CNC machine tool operation status monitoring system based on digital twin

Abstract

The present invention discloses a CNC machine tool operation status monitoring system based on digital twins, which relates to the field of CNC machine tools and includes an operation status data acquisition module, a data processing module, a twin device construction module, and an operation status determination module. By determining whether the acquired operation status data of the CNC machine tool to be monitored is abnormal, and when it is determined that the operation process data is abnormal, the operation status of the sensor data acquisition submodule that collects the abnormal operation process data is determined. When it is determined that the operation status of the sensor data acquisition submodule is normal, the operation process time series data d is calculated. i The difference De at different sampling moments, when it is determined that the operating state of the sensor data acquisition submodule is abnormal, constructs an operation process data prediction model, calculates the difference Dy between the predicted value and the sampling value of the operation process data, and determines the operating state of the monitored CNC machine tool based on the calculation result of the difference.

Description

Technical Field

[0001] The present invention relates to the field of CNC machine tools, and in particular to a CNC machine tool operation status monitoring system based on digital twins. Background Art

[0002] As a widely used production tool in the field of mechanical manufacturing, CNC machine tools have brought huge benefits to the mechanical manufacturing industry, and their development is of great significance to the manufacturing of intelligent equipment. At present, CNC machine tools are developing in the direction of digitalization and intelligence, and the production process is becoming increasingly complex and refined. It is particularly important to monitor the working status of CNC machine tools. Digital twin technology is based on data, with models as the core and software as the carrier. It maps the status and behavior of physical equipment in the production environment in real time. It is widely used to improve the debugging quality of electromechanical systems of CNC machine tools in complex processing environments.

[0003] At present, the basis for using digital twin technology to monitor the operation status of CNC machine tools is to realize the interaction between data and models. Generally, the data types obtained include the internal working condition data of the CNC machine tool and the external sensor data. For the acquisition of external sensor data, various sensors are installed on various key components of the machine tool to obtain operation data, such as installing force sensors on the tool holder to obtain cutting force data, installing current and power sensors in the machine tool electrical cabinet to obtain machine tool current and power signals, and installing acceleration sensors on the machine tool bed to obtain machine tool vibration. In the actual operation process, due to the complex working environment of the machine tool and the high failure rate of the sensor equipment under the influence of multiple factors, there is a deviation between the real-time operation data collected and the actual situation, which makes the decision-making unit inaccurate in judging the operation status of the machine tool. To this end, we propose a CNC machine tool operation status monitoring system based on digital twins. Summary of the invention

[0004] The main purpose of the present invention is to provide a CNC machine tool operation status monitoring system based on digital twins, which can effectively solve the problems in the background technology.

[0005] In order to achieve the above object, the technical solution adopted by the present invention is:

[0006] The CNC machine tool operation status monitoring system based on digital twins includes an operation status data acquisition module, a data processing module, a twin device construction module, and an operation status determination module;

[0007] The data acquisition module is used to obtain the operating status data of the CNC machine tool to be monitored, including internal working condition data and operation process data.

[0008] The data acquisition module includes an internal working condition data acquisition submodule for acquiring internal working condition data from the electromechanical equipment controller and a sensor data acquisition submodule for acquiring working process data of the machine tool motion component;

[0009] The data processing module is used to perform time registration and fusion of different types of collected data to obtain fused operating status data;

[0010] The twin device construction module is used to construct a twin device model of the CNC machine tool to be monitored, including an equipment data acquisition submodule for collecting physical parameters of the CNC machine tool to be monitored and the workpiece to be processed, a virtual body construction submodule for building a digital model of the CNC machine tool to be monitored and the workpiece to be processed, a data interaction submodule for obtaining fused operating status data, and a data driving submodule for driving the digital model to perform dynamic processing simulation;

[0011] The operation status determination module is used to determine the operation status of the CNC machine tool to be monitored according to the acquired operation status data, and to perform alarm processing when the determination result is abnormal. The operation status determination module includes a sensor data determination submodule for determining abnormal operation process data, a sensor operation status determination submodule for determining the operation status of the sensor data acquisition submodule, and a machine tool operation status determination submodule for determining the operation status of the CNC machine tool to be monitored;

