CN117420792A - Central control system for composite processing machine tool - Google Patents
Central control system for composite processing machine tool Download PDFInfo
- Publication number
- CN117420792A CN117420792A CN202311461920.9A CN202311461920A CN117420792A CN 117420792 A CN117420792 A CN 117420792A CN 202311461920 A CN202311461920 A CN 202311461920A CN 117420792 A CN117420792 A CN 117420792A
- Authority
- CN
- China
- Prior art keywords
- servo motor
- time sequence
- training
- machine tool
- parameter time
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 48
- 239000002131 composite material Substances 0.000 title description 14
- 238000012544 monitoring process Methods 0.000 claims abstract description 43
- 230000002159 abnormal effect Effects 0.000 claims abstract description 30
- 150000001875 compounds Chemical class 0.000 claims abstract description 24
- 238000004458 analytical method Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 90
- 230000008447 perception Effects 0.000 claims description 56
- 238000010586 diagram Methods 0.000 claims description 52
- 238000012800 visualization Methods 0.000 claims description 23
- 238000003062 neural network model Methods 0.000 claims description 20
- 239000011159 matrix material Substances 0.000 claims description 19
- 230000033001 locomotion Effects 0.000 claims description 17
- 230000005856 abnormality Effects 0.000 claims description 15
- 238000005728 strengthening Methods 0.000 claims description 15
- 238000001514 detection method Methods 0.000 claims description 14
- 238000003754 machining Methods 0.000 claims description 13
- 238000000605 extraction Methods 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 11
- 238000004891 communication Methods 0.000 claims description 10
- 238000013527 convolutional neural network Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000003745 diagnosis Methods 0.000 claims description 7
- 238000005457 optimization Methods 0.000 claims description 6
- 230000002787 reinforcement Effects 0.000 claims description 5
- 239000013598 vector Substances 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 abstract description 10
- 238000000034 method Methods 0.000 description 23
- 238000009826 distribution Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011960 computer-aided design Methods 0.000 description 2
- 238000005520 cutting process Methods 0.000 description 2
- 238000005553 drilling Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003801 milling Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001816 cooling Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000002195 synergetic effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/18—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form
- G05B19/406—Numerical control [NC], i.e. automatically operating machines, in particular machine tools, e.g. in a manufacturing environment, so as to execute positioning, movement or co-ordinated operations by means of programme data in numerical form characterised by monitoring or safety
- G05B19/4065—Monitoring tool breakage, life or condition
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/37—Measurements
- G05B2219/37616—Use same monitoring tools to monitor tool and workpiece
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Manufacturing & Machinery (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Numerical Control (AREA)
Abstract
The invention discloses a central control system for a compound processing machine tool, which is used for monitoring and collecting speed values, current values and temperature values of a servo motor in real time, introducing a data processing and analyzing algorithm at the rear end to carry out time sequence collaborative analysis of parameters of the servo motor, so as to monitor the working state of the servo motor, help operators to more intuitively and accurately know the working state information of the servo motor, help the operators to better grasp the running condition of the machine tool, timely take measures to treat abnormal conditions, ensure the processing quality and efficiency, and improve the safety and reliability of the machine tool.
Description
Technical Field
The invention relates to the technical field of central control of intelligent machine tools, in particular to a central control system for a composite machining machine tool.
Background
The composite machine tool is a machine tool integrating multiple machining functions and generally comprises multiple processes such as milling, drilling, boring, cutting and the like. In order to ensure the normal operation of the machine tool and to improve the machining efficiency, a central control system plays an important role therein. The central control system acquires running state information in real time by monitoring each subsystem of the machine tool, and detects and alarms abnormal conditions so as to ensure the stability and safety of the machine tool.
In the complex machine tool, a servo motor or a stepping motor is used to drive each movement axis, such as a feed axis, a spindle, and the like. The operating state of these motors has an important influence on the machining accuracy and efficiency of the machine tool. Monitoring and controlling the operating state of these motors is therefore one of the critical tasks of the central control system. However, conventional monitoring systems generally provide limited operating state information, monitor and analyze only a single parameter, such as rotational speed or current data of a motor, and use a threshold monitoring method to perform abnormality or fault warning. The method cannot capture the relevance and the mutual influence among a plurality of parameters, so that the working state of the motor cannot be comprehensively perceived, and potential faults or abnormal conditions are difficult to discover in time, so that the motor abnormality detection capability is low.
Accordingly, an optimized central control system for a compound machine tool is desired.
Disclosure of Invention
The embodiment of the invention provides a central control system for a compound processing machine tool, which is used for monitoring and collecting speed values, current values and temperature values of a servo motor in real time, introducing a data processing and analyzing algorithm at the rear end to carry out time sequence collaborative analysis of parameters of the servo motor, so as to monitor the working state of the servo motor, further helping operators to more intuitively and accurately know the working state information of the servo motor, helping the operators to better master the running condition of the machine tool, timely taking measures to handle abnormal conditions, ensuring the processing quality and efficiency and improving the safety and reliability of the machine tool.
