Machine tool abnormal action monitoring system and method based on AI model diagnosis and medium

Abstract

The invention discloses a machine tool abnormal action monitoring system and method based on AI model diagnosis and a medium. The system comprises a communication module, a data acquisition module, a data processing module and a display module, wherein the communication module is connected with a machine tool communication port and is used for communicating with a machine tool; the data acquisition module is used for acquiring data on a target register address in the machine tool PMC controller through the communication module to obtain machine tool action data; an AI model is carried in the data processing module, machine tool action data are monitored in real time based on the AI model, and an alarm is triggered when abnormal actions are found; and the display module is used for displaying machine tool action data information and abnormal action alarm information. Abnormal action detection of the machine tool can be automatically completed based on the AI model; the system only carries out data acquisition operation on the machine tool, equipment operation is not affected, and equipment anomaly detection can be completed under the condition that the production efficiency of equipment is maintained.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of intelligent manufacturing, and in particular to a machine tool abnormal action monitoring system and method based on AI model diagnosis and a medium. BACKGROUND

[0002] In the current parts processing manufacturing industry, advanced processing machine tools are widely used to precisely process aluminum, iron, alloy and other material rough parts. The popularization rate of machine tools is high, and some international brands dominate. However, it is found in actual production that the failure rate of processing machine tools is generally high, and the overall performance operation rate (OEE) has great potential for improvement. In order to enhance global competitiveness, enterprises need to reduce failure rate and improve production efficiency through technical transformation.

[0003] In the prior art, abnormal detection of processing machine tools usually relies on the installation of vibration sensors, but this poses significant challenges to the modification process for a large number of old equipment already deployed by enterprises. The modification requires a large amount of time and cost, and the production plan of the enterprise is usually saturated, with very limited available construction time every week; at the same time, the modification work must rely on professional experience and technical guidance, because the scheme is customized according to the process, procedure and brand difference of the machine tool, and lacks universality. In addition, as the service life of the equipment increases and the technical parameters change, the detection function will gradually fail to automatically adapt to updates, further weakening the abnormal detection effect of the modification scheme.

[0004] In summary, the existing machine tool modification scheme has poor generalizability and is difficult to effectively popularize in enterprises, thereby limiting the improvement of overall production efficiency. SUMMARY

[0005] Therefore, the embodiments of the present application provide a machine tool abnormal action monitoring system and method based on AI model diagnosis and a medium.

[0006] In one aspect, the present application provides a machine tool abnormal action monitoring system based on AI model diagnosis, comprising a communication module, a data acquisition module, a data processing module and a display module:

[0007] The communication module is connected to the machine tool communication port and is used for communication with the machine tool;

[0008] The data acquisition module is used to acquire data on the target register address in the PMC controller of the machine tool through the communication module to obtain machine tool action data;

[0009] The data processing module carries an AI model, and the machine tool action data is monitored in real time based on the AI model, and an alarm is triggered when an abnormal action is found;

[0010] The display module is used to display machine tool action data information and abnormal action alarm information.

[0011] Further, the communication module is loaded with multiple communication protocols, and a target communication protocol is selected according to the model of the machine tool to communicate with the machine tool.

[0012] Further, the data acquisition module specifically acquires the machine tool action data through the following steps:

[0013] Inquiring a register address list of the machine tool;

[0014] Determining a mapping relationship between each machine tool action signal and the register address, and determining a target register address to be acquired;

[0015] According to the data change of the target register address, the machine tool action signal is restored;

[0016] The restored machine tool action signal is sequentially recorded to obtain the machine tool action data.

[0017] Further, the machine tool action data acquired by the data acquisition module starts from a start action signal of a machining operation of the machine tool and ends at an end action signal of the machining operation.

[0018] Further, the AI model is loaded with a standard time of each machine tool action, and according to a difference between the duration of each machine tool action in the machine tool action data and the corresponding standard time, it is determined whether the machine tool action is an abnormal action.

[0019] Further, the AI model is trained based on historical action data of the machine tool to obtain model parameter values of the machine tool; the model parameter values include a standard time of each machine tool action and a time difference threshold value;

[0020] For different machine tools, the model parameter values trained by the AI model are different; different files are used in the data processing module to save the model parameter values of different machine tools; after the target machine tool is determined, the model parameter values of the target machine tool are loaded into the AI model.