[0012] The system also includes a memory, a processor, and an electronic program stored in the memory and capable of running on the processor;

[0013] The method for determining the operating status of the CNC machine tool to be monitored comprises the following steps:

[0014] Step 1: Determine whether the acquired operation process data has any abnormality. The operation process data abnormality determination method includes the quartile method. The specific determination steps are as follows:

[0015] Step s11: Obtain the time series data d of the i-th type of operation process in period T i , i=1,2,3,...;

[0016] Step s12: Arrange all acquired operation process time series data in ascending order;

[0017] Step s13: Calculate the first quartile Q of the acquired data 1i , the calculation formula is: , according to the first quartile Q 1i Determine the first quartile, where λ i is the total number of samples collected from the time series data of the i-th type of operation process within period T;

[0018] Step s14: Calculate the third quartile Q of the acquired data 3i , the calculation formula is: , according to the third quartile Q 3i Determine the third quartile;

[0019] Step s15: Based on the determined first quartile Q 1i and the third quartile Q 3i Calculate the time series data d of the i-th type of operation process i IQR i The value is calculated as: ;

[0020] Step s16: Set the threshold of the time series data of the i-th type of operation process to 1.5 times the IQR i , calculate the upper IQR according to the set threshold imax and lower IQR imin , the calculation formula is:

[0021] IQR imax =Q 3i +1.5*IQR i ;

[0022] IQR imin =Q 1i -1.5*IQR i ;

[0023] Step s17: Based on the j-th collected operation process time series data d ij The upper and lower limits of the threshold are used to determine the value. The determination principle is:

[0024] When ij >IQR imax or ij <IQR imin When the data d is obtained, ij is an outlier;

[0025] When IQR imax ≥d ij ≥IQR imin When the data d is obtained, ij is the normal value;

[0026] Step 2: When it is determined that the operation process data is abnormal, the operating state of the sensor data acquisition submodule that collects the abnormal operation process data is determined. The determination method is specifically as follows:

[0027] Step s21: Acquire all sensor data acquisition submodule types, including sensor data acquisition submodule 1, sensor data acquisition submodule 2, ..., sensor data acquisition submodule i;

[0028] Step s22: Calculate the operation process data d collected by the sensor data collection submodule p where there is an abnormality in the operation process data p The operation process data d obtained by any other sensor data acquisition submodule q q The correlation coefficient r pq , where q=1,2,...,i-1; q≠p;

[0029] Step s23: Screening correlation coefficient r pq The sensor data acquisition submodule u corresponding to the maximum value is used as a strongly correlated submodule, and the operation process data of the strongly correlated submodule is obtained as the strongly correlated operation process data d u ;

[0030] Step s24: the strongly correlated operation process data d u Whether it is an outlier is determined. If the data d p is an outlier and has strong correlation with the process data d u When it is a normal value, the operating state of the sensor data acquisition submodule is determined to be abnormal, otherwise, it is determined to be normal;

[0031] Step 3: According to the operation status determination result of the sensor data acquisition submodule, the operation status of the CNC machine tool to be monitored is determined. The specific process is as follows;

[0032] When the sensor data acquisition submodule is judged to be in normal operation, the time series data d of the i-th type of operation process in the period T is calculated. i The difference De between the current sampling time t and the previous sampling time t-1 is calculated as:

[0033]

[0034] Where n is the total number of data types in the operation process; ω i is the weight of the time series data of the i-th type of operation process, and ;d it is the sampling value of the process data of the i-th type of operation at the current sampling time t; d i（t-1） is the sampling value of the operation process data at the previous sampling time t-1, and the operating state of the CNC machine tool to be monitored is determined according to the calculation result of the difference degree;

[0035] When the sensor data acquisition submodule is judged to be operating abnormally, a prediction model for the operation process data is constructed. According to the prediction value of the operation process data at the current sampling time t within the model output cycle T, the difference Dy between the prediction value of the operation process data and the sampling value of the operation process data at the previous sampling time t-1 is calculated. The calculation formula is:

[0036]

[0037] Where Pd it is the predicted value of the process data of the i-th type of operation at the current sampling time t, Pd it The calculation formula is:

