Numerical control machining center main shaft operation monitoring device for practical training

Abstract

The invention discloses a numerical control machining center spindle operation monitoring device for practical training, which relates to the technical field of digital control and comprises a data acquisition module, a core processing device and an alarm reminding module. The data acquisition module is used for acquiring vibration, rotating speed, voltage and current information of the main shaft and transmitting the acquired data to the core processing device; the core processing device adopts a data analysis algorithm to analyze the acquired data, judges whether the main shaft breaks down or not and sends acquired data information and fault judgment information to the remote monitoring terminal in a wireless communication mode, and the remote monitoring terminal is used for predicting the fault of the main shaft and conducting three-dimensional visual monitoring on the state of the main shaft; and the alarm reminding module is used for automatically triggering an alarm mode or an early warning mode according to the received alarm signal and a preset alarm rule to carry out alarm reminding. Through real-time monitoring and early warning, the shutdown time is shortened, the machining efficiency is improved, and stable operation of the main shaft is ensured.

Description

Technical Field

[0001] The present application relates to the field of digital control technology, and in particular to a spindle operation monitoring device for a CNC machining center used for practical training. Background Art

[0002] As the core equipment of modern manufacturing industry, the operation status of the spindle of CNC machining center is directly related to the processing quality and production efficiency. Therefore, real-time monitoring of the spindle status, especially the ability to quickly and accurately identify and arrange maintenance after a fault occurs, is particularly critical. However, most of the traditional electric spindle fault diagnosis methods rely on manual design of noise reduction, filtering, feature extraction and other processes. These processes are not only cumbersome and complicated, but also lack intelligence. In the face of massive data, manual diagnosis alone is becoming increasingly difficult. In addition, the spindle operating environment and working conditions of different equipment are different, and it is more difficult to manually extract fault features. The research on intelligent spindle fault diagnosis under complex working conditions needs to be improved. In addition, the existing spindle operation monitoring device lacks the function of data monitoring of multiple spindles, and cannot well meet the monitoring needs of practical training equipment for students majoring in mechanical or electromechanical automation. Summary of the invention

[0003] In view of this, the present application provides a spindle operation monitoring device for a CNC machining center for practical training, which solves the technical problems that most traditional spindle fault diagnosis methods rely on manual design of noise reduction, filtering, feature extraction and other processes, which are cumbersome and complicated, and the degree of intelligence is insufficient, and manual extraction of fault features is even more difficult, and the existing spindle operation monitoring devices cannot well meet the monitoring needs of practical training equipment for students majoring in mechanical or mechatronics automation.

[0004] To achieve the above object, the present invention provides the following technical solutions: A spindle operation monitoring device for a CNC machining center for practical training, comprising: a data acquisition module, a core processing device and an alarm reminder module; The data acquisition module includes a sensor group, which is used to collect the vibration information, speed information, voltage information, and current information of the main shaft, and transmit the collected information data to the core processing device through the data acquisition device; The core processing device uses a data analysis algorithm to analyze the acquired data to determine whether the spindle has a fault. According to the fault judgment result, a warning signal is sent to the alarm reminder module, and the collected data information and fault judgment information are sent to the remote monitoring terminal through wireless communication. The remote monitoring terminal is used to predict spindle faults based on historical operation monitoring data and perform three-dimensional visual monitoring of the spindle status. The alarm reminder module is electrically connected to the core processing device, and is used to automatically trigger an alarm mode or a pre-warning mode for alarm reminder according to a received alarm signal and preset alarm rules.

[0005] A training machining center is a CNC machine tool that integrates multiple machining functions. It has the ability to automatically change tools and can perform multiple processes on a workpiece that is clamped at one time. Training machining centers are usually classified according to the state of the spindle in space, mainly including vertical machining centers, horizontal machining centers, gantry machining centers, and universal machining centers.