[0021] Another aspect of the present application discloses a machine tool abnormal action monitoring method based on AI model diagnosis, which is realized based on the above-mentioned machine tool abnormal action monitoring system based on AI model diagnosis, and includes the following steps:

[0022] Connect the communication port of the machine tool, and communicate with the machine tool using the communication protocol of the machine tool;

[0023] Acquire data on the target register address in the PMC controller of the machine tool to obtain machine tool action data;

[0024] Use the AI model to monitor the machine tool action data in real time, and trigger an alarm when an abnormal action is found.

[0025] Further, the AI model is trained based on historical action data of the machine tool; and the AI model judges whether each machine tool action in the machine tool action data is an abnormal action by comparing a difference between a duration of the machine tool action and a corresponding standard time.

[0026] Further, the method further comprises the following steps:

[0027] When the machine tool action data does not contain abnormal actions, the machine tool action data is added to the historical action data to train the machine tool.

[0028] In another aspect of the present application, a computer readable storage medium stores a program of the machine tool abnormal action monitoring system based on AI model diagnosis described above, and the program is executed by a processor to implement the machine tool abnormal action monitoring method based on AI model diagnosis described above.

[0029] The embodiment of the present application also discloses a computer program product or a computer program, which comprises computer instructions stored in a computer readable storage medium. A processor of a computer device can read the computer instructions from the computer readable storage medium, and the processor executes the computer instructions to enable the computer device to execute the foregoing method.

[0030] The embodiment of the present application has the following beneficial effects: the machine tool abnormal action monitoring system, method and medium based on AI model diagnosis can automatically complete abnormal action detection of the machine tool based on the AI model. The system only performs data collection operation on the machine tool, does not affect the operation of the device, and can complete abnormal detection of the device while maintaining the production efficiency of the device. The operator only needs to connect the system with the Ethernet port of the machine tool and the device port, and the system can automatically detect the abnormal action of the machine tool, without the need of additional sensors and other devices, and the modification of the device is minimal, and the cost is minimal. The system can also be automatically upgraded through updating of the AI model training data, and the problem of inaccurate detection caused by data deviation due to old equipment and the like can be avoided.

[0031] Additional aspects and advantages of the present application will be described in the following description section, some of which will become apparent from the following description, or will be understood through practice of the present application. BRIEF DESCRIPTION OF DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0033] Figure 1 is a schematic diagram of a machine tool abnormal action monitoring system based on AI model diagnosis of the present application;

[0034] Figure 2 is a schematic diagram of PMC controller internal register address bits of the machine tool;

[0035] Figure 3 is a schematic diagram of the system recording machine tool action data of the present application;

[0036] Figure 4 is a schematic diagram of a machine tool abnormal action monitoring method based on AI model diagnosis of the present application;

[0037] Figure 5 is a schematic diagram of a computer readable storage medium of the present application. DETAILED DESCRIPTION

[0038] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and do not limit the present application.

[0039] As shown in Figure 1 , the first embodiment of the present application provides a machine tool abnormal action monitoring system based on AI model diagnosis, which comprises a communication module, a data acquisition module, a data processing module and a display module.

[0040] Communication module: In the embodiment of the present application, the communication module is connected to the machine tool communication port for communication with the machine tool. In the embodiment of the present application, the communication module is connected to the machine tool communication port through end-to-end networking. Exemplarily, a network cable can be used to bridge the communication network port (such as Ethernet port and / or device network port) of the machine tool through a switch.

[0041] In the embodiment of the present application, a plurality of communication protocols are loaded in the communication module, and the target communication protocol is selected according to the model of the machine tool to communicate with the machine tool. Taking the machine tool of the brand of Fanuc as an example, the Focas2 protocol officially opened by Fanuc is loaded in the communication module in the embodiment of the present application, so as to realize communication with Series 0i, Series 15i, Series 16i, Series 18i, Series 21i, Series 30i and other Fanuc machine tools. For machine tools of other brands, the communication protocol of the brand machine tool can be obtained through the official channel of the brand and loaded in the communication module, so that the abnormal action monitoring system of the present application can be applied to machine tools of different brands.