[0038]

[0039] In the formula, It is expressed as the predicted value of the k-th abnormal operation process data at sampling time t, It is represented as the sampling value of the k-th abnormal operation process data at the sampling time t-1, a is a constant coefficient, a∈(0,1), k∈i;

[0040] The operating status of the CNC machine tool to be monitored is determined based on the calculation results of the difference degree. The determination principle is:

[0041] When the sensor data acquisition submodule is in normal operation and De≤Da, it is determined that the operation status of the CNC machine tool to be monitored is normal;

[0042] When the operating state of the sensor data acquisition submodule is normal and De>Da, it is determined that the operating state of the CNC machine tool to be monitored is abnormal;

[0043] When the operating state of the sensor data acquisition submodule is abnormal and Dy≤Db, it is determined that the operating state of the CNC machine tool to be monitored is normal;

[0044] When the operating state of the sensor data acquisition submodule is abnormal, and Dy>Db, it is determined that the operating state of the CNC machine tool to be monitored is abnormal.

[0045] Furthermore, the internal working condition data include the X-direction position, Y-direction position, Z-direction position, C-axis rotation angle, cycle start, line number, rotation speed, feed speed, rotation repair, repair, fast shift adjustment, and emergency stop parameters of the CNC machine tool to be monitored during operation; the operation process data include the current, vibration, and sound parameters of the CNC machine tool to be monitored during operation.

[0046] The present invention has the following beneficial effects:

[0047] Compared with the prior art, the technical solution of the present invention determines whether the acquired operating status data of the CNC machine tool to be monitored is abnormal, and when it is determined that the operation process data is abnormal, the operating status of the sensor data acquisition submodule that collects the abnormal operation process data is determined, and when it is determined that the operating status of the sensor data acquisition submodule is normal, the operation process time series data d is calculated. iThe difference De at different sampling moments, when it is judged that the operating state of the sensor data acquisition submodule is abnormal, constructs an operation process data prediction model, calculates the difference Dy between the operation process data prediction value and the sampling value, and judges the operating state of the monitored CNC machine tool according to the calculation result of the difference. Based on the digital twin technology, real-time monitoring of the operating state of the CNC machine tool is realized, which can effectively solve the problems of inaccurate collection data and inaccurate judgment of the operating state caused by failure of the sensor equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a logic control block diagram of the CNC machine tool operation status monitoring system based on digital twin of the present invention;

[0049] Figure 2 This is a structural block diagram of the CNC machine tool operation status monitoring system based on digital twins of the present invention. DETAILED DESCRIPTION

[0050] The present invention will be further described below in conjunction with specific implementation methods, wherein the accompanying drawings are only used for exemplary descriptions and represent only schematic diagrams rather than actual drawings, and should not be understood as limiting the present invention. In order to better illustrate the specific implementation methods of the present invention, some parts of the accompanying drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product.

[0051] Example 1

[0052] like Figure 1-2 As shown, the specific implementation process of the technical solution of the present invention includes the following steps:

[0053] Step 1): Collect and obtain the physical parameters of the CNC machine tool to be monitored and the workpiece to be processed, including the size, shape, assembly features of each component of the machine tool and the size of the workpiece to be processed, and build a virtual model of the CNC machine tool to be monitored based on the acquired parameters;

[0054] Step 2): Obtain the operating status data of the CNC machine tool to be monitored, including internal working condition data and operation process data. The internal working condition data includes the X-direction position, Y-direction position, Z-direction position, C-axis rotation angle, cycle start, line number, speed, feed speed, rotation repair, repair, fast shift adjustment, and emergency stop parameters of the CNC machine tool to be monitored during operation; the operation process data includes the current, vibration, and sound parameters of the CNC machine tool to be monitored during operation;

[0055] Step 3): Perform time registration and fusion on the acquired operation status data to obtain the fused operation status data, and interact the fused data with the constructed machine tool virtual model through the data interaction submodule, and drive the digital model to perform dynamic processing simulation through the data driving submodule;

[0056] Step 4): Determine the operating status of the CNC machine tool to be monitored based on the acquired operating status data. The specific steps are as follows:

[0057] Step 41: Determine whether the acquired operation process data is abnormal. The operation process data abnormality determination method includes the quartile method. The determination steps are as follows:

[0058] Step s11: Obtain the time series data d of the i-th type of operation process in period T i , i=1,2,3,...;

[0059] Step s12: Arrange all acquired operation process time series data in ascending order;

[0060] Step s13: Calculate the first quartile Q of the acquired data 1i , the calculation formula is: , according to the first quartile Q 1i Determine the first quartile, where λ i is the total number of samples collected from the time series data of the i-th type of operation process within period T;

[0061] Step s14: Calculate the third quartile Q of the acquired data 3i , the calculation formula is: , according to the third quartile Q 3i Determine the third quartile;

[0062] Step s15: Based on the determined first quartile Q 1i and the third quartile Q 3i Calculate the time series data d of the i-th type of operation process i IQR i The value is calculated as: ;

[0063] Step s16: Set the threshold of the time series data of the i-th type of operation process to 1.5 times the IQR i , calculate the upper IQR according to the set threshold imax and lower IQR imin , the calculation formula is:

[0064] IQR imax =Q 3i +1.5*IQR i ;

[0065] IQR imin =Q 1i -1.5*IQR i ;

[0066] Step s17: Based on the j-th collected operation process time series data d ijThe upper and lower limits of the threshold are used to determine the value. The determination principle is:

[0067] When ij >IQR imax or ij <IQR imin When the data d is obtained, ij is an outlier;

[0068] When IQR imax ≥d ij ≥IQR imin When the data d is obtained, ij is the normal value;

[0069] Step 42: When it is determined that the operation process data is abnormal, the operation state of the sensor data acquisition submodule that collects the abnormal operation process data is determined. The determination method is specifically as follows:

[0070] Step s21: Acquire all sensor data acquisition submodule types, including sensor data acquisition submodule 1, sensor data acquisition submodule 2, ..., sensor data acquisition submodule i;

[0071] Step s22: Calculate the operation process data d collected by the sensor data collection submodule p where there is an abnormality in the operation process data p The operation process data d obtained by any other sensor data acquisition submodule q q The correlation coefficient r pq , where q=1,2,...,i-1; q≠p;

[0072] Step s23: Screening correlation coefficient r pq The sensor data acquisition submodule u corresponding to the maximum value is used as a strongly correlated submodule, and the operation process data of the strongly correlated submodule is obtained as the strongly correlated operation process data d u ;

[0073] Step s24: For strongly correlated operation process data d u Whether it is an outlier is determined. If the data d p is an outlier and has strong correlation with the process data d u When it is a normal value, the operating state of the sensor data acquisition submodule is determined to be abnormal, otherwise, it is determined to be normal;

[0074] Step 43: According to the operation status determination result of the sensor data acquisition submodule, the operation status of the CNC machine tool to be monitored is determined. The specific process is as follows;

[0075] When the sensor data acquisition submodule is judged to be in normal operation, the time series data d of the i-th type of operation process in the period T is calculated.i The difference De between the current sampling time t and the previous sampling time t-1 is calculated as:

[0076]

[0077] Where n is the total number of data types in the operation process; ω i is the weight of the time series data of the i-th type of operation process, and ;d it is the sampling value of the process data of the i-th type of operation at the current sampling time t; d i（t-1） is the sampling value of the operation process data at the previous sampling time t-1, and the operating state of the CNC machine tool to be monitored is determined according to the calculation result of the difference degree;

[0078] When the sensor data acquisition submodule is judged to be operating abnormally, a prediction model for the operation process data is constructed. According to the prediction value of the operation process data at the current sampling time t within the model output cycle T, the difference Dy between the prediction value of the operation process data and the sampling value of the operation process data at the previous sampling time t-1 is calculated. The calculation formula is:

[0079]

[0080] Where Pd it is the predicted value of the process data of the i-th type of operation at the current sampling time t, Pd it The calculation formula is:

[0081]

[0082] In the formula, It is expressed as the predicted value of the k-th abnormal operation process data at sampling time t, It is represented as the sampling value of the k-th abnormal operation process data at the sampling time t-1, a is a constant coefficient, a∈(0,1), k∈i;