[0006] Furthermore, the sensor group includes two groups of vibration sensors, two groups of speed sensors and a voltage and current detection circuit. The two groups of vibration sensors are arranged on the tool holder of the main shaft, and each group of vibration sensors includes two unidirectional acceleration sensors. The two groups of speed sensors include a magnetic induction encoder arranged on the rear bearing cover of the main shaft drive motor and an infrared tachometer arranged about 30 cm away from the main shaft. The vibration sensor is used to collect the vibration signal of the main shaft during operation, and the speed sensor is used to detect the speed signal of the main shaft. The parallel direction of the main shaft is the x direction, and the vertical direction of the main shaft is the y direction. The two groups of vibration sensors include two unidirectional acceleration sensors arranged in the x direction and two unidirectional acceleration sensors arranged in the y direction. The voltage and current detection circuit is used to detect the voltage information and current information corresponding to the load when the main shaft is running. The output end of the sensor group is electrically connected to the input end of the data acquisition device. The data acquisition device filters, amplifies and digitally converts the raw data collected by the sensor group, and transmits the processed data characteristic signal to the core processing device through the connecting line.

[0007] Further, the core processing device includes a comparison and analysis unit, a fault classification unit and a data communication unit; The comparison and analysis unit includes a first comparison module, a second comparison module and a third comparison module. The first comparison module is used to obtain a vibration average value for two vibration signals obtained by each group of vibration sensors to obtain two vibration average values, and compare the two vibration average values ​​with the corresponding preset vibration thresholds respectively. If the vibration average value is greater than the corresponding preset vibration threshold, a first fault signal is output to the fault classification unit, otherwise the next group of vibration average values ​​is compared with the corresponding preset vibration threshold. The second comparison module is used to obtain a speed average value for the two groups of speed signals obtained, and perform a difference calculation between the speed average value and the set speed value to obtain a speed deviation value. The set speed value is the current working speed of the spindle set by the operator, and the speed deviation value is compared with the preset speed deviation threshold. If the speed deviation value is greater than the speed deviation threshold, a second fault signal is output to the fault classification unit. The third comparison module is used to compare the detected voltage value of the drive motor with the voltage upper limit threshold and the voltage lower limit threshold, and is also used to compare the detected current value of the drive motor with the current upper limit threshold and the current lower limit threshold respectively. If the voltage value is greater than the voltage upper limit threshold or the voltage value is less than the voltage lower limit threshold or the current value is greater than the current upper limit threshold or the current value is less than the current lower limit threshold, a third fault signal is output to the fault classification unit; The fault classification unit is connected with the comparison and analysis unit and the fault database, and is used for receiving the first fault signal, the second fault signal and the third fault signal, and automatically searching and matching the fault type, location and fault treatment plan of the spindle in various working states stored in the fault database through a search rule association list according to the code corresponding to each fault signal; The data communication unit is connected to the comparison and analysis unit and the fault classification unit. The data communication unit is used to receive the vibration information, speed information, voltage information, and current information of the main shaft collected by the data acquisition module, and output the fault type, location, and fault recommended processing plan data matching the current fault signal to the alarm reminder module.

[0008] Furthermore, the alarm reminder module includes an alarm host, a voice intelligent alarm module and a light alarm module; The alarm host is used to generate a fault alarm code according to the received fault alarm signal, and send an alarm signal to the voice intelligent alarm module or the light alarm module for fault alarm prompt according to the alarm mode preset in the alarm code; The voice intelligent alarm module includes a voice alarm and a liquid crystal display. Both the voice alarm and the liquid crystal display are electrically connected to the alarm host through a connecting line. The voice alarm is used to give a voice prompt alarm according to the alarm control signal sent by the alarm host, and the liquid crystal display is used to display the fault type, location and fault recommended processing plan; The light alarm module includes a light alarm, which is electrically connected to the alarm host via a connecting line. The light alarm is used to perform a light prompt alarm according to an alarm control signal.

