Intelligent evaluation system model
According to the hardware system, the machining accuracy evaluation model is established. The model is composed of different layer structures, mainly including signal acquisition layer, signal output layer, signal transformation layer, signal conditioning layer, data acquisition layer, acquisition software, data storage, feature extraction and user layer.
The functions of each part are as follows:
(1) Signal acquisition layer: it is mainly that each sensor collects corresponding signals from the measuring points at the installed position, and the signals output by the sensor are transmitted to the signal output layer.
(2) Signal input layer: it transmits the signal to the discharge conditioning circuit of the NC machine tool, and the signal output layer links the signal measuring point and the preprocessing circuit.
(3) Signal transformation layer: it can realize the transformation of signal form. Because the original signals output by each sensor include voltage signal, resistance signal and current signal, in order to facilitate data acquisition, these signals need to be transformed in the signal transformation layer and uniformly converted into voltage signals.
(4) Signal conditioning layer: it is mainly composed of signal conditioning instrument. Because the original signal is mixed with a large number of noise signals, and the original signal value is relatively weak, the signal conditioning layer mainly realizes the amplification and filtering of the original signal.
(5) Data acquisition layer: it is mainly composed of data acquisition card to realize high-speed signal acquisition.
(6) Acquisition software: it mainly realizes the automatic data acquisition, transmission, storage and other operations of the computer.
(7) Data storage: it is the basic basis for data processing, and the stored data needs to be called in subsequent processing.
(8) Feature extraction: it mainly extracts relevant time-domain features and frequency-domain features from the processed signals for subsequent neural network training.
(9) User level: it is mainly the neural network that trains and learns the extracted eigenvalues and outputs the decision results.
Signal feature extraction
The feature selection value uses various digital signal analysis and processing methods to extract the feature information that can best reflect the change of machining accuracy from the original signal. The original signal collected by the sensor contains a large number of noise signals. In order to effectively extract the eigenvalue of the signal, wavelet packet is selected to extract the eigenvalue.