CN114905334A - An intelligent real-time cleaning and cutting monitoring system and method - Google Patents

Abstract

The invention discloses an intelligent real-time cleaning cutting monitoring system and method, which are used for system monitoring and comprise the following steps: the system comprises an acquisition module, a processing module, a control module, a display module, a communication module, remote terminal equipment and a modeling system; the control module controls the acquisition module to synchronously acquire the processing process information, integrate the processing process information with hardware and send the processing process information to the modeling system; the processing module processes the signals acquired by the acquisition module to obtain two-dimensional data and transmits the two-dimensional data to the modeling system; the modeling system establishes an offline network model based on the two-dimensional data and the processing process information; the acquisition module transmits the real-time processing process information to the offline network module to obtain real-time cutter information, and the real-time cutter information is displayed through the display module; and the communication module transmits the real-time cutter information and the machining process information to the remote terminal equipment. The invention carries out real-time on-line monitoring on the cutting processing state, can consider different materials, different cutting quantities and different working conditions, and has higher system universality.

Description

An intelligent real-time cleaning and cutting monitoring system and method

technical field

The invention relates to the technical field of monitoring, in particular to an intelligent real-time cleaning and cutting monitoring system and method.

Background technique

In the cutting process, tool wear will reduce the surface quality of the workpiece, especially in the stage of severe tool wear, the tool wear value will change greatly in a short period of time, resulting in the dimensional accuracy of the machined parts cannot meet the target requirements. Monitoring tool wear status is one of the important means to reduce manufacturing costs, reduce manufacturing environmental hazards, and ensure the normal and efficient operation of manufacturing systems and product quality. The online monitoring of the machined surface roughness based on the tool wear state can display the machining state more intuitively and ensure the smooth progress of the machining process. The existing cutting intelligence monitoring systems are not highly integrated and real-time, and cover environmental sensors related to clean cutting.

Therefore, there is an urgent need for a new cutting intelligent monitoring system and method to solve the above problems.

SUMMARY OF THE INVENTION

The purpose of the present invention is to provide an intelligent real-time cleaning and cutting monitoring system and method, which solves the problem of real-time online monitoring of tool wear and surface roughness during processing under the background of clean cutting and intelligent manufacturing.

In order to achieve the above object, the present invention provides the following technical solutions:

An intelligent real-time cleaning and cutting monitoring system, comprising: an acquisition module, a processing module, a control module, a display module, a communication module, a remote terminal device, and a modeling system;

The control module controls the acquisition module to perform synchronous acquisition and hardware integration of processing process information, and send it to the modeling system;

The processing module processes the signals collected by the acquisition module to obtain two-dimensional data, which are transmitted to the modeling system;

The modeling system establishes an offline network model based on the two-dimensional data and the processing process information;

The acquisition module transmits the real-time processing process information to the offline network module, obtains real-time tool information, and displays it through the display module;

The communication module transmits the real-time tool information and the machining process information to the remote terminal device.

Optionally, the acquisition module includes: a three-way piezoelectric cutting force sensor, a three-way vibration acceleration sensor, a sound sensor, a dust particle sensor, a Keyence microscope and a surface roughness meter.

Optionally, the processing process information includes: work information, tool information, and workpiece material information in the machining process of the machine tool.

Optionally, the processing module uses LabVIEW software combined with a python deep learning neural network program to process the collected signals.

An intelligent real-time cleaning and cutting monitoring method, comprising the following contents:

Collect work information, tool information and workpiece material information during machine tool processing;

Analyze and process the work information through PCA technology and radar charts, and establish an offline network model in combination with the tool;

Inputting the real-time work information and the workpiece material information into the offline network model to obtain a real-time offline network model;

The real-time working information is input into the real-time offline network model to obtain the real-time tool information.

Optionally, the work information includes: cutting force, amount of change in cutting force, amount of vibration at cutting position, noise, amount of noise change, and amount of dust.

Optionally, the tool information includes: tool wear amount and workpiece surface roughness.