[0009] Furthermore, the remote monitoring terminal includes a model storage database, a data interaction module and a data drive module; The model storage database is used to mark the three-dimensional models of different spindles of the CNC machining center according to preset identifications, and store the virtual three-dimensional models of different spindles according to the marking information; The data interaction module is used to obtain the operation monitoring data of the spindle of the CNC machining center sent by the core processing device, and to extract the operation parameters of the operation monitoring data, generate model driving parameters according to the extracted operation parameter data and the preset execution control logic, and is also used to associate the spindle operation control data, text prompt data and the physical model of the spindle in the graphical user interface for display. The data driving module is connected to the data interaction module and the model storage database. The data driving module is used to obtain the corresponding spindle model data according to the spindle type number of the CNC machining center selected by the user, and drive the corresponding spindle model according to the model driving parameters to perform simulated production tasks.

[0010] Furthermore, the remote monitoring terminal also includes an operation monitoring database, a fault prediction module and a prediction status output module; The operation monitoring database is connected to the data interaction module, and the operation monitoring database is used to store the collected historical operation monitoring data of the spindle; The fault prediction module is connected to the data interaction module, and the fault prediction module is used to predict the spindle fault by using a deep learning-based fault prediction method according to the extracted historical operating parameter data within a preset period; The prediction state output module is connected to the fault prediction module. The prediction state output module is used to generate a spindle operation state monitoring and analysis report according to the prediction result. The spindle operation state monitoring and analysis report includes fault classification, risk level and maintenance suggestion.

[0011] Furthermore, the deep learning-based fault prediction method is used to predict spindle faults including: Obtain vibration data characteristic values ​​corresponding to multiple consecutive characteristic speeds; The vibration data characteristic values ​​corresponding to multiple consecutive characteristic speeds are input into the trained fault prediction model based on the ResNet18 deep convolutional network for fault identification to obtain fault identification information.

[0012] It can be seen from the above technical solution that the advantages of the present invention are: In this application, real-time monitoring and early warning are used to reduce downtime, improve processing efficiency, and preventive maintenance strategies can reduce sudden failures and reduce maintenance costs. Stable operation of the spindle is ensured, and processing accuracy and surface quality are improved. The spindle status is monitored in real time to promptly discover and deal with potential safety hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application.

[0014] Figure 1 This is a schematic diagram of the composition structure of this application.

[0015] Figure 2 This is a schematic diagram of the composition structure of the data acquisition module of this application.

[0016] Figure 3 This is a schematic diagram of the composition structure of the alarm reminder module of this application.

[0017] Figure 4 This is a schematic diagram of the composition structure of the remote monitoring terminal of this application.

[0018] Figure 5 Schematic diagram of the real-time monitoring process of the spindle operating status of this embodiment.

[0019] Figure 6 Schematic diagram of the alarm reminder process of this embodiment. DETAILED DESCRIPTION

[0020] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the implementation modes and the accompanying drawings. Here, the illustrative implementation modes and descriptions of the present application are used to explain the present application, but are not intended to limit the present application.

[0021] The CNC machining center for training is a highly automated CNC machine tool, mainly used for practical training of students majoring in mechanics or mechatronics. In order to achieve real-time monitoring and early warning of the spindle operation status of the CNC machining center for training, this technical solution proposes a spindle operation monitoring device for the CNC machining center for training, which aims to comprehensively monitor the vibration, speed, load and other key parameters of the spindle through high-precision sensors and intelligent algorithms, and provide strong support for equipment maintenance, fault diagnosis and production efficiency optimization. Figures 1 to 6, This embodiment provides a spindle operation monitoring device for a CNC machining center for practical training. The device reduces downtime and improves machining efficiency through real-time monitoring and early warning. The preventive maintenance strategy can reduce sudden failures, reduce maintenance costs, and ensure stable operation of the spindle, improve machining accuracy and surface quality. Specifically, it includes: a data acquisition module, a core processing device, and an alarm reminder module. The data acquisition module includes a sensor group, which is used to collect vibration information, speed information, voltage information, and current information of the spindle, and transmit the collected information data to the core processing device through a data acquisition device. The core processing device uses a data analysis algorithm to analyze the acquired data to determine whether the spindle has a fault, sends an early warning signal to the alarm reminder module according to the fault judgment result, and sends the collected data information and fault judgment information to a remote monitoring terminal through wireless communication. The remote monitoring terminal is used to predict spindle faults based on historical operation monitoring data and perform three-dimensional visual monitoring of the spindle status. The three-dimensional visual monitoring can provide an intuitive three-dimensional visual interface to display the operation status, historical data trends, and fault warning information of the spindle.