[0042] Through the design of the communication module, the embodiment of the present invention enables the system to collect machine tool data by using only the existing network port of the machine tool, without the need to install hardware modifications such as vibration sensors on the machine tool body, which is convenient for enterprises to use.

[0043] Data acquisition module: In the embodiment of the present invention, the data acquisition module is used to collect data on the target register address in the machine tool PMC controller through the communication module to obtain machine tool motion data.

[0044] As a preferred embodiment, the data acquisition module collects machine tool motion data specifically through the following steps:

[0045] S101. Query the machine tool register address list;

[0046] S102. Determine the mapping relationship between each machine tool action signal and the register address, and determine the target register address to be collected;

[0047] S103. According to the data change of the target register address, restore the machine tool action signal;

[0048] S104. Record the restored machine tool motion signals in sequence to obtain machine tool motion data.

[0049] The data acquisition module in the embodiment of the present invention is loaded with various motion signals of the machine tool. Since machine tool processing involves thousands of motions, which are specifically related to the machine tool's processing technology and have no fixed standards, the present invention does not list them one by one. In theory, the more processing motion data monitored, the wider the abnormality judgment range of the machine tool abnormal motion monitoring. For example, for a FANUC machine tool, the data acquisition module in the embodiment of the present invention collects the following motion signals:

[0050]

[0051]

[0052] The PMC (Programmable Machine Controller) of a machine tool is used to process the machine tool's logical control signals, including switch input and output, relay control, spindle control, etc. Therefore, the data acquisition module of the present invention can obtain the machine tool's motion data from the PMC controller of the machine tool.

[0053] The register address data on the machine tool PMC controller is as follows Figure 2As shown. Taking FANUC machine tools as an example, FANUC machine tools can query the register addresses that need to be collected on the display screen interface of the machine tool body. For example, addresses starting with F and G represent the signal register bits sent by the machine tool CNC system to the PMC controller and the signal register bits returned by the PMC controller to the machine tool CNC system, respectively. By operating the machine tool to perform different processing actions and determining the changes in the register address bits on the machine tool PMC controller under each action, the mapping relationship between each processing action and the register address change can be obtained. After determining the mapping relationship between the processing action and the register address change, the register address collection is taken as the target register address that the data acquisition module needs to collect.

[0054] As a machine tool performs a machining operation, the data acquisition module in this embodiment infers the current machining action by inferring it from register bit state changes, enabling sensorless detection of the machine tool's machining motion. This significantly differs from traditional vibration sensor solutions that rely on the machine tool's hardware. Based on the sequence of machining operations performed by the machine tool, motion signals for multiple machining operations are obtained and recorded sequentially, serving as a set of machine motion data for the AI ​​model to detect anomalies.

[0055] In some embodiments, the machine tool motion data collected by the data acquisition module starts with the start motion signal of the machine tool performing a processing operation and ends with the end motion signal of the processing operation. By clarifying the start signal and end signal of the machine tool motion data, it is possible to ensure that the data acquisition module fully records the motion chain of the machine tool in a processing operation. In addition, for detection scenarios where abnormal interruptions occur in some machine tool processing, since the corresponding machine tool motion data lacks an end motion signal, the AI ​​model can identify that an abnormal terminal situation has occurred in the machine tool, thereby improving the abnormality detection efficiency of the AI ​​model.

[0056] The machine tool motion data collected by the data acquisition module is as follows: Figure 3 As shown in the figure, each set of machine tool motion data contains an action chain. The operator can call up the data details of the corresponding action through the display module, which makes it easier for the operator to determine the specific cause of the abnormal action.

[0057] Data processing module: The data processing module of the embodiment of the present invention is equipped with an AI model, which monitors the machine tool motion data in real time based on the AI ​​model and triggers an alarm when abnormal motion is detected.