Optionally, the analysis and processing method includes: quantitative representation, data dimensionality reduction, and feature fusion.

Optionally, it also includes: real-time display of cutting force, vibration amount of cutting position, noise, dust amount, and tool information.

Optionally, the real-time work information is input into the real-time offline network model, and the specific content that obtains the real-time tool information is:

The data features are obtained after being processed by the feature fusion method, and the time domain features and frequency domain features that reflect the tool wear information and the machining surface roughness information are extracted according to the feature formula;

The real-time tool information is obtained by using the real-time data features of the work information and the workpiece material information in the first n seconds as the input of the real-time offline network model.

Compared with the prior art, the beneficial effects of the present invention are as follows:

A monitoring system with high software and hardware integration is proposed, which can conduct real-time online monitoring of cutting processing status, and can take into account different materials, different cutting quantities and different working conditions, and the system has high universality; Cutting-related environmental sensors, and real-time online monitoring of environmental parameters such as sound and dust; fusion and dimension reduction processing of multi-source heterogeneous data collected by multi-sensors to monitor tool wear and surface roughness to improve accuracy and model training efficiency .

Description of drawings

In order to explain the embodiments of the present invention or the technical solutions in the prior art more clearly, the following briefly introduces the accompanying drawings that need to be used in the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only It is an embodiment of the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to the provided drawings without creative work.

1 is a schematic diagram of the construction of the hardware system of the system of the present invention;

Fig. 2 is the display front panel of the system of the present invention;

FIG. 3 is a block diagram of the implementation of the system of the present invention.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Example 1

The present embodiment discloses an intelligent real-time cleaning and cutting monitoring system, including: a collection module, a processing module, a control module, a display module, a communication module, a remote terminal device, and a modeling system;

The control module controls the acquisition module to synchronously acquire and integrate the processing process information, and send it to the modeling system;

The processing module processes the signals collected by the acquisition module, obtains two-dimensional data, and transmits it to the modeling system;

The modeling system establishes an offline network model based on two-dimensional data and processing process information;

The acquisition module transmits real-time machining process information to the offline network module, obtains real-time tool information, and displays it through the display module;

The communication module transmits real-time tool information and machining process information to remote terminal equipment.

specific:

The acquisition module includes: three-way piezoelectric cutting force sensor, three-way vibration acceleration sensor, sound sensor, dust particle sensor, KEYENCE microscope and surface roughness meter. Among them, the three-way piezoelectric cutting force sensor is used for real-time measurement of the cutting force and variation of X, Y, and Z axes during the machining process of the machine tool; the three-way vibration acceleration sensor is used for real-time measurement of the vibration of the cutting position during the machining process of the machine tool. The sound sensor is used to measure the sound change and noise level in the machining process of the machine tool in real time; the dust particle sensor is used to measure the PM2. The surface roughness meter is used to observe the tool wear and surface roughness data; in this embodiment, the cutting force sensor is installed between the machine tool table and the workpiece material, the vibration sensor is installed on the workpiece material, and the sound sensor is placed in the machine box. In the machine body, the dust particle sensor is placed outside the machine tool box. The acquisition card is used to collect various sensor signals, and the box is connected to the display screen to display the data in real time and connect to the remote transmission equipment through the network cable.

The machining process information includes: work information, tool information, and workpiece material information in the machining process of the machine tool.

The processing module uses LabVIEW software combined with python's deep learning neural network program to process the collected signals.

The display module displays cutting force, vibration acceleration, noise, PM2.5, PM10, tool wear, surface roughness, etc. on one interface in real time by building the LabVIEW front panel; the communication module uses a wireless network or a server to display the LabVIEW front panel. Panel remote transmission realizes the purpose of remote real-time monitoring. Figure 2 shows the software display front panel in this embodiment, the left side of which displays the time domain and frequency domain numerical changes of the directly measured data, and displays the numerical value in real time, wherein the numerical value display is updated once per second, and the numerical value is equal to this The average of the second data. The upper right side is the setting panel for processing parameters, and different sensor measurement methods and indirect measurement network models are determined according to different parameter settings. The bottom right is the real-time display interface of tool wear and surface roughness. The processing status is determined through the real-time displayed data, and the decision whether to change the tool is needed.