[0022] This application uses the monitoring signals (vibration, speed, load voltage and current) of the spindle system as important performance indicators. By integrating multi-source information such as vibration signals, voltage / current, speed, etc., and comprehensively judging the health status of the spindle, the comprehensiveness and accuracy of the diagnosis can be improved. And multi-channel analog-to-digital (A / D) synchronous sampling can be achieved through the sensor group and data acquisition device. Equipped with standard configuration interfaces such as RS485 serial port and USB interface, external multi-sensors can realize automatic data acquisition. The monitoring device uses the embedded hardware platform as the main operating platform, and combines the built-in and external sensors of the machine tool to obtain important dynamic process signals and machining process status data of the spindle operation process, so as to realize the monitoring of the operating status of the precision machining center.

[0023] Specifically, the sensor group includes two groups of vibration sensors, two groups of speed sensors and voltage and current detection circuits. The two groups of vibration sensors are arranged on the tool holder of the spindle. Each group of vibration sensors includes two unidirectional acceleration sensors. The two groups of speed sensors include a magnetic induction encoder arranged on the rear bearing cover of the driving motor of the spindle and an infrared tachometer arranged about 30 cm away from the spindle. The vibration sensor is used to collect the vibration signal of the spindle when it is running, and the speed sensor is used to detect the speed signal of the spindle. Taking the parallel direction of the spindle as the x direction and the vertical direction of the spindle as the y direction, the two groups of vibration sensors include two unidirectional acceleration sensors arranged in the x direction and two unidirectional acceleration sensors arranged in the y direction. The voltage and current detection circuit is used to detect the voltage information and current information corresponding to the load when the spindle is running. The output end of the sensor group is electrically connected to the input end of the data collector. The data collector filters, amplifies and digitally converts the raw data collected by the sensor group, and transmits the processed data feature signal to the core processing device through the connecting line. The data collector adopts a multi-channel signal collector. The voltage and current detection circuit comprises a voltage sensor and a current transformer, and the voltage sensor and the current transformer are arranged on the power supply circuit of the main shaft driving motor.

[0024] The vibration sensor can detect the vibration amplitude and frequency of the spindle, which is the key data for judging spindle wear, imbalance or looseness. The speed sensor can monitor the rotation speed of the spindle, which helps to analyze the running stability of the spindle. The voltage / current sensor can monitor the electrical parameters of the spindle drive system and identify the load condition of the spindle. The data collector is responsible for converting the analog signal collected by the sensor into a digital signal, filtering and formatting it, and efficiently transmitting it to the core processing device.

[0025] This embodiment uses the vibration signal, speed deviation signal and load electrical signal of the main shaft as research signals. In view of the fact that the data collected by a single sensor in reality is easily affected by the environment and other equipment, in order to improve the stability and redundancy of the vibration sensor, multiple sensors of the same type are used to collect data from different directions to obtain more useful information.