[0083] The operating status of the CNC machine tool to be monitored is determined based on the calculation results of the difference degree. The determination principle is:

[0084] When the sensor data acquisition submodule is in normal operation and De≤Da, it is determined that the operation status of the CNC machine tool to be monitored is normal;

[0085] When the sensor data acquisition submodule is in normal operation and De>Da, the operation status of the CNC machine tool to be monitored is determined to be abnormal, and an alarm is performed when the determination result is abnormal;

[0086] When the operating state of the sensor data acquisition submodule is abnormal and Dy≤Db, it is determined that the operating state of the CNC machine tool to be monitored is normal;

[0087] When the operating state of the sensor data acquisition submodule is abnormal and Dy>Db, the operating state of the CNC machine tool to be monitored is determined to be abnormal, and an alarm is processed when the determination result is abnormal.

[0088] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It should be understood by those skilled in the art that the present invention is not limited to the above embodiments. The above embodiments and descriptions are only for explaining the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention to be protected. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. The CNC machine tool operation status monitoring system based on digital twin is characterized by: It includes operation status data acquisition module, data processing module, twin device construction module and operation status determination module; The data acquisition module is used to obtain the operating status data of the CNC machine tool to be monitored, including internal working condition data and operation process data, and the data acquisition module includes an internal working condition data acquisition submodule for acquiring internal working condition data from the electromechanical equipment controller and a sensor data acquisition submodule for acquiring the operation process data of the machine tool motion component; The data processing module is used to perform time registration and fusion of different types of collected data to obtain fused operating status data; The twin device construction module is used to construct a twin device model of the CNC machine tool to be monitored, including an equipment data acquisition submodule for collecting physical parameters of the CNC machine tool to be monitored and the workpiece to be processed, a virtual body construction submodule for building a digital model of the CNC machine tool to be monitored and the workpiece to be processed, a data interaction submodule for obtaining fused operating status data, and a data driving submodule for driving the digital model to perform dynamic processing simulation; The operation status determination module is used to determine the operation status of the CNC machine tool to be monitored according to the acquired operation status data, and to perform alarm processing when the determination result is abnormal. The operation status determination module includes a sensor data determination submodule for determining abnormal operation process data, a sensor operation status determination submodule for determining the operation status of the sensor data acquisition submodule, and a machine tool operation status determination submodule for determining the operation status of the CNC machine tool to be monitored; The method for determining the operating status of the CNC machine tool to be monitored comprises the following steps: Step 1: Determine whether the acquired operation process data has any abnormality; Step 2: When it is determined that the operation process data is abnormal, the operation state of the sensor data acquisition submodule that collects the abnormal operation process data is determined; Step 3: According to the operation status determination result of the sensor data acquisition submodule, the operation status of the CNC machine tool to be monitored is determined; The internal working condition data include the X-direction position, Y-direction position, Z-direction position, C-axis rotation angle, cycle start, line number, speed, feed speed, rotation repair, repair, fast shift adjustment, and emergency stop parameters during the operation of the CNC machine tool to be monitored; the operation process data include the current, vibration, and sound parameters during the operation of the CNC machine tool to be monitored; The method for determining abnormal data during the operation process includes the quartile method, and the specific determination steps are as follows: Step s11: Obtain the time series data d of the i-th type of operation process in period T i , i=1,2,3,...; Step s12: Arrange all acquired operation process time series data in ascending order; Step s13: Calculate the first quartile Q of the acquired data 1i , the calculation formula is: According to the first quartile Q 1i Determine the first quartile, where λ i is the total number of samples collected from the time series data of the i-th type of operation process within period T; Step s14: Calculate the third quartile Q of the acquired data 3i , the calculation formula is: According to the third quartile Q 3i Determine the third quartile; Step s15: Based on the determined first quartile Q 1i and the third quartile Q 3i Calculate the time series data d of the i-th type of operation process i IQR i Value, calculated as: IQR i =Q 3i -Q 1i ; Step s16: Set the threshold of the time series data of the i-th type of operation process to 1.5 times the IQR i , calculate the upper IQR according to the set threshold imax and lower IQR imin , the calculation formula is: IQR imax JQ 3i +1.5*IQR i 100. IQR imin JQ 1i -1.5*IQR i 100. Step s17: Based on the j-th collected operation process time series data d ij The upper and lower limits of the threshold are used to determine the value. The determination principle is: When ij >IQR imax or ij <IQR imin When the data d is obtained, ij is an outlier; When IQR imax ≥d ij ≥IQR imin When the data d is obtained, ij is the normal value; The specific method for determining the operating status of the sensor data acquisition submodule is as follows: Step s21: Acquire all sensor data acquisition submodule types, including sensor data acquisition submodule 1, sensor data acquisition submodule 2, ..., sensor data acquisition submodule i; Step s22: Calculate the operation process data d collected by the sensor data collection submodule p where there is an abnormality in the operation process data p The operation process data d obtained by any other sensor data acquisition submodule q q The correlation coefficient r pq , where q=1,2,...,i-1; q≠p; Step s23: Screening correlation coefficient r pq The sensor data acquisition submodule u corresponding to the maximum value is used as a strongly correlated submodule, and the operation process data of the strongly correlated submodule is obtained as the strongly correlated operation process data d u ; Step s24: the strongly correlated operation process data d u Whether it is an outlier is determined. If the data d p is an outlier and has strong correlation with the process data d u When it is a normal value, the operating state of the sensor data acquisition submodule is determined to be abnormal, otherwise, it is determined to be normal; The specific process of step 3 is: When the sensor data acquisition submodule is judged to be in normal operation, the time series data d of the i-th type of operation process in the period T is calculated. i The difference De between the current sampling time t and the previous sampling time t-1 is used to determine the operating state of the CNC machine tool to be monitored according to the calculation result of the difference; When it is determined that the operating state of the sensor data acquisition submodule is abnormal, a working process data prediction model is constructed, and according to the working process data prediction value at the current sampling time t within the model output cycle T, the difference Dy between the working process data prediction value and the working process data sampling value at the previous sampling time t-1 is calculated, and the operating state of the CNC machine tool to be monitored is determined according to the calculation result of the difference; The expression of the operation process data prediction model is: Pd kt =a×pd k(t-1) +a(1-a)×pd k(t-2) +a(1-a) 2 ×pd k(t-3) +...+a(1-a) t-2 ×pd k1 +(1-a) t-1 ×Pd k1 Where Pd kt It is expressed as the predicted value of the k-th abnormal operation process data at sampling time t, pd k(t-1) It is represented as the sampling value of the kth abnormal operation process data at the sampling time t-1, a is a constant coefficient, a∈(0,1), k∈i.