The embodiment of the invention also provides a central control system for the composite processing machine tool, which comprises:
a central processor for receiving and processing signals from the various subsystems;
a motion controller for controlling the motion of each axis of the machine tool;
the numerical control system is used for executing a numerical control program and displaying information of a machining process;
the man-machine interface is used for interacting with an operator and setting parameters;
the monitoring system is used for monitoring the working state and fault diagnosis of the machine tool;
and the communication module is used for carrying out data transmission and remote control with external equipment.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art. In the drawings:
fig. 1 is a block diagram of a central control system for a compound machine tool according to an embodiment of the present invention.
Fig. 2 is a flowchart of a central control method for a compound machine tool according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of a system architecture of a central control method for a compound machine tool according to an embodiment of the present invention.
Fig. 4 is an application scenario diagram of a central control system for a composite machine tool according to an embodiment of the present invention.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the embodiments of the present invention will be described in further detail with reference to the accompanying drawings. The exemplary embodiments of the present invention and their descriptions herein are for the purpose of explaining the present invention, but are not to be construed as limiting the invention.
Unless defined otherwise, all technical and scientific terms used in the examples of this application have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present application.
In the description of the embodiments of the present application, unless otherwise indicated and defined, the term "connected" should be construed broadly, and for example, may be an electrical connection, may be a communication between two elements, may be a direct connection, or may be an indirect connection via an intermediary, and it will be understood by those skilled in the art that the specific meaning of the term may be understood according to the specific circumstances.
It should be noted that, the term "first\second\third" in the embodiments of the present application is merely to distinguish similar objects, and does not represent a specific order for the objects, it is to be understood that "first\second\third" may interchange a specific order or sequence where allowed. It is to be understood that the "first\second\third" distinguishing objects may be interchanged where appropriate such that the embodiments of the present application described herein may be implemented in sequences other than those illustrated or described herein.
The composite machine tool is a machine tool integrating multiple machining functions and can finish multiple processes, such as milling, drilling, boring, cutting and the like. Compared with the traditional single-function machine tool, the composite machine tool has higher flexibility and diversified processing capacity, can meet the processing requirements of different workpieces, and improves the production efficiency and the processing quality.
The compound machine tool is generally composed of a plurality of moving axes including a feed axis, a main axis, etc., which are driven by a servo motor or a stepping motor to realize movement of a workpiece in different directions. The central control system plays a key role in the composite processing machine tool and is responsible for monitoring and controlling each subsystem of the machine tool so as to ensure the normal operation and the processing efficiency of the machine tool. The central control system acquires the data of the key parameters by monitoring the running state of each subsystem in real time, and analyzes and processes the data. For a servo motor or a stepping motor, a central control system needs to monitor parameters such as speed, current, temperature and the like so as to know the working state of the motor. By carrying out time sequence collaborative analysis on the parameters, the central control system can judge whether the motor normally operates, whether abnormal conditions or potential faults exist or not, and timely alarm or take measures.
The central control system of the composite processing machine tool can also provide an operation interface, so that an operator can intuitively know the running condition of the machine tool. The operator can monitor the state of each subsystem, such as the position of the feed shaft, the rotating speed of the main shaft, and the like, and the working state information of the motor through the central control system. When abnormal conditions are found, an operator can take measures in time, such as parameter adjustment, shutdown maintenance and the like, so as to ensure the processing quality and efficiency. In addition, the central control system of the composite processing machine tool can also perform data interaction with other systems, so that automatic production is realized. For example, the central control system may be in data communication with a Computer Aided Design (CAD) system or a Computer Aided Manufacturing (CAM) system to enable automatic programming of workpieces and automatic control of the machining process.
In a compound machine tool, monitoring and controlling the operating state of a servo motor is one of the key tasks of a central control system. The servo motor plays an important role in a machine tool, drives the motion of each motion axis, and directly influences the machining precision, speed and stability. Therefore, ensuring the normal operation state of the servo motor is critical to the performance and processing quality of the machine tool.
However, the conventional monitoring system has some limitations in monitoring and controlling the operation state of the servo motor, generally only limited operation state information can be provided, and only single parameters, such as the rotation speed or current data of the motor, can be monitored and analyzed, and the method utilizes a threshold monitoring method for abnormality or fault early warning, but cannot capture the correlation and interaction among a plurality of parameters. The limitation of the single parameter monitoring method is that the working state of the motor cannot be comprehensively perceived, the running state of the servo motor is determined by the mutual influence and the synergistic effect of a plurality of parameters, such as speed, current, temperature and the like, and the whole working state of the motor cannot be accurately reflected by monitoring only a single parameter, and the health condition of the motor cannot be comprehensively known. In addition, the traditional monitoring system usually adopts a fixed threshold value to perform abnormality or fault early warning, and cannot adapt to the change of the working state of the motor and the difference under different working conditions, so that false alarm or missing alarm can be caused, and the detection capability of the motor abnormality is reduced.