[0026] The core processing device includes a comparison and analysis unit, a fault classification unit and a data communication unit; the comparison and analysis unit includes a first comparison module, a second comparison module and a third comparison module. The first comparison module is used to obtain a vibration average value for two vibration signals obtained by each group of vibration sensors to obtain two vibration average values, and compare the two vibration average values ​​with the corresponding preset vibration thresholds respectively. If the vibration average value is greater than the corresponding preset vibration threshold, a first fault signal is output to the fault classification unit, otherwise the next group of vibration average values ​​is compared with the corresponding preset vibration threshold. The second comparison module is used to obtain a speed average value for the two groups of speed signals obtained, and calculate the difference between the speed average value and the set speed value to obtain a speed deviation value. The set speed value is the current working speed of the spindle set by the operator, and the speed deviation value is compared with the preset speed deviation threshold. If the speed deviation value is greater than the speed deviation threshold, a second fault signal is output to the fault classification unit. The third comparison module is used to compare the detected voltage value of the drive motor with the voltage upper limit threshold. The first fault signal is used to compare the first fault signal with the voltage lower limit threshold, and the second fault signal is used to compare the detected current value of the driving motor with the current upper limit threshold and the current lower limit threshold respectively. If the voltage value is greater than the voltage upper limit threshold or the voltage value is less than the voltage lower limit threshold or the current value is greater than the current upper limit threshold or the current value is less than the current lower limit threshold, the third fault signal is output to the fault classification unit; the fault classification unit is connected with the comparison and analysis unit and the fault database, and the fault classification unit is used to receive the first fault signal, the second fault signal and the third fault signal, and automatically search and match the fault type, position and fault recommended processing scheme of the main shaft in various working states stored in the fault database through the search rule association list according to the code corresponding to each fault signal; the data communication unit is connected with the comparison and analysis unit and the fault classification unit, and the data communication unit is used to receive the vibration information, speed information, voltage information and current information of the main shaft collected by the data acquisition module, and output the fault type, position and fault recommended processing scheme data matching the current fault signal to the alarm reminder module. The core processing device uses the embedded hardware platform as the main operating platform.

[0027] like Figure 5 As shown in the figure, the real-time monitoring process of the spindle operation status of the CNC machining center includes: firstly collecting the vibration information, speed information, voltage information, and current information of the spindle, and performing preprocessing such as filtering and formatting the collected information and calculating the average value; then comparing the preprocessed data values ​​with the corresponding preset thresholds, and outputting the fault signal according to the comparison result; finally, according to the corresponding codes of each fault signal, the fault type, location, and fault recommended processing scheme of the spindle in various working states stored in the matching fault database are automatically searched through the search rule association list.

[0028] The alarm reminder module is electrically connected to the core processing device. The alarm reminder module is used to automatically trigger the alarm mode or early warning mode for alarm reminder according to the received alarm signal and the preset alarm rules. For example, the alarm mode is a simultaneous reminder of voice and light, and the early warning mode is a single voice reminder. Figure 3 As shown, specifically, the alarm reminder module includes an alarm host, a voice intelligent alarm module and a light alarm module; the alarm host is used to generate a fault alarm code according to the received fault alarm signal, and send an alarm signal to the voice intelligent alarm module or the light alarm module for fault alarm prompt according to the alarm method preset in the alarm code; the voice intelligent alarm module includes a voice alarm and a liquid crystal display, and the voice alarm and the liquid crystal display are electrically connected to the alarm host through a connecting line, the voice alarm is used to make a voice prompt alarm according to the alarm control signal sent by the alarm host, and the liquid crystal display is used to display the fault type, location and recommended fault handling plan; the light alarm module includes a light alarm, the light alarm is electrically connected to the alarm host through a connecting line, and the light alarm is used to make a light prompt alarm according to the alarm control signal.

[0029] like Figure 6 As shown, the alarm reminder process of the monitoring device includes: generating a fault alarm code according to the received fault alarm signal; sending an alarm signal to the voice intelligent alarm module or the light alarm module for fault alarm prompt according to the alarm mode preset in the alarm code.