[0058] In the embodiment of the present application, the AI model is trained based on historical action data of the machine tool to obtain model parameter values of the machine tool. The model parameter values include standard time and time difference threshold of each machine tool action. For example, for a Fanuc machine tool, the embodiment of the present application collects action data of not less than 3000 normal machining cycles of the machine tool, analyzes the historical data through an AI training engine, generates model parameter values exclusive to the machine tool by using a normal distribution statistical method, and saves the model parameter values in a file. The model parameter file contains a standard time baseline and a dynamic threshold matrix. The standard time baseline represents the average duration of the 21 standard actions of the above-mentioned Fanuc machine tool in a normal action state (such as a standard value of 2.34 seconds for the tool changing arm operation). The dynamic threshold matrix automatically sets the allowed deviation range of each action according to the data dispersion of different action durations (such as an allowed deviation of ±5% for the work feed action).

[0059] Since the parameters of each machine tool adjustment are different, the model parameter values obtained by using the AI model for training are different for different machine tools. Therefore, in the data processing module, different files are used to save the model parameter values of different machine tools. For different machine tools, the data processing module loads the corresponding file of the target machine tool into the AI model, so that the abnormality detection of the AI model is applicable to the target machine tool.

[0060] In the abnormality detection process, the AI model captures the actual duration of each action in the current machining cycle in real time, retrieves the standard time parameter in the model for percentage deviation calculation, i.e. (actual duration-standard duration) / standard duration. When the deviation value exceeds the dynamic threshold set by the model, it is judged that the machine tool action is an abnormal action, and an alarm is triggered.

[0061] In some embodiments, the data processing module can also add the machine tool action data without abnormality to the training data of the AI model for the machine tool to support the model to be updated regularly to adapt to the aging of the equipment.

[0062] Display module: The display module of the embodiment of the present application is used to display machine tool action data information and abnormal action alarm information. The operator can query the detailed action time of each machining action and the parameters in the action associated time period in the machine tool action data through the display module. When the data processing module triggers an alarm, the display module can display the data deviation degree (in percentage) of the abnormal action to realize the alarm of a specific abnormal action and further notify the operator to maintain the equipment. When the operator maintains the equipment, he / she preferentially checks the physical parts of the equipment associated with the abnormal action, such as aluminum chip jamming, wear, aging, cutting fluid leakage, etc., to find out the causes of the abnormal action in a timely manner.

[0063] For example, when an abnormal closing action of the tool changer door is detected on the display module, that is, the AI model finds that the closing time of the tool changer door is slower or faster than the standard action time. The operator can further call the detailed information of the closing action of the tool changer door to confirm whether the abnormal reason is aging or jamming of the tool changer door, and then maintain the tool changer door. That is, it can avoid unpredictable fault problems such as processing defects and slow pace caused by abnormalities.

[0064] The embodiment of the application realizes intelligent monitoring of abnormal actions of the machine tool through non-invasive data acquisition and AI modeling of the machine tool. By constructing a timing feature library of standard actions, and combining with more than 3000 machining data to train and generate AI model parameters special for each machine tool, the machine tool is monitored in real time. Through the machine tool abnormal action monitoring system of the embodiment of the application, the operator can automatically complete the abnormal action monitoring of the machine tool after configuring the basic communication connection, without manual intervention, and without additional machine tool modification cost and labor cost. According to the observation of the past project, for the production line with a large number of Genmac brand machine tools, the machining cycle time can be reduced by 4.1%, and the equipment OEE is improved by 4%. The action timing covered by the monitoring includes ATC, spindle, tooling fixture, cutting process, fast forward process, operator loading and unloading time, etc. (precision 0.01 seconds).

[0065] As shown in Figure 4 The second embodiment of the application discloses a machine tool abnormal action monitoring method based on AI model diagnosis, which is realized based on the machine tool abnormal action monitoring system based on AI model diagnosis described above, and includes the following steps:

[0066] S201. Connect the communication port of the machine tool, and communicate with the machine tool using the communication protocol of the machine tool;

[0067] S202. Collect data on the target register address in the PMC controller of the machine tool to obtain machine tool action data;

[0068] S203. Use the AI model to monitor the machine tool action data in real time, and trigger an alarm when an abnormal action is found.

[0069] In the embodiment of the application, the AI model is trained based on the historical action data of the machine tool; the AI model compares the difference between the duration of each machine tool action in the machine tool action data and the corresponding standard time to determine whether the machine tool action is an abnormal action.