To overcome these limitations, modern central control systems employ more advanced monitoring and control techniques to improve the perceptibility of the operating state of the servo motor and the anomaly detection capability. A method for detecting abnormal condition of motor includes utilizing multiple parameters to monitor and analyze multiple parameters such as speed, current and temp. of motor, carrying out comprehensive analysis on correlation and mutual influence between these parameters so as to fully sense working state of motor. The other method is to adopt an intelligent monitoring and control algorithm, and the central control system can model and predict the working state of the motor by using machine learning, pattern recognition and other technologies. Through learning and analyzing historical data, the central control system can automatically adjust the threshold value and perform dynamic early warning and control according to the working state of the motor, so that the accuracy and the sensitivity to abnormal conditions of the motor can be improved.
In one embodiment of the present invention, fig. 1 is a block diagram of a central control system for a compound machine tool according to an embodiment of the present invention. As shown in fig. 1, a central control system 100 for a complex machine tool according to an embodiment of the present invention includes: a central processor 110 for receiving and processing signals from the various subsystems; a motion controller 120 for controlling the motion of the respective axes of the machine tool; the numerical control system 130 is used for executing a numerical control program and displaying information of a machining process; a human-machine interface 140 for interacting with an operator and setting parameters; a monitoring system 150 for monitoring the working state and fault diagnosis of the machine tool; and a communication module 160 for data transmission and remote control with an external device.
The central processing unit is the core of the central control system and is used for receiving and processing signals from all subsystems, and when the central processing unit is selected, the computing capacity, stability and reliability of the central processing unit are considered, and the high-performance central processing unit can provide faster data processing speed and higher system response capacity, so that the processing efficiency and accuracy of the machine tool are improved.
The motion controller is responsible for controlling the motion of each axis of the machine tool, and when the motion controller is configured, the excellent motion controller can realize high-precision axis motion control in consideration of control precision, motion smoothness and response speed, and ensure the stability and precision of the machining process.
The numerical control system is a key module for executing a numerical control program and displaying processing procedure information, and when the numerical control system is selected, the programming flexibility, the friendly operation interface and the functional completeness of the numerical control system are considered. The advanced numerical control system can provide rich programming functions and visual operation interfaces, and helps operators to quickly and accurately set processing parameters and monitor the processing process.
The human-computer interface is used for interacting with an operator and setting parameters, and the usability, the visualization degree and the operation convenience of the human-computer interface are considered when the human-computer interface is designed. The visual and concise man-machine interface can improve the working efficiency and accuracy of operators and reduce risks caused by operation errors and misoperation.
The monitoring system is used for monitoring the working state of the machine tool and carrying out fault diagnosis, and the data acquisition capacity, the abnormality detection algorithm and the alarm mechanism of the monitoring system are considered when the monitoring system is configured. The advanced monitoring system can collect and analyze the operation data of the machine tool in real time, discover potential faults or abnormal conditions in time, and improve the safety and reliability of the machine tool.
The communication module is used for carrying out data transmission and remote control with external equipment, and the communication speed, stability and compatibility of the communication module are considered when the communication module is selected. The reliable communication module can realize seamless connection of the machine tool and other equipment, support data transmission and remote monitoring, and improve the intelligent and automatic level of the machine tool.
The good configuration and cooperative work of each module can improve the overall performance and the function of the central control system, so that the machining efficiency, precision and reliability of the machine tool are improved. Meanwhile, attention is paid to selecting high-quality hardware and advanced technology to ensure the stability and reliability of a central control system and meet the requirements of a compound processing machine tool.
Accordingly, since the monitoring system 150 is capable of monitoring the operation of the various subsystems of the machine tool in real time. In a monitoring system, the running state of a servo motor or a stepping motor is monitored and analyzed in real time to help know the working state of the servo motor and find out abnormal conditions in time, which is the key for ensuring the normal running of a machine tool. Specifically, if the speed of the motor exceeds a preset range during operation of the monitoring system, it may be caused by motor driver malfunction, sensor damage, or control signal distortion. If the motor current is abnormal, it may be caused by excessive processing load, transmission system failure, or power supply problems. If the motor temperature is abnormal, it may be caused by overload, cooling system failure, or excessive ambient temperature. The monitoring system is used for processing the parameter data of the servo motors, so that the running state of the servo motors can be monitored in real time, and abnormal conditions can be found timely, therefore, the monitoring system can help operators to quickly find and solve potential problems, faults and damages in the running process of the machine tool are avoided, and the reliability and the production efficiency of the machine tool are improved.
Based on the above, the technical concept of the method is to collect the speed value, the current value and the temperature value of the servo motor through real-time monitoring, introduce a data processing and analyzing algorithm at the rear end to conduct time sequence collaborative analysis of the parameters of the servo motor, so as to monitor the working state of the servo motor, help operators to know the working state information of the servo motor more intuitively and accurately, help the operators to master the running condition of a machine tool better, take measures in time to handle abnormal conditions, ensure the processing quality and efficiency, and improve the safety and reliability of the machine tool.