2. The CNC machine tool operation status monitoring system based on digital twin according to claim 1 is characterized in that: The principle for judging the operating status of the CNC machine tool to be monitored based on the difference is: When the sensor data acquisition submodule is in normal operation and De≤Da, it is determined that the operation status of the CNC machine tool to be monitored is normal; When the operating state of the sensor data acquisition submodule is normal and De>Da, it is determined that the operating state of the CNC machine tool to be monitored is abnormal; When the operating state of the sensor data acquisition submodule is abnormal and Dy≤Db, it is determined that the operating state of the CNC machine tool to be monitored is normal; When the operating state of the sensor data acquisition submodule is abnormal, and Dy>Db, it is determined that the operating state of the CNC machine tool to be monitored is abnormal.

3. The CNC machine tool operation status monitoring system based on digital twin according to claim 1 is characterized in that: The calculation formula of difference degree De is: Where n is the total number of data types in the operation process; ω i is the weight of the time series data of the i-th type of operation process, and d it is the sampling value of the process data of the i-th type of operation at the current sampling time t; d i(t-1) It is the sampling value of the operation process data at the previous sampling time t-1.

4. The CNC machine tool operation status monitoring system based on digital twin according to claim 1 is characterized in that: The calculation formula of difference degree Dy is: Where Pd it It is the predicted value of the process data of the i-th type of operation at the current sampling time t.

5. The CNC machine tool operation status monitoring system based on digital twin according to claim 1 is characterized in that: The system further includes a memory, a processor, and an electronic program stored in the memory and capable of running on the processor.

Images