| Deep hole machining occupies an important position in the machinery manufacturing industry.Deep hole cutting tool is the core part of deep hole machining.BTA deep hole drilling as a deep hole processing of the commonly used tool,the most prone to the problem is the tool wear,a direct impact on the quality of processing.Therefore,it is of great significance to study the wear condition of the deep hole tool and to monitor the wear state of the drill bit in time.In this paper,the structure of single-tooth BTA deep-hole drilling is introduced,and the wear state of the tool is divided into three types: normal wear,excessive wear and chipping.The wear mechanism,wear factors and wear mechanism are analyzed.Then the Deform-3D finite element software was used to simulate the drilling process.The temperature field distribution and tool wear were analyzed according to the simulation results.Based on the analysis of the deep hole machining characteristics and the working condition signal,a deep hole cutting condition monitoring system with cutting power as the monitoring signal is established.To the power signal to the noise reduction and feature extraction,and finally to identify the eigenvalues.Due to the complexity of the processing environment,the direct acquisition of the power signal with non-stationary characteristics and contains interference noise,must first be processed,so the de-noising process.Then the wavelet analysis method is used to extract the power signal after noise reduction.The power signal is decomposed and reconstructed by wavelet transform principle,and the high frequency band energy with strong correlation with the tool wear state is extracted and regarded as the eigenvector.Finally,a tool recognition model of deep hole machining tool wear based on RBF neural network is established,and the mapping of eigenvector to tool wear state is realized.The resultsshow that the model can recognize the wear state of the tool in deep hole drilling well. |
PDF Full Text Request