In one embodiment of the present application, the monitoring system 150 includes: the data acquisition module is used for acquiring speed values, current values and temperature values of the monitored servo motor at a plurality of preset time points in a preset time period; the multi-parameter time sequence arrangement module is used for arranging the speed values, the current values and the temperature values of the plurality of preset time points into a servo motor multi-parameter time sequence coordination matrix according to the time dimension and the sample dimension; the multi-parameter time sequence feature extraction module is used for carrying out feature extraction on the multi-parameter time sequence cooperative matrix of the servo motor through a multi-parameter local time sequence association mode feature extractor based on the deep neural network model so as to obtain a multi-parameter time sequence feature diagram of the servo motor; the global perception enhancement module is used for carrying out global perception and feature association enhancement processing on the multi-parameter time sequence feature map of the servo motor so as to obtain multi-parameter time sequence features of the mode-display global perception servo motor; and the working state abnormality detection module is used for determining whether the working state of the monitored servo motor is abnormal or not based on the mode-display global perception servo motor multi-parameter time sequence characteristics.
The deep neural network model is a convolutional neural network model.
And in the data acquisition module, acquiring speed values, current values and temperature values of the monitored servo motor at a plurality of preset time points in a preset time period. When the data acquisition module is designed, the acquisition frequency, the precision and the stability are considered, and the high-quality data acquisition module can ensure that the operation data of the servo motor can be accurately and reliably acquired, so that a reliable basis is provided for subsequent analysis and processing.
In the multi-parameter time sequence arrangement module, speed values, current values and temperature values of a plurality of preset time points are arranged into a servo motor multi-parameter time sequence coordination matrix according to a time dimension and a sample dimension. When the multi-parameter time sequence arrangement module is designed, the organization structure and the storage mode of the data are considered, and the reasonable data arrangement mode can facilitate the subsequent feature extraction and analysis.
And in the multi-parameter time sequence feature extraction module, a multi-parameter local time sequence correlation mode feature extractor based on a deep neural network model is utilized to extract features of a multi-parameter time sequence coordination matrix of the servo motor so as to obtain a multi-parameter time sequence feature diagram of the servo motor. When designing the multi-parameter time sequence feature extraction module, proper feature extraction algorithm and model structure are selected to extract representative and distinguishing features.
And in the global perception enhancement module, performing global perception and feature association enhancement processing on the multi-parameter time sequence feature map of the servo motor to obtain the multi-parameter time sequence feature of the mode-display global perception servo motor. When the global perception enhancement module is designed, how to use global information and context correlation is considered to further process and enhance the feature map so as to improve the perception capability of the working state of the servo motor.
In the working state abnormality detection module, whether the working state of the monitored servo motor is abnormal or not is determined based on the multi-parameter time sequence characteristics of the mode-display global perception servo motor. When the working state abnormality detection module is designed, a proper abnormality detection algorithm and model are established, and proper threshold values and rules are set so as to realize accurate detection and early warning of the working state of the servo motor.
The good configuration and cooperative work of the modules can improve the sensing and abnormality detection capability of the working state of the servo motor, discover potential faults or abnormal conditions in time and improve the safety and reliability of the machine tool. Meanwhile, the performance and effect of the module are optimized by selecting a proper algorithm and model, so that the requirements of the compound processing machine tool on working state monitoring and fault diagnosis are met.
Specifically, in the technical scheme of the application, first, speed values, current values and temperature values of a monitored servo motor at a plurality of preset time points in a preset time period are obtained. Then, considering that the speed value, the current value and the temperature value of the servo motor to be monitored have a time sequence dynamic change rule in the time dimension, and the monitoring parameters of the servo motors have a time sequence association relationship, the association relationship is critical to the working state monitoring of the servo motor. Therefore, in the technical scheme of the application, the speed value, the current value and the temperature value of the plurality of preset time points are required to be arranged into a multi-parameter time sequence coordination matrix of the servo motor according to the time dimension and the sample dimension, so that the distribution information of the speed value, the current value and the temperature value of the monitored servo motor in the time dimension and the sample dimension is integrated.
And then, carrying out feature mining on the multi-parameter time sequence collaborative matrix of the servo motor by a multi-parameter local time sequence association mode feature extractor based on a convolutional neural network model so as to extract time sequence association feature distribution information of each parameter of the monitored servo motor in a time dimension, thereby obtaining a multi-parameter time sequence feature diagram of the servo motor.
Further, consider that since convolution is a typical local operation, it can only extract multi-parameter local timing correlation features about the servo motor, but cannot focus on global correlation information. That is, the convolution operation can only perform feature extraction and analysis by the information of the local area, however, in the compound processing machine tool, the operation state of the servo motor is often affected by a plurality of parameters, and the parameters may have correlation at different time points and different spatial positions of the matrix. Therefore, the global characteristics and the interrelationships of the working state of the motor cannot be fully captured only through local perception, and the working state detection precision of the servo motor can be influenced. Therefore, in the technical scheme of the application, the multi-parameter time sequence characteristic diagram of the servo motor is further obtained through a non-local neural network model. It should be appreciated that the non-local neural network model is capable of capturing long-range dependencies between different locations in the timing diagram, thereby enabling global perception. The non-local neural network model is used for processing, so that the dependency information of each position in the multi-parameter time sequence characteristic diagram of the servo motor can be subjected to global interaction and integration, and therefore more comprehensive and accurate characteristic representation is obtained.