[0070] In some embodiments, the method of the application further includes the following steps:

[0071] When the machine tool action data does not contain abnormal actions, the machine tool action data is added to the historical action data to train the machine tool.

[0072] The content of the system in the first embodiment of the application is applicable to the method embodiment, the function realized by the method embodiment is the same as that of the system method embodiment, and the beneficial effects achieved are also the same as those of the system.

[0073] Figure 5 A structural schematic diagram of the computer readable storage medium of the third embodiment of the application. The computer readable storage medium of the fourth embodiment of the application stores program instructions capable of realizing the machine tool abnormal action monitoring system based on AI model diagnosis, wherein the program instructions can be stored in the storage medium in the form of a software product, and include a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the method of each embodiment of the application. The aforementioned computer readable storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media capable of storing program codes, or a computer, a server, a mobile phone, a tablet, and other terminal devices.

[0074] The embodiment also provides a computer program product, which, when running on a computer, causes the computer to execute the related steps described above to realize the machine tool abnormal action monitoring method based on AI model diagnosis provided by the above embodiments.

[0075] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the embodiments of the application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of the related data need to comply with the relevant laws, regulations and standards of the relevant countries and regions, and provide corresponding operation entrances for the user to choose authorization or refusal.

[0076] Those skilled in the art can understand that the modules in the device in the embodiments of the present application can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments of the present application can be combined into one module or unit or component, and furthermore can be divided into multiple sub-modules or sub-units or sub-components. Except that at least some of such features and / or processes or units are mutually exclusive, all combinations of all features disclosed in the present specification (including the corresponding claims, abstract and drawings) and all processes or units of any methods or apparatuses disclosed herein can be adopted. Unless explicitly stated otherwise, each feature disclosed in the present specification (including the corresponding claims, abstract and drawings) can be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0077] Through the description of the above embodiments, those skilled in the art can understand that, for the convenience and brevity of description, only the division of the above functional modules is taken as an example, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above.

[0078] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a list of executable instructions for implementing logic functions, which can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus, such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from the instruction execution system, device or apparatus, or in conjunction with these instructions.

[0079] Furthermore, each embodiment in the present specification is described in a progressive manner, and the same or similar parts between embodiments can be referred to each other. Especially, for the device, apparatus and the like embodiments, since they are basically similar to the method embodiments, the relevant parts can be referred to the part of the description of the method embodiments. The above described device, apparatus and the like embodiments are only illustrative, and the modules, units and the like explained as separate components can be or can not be physically separated, that is, can be located in one place, or can be distributed to multiple places, for example, nodes of a system network. Specifically, part or all of the modules, units can be selected to achieve the purpose of the above embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0080] It should be understood that aspects of the application can be implemented in hardware, software, firmware or a combination thereof. In the above embodiments, various steps or methods can be implemented in software or firmware that is stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and in another embodiment, any of the following can be used: discrete logic circuitry having logic gates for implementing logic functions upon data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), and / or the like.

[0081] In the description of the present application, the terms "one embodiment", "some embodiments", "an example", "a specific example", or "some examples" and the like, are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present application. The appearances of the above terms in various places in the specification are not necessarily all referring to the same embodiment or example. Furthermore, the described specific features, structures, materials, or characteristics can be combined in any suitable manner in one or more embodiments or examples.

[0082] In addition, the terms "first", "second", and the like, in the description of the embodiments of the present application, are used for descriptive purposes and not necessarily for describing all embodiments, or implying relative importance or implicitly dictating the order of elements mentioned in this embodiment. Therefore, the features defined with "first", "second" and the like in the embodiments of the present application can explicitly or implicitly indicate that the embodiments include at least one of the features. In the description of the present application, the term "a plurality of" means at least two or two or more, such as two, three, four, etc., unless otherwise specifically limited in the embodiments.

[0083] In the embodiments of the present application, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or includes elements inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a" does not exclude the presence of other identical elements in the process, method, article or device including the element, in addition, components, features, elements with the same name in different embodiments of the present application can have the same meaning or different meaning, and the specific meaning thereof should be determined in the interpretation of the specific embodiment or further combined with the context in the specific embodiment.