[0030] The remote monitoring terminal can predict spindle failures based on historical operation monitoring data and perform three-dimensional visual monitoring of the spindle status. Figure 4As shown, the remote monitoring terminal includes a model storage database, a data interaction module and a data drive module; the model storage database is used to mark the three-dimensional models of different spindles of the CNC machining center according to the preset identification, and store the virtual three-dimensional models of different spindles according to the marking information. Because the spindle body is usually made of high-strength and high-rigidity materials, such as alloy steel or stainless steel, and its shape and size are designed according to the needs of the workpiece, the three-dimensional models of multiple spindles are stored to facilitate monitoring of different spindles. The data interaction module is used to obtain the operation monitoring data of the spindle of the CNC machining center sent by the core processing device, and extract the operation parameters of the operation monitoring data, generate model drive parameters according to the extracted operation parameter data and the preset execution control logic, and also used to associate the operation control data of the spindle, the text prompt data and the physical model of the spindle in the graphical user interface for display. The data drive module is connected to the data interaction module and the model storage database. The data drive module is used to obtain the corresponding spindle model data according to the spindle type number of the CNC machining center selected by the user, and drive the corresponding spindle model to perform the simulation production task according to the model drive parameters. The remote monitoring terminal can predict the faults of the spindle operation status of different CNC machining centers according to user needs and collected data, which can reduce sudden failures and reduce maintenance costs.

[0031] The remote monitoring terminal also includes an operation monitoring database, a fault prediction module and a prediction state output module; the operation monitoring database is connected to the data interaction module, and the operation monitoring database is used to store the collected historical operation monitoring data of the spindle, and the historical operation monitoring data includes historical fault discrimination data and the collected historical spindle vibration information, speed information, speed deviation information and load power parameter information; the fault prediction module is connected to the data interaction module, and the fault prediction module is used to predict the spindle fault based on the extracted historical operation parameter data within the preset period using a fault prediction method based on deep learning; the prediction state output module is connected to the fault prediction module, and the prediction state output module is used to generate a spindle operation state monitoring and analysis report based on the prediction results, and the spindle operation state monitoring and analysis report includes fault classification, risk level and maintenance suggestions. The remote monitoring terminal uses hardware platforms such as servers and LCD monitors as the main operating platform.

[0032] Spindle failures generally include bearing failure, gear failure, loose bearing seat, spindle bending and electrical failure. Bearing failure: The bearing is an important supporting component of the spindle. If the bearing is damaged or severely worn, the spindle will not run smoothly and vibrate abnormally. Common causes of bearing failure include poor lubrication, overload, improper installation, etc. Gear failure: If the gears on the spindle are damaged or worn, it will affect the smoothness of the transmission, and then affect the normal operation of the spindle, and the speed and vibration will be abnormal. Gear failure may be caused by material problems, installation errors, insufficient lubrication, etc. Loose bearing seat: Loose bearing seat will cause increased spindle vibration and affect the accuracy and stability of the spindle. The reasons for looseness may include loose fasteners, unstable installation foundation, etc. Spindle bending: Spindle bending will cause unstable operation, vibration and noise. The reasons for bending may include collision, overload, etc. Electrical failure: Abnormal power supply may also cause the spindle to fail to operate normally.

[0033] The powerful feature extraction capability of deep learning can use a large amount of data to automatically learn fault features, thereby improving the efficiency of spindle fault diagnosis. The deep learning model is used to automatically learn the feature representation of spindle fault data, reducing the complexity of the manually designed feature extraction process. The model is trained with a large amount of historical data to enable it to identify different fault types and their corresponding characteristic patterns, which can improve the accuracy and efficiency of fault diagnosis. Fault prediction for the spindle can reduce sudden failures. In this embodiment, the spindle fault is predicted mainly by processing and analyzing the vibration signal and the speed signal, and a fault prediction method based on deep learning is used, which specifically includes: Step S1: Obtain the vibration data eigenvalues ​​corresponding to the continuous multiple characteristic speeds. Extract key eigenvalues ​​from the preprocessed vibration signal, which can reflect the operating status and potential failure modes of the spindle. The key eigenvalues ​​of the vibration signal include the waveform maximum value, peak factor, mean square error, average value of the absolute value, variance and other eigenvalues ​​in the time domain. The characteristic coefficient matrix is ​​obtained by discrete wavelet packet transform, and the corresponding fault identification result can be obtained by inputting the characteristic coefficient matrix into the ResNet18 deep convolutional network.