In a compound machine tool, there may be various abnormal modes of operation of the servo motor, such as vibration, overload, temperature abnormality, and the like. These anomaly patterns tend to have certain timing characteristics and spatial correlation. However, due to the complexity of the data and the presence of noise, these abnormal patterns may be confused or masked and difficult to accurately detect and identify. Therefore, in order to enhance the feature expression capability, the abnormal mode is more easily detected, and the mode-developed global sensing servo motor multi-parameter time sequence feature diagram is further obtained through the feature autocorrelation strengthening module. Specifically, the feature autocorrelation strengthening module can strengthen the correlation among features and the significance of time sequence patterns by carrying out autocorrelation operation on the feature graphs, and can capture and highlight repeated patterns and time sequence variation trends in the feature graphs. By pattern visualization, the abnormal pattern may exhibit more pronounced features in the feature map and thus be more easily detected and identified.
In one embodiment of the present application, the global perception enhancement module includes: the global sensing unit is used for enabling the multi-parameter time sequence feature diagram of the servo motor to pass through a non-local neural network model to obtain a multi-parameter time sequence feature diagram of the global sensing servo motor; and the characteristic autocorrelation correlation reinforcement unit is used for carrying out characteristic autocorrelation correlation reinforcement analysis on the multi-parameter time sequence characteristic diagram of the global perception servo motor so as to obtain the multi-parameter time sequence characteristic of the mode-developed global perception servo motor.
The characteristic autocorrelation correlation strengthening unit is used for: and the multi-parameter time sequence characteristic diagram of the mode-display global sensing servo motor is obtained through a characteristic autocorrelation strengthening module and is used as the multi-parameter time sequence characteristic of the mode-display global sensing servo motor.
And then, the mode-display global perception servo motor multi-parameter time sequence feature diagram is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the working state of the monitored servo motor is abnormal or not. That is, the multi-parameter time sequence collaborative correlation characteristic information of the servo motor after characteristic display and global perception reinforcement is used for classification processing, so that the working state of the servo motor is monitored, an operator is helped to more intuitively and accurately know the working state information of the servo motor, and the operation condition of a machine tool is helped to be mastered better.
In a specific embodiment of the present application, the working state anomaly detection module is configured to: and the mode-display universe perception servo motor multi-parameter time sequence feature diagram is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the working state of the monitored servo motor is abnormal or not.
In one embodiment of the present application, the central control system for a composite machine tool further includes a training module for training the multi-parameter local time-series correlation mode feature extractor based on the convolutional neural network model, the non-local neural network model, the feature autocorrelation strengthening module, and the classifier. The training module comprises: the training data acquisition unit is used for acquiring training speed values, training current values and training temperature values of the monitored servo motor at a plurality of preset time points in a preset time period and judging whether the working state of the monitored servo motor has abnormal true values or not; the training multi-parameter time sequence arrangement unit is used for arranging the training speed values, the training current values and the training temperature values of the plurality of preset time points into a training servo motor multi-parameter time sequence cooperative matrix according to the time dimension and the sample dimension; the training multi-parameter time sequence feature extraction unit is used for extracting features of the training servo motor multi-parameter time sequence cooperative matrix through a multi-parameter local time sequence association mode feature extractor based on a deep neural network model so as to obtain a training servo motor multi-parameter time sequence feature diagram; the training universe sensing unit is used for enabling the training servo motor multi-parameter time sequence feature diagram to pass through a non-local neural network model to obtain the training universe sensing servo motor multi-parameter time sequence feature diagram; the training characteristic autocorrelation associated strengthening unit is used for enabling the training universe perception servo motor multi-parameter time sequence characteristic diagram to pass through the characteristic autocorrelation strengthening module to obtain a training mode visualization universe perception servo motor multi-parameter time sequence characteristic diagram; the training optimization unit is used for optimizing the multi-parameter time sequence feature diagram of the training mode visualization global perception servo motor to obtain the multi-parameter time sequence feature diagram of the training mode visualization global perception servo motor; the training classification unit is used for enabling the multi-parameter time sequence feature diagram of the optimized training mode visualization global perception servo motor to pass through a classifier so as to obtain a classification loss function value; and the training unit is used for training the multi-parameter local time sequence association mode feature extractor based on the convolutional neural network model, the non-local neural network model, the feature autocorrelation strengthening module and the classifier based on the classification loss function value.
In particular, in the technical scheme of the application, after the multi-parameter time sequence collaborative matrix of the training servo motor passes through the multi-parameter local time sequence correlation mode feature extractor based on the convolutional neural network model, each feature matrix of the obtained multi-parameter time sequence feature map of the training servo motor expresses the time sequence-sample cross dimension local correlation features of the training speed value, the training current value and the training temperature value, and the channel distribution of the convolutional neural network model is followed among the matrixes, so that the multi-parameter time sequence feature map of the training servo motor passes through the non-local neural network model to obtain a multi-parameter time sequence feature map of the training global perception servo motor, and the multi-parameter time sequence feature map of the training global perception servo motor is further subjected to the feature autocorrelation enhancement module to obtain a training mode-displaying global perception servo motor multi-parameter time sequence feature map.