[0084] Although the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are exemplary and are not to be construed as limiting the present application, and that variations, modifications, substitutions and changes can be suggested to one skilled in the art without departing from the scope of the present application. Other embodiments of the present application will be apparent to those skilled in the art from consideration of the specification and practice of the present application. It is intended that the present application cover any and all variations of the application that come within the scope of the present application, along with all of the equivalents thereof. It is intended that the specification and examples be considered exemplary only, with the true scope and spirit of the application indicated by the following claims.

Claims

1. A machine tool abnormal motion monitoring system based on AI model diagnosis, characterized in that: Including communication module, data acquisition module, data processing module and display module: The communication module is connected to the machine tool communication port for communicating with the machine tool; The data acquisition module is used to collect data on the target register address in the machine tool PMC controller through the communication module to obtain machine tool motion data; The data processing module is equipped with an AI model, which monitors the machine tool motion data in real time based on the AI ​​model and triggers an alarm when an abnormal motion is found; The display module is used to display machine tool action data information and abnormal action alarm information.

2. The machine tool abnormal motion monitoring system based on AI model diagnosis according to claim 1 is characterized in that: The communication module is loaded with a variety of communication protocols, and a target communication protocol is selected according to the model of the machine tool to communicate with the machine tool.

3. The machine tool abnormal motion monitoring system based on AI model diagnosis according to claim 1 is characterized in that: The data acquisition module specifically collects machine tool motion data through the following steps: Query the register address list of the machine tool; Determine the mapping relationship between each machine tool action signal and register address, and determine the target register address that needs to be collected; Restore the machine tool action signal according to the data change of the target register address; The restored machine tool motion signals are recorded in sequence to obtain the machine tool motion data.

4. The machine tool abnormal motion monitoring system based on AI model diagnosis according to claim 3 is characterized in that: The machine tool motion data collected by the data collection module starts with a start motion signal of a machining operation performed by the machine tool and ends with an end motion signal of the machining operation.

5. The machine tool abnormal motion monitoring system based on AI model diagnosis according to claim 1 is characterized in that: The AI ​​model is loaded with the standard time of each machine tool action. Based on the difference between the duration of each machine tool action in the machine tool action data and the corresponding standard time, it is determined whether the machine tool action is an abnormal action.

6. The machine tool abnormal motion monitoring system based on AI model diagnosis according to claim 5 is characterized in that: The AI ​​model is trained based on the historical motion data of the machine tool to obtain model parameter values ​​of the machine tool; the model parameter values ​​include the standard time and time difference threshold of each machine tool motion; For different machine tools, the model parameter values ​​obtained by training the AI ​​model are different; different files are used in the data processing module to save the model parameter values ​​of different machine tools; after the target machine tool is determined, the model parameter values ​​of the target machine tool are loaded into the AI ​​model.

7. A method for monitoring abnormal motion of a machine tool based on AI model diagnosis, implemented based on the machine tool abnormal motion monitoring system based on AI model diagnosis according to any one of claims 1 to 6, characterized in that: The following steps are involved: Connect to the communication port of the machine tool and communicate with the machine tool using the machine tool's communication protocol; Collect data on the target register address in the machine tool PMC controller to obtain machine tool motion data; An AI model is used to monitor the machine tool motion data in real time, and an alarm is triggered when abnormal motion is detected.

8. The method for monitoring abnormal machine tool movements based on AI model diagnosis according to claim 7, characterized in that: The AI ​​model is trained based on the historical motion data of the machine tool; the AI ​​model determines whether the machine tool motion is an abnormal motion by comparing the difference between the duration of each machine tool motion in the machine tool motion data and the corresponding standard time.

9. The method for monitoring abnormal machine tool movements based on AI model diagnosis according to claim 8, characterized in that: The following steps are also included: When the machine tool motion data does not contain abnormal motion, the machine tool motion data is added to the historical motion data to train the machine tool.

10. A computer-readable storage medium, characterized in that The storage medium stores a program of a machine tool abnormal motion monitoring system based on AI model diagnosis as described in any one of claims 1-6, and the program is executed by a processor to implement a machine tool abnormal motion monitoring method based on AI model diagnosis as described in any one of claims 7-9.

Images