main idea of the method is firstly to select the condition-sensitive features extracted from rolling bearing vibration signals using Genetic Algorithm to form a condition vector. Then prediction model is established for each feature time series. And the third step is to establish support vector regression models to obtain prediction result in each series. Finally, the condition prognosis can be obtained through combing all components to form a condition vector. Vibration data from a rolling bearing bench test process are used to verify accuracy of the proposed method. The results show that the model is an effective prediction method with a higher speed and a better accuracy.