[0034] Step S2: Input the vibration data characteristic values ​​corresponding to the continuous multiple characteristic speeds into the trained fault prediction model based on the ResNet18 deep convolutional network for fault identification to obtain fault identification information. The ResNet18 deep convolutional network includes a convolutional layer and a fully connected layer, with a total of 18 weight layers. For example, the vibration data characteristic values ​​corresponding to the continuous multiple characteristic speeds of 1000r / min, 1100r / min and 1200r / min are collected, processed and input into the fault prediction model for fault identification to obtain fault identification information. This embodiment proposes a data-level fusion diagnosis model of the ResNet18 deep convolutional network, which realizes accurate diagnosis of shaft faults through multi-sensor data-level fusion. The anti-noise performance is better than that of the unfused data model.

[0035] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A spindle operation monitoring device for a CNC machining center for practical training, characterized in that: include: Data acquisition module, core processing device and alarm reminder module; The data acquisition module includes a sensor group, which is used to collect vibration information, speed information, voltage information, and current information of the main shaft, and transmit the collected information data to the core processing device through a data collector; The core processing device uses a data analysis algorithm to analyze the acquired data, judges whether the spindle fails, sends a warning signal to the alarm reminder module according to the fault judgment result, and sends the collected data information and fault judgment information to the remote monitoring terminal through wireless communication. The remote monitoring terminal is used to predict the spindle failure based on the historical operation monitoring data and perform three-dimensional visual monitoring of the spindle status; The alarm reminder module is electrically connected to the core processing device, and is used to automatically trigger an alarm mode or a pre-warning mode for alarm reminder according to a received alarm signal and a preset alarm rule.

2. The spindle operation monitoring device for a CNC machining center for practical training according to claim 1 is characterized in that: The sensor group includes two groups of vibration sensors, two groups of speed sensors and a voltage and current detection circuit. The two groups of vibration sensors are arranged on the tool holder of the main shaft. The vibration sensors are used to collect vibration signals of the main shaft when it is running, and the speed sensor is used to detect the speed signal of the main shaft. Each group of vibration sensors includes two unidirectional acceleration sensors. The two groups of speed sensors include a magnetic induction encoder and an infrared tachometer. The voltage and current detection circuit is used to detect the voltage information and current information corresponding to the load when the main shaft is running. The output end of the sensor group is electrically connected to the input end of the data collector. The data collector filters, amplifies and digitally converts the raw data collected by the sensor group, and transmits the processed data characteristic signal to the core processing device through a connecting line.

3. The spindle operation monitoring device for a CNC machining center for practical training according to claim 1 is characterized in that: The core processing device includes a comparison and analysis unit, a fault classification unit and a data communication unit; The comparison and analysis unit includes a first comparison module, a second comparison module and a third comparison module. The first comparison module is used to obtain a vibration average value for two vibration signals obtained by each group of vibration sensors to obtain two vibration average values, and compare the two vibration average values ​​with the corresponding preset vibration thresholds respectively. If the vibration average value is greater than the corresponding preset vibration threshold, a first fault signal is output to the fault classification unit, otherwise the next group of vibration average values ​​is compared with the corresponding preset vibration threshold. The second comparison module is used to obtain a speed average value for the two groups of speed signals obtained, and calculate the difference between the speed average value and the set speed value to obtain a speed deviation value. The speed deviation value is compared with a preset speed deviation threshold value. If the speed deviation value is greater than the speed deviation threshold value, a second fault signal is output to the fault classification unit. The third comparison module is used to compare the detected voltage value of the drive motor with the voltage upper limit threshold value and the voltage lower limit threshold value, and is also used to compare the detected current value of the drive motor with the current upper limit threshold value and the current lower limit threshold value, respectively. If the voltage value is greater than the voltage upper limit threshold value or the voltage value is less than the voltage lower limit threshold value or the current value is greater than the current upper limit threshold value or the current value is less than the current lower limit threshold value, a third fault signal is output to the fault classification unit. The fault classification unit is connected to the comparison and analysis unit and the fault database, and is used to receive the first fault signal, the second fault signal and the third fault signal, and automatically search and match the fault type, location and fault treatment plan of the spindle in various working states stored in the fault database by searching the rule association list according to the code corresponding to each fault signal; The data communication unit is connected to the comparison and analysis unit and the fault classification unit. The data communication unit is used to receive the vibration information, speed information, voltage information, and current information of the main shaft collected by the data acquisition module, and output the fault type, location, and fault recommended processing plan data matching the current fault signal to the alarm reminder module.

