This study proposed convolutional neural network (CNN) training for different figure recognition to diagnose electric motorbike faults. Traditional motorbike maintenance is usually carried out by technicians to find the problem step by step. Many resources are wasted and time consumed in diagnosing maintenance problems. Due to rising environmental protection awareness, motorbike power systems gradually transformed from combustion engines into the electric motor. The sound amplitude generated by the combustion engine is great and may cover other faulty sounds. The electric power system sound amplitude is greatly decreased, permitting various fault diagnosis to be performed by extracting the electric motor sound. With the development of computers and image processing, deep learning neural network for picture recognition technology becomes more feasible. This study presents the motor system sound visualization for fault diagnosis. First obtain the sound signals of the motor in the five different states of the operation in the laboratory and the road test, and draw the time domain graph, frequency domain graph and spectrogram graph to be used as the test database. The results graphs of various states were trained through a CNN. The signal states were then classified to achieve fault diagnosis. Experiments and identification results show that the spectrogram and CNN method can identify motorbike faults most effectively compared to the time domain graph and the frequency domain graph.

Responding to the market demand for high quality and production limited quantity and variety, the automation technology of flexible manufacturing system or computer integration manufacture sytem has being developed.During the automation manufacturing, to some extent the instability of product quality would be resulted from different precision of machine tool, qualification of operators and manufacturing technology. In addition, the utilization of traditional mannual measurement or off-line contact quality inspection would reduce productivity.Therefore, the technology of non-contact on-line product quality inspection is becoming a very important research issue. This report is focusing on the setup of non-contact automatic measurement of concentricity by applying personal computer and image processing technology. LOG and zero-crossing method is used to complete image edge detection. Then curve-fitting is applied to generate the inner circle and outter circle of mechanical part.Subsequently, the coordinate of edge points of the inner and outter circles, together with the least-square error method, will be applied to estimate the concentricity of the mechanical part waiting for inspection.Comparing the result of experiment with the data measured by a FEDERAL high-precision roundest equipment the proposed system is proved with good repetitivity and accuracy.

No abstract

No abstract