Tool wear monitoring method

Abstract

The invention relates to a real-time online tool wear monitoring method which comprises the steps of: firstly, under different cutting parameters, respectively acquiring acoustic emission signals in different wear states, current signals of a spindle motor and a feed motor in a machine tool, cutting speed, cutting depth and feed rate; taking the acquired values as condition attributes, and establishing a decision table; carrying out discretization treatment on the continuous attribute values in the decision table by adopting a self-organizing map neural network; reducing the number of the attributes by adopting the Johnson algorithm; optimizing the initial weight value and the threshold values of a back propagation (BP) neural network by the genetic algorithm, and using the reduced attribute value which is taken as an input neuron of the BP neural network to train and learn the optimized BP neural network; using the trained BP neural network to predict the tool wear degree. The method not only simplifies the structure of the neural network so as to enable the neural network to have rapid neural astringency and stronger learning ability, but also improves the recognition rate of tool wear detection.

Description

technical field [0001] The invention relates to the field of tool wear detection, in particular to a real-time online tool wear monitoring method for tool wear in precision machining of difficult-to-machine components in the aviation field. Background technique [0002] With the improvement of the automation and intelligence level of the processing system, in order to avoid damage to the machine tool, tool and workpiece, and improve the quality and dimensional accuracy of the processed workpiece, the traditional single-factor sensor has been difficult to meet the requirements of the high-precision tool state detection system. The research on tool state detection system based on multi-sensor fusion has received widespread attention. The use of multi-sensor technology can overcome the limitation that a single sensor can only provide partial information technology conditions, and obtain comprehensive status information, thereby more comprehensively reflecting the status changes...

AI Technical Summary

Problems solved by technology

There is a good correspondence between the wear state of the tool and the change of the cutting force, but the change of the cutting processing condition will also cause the change of the cutting force. It is difficult to distinguish whether the change of the cutting force is caused by the change of the processing condition or the tool wear. Yes, and the installation of its sensors requires some changes to the machine tool, which has poor applicability

Images