Abstract
In view of the low accuracy of single signal monitoring for the wear state of vibration drilling bit, a multisignal acquisition system for the wear state of ultrasonic axial vibration drilling bit is built to collect the drilling force, vibration, and acoustic emission signals under three different wear states. The drilling force, vibration and acoustic emission signals of the bit in the drilling process are processed by using wavelet decomposition technology, and the signals are extracted from the wear state of the bit, The wavelet energy coefficient with high state correlation is used as the feature parameter to identify the bit wear state. The feature parameter is trained by the combination of noise assisted LMD method and BP neural network. The experiment of single signal and multisignal fusion monitoring bit wear state is carried out, and the neural network structure is optimized according to the error. The results show that the accuracy of monitoring bit wear with a single signal of drilling force is 83.3%, the accuracy of monitoring bit wear with a single signal of vibration is 91.6%, the accuracy of monitoring bit wear with a single signal of acoustic emission is 91.6%, and the accuracy of monitoring bit wear with multisignal fusion is 95.8%; when the number of network layer is 4, the vibration is monitored with the fusion of force signal, acoustic emission signal, and vibration signal The accuracy of the state of drilling tool is up to 100%. The structure model of neural network is optimized reasonably to improve the recognition rate of bit wear in vibration drilling.
Highlights
Ultrasonic vibration drilling has many advantages, such as good chip breaking and chip removal performance, smooth hole wall surface, etc., which is widely used in deep hole drilling [1]
In 2015, Azmi verified that the feed force in the milling process has awesome prediction for tool wear state and established a milling cutter condition monitoring system based on feed force monitoring signal, which has awesome milling cutter status recognition [9]
Recognition Model of Bit Wear State rough BP neural network, the nonlinear mapping relationship between the bit wear state and signal eigenvector can be constructed to judge the bit wear state [17]. erefore, this paper uses BP neural network technology to fuse the feature bands extracted from the wavelet decomposition of drilling force, AE, and vibration signals, to realize the recognition of tool wear state in ultrasonic vibration drilling
Summary
Ultrasonic vibration drilling has many advantages, such as good chip breaking and chip removal performance, smooth hole wall surface, etc., which is widely used in deep hole drilling [1]. It is impossible to directly observe and monitor the wear state of the tool. It is mainly through the operator’s experience to judge the wear degree of the tool and determine the tool change strategy. E drilling force, vibration and acoustic emission signals collected under different wear conditions are processed by wavelet decomposition, and the wavelet energy coefficient with high correlation with the bit wear condition is obtained as the characteristic parameter, which is input into the BP neural network model to identify the bit wear condition, and the recognition result is compared with that based on a single signal to identify the bit wear condition. Using a single signal to monitor the status of cutting tools has the problem of low recognition rate. erefore, in this paper, a multisignal acquisition system for the wear state of the axial vibration drilling bit is built with the drilling force, vibration, and acoustic emission signals as the monitoring signals. e wear state monitoring test of the 7075 aluminum plate is carried out on the 40 kHz ultrasonic vibration drilling device. e drilling force, vibration and acoustic emission signals collected under different wear conditions are processed by wavelet decomposition, and the wavelet energy coefficient with high correlation with the bit wear condition is obtained as the characteristic parameter, which is input into the BP neural network model to identify the bit wear condition, and the recognition result is compared with that based on a single signal to identify the bit wear condition. e results of damage state discrimination are compared and analyzed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