Example 2

The present embodiment discloses an intelligent real-time cleaning and cutting monitoring method, which includes the following contents:

Online data collection stage: collect work information, tool information, workpiece material information during machine tool processing;

Offline modeling stage: analyze and process the work information through PCA technology and radar chart, and establish an offline network model combined with the tool;

Input the real-time work information and workpiece material information into the offline network model to obtain the real-time offline network model; specifically: for different materials, different cutting amounts and different working conditions, combine a large number of processing data features measured by sensors in the monitoring system with the main Component analysis PCA and radar map method dimensionality reduction processing becomes only two-dimensional data containing radar map perimeter and area as input, and offline tool wear and surface roughness data observed by KEYENCE microscope and surface roughness meter Train the neural network to obtain an offline network model, and put the trained network model into the machining database.

Real-time monitoring stage of processing information: input real-time work information into real-time offline network model to obtain real-time tool information.

The working information includes: cutting force, cutting force change, vibration at cutting position, noise, noise change, and dust. Tool information includes: tool wear amount, workpiece surface roughness.

Analysis and processing methods include: quantitative representation, data dimensionality reduction, and feature fusion.

Also includes: real-time display of cutting force, vibration of cutting position, noise, dust, and tool information.

The real-time work information is input into the real-time offline network model, and the specific content of the real-time tool information is obtained as follows:

The data features are obtained after being processed by the feature fusion method, and the time domain features and frequency domain features that reflect the tool wear information and the machined surface roughness information are extracted according to the feature formula; specific: three-way cutting force, three-way vibration acceleration, sound signal All are dynamic high-frequency signals, and dust particle signals are dynamic low-frequency signals, and different signal sources and data structures are different. In the online data acquisition stage, the multi-source heterogeneous signals of three-dimensional cutting force, three-dimensional vibration acceleration, sound signal and dust particle signal are dynamically collected and quantitatively characterized, data dimensionality reduction and feature fusion, and the physical quantities that can be directly monitored; cutting; Force, vibration acceleration, sound, PM2.5, PM10 are displayed in real time. Among them, the data features are extracted according to formulas (1) to (10) to extract the time domain features and frequency domain features that can objectively reflect the tool wear information and the machined surface roughness information.

Time Domain Features:

Max=max(|x _i |)&Min=min(|x _i |)(2, 3);

Among them, x _i represents the signal collected by the ith sensor in a certain period of time during the cutting process, i=1, 2, 3,...N; N is the number of sensors; M represents the number of sensors in the cutting process The average value of the monitoring signals collected in a certain period of time, that is, the length of the power spectrum;

Frequency domain feature: Max represents the maximum value of the absolute value of the monitoring signal collected in a certain period of time during the cutting process; Min is the minimum value of the absolute value of the monitoring signal collected in a certain period of time during the cutting process ;RMS indicates the intensity of the monitoring signal in a certain period of time during the cutting process; Var indicates the degree of fluctuation of the monitoring signal near the mean value in a certain period of time during the cutting process; Cov(X, Y) indicates the degree of fluctuation of the monitoring signal during the cutting process The overall error of the two variables of the monitoring signal in a certain period of time; Skew(X) represents the asymmetry of the monitoring signal in a certain period of time in the cutting process with the mean value of the symmetrical line; Kurt represents the asymmetry in the cutting process. The kurtosis of the monitoring signal collected in a certain period of time, that is, the transient phenomenon and stationarity of the monitoring signal;

Among them, f _i represents the spectrum converted from the time domain signal, that is, the original signal, by the fast Fourier transform of the monitoring signal collected in a given period of time; P(fi ₎ represents the power spectrum of the monitoring signal Density; FCG is the frequency center of gravity of the monitoring signal, which is the static part of the spectrum; FV is the frequency variance of the monitoring signal, and the dynamic part of the spectrum reflects the degree of fluctuation of the spectrum of the monitoring signal near the frequency center of gravity.