However, the local-global associated feature distribution in the cross dimension of the training mode-visualized global perception servo motor multi-parameter time sequence feature map also causes sparsification of the overall feature representation, so that when the training mode-visualized global perception servo motor multi-parameter time sequence feature map is subjected to quasi-probability regression mapping through a classifier, the training mode-visualized global perception servo motor multi-parameter time sequence feature map has poor convergence of probability density distribution of regression probability of each feature value, and accuracy of classification results obtained through the classifier is affected.
Therefore, preference is given toOptimizing each characteristic value of the training mode visualization global perception servo motor multi-parameter time sequence characteristic diagram, wherein the specific expression is as follows: optimizing the multi-parameter time sequence feature diagram of the training mode visualization global perception servo motor by using the following optimization formula to obtain the multi-parameter time sequence feature diagram of the optimization training mode visualization global perception servo motor; wherein, the optimization formula is:wherein (1)>And->Is the multi-parameter time sequence characteristic diagram of the training mode visualization global perception servo motor>Is>And->Characteristic value, and->Is the multi-parameter time sequence characteristic diagram of the training mode visualization global perception servo motor>Global feature mean,/, of>Is the +.f. of the multi-parameter time sequence feature diagram of the optimized training mode visualization global perception servo motor>Personal characteristic value->Representing the calculation of a value of a natural exponent function that is a power of a value.
Specifically, aiming at the training mode, the multi-parameter time sequence characteristic diagram of the global perception servo motor is displayedLocal probability density mismatch of probability density distribution in probability space caused by sparse distribution in high-dimensional feature space simulates a multi-parameter time sequence feature diagram>Global self-consistent relation of coding behaviors of high-dimensional features in probability space to adjust error landscapes of feature manifold in high-dimensional open space domain, and realizing multi-parameter time sequence feature diagram of training mode visualization global perception servo motor>Self-consistent matching type codes embedded in explicit probability space are encoded by the high-dimensional features of (2), so that the multi-parameter time sequence feature diagram of the training mode visualization global perception servo motor is improved>The convergence of the probability density distribution of the regression probabilities of (2) improves the accuracy of the classification results obtained by the classifier. Like this, can carry out servo motor's operating condition control through central control system is intelligent to help the operator to know servo motor's operating condition information more directly perceivedly and accurately, help grasping the running condition of lathe better through this kind of mode, and can take measures in time and handle abnormal conditions, thereby ensure the processingquality and the efficiency of compound machine tool, improve the security and the reliability of lathe.
In a specific embodiment of the present application, the training classification unit is configured to: the classifier processes the multi-parameter time sequence feature map of the optimized training mode visualization global perception servo motor according to the following training classification formula to obtain a training classification result, wherein the training classification formula is as follows:wherein->To the point ofIs a weight matrix>To->For the bias vector +.>Projecting the multi-parameter time sequence feature map of the optimized training mode visualization global perception servo motor into vectors; and calculating a cross entropy value between the training classification result and a true value as the classification loss function value.
In summary, the central control system 100 for a composite processing machine tool according to the embodiment of the invention is illustrated, which helps operators to more intuitively and accurately know the working state information of a servo motor, so as to help the operators to better grasp the running condition of the machine tool, take measures in time to handle abnormal conditions, ensure the processing quality and efficiency, and improve the safety and reliability of the machine tool.
As described above, the center control system 100 for a complex machine tool according to the embodiment of the present invention may be implemented in various terminal devices, such as a server or the like for center control of a complex machine tool. In one example, the central control system 100 for a complex machine tool according to an embodiment of the present invention may be integrated into the terminal device as one software module and/or hardware module. For example, the central control system 100 for a compound machine tool may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the central control system 100 for a complex machine tool can equally be one of the plurality of hardware modules of the terminal device.
Alternatively, in another example, the central control system 100 for a complex machine tool and the terminal device may be separate devices, and the central control system 100 for a complex machine tool may be connected to the terminal device through a wired and/or wireless network and transmit interactive information in a agreed data format.
In one embodiment of the present invention, fig. 2 is a flowchart of a central control method for a compound machine tool according to an embodiment of the present invention. As shown in fig. 2, a central control method for a compound machine tool according to an embodiment of the present invention includes: 210, receiving and processing signals from the various subsystems; 220, controlling the movement of each axis of the machine tool; 230, executing a numerical control program and displaying information of the machining process; 240, interacting with an operator and setting parameters; 250, monitoring the working state and fault diagnosis of the machine tool; 260, data transmission and remote control with external devices.