4. The spindle operation monitoring device for a CNC machining center for practical training according to claim 3 is characterized in that: The alarm reminder module includes an alarm host, a voice intelligent alarm module and a light alarm module; The alarm host is used to generate a fault alarm code according to the received fault alarm signal, and send an alarm signal to the voice intelligent alarm module or the light alarm module for fault alarm prompt according to the alarm mode preset by the alarm code; The voice intelligent alarm module includes a voice alarm and a liquid crystal display, the voice alarm and the liquid crystal display are electrically connected to the alarm host through a connecting line, the voice alarm is used to make a voice prompt alarm according to the alarm control signal sent by the alarm host, and the liquid crystal display is used to display the fault type, location and fault recommended processing plan; The light alarm module includes a light alarm, which is electrically connected to the alarm host via a connecting line, and is used to issue a light prompt alarm according to an alarm control signal.

5. The spindle operation monitoring device for a CNC machining center for practical training according to claim 1 is characterized in that: The remote monitoring terminal includes a model storage database, a data interaction module and a data driving module; The model storage database is used to mark the three-dimensional models of different spindles of the CNC machining center according to preset identifications, and store the virtual three-dimensional models of the different spindles according to the marking information; The data interaction module is used to obtain the operation monitoring data of the spindle of the CNC machining center sent by the core processing device, and to extract the operation parameters of the operation monitoring data, generate model driving parameters according to the extracted operation parameter data and the preset execution control logic, and is also used to associate the spindle operation control data, text prompt data and the physical model of the spindle for display in a graphical user interface. The data driving module is connected to the data interaction module and the model storage database. The data driving module is used to obtain the corresponding spindle model data according to the spindle type number of the CNC machining center selected by the user, and drive the corresponding spindle model according to the model driving parameters to perform simulated production tasks.

6. The spindle operation monitoring device for a CNC machining center for practical training according to claim 5 is characterized in that: The remote monitoring terminal also includes an operation monitoring database, a fault prediction module and a prediction status output module; The operation monitoring database is connected to the data interaction module, and the operation monitoring database is used to store the collected historical operation monitoring data of the spindle; The fault prediction module is connected to the data interaction module, and the fault prediction module is used to predict the spindle fault by using a fault prediction method based on deep learning according to the historical operating parameter data extracted within a preset period; The prediction status output module is connected to the fault prediction module, and is used to generate a spindle operation status monitoring and analysis report according to the prediction result, wherein the spindle operation status monitoring and analysis report includes fault classification, risk level and maintenance suggestion.

7. The spindle operation monitoring device for a CNC machining center for practical training according to claim 6 is characterized in that: The method of predicting spindle failure using a deep learning-based fault prediction method includes: Obtain vibration data characteristic values ​​corresponding to multiple consecutive characteristic speeds; The vibration data characteristic values ​​corresponding to multiple consecutive characteristic speeds are input into the trained fault prediction model based on the ResNet18 deep convolutional network for fault identification to obtain fault identification information.

Images