It should be noted that M is the average value of the monitoring signals collected in a certain period of time during the cutting process, which is the static part of the monitoring signals and reflects the changing trend of the monitoring signals; Max and Min are the average value of the monitoring signals during the cutting process. The maximum and minimum absolute values of the monitoring signals collected in a certain period of time reflect the variation range of the monitoring signals;

The real-time working information and the data features of the workpiece material information in the first n seconds are used as the input of the real-time offline network model to obtain real-time tool information. And the real-time machining data and tool wear and surface roughness information are displayed on the built LabVIEW front panel in real time, and the data in the LabVIEW front panel is displayed on the remote mobile phone or computer through the network service.

The above description of the disclosed embodiments enables any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. an intelligent real-time cleaning and cutting monitoring system, is characterized in that, comprises: acquisition module, processing module, control module, display module, communication module, remote terminal equipment, modeling system; The control module controls the acquisition module to perform synchronous acquisition and hardware integration of processing process information, and send it to the modeling system; The processing module processes the signals collected by the acquisition module to obtain two-dimensional data, which are transmitted to the modeling system; The modeling system establishes an offline network model based on the two-dimensional data and the processing process information; The acquisition module transmits the real-time processing process information to the offline network module, obtains real-time tool information, and displays it through the display module; The communication module transmits the real-time tool information and the machining process information to the remote terminal device. 2. An intelligent real-time cleaning and cutting monitoring system according to claim 1, wherein the acquisition module comprises: a three-way piezoelectric cutting force sensor, a three-way vibration acceleration sensor, a sound sensor, a dust particle sensor, KEYENCE microscopes and surface roughness meters. 3. a kind of intelligent real-time cleaning and cutting monitoring system according to claim 1, is characterized in that, described processing process information comprises: work information, tool information, workpiece material information in machine tool processing process. 4. A kind of intelligent real-time cleaning and cutting monitoring system according to claim 1, is characterized in that, described processing module adopts LabVIEW software and combines the deep learning neural network program of python to process the collected signal. 5. an intelligent real-time cleaning and cutting monitoring method, is characterized in that, comprises the following content: Collect work information, tool information and workpiece material information during machine tool processing; Analyze and process the work information through PCA technology and radar charts, and establish an offline network model in combination with the tool; Inputting the real-time work information and the workpiece material information into the offline network model to obtain a real-time offline network model; The real-time working information is input into the real-time offline network model to obtain the real-time tool information. 6 . The intelligent real-time cleaning and cutting monitoring method according to claim 5 , wherein the working information includes: cutting force, variation of cutting force, vibration of cutting position, noise, variation of noise, and amount of dust. 7 . 7 . The intelligent real-time cleaning and cutting monitoring method according to claim 5 , wherein the tool information includes: tool wear amount and workpiece surface roughness. 8 . 8 . The intelligent real-time cleaning and cutting monitoring method according to claim 5 , wherein the analysis and processing method comprises: quantitative characterization, data dimensionality reduction, and feature fusion. 9 . 9 . The intelligent real-time cleaning and cutting monitoring method according to claim 5 , further comprising: displaying cutting force, vibration amount of cutting position, noise, dust amount and tool information in real time. 10 . 10. a kind of intelligent real-time cleaning and cutting monitoring method according to claim 5, is characterized in that, the real-time described work information is input described real-time offline network model, the concrete content that obtains real-time described tool information is: The data features are obtained after being processed by the feature fusion method, and the time domain features and frequency domain features reflecting the tool wear information and the machining surface roughness information are extracted according to the feature formula; The real-time tool information is obtained by using the real-time working information and the data features of the workpiece material information in the first n seconds as the input of the real-time offline network model.

Images