Fig. 3 is a schematic diagram of a system architecture of a central control method for a compound machine tool according to an embodiment of the present invention. As shown in fig. 3, the monitoring of the working state and fault diagnosis of the machine tool includes: firstly, acquiring speed values, current values and temperature values of a monitored servo motor at a plurality of preset time points in a preset time period; then, arranging the speed values, the current values and the temperature values of the plurality of preset time points into a multi-parameter time sequence coordination matrix of the servo motor according to the time dimension and the sample dimension; then, carrying out feature extraction on the multi-parameter time sequence coordination matrix of the servo motor by a multi-parameter local time sequence association mode feature extractor based on a deep neural network model so as to obtain a multi-parameter time sequence feature map of the servo motor; then, performing global sensing and feature association strengthening treatment on the multi-parameter time sequence feature map of the servo motor to obtain multi-parameter time sequence features of the mode-display global sensing servo motor; and finally, determining whether the working state of the monitored servo motor is abnormal or not based on the multi-parameter time sequence characteristics of the mode visualization global perception servo motor.
It will be appreciated by those skilled in the art that the specific operation of the respective steps in the above-described central control method for a complex machine tool has been described in detail in the above description of the central control system for a complex machine tool with reference to fig. 1, and thus, repetitive description thereof will be omitted.
Fig. 4 is an application scenario diagram of a central control system for a composite machine tool according to an embodiment of the present invention. As shown in fig. 4, in this application scenario, first, speed values (e.g., C1 as illustrated in fig. 4), current values (e.g., C2 as illustrated in fig. 4), and temperature values (e.g., C3 as illustrated in fig. 4) of a monitored servo motor at a plurality of predetermined time points within a predetermined period of time are acquired; the obtained speed value, current value and temperature value are then input into a server (e.g., S as illustrated in fig. 4) deployed with a central control algorithm for a compound machine tool, wherein the server is capable of processing the speed value, the current value and the temperature value based on the central control algorithm for the compound machine tool to determine whether there is an abnormality in the operating state of the monitored servo motor.
The foregoing description of the embodiments has been provided for the purpose of illustrating the general principles of the invention, and is not meant to limit the scope of the invention, but to limit the invention to the particular embodiments, and any modifications, equivalents, improvements, etc. that fall within the spirit and principles of the invention are intended to be included within the scope of the invention.
Claims (9)
1. A central control system for a compound machine tool, comprising:
a central processor for receiving and processing signals from the various subsystems;
a motion controller for controlling the motion of each axis of the machine tool;
the numerical control system is used for executing a numerical control program and displaying information of a machining process;
the man-machine interface is used for interacting with an operator and setting parameters;
the monitoring system is used for monitoring the working state and fault diagnosis of the machine tool;
and the communication module is used for carrying out data transmission and remote control with external equipment.
2. The central control system for a compound machine tool of claim 1, wherein the monitoring system comprises:
the data acquisition module is used for acquiring speed values, current values and temperature values of the monitored servo motor at a plurality of preset time points in a preset time period;
the multi-parameter time sequence arrangement module is used for arranging the speed values, the current values and the temperature values of the plurality of preset time points into a servo motor multi-parameter time sequence coordination matrix according to the time dimension and the sample dimension;
the multi-parameter time sequence feature extraction module is used for carrying out feature extraction on the multi-parameter time sequence cooperative matrix of the servo motor through a multi-parameter local time sequence association mode feature extractor based on the deep neural network model so as to obtain a multi-parameter time sequence feature diagram of the servo motor;
the global perception enhancement module is used for carrying out global perception and feature association enhancement processing on the multi-parameter time sequence feature map of the servo motor so as to obtain multi-parameter time sequence features of the mode-display global perception servo motor;
and the working state abnormality detection module is used for determining whether the working state of the monitored servo motor is abnormal or not based on the mode-display global perception servo motor multi-parameter time sequence characteristics.
3. The central control system for a complex machine tool of claim 2, wherein the deep neural network model is a convolutional neural network model.
4. A central control system for a compound machine tool according to claim 3, wherein the global perception enhancement module comprises:
the global sensing unit is used for enabling the multi-parameter time sequence feature diagram of the servo motor to pass through a non-local neural network model to obtain a multi-parameter time sequence feature diagram of the global sensing servo motor;
and the characteristic autocorrelation correlation reinforcement unit is used for carrying out characteristic autocorrelation correlation reinforcement analysis on the multi-parameter time sequence characteristic diagram of the global perception servo motor so as to obtain the multi-parameter time sequence characteristic of the mode-developed global perception servo motor.
5. The central control system for a complex machine tool according to claim 4, wherein the characteristic autocorrelation strengthening unit is configured to: and the multi-parameter time sequence characteristic diagram of the mode-display global sensing servo motor is obtained through a characteristic autocorrelation strengthening module and is used as the multi-parameter time sequence characteristic of the mode-display global sensing servo motor.
6. The central control system for a complex machine tool according to claim 5, wherein the operating condition abnormality detection module is configured to: and the mode-display universe perception servo motor multi-parameter time sequence feature diagram is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the working state of the monitored servo motor is abnormal or not.
7. The central control system for a complex machine tool of claim 6, further comprising a training module for training the multi-parameter local time-series correlation pattern feature extractor based on a convolutional neural network model, the non-local neural network model, the feature autocorrelation strengthening module, and the classifier.
8. The central control system for a compound machine tool of claim 7, wherein the training module comprises:
the training data acquisition unit is used for acquiring training speed values, training current values and training temperature values of the monitored servo motor at a plurality of preset time points in a preset time period and judging whether the working state of the monitored servo motor has abnormal true values or not;
the training multi-parameter time sequence arrangement unit is used for arranging the training speed values, the training current values and the training temperature values of the plurality of preset time points into a training servo motor multi-parameter time sequence cooperative matrix according to the time dimension and the sample dimension;
the training multi-parameter time sequence feature extraction unit is used for extracting features of the training servo motor multi-parameter time sequence cooperative matrix through a multi-parameter local time sequence association mode feature extractor based on a deep neural network model so as to obtain a training servo motor multi-parameter time sequence feature diagram;
the training universe sensing unit is used for enabling the training servo motor multi-parameter time sequence feature diagram to pass through a non-local neural network model to obtain the training universe sensing servo motor multi-parameter time sequence feature diagram;
the training characteristic autocorrelation associated strengthening unit is used for enabling the training universe perception servo motor multi-parameter time sequence characteristic diagram to pass through the characteristic autocorrelation strengthening module to obtain a training mode visualization universe perception servo motor multi-parameter time sequence characteristic diagram;
the training optimization unit is used for optimizing the multi-parameter time sequence feature diagram of the training mode visualization global perception servo motor to obtain the multi-parameter time sequence feature diagram of the training mode visualization global perception servo motor;
the training classification unit is used for enabling the multi-parameter time sequence feature diagram of the optimized training mode visualization global perception servo motor to pass through a classifier so as to obtain a classification loss function value;
and the training unit is used for training the multi-parameter local time sequence association mode feature extractor based on the convolutional neural network model, the non-local neural network model, the feature autocorrelation strengthening module and the classifier based on the classification loss function value.
9. The central control system for a complex machine tool of claim 8, wherein the training classification unit is configured to:
the classifier models the optimization with the following training classification formulaProcessing a multi-parameter time sequence feature diagram of the visualization global perception servo motor to obtain a training classification result, wherein the training classification formula is as follows:wherein->To->Is a weight matrix>To->For the bias vector +.>Projecting the multi-parameter time sequence feature map of the optimized training mode visualization global perception servo motor into vectors; and
and calculating a cross entropy value between the training classification result and a true value as the classification loss function value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311461920.9A CN117420792A (en) | 2023-11-06 | 2023-11-06 | Central control system for composite processing machine tool |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311461920.9A CN117420792A (en) | 2023-11-06 | 2023-11-06 | Central control system for composite processing machine tool |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117420792A true CN117420792A (en) | 2024-01-19 |
Family
ID=89528140
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311461920.9A Pending CN117420792A (en) | 2023-11-06 | 2023-11-06 | Central control system for composite processing machine tool |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117420792A (en) |
-
2023
- 2023-11-06 CN CN202311461920.9A patent/CN117420792A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104808585B (en) | A kind of quick inspection method of lathe health status | |
| CN112034789A (en) | Health assessment method, system and assessment terminal for key parts and complete machine of numerical control machine tool | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN108873830A (en) | A kind of production scene online data collection analysis and failure prediction system | |
| Tansel et al. | Detecting chatter and estimating wear from the torque of end milling signals by using Index Based Reasoner (IBR) | |
| US20190005413A1 (en) | Control device and machine learning device | |
| CN111459700A (en) | Method and apparatus for diagnosing device failure, diagnostic device, and storage medium | |
| CN101733678B (en) | Graphical cutter position tracking and controlling system and method | |
| WO2023151166A1 (en) | Dynamic protection method for mechanical part of machine tool, and computer numerical control machine tool device | |
| CN117251812A (en) | High-voltage power line operation fault detection method based on big data analysis | |
| CN207457811U (en) | A kind of numerically-controlled machine tool intelligent trouble diagnosis device | |
| TWM575368U (en) | Cloud computing system for intelligent machine tools | |
| CN114800040B (en) | Cutter wear monitoring method and system related to process-state data | |
| CN113341879A (en) | Data acquisition and monitoring method and system for numerical control machine tool | |
| CN115146798A (en) | Assembly robot full-process monitoring and assisting method and system based on body data | |
| Kang et al. | An integrated energy data analytics approach for machine tools | |
| CN105807716B (en) | Remanufacture lathe health monitoring systems | |
| CN113051685B (en) | Numerical control equipment health state evaluation method, system, equipment and storage medium | |
| CN114519382A (en) | Nuclear power plant key operation parameter extraction and abnormity monitoring method | |
| CN117420792A (en) | Central control system for composite processing machine tool | |
| CN117170310A (en) | Digital twin-based remote fault diagnosis method and system for numerical control machine tool | |
| CN111993158B (en) | Method for generating tool detection model, method, system, device and medium for detecting tool detection model | |
| TW202014814A (en) | Tools monitoring system and monitoring method thereof | |
| CN111531581B (en) | Industrial robot fault action detection method and system based on vision | |
| CN117826770B (en) | Abnormal monitoring method and system of bearing valve seat milling control system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |