Large machine tool cutter wear monitoring and interaction device

Abstract

The invention discloses a large-scale machine tool cutter wear monitoring and interaction device, and relates to the technical field of machine manufacturing and control, the large-scale machine tool cutter wear monitoring and interaction device comprises a cantilever support assembly and a protection main case, and the cantilever support assembly is connected with the protection main case through a fast-assembly interface; an edge end data acquisition terminal and a man-machine interaction module are integrated in the protection main case; the edge end data acquisition terminal comprises a data acquisition module which is used for acquiring a cutter vibration signal, cutter head nearby temperature information and a main shaft current signal; the host module can calculate the state, abrasion and service life of the cutter; the numerical control system communication module obtains machining parameters in real time and issues emergency control instructions. And the man-machine interaction module performs information interaction with the edge end data acquisition terminal. Through multi-source signal fusion analysis and an intelligent early warning algorithm, real-time sensing of the state of the cutter and life prediction are achieved, the change trend of cutting of the cutter can be visually sensed, and therefore recognition and early warning prompt of cutter replacement are made.

Description

Technical Field

[0001] The present invention relates to the field of mechanical manufacturing and control technology, and in particular to a large machine tool tool wear monitoring and interaction device. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.

[0003] In discrete machining applications on large machine tools, the cutting area and wear status of the tool are often difficult to directly, promptly, and accurately determine due to the large size of the machine tool and workpiece, and the operator's limited field of view. Large machine tools experience high tool wear and complex operating conditions. When tool breakage, chipping, or loose blades occur, they can easily lead to tool jamming, overcutting, and deformation. The traditional solution is to manually determine the degree of tool wear and determine whether to replace the tool. This approach relies heavily on personal experience and responsibility, and carries the risk of delayed judgment. Summary of the Invention

[0004] The purpose of the present invention is to provide a large-scale machine tool tool wear monitoring and interaction device to address the shortcomings of the existing technology. The device realizes real-time perception of tool status and life prediction through multi-source signal fusion analysis and intelligent early warning algorithm, and can intuitively feel the changing trend of tool cutting, thereby making identification and early warning prompts for tool replacement.

[0005] The technical solutions of the present invention are as follows: A large machine tool tool wear monitoring and interaction device, comprising: a cantilever support assembly and a protective main housing, wherein the cantilever support assembly is connected to the protective main housing via a quick-release interface; The protective main housing is internally integrated with an edge data acquisition terminal and a human-computer interaction module; The edge data acquisition terminal includes: The data acquisition module includes a vibration acquisition module for acquiring tool vibration signals, a temperature acquisition module for acquiring temperature information near the cutter head, and a current acquisition module for acquiring spindle current signals; The host module serves as the core computing unit and has built-in dynamic threshold method state detection model, wear prediction model, and life prediction model. It can calculate the tool state, wear, and life based on the data collected by the data acquisition module. The CNC system communication module is responsible for communicating with the CNC system to achieve real-time acquisition of processing parameters and issuance of emergency control instructions; The human-computer interaction module exchanges information with the edge data acquisition terminal, can display real-time processing parameters, data collected by the data acquisition module and calculation results of the host module, and has human-computer interaction functions.

[0006] Furthermore, the human-computer interaction module is a touch screen embedded in the protective main housing; The protective main housing is also provided with an audible and visual alarm device, which will sound an alarm when the calculation result of the main module is abnormal.

[0007] Furthermore, the host module communicates with the temperature acquisition module, vibration acquisition module, current acquisition module and CNC system communication module at high speed via the EtherCAT bus; The human-computer interaction module exchanges information with the edge data acquisition terminal through Ethernet.

[0008] Furthermore, a vibration sensor is installed on the tool to obtain the tool vibration signal; a temperature sensor is installed near the cutter head to obtain temperature information near the cutter head; and a three-phase current sensor is installed on the spindle to obtain the spindle current signal.

[0009] Furthermore, a filtering module is provided between the vibration acquisition module and the vibration sensor, the temperature acquisition module and the temperature sensor, and the current acquisition module and the three-phase current sensor.

[0010] Furthermore, the dynamic threshold method state detection model includes: The tool status is identified by comparing the characteristic values ​​of the signals collected by the data acquisition module with the set dynamic threshold in real time. The tool is judged to be abnormal based on the preset judgment rules. If it is judged to be abnormal, an emergency command is sent to the CNC system to control the machine tool to stop processing.

[0011] At the same time, the characteristics that are sensitive to tool wear are analyzed to obtain the percentage of tool wear. When the set value is reached, the operator is prompted to replace the tool through the human-computer interaction module.

[0012] Furthermore, the determination rules include: single signal threshold triggering and multi-signal collaborative verification; The single signal threshold triggering includes: triggering a preliminary abnormality mark when any signal characteristic value exceeds a dynamic threshold; The multi-signal collaborative verification includes: performing further abnormality judgment based on the tool vibration signal, temperature information near the cutter head, and spindle current signal according to the multi-signal combination relationship constructed based on experience.

[0013] Furthermore, the calculation formula of the dynamic threshold is as follows:

[0014] λ(t) represents the dynamic threshold at the current moment, that is, the dynamic threshold corresponding to time t; represents the smoothing coefficient; Indicates the number of sliding window samples; (t) indicates the The sampling value of a sensor at time t; Indicates the dynamic threshold at the previous moment.

[0015] Furthermore, the wear prediction model includes: Based on the data collected by the data acquisition module, a cascaded deep learning architecture is designed. The front stage uses a convolutional neural network (CNN) to extract the frequency domain spatial features of the signal, and the back stage uses a bidirectional long short-term memory (Bi-LSTM) network to model the temporal dependency of the signal. The model outputs the wear prediction value of the tool wear.

[0016] Furthermore, the lifespan prediction model includes: A combined model based on the convolutional neural network (CNN) and the fully connected layer (Dense) was selected to establish the mapping relationship. Historical data was used to train the model to find the best fit relationship between wear value and usage time. Finally, the predicted results were compared with the actual service life to evaluate the error and reliability of the model.

[0017] Compared with the existing technology, the beneficial effects of the present invention are: 1. This paper proposes a tool state perception architecture with multimodal sensor fusion. Based on the collaborative acquisition scheme of three-source signals: vibration (tool), temperature (tool head), and current (spindle motor), it breaks through the limitations of traditional single vibration monitoring and realizes multi-channel signal synchronous acquisition and real-time fusion analysis through the EtherCAT bus, significantly improving the recognition accuracy of sudden anomalies such as tool breakage and chipping.

[0018] 2. The present invention adopts an integrated design of embedded edge computing and interaction, integrating the industrial-grade touch screen host computer and the edge computing terminal into an IP65 protective main housing, realizing localized closed-loop processing of signal acquisition-feature extraction-state recognition-model prediction, with a system response delay of ≤50ms, which is 8 times more efficient than the traditional cloud processing mode.

[0019] 3. This invention introduces a collaborative warning mechanism of adaptive threshold learning and wear prediction dual models, develops a wear / life prediction algorithm based on the CNN-LSTM hybrid model, generates a red warning threshold curve through autonomous learning of historical processing data, and combines the fixed threshold method with the dual verification of the life prediction model to effectively reduce the false alarm rate. 4. The present invention also proposes an ergonomic cantilever observation system, designs a multi-section straight-arm torsion cantilever bracket, supports 1-3m stepless telescopic adjustment, and cooperates with a 15° elevation touch screen to enable operators to complete full-view status monitoring in the machine tool safety area. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a schematic diagram of the structure of a large machine tool tool wear monitoring and interaction device; Figure 2 This is a flow chart for monitoring tool wear and interactive devices for large machine tools; Figure 3 The figure is a schematic structural diagram of an electronic device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0021] It should be noted that relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of additional identical elements in the process, method, article, or apparatus comprising the element.

[0022] The features and performance of the present invention are further described in detail below with reference to the embodiments.

[0023] Example 1 See also Figure 1 and Figure 2 , a large machine tool tool wear monitoring and interaction device, comprising: a cantilever support assembly and a protective main housing, wherein the cantilever support assembly is connected to the protective main housing via a quick-release interface; The protective main housing is internally integrated with an edge data acquisition terminal and a human-computer interaction module; The edge data acquisition terminal includes: The data acquisition module includes a vibration acquisition module for acquiring tool vibration signals, a temperature acquisition module for acquiring temperature information near the cutter head, and a current acquisition module for acquiring spindle current signals; The host module serves as the core computing unit and has built-in dynamic threshold method state detection model, wear prediction model, and life prediction model. It can calculate the tool state, wear, and life based on the data collected by the data acquisition module. The CNC system communication module is responsible for communicating with the CNC system to achieve real-time acquisition of processing parameters and issuance of emergency control instructions; The human-computer interaction module exchanges information with the edge data acquisition terminal, can display real-time processing parameters, data collected by the data acquisition module and calculation results of the host module, and has human-computer interaction functions.

[0024] In this embodiment, specifically, the cantilever bracket assembly adopts a three-section straight arm torsion structure made of aluminum (total length 1-3m adjustable), a quick-release interface is configured at the end to connect with the protective main housing, and a damper is provided at the bracket joint to ensure that the observation angle remains stable under the vibration environment of the machine tool.

[0025] In this embodiment, specifically, the protective main housing adopts an aluminum alloy shell with IP65 protection grade (size 600×350×80mm), a shielding layer is set inside, and a three-color sound and light alarm light is integrated on the top (supporting remote control).

[0026] In this embodiment, the human-computer interaction module is a touch screen embedded in the protective main housing; specifically, it is a 7-inch industrial-grade touch screen, embedded at a 15° elevation angle, and the surface is covered with oil-proof tempered glass. The protective main housing is also provided with an audible and visual alarm device (in this embodiment, the audible and visual alarm device is the above-mentioned audible and visual alarm tricolor light). When the calculation result of the host module is abnormal, the audible and visual alarm device will sound an alarm.

[0027] In this embodiment, specifically, the host module communicates with the temperature acquisition module, the vibration acquisition module, the current acquisition module, and the CNC system communication module via the EtherCAT bus at high speed; The human-computer interaction module exchanges information with the edge data acquisition terminal through Ethernet.

[0028] In this embodiment, it should be noted that during the machining process, the status of the tool can be determined by analyzing a large number of high-frequency vibration signals and load signals. However, the sampling frequency of the equipment status data provided by the traditional machine tool CNC system is insufficient to support the judgment of the tool status, so an additional vibration sensor is required. In this embodiment, the sensors installed are as follows: A vibration sensor is installed on the tool to obtain the tool vibration signal; A temperature sensor is placed near the cutter head to obtain temperature information near the cutter head; A three-phase current sensor is installed on the spindle to obtain the spindle current signal.

[0029] In this embodiment, it should be noted that the configuration requirements of the vibration sensor and the three-phase current sensor are shown in the table below.

[0030] Table 1 Sensor configuration requirements

[0031] In this embodiment, specifically, a filtering module is provided between the vibration acquisition module and the vibration sensor, the temperature acquisition module and the temperature sensor, and the current acquisition module and the three-phase current sensor; that is, each data acquisition module is connected to its corresponding sensor. In order to consider the problem of signal interference, a special filtering module is added between the sensor and the acquisition module, and the selection of filtering parameters is related to the frequency band of interest of the acquired signal.

[0032] In this embodiment, specifically, the dynamic threshold method state detection model includes: The tool status is identified by comparing the characteristic values ​​of the signals collected by the data acquisition module with the set dynamic threshold in real time. Based on the preset judgment rules, it is determined whether the tool is abnormal. If it is judged to be abnormal (chipping, tool breakage, wear), an emergency command is sent to the CNC system to control the machine tool to stop processing.

[0033] At the same time, the characteristics that are sensitive to tool wear are analyzed to obtain the percentage of tool wear. When the set value is reached, the human-computer interaction module prompts the operator to replace the tool, thereby improving the utilization rate of the tool.

[0034] In this embodiment, specifically, the determination rules include: single signal threshold triggering and multi-signal collaborative verification; The single signal threshold triggering includes: triggering a preliminary abnormality mark when any signal characteristic value exceeds a dynamic threshold; The multi-signal collaborative verification includes: making further abnormality judgment based on the tool vibration signal, temperature information near the tool disc, and spindle current signal according to the multi-signal combination relationship constructed by experience; in this embodiment, it should be noted that the multi-signal combination relationship refers to the use of two or three combinations of the tool vibration signal, temperature information near the tool disc, and spindle current signal to make judgments to further determine whether the tool is abnormal.

[0035] In this embodiment, it should also be noted that the construction of the multi-signal combination relationship can be obtained by those skilled in the art through experiments and experience without creative work based on the above-mentioned device, and will not be elaborated here.

[0036] In this embodiment, specifically, the calculation formula of the dynamic threshold is as follows:

[0037] λ(t) represents the dynamic threshold at the current moment, that is, the dynamic threshold corresponding to time t; represents the smoothing coefficient; Indicates the number of sliding window samples; (t) indicates the The sampling value of a sensor at time t; Indicates the dynamic threshold of the previous moment; Furthermore, the technical relevance of the above parameters is described in the table below: Table 2 Description of technical relevance of symbols

[0038] In this embodiment, it should also be noted that the calculation of the dynamic threshold is based on historical processing data.

[0039] In this embodiment, specifically, the wear prediction model includes: Based on the data collected by the data acquisition module, a cascaded deep learning architecture is designed. The front stage uses a convolutional neural network (CNN) to extract the frequency domain spatial features of the signal, and the back stage uses a bidirectional long short-term memory (Bi-LSTM) network to model the temporal dependency of the signal. The model outputs the wear prediction value of the tool wear.

[0040] In this embodiment, it should be noted that the prediction idea of ​​the life prediction model is: wear prediction is a relatively simple and accurate prediction method, and the wear prediction can be converted into life prediction by establishing a mapping relationship between the wear value and life of the tool.

[0041] In this embodiment, specifically, the lifespan prediction model includes: A combined model based on the convolutional neural network (CNN) and the fully connected layer (Dense) was selected to establish the mapping relationship. Historical data was used to train the model to find the best fit relationship between wear value and usage time. Finally, the predicted results were compared with the actual service life to evaluate the error and reliability of the model.

[0042] The specific working process of the above-mentioned large machine tool tool wear monitoring and interaction device is as follows: Hardware installation: Install a current sensor on the spindle motor, a vibration sensor on the machine tool tool, a temperature sensor near the tool head, a cantilever beam and an interactive device next to the machine tool operation panel, and a lower computer in the electrical cabinet and bus cabinet to build a data acquisition platform.

[0043] Data acquisition and processing: The lower computer collects and integrates real-time data from sensors and transmits the data to the upper computer interactive interface via a network cable. The host module processes the raw data and displays it on the interactive screen.

[0044] Human-computer interaction process: The touch screen displays real-time current and vibration data, the threshold red curve is automatically learned and displayed on the screen, and presented to the operator together with the data curve; historical data is compressed, and the touch screen displays the global curve; the life system automatically predicts the life and displays the life progress bar on the screen; if the status monitoring module and the life module exceed the threshold curve, the device will alarm, the sound and light alarm tricolor light will turn yellow or red, and the buzzer will sound an alarm.

[0045] Based on the same technical concept, an embodiment of the present invention also provides an electronic device that can implement the working methods of the dynamic threshold method state detection model, wear prediction model, and life prediction model provided in the above embodiments of the present invention. In one embodiment, the electronic device can be a server, a terminal device, or other electronic device. Figure 3 As shown, the electronic device may include: At least one processor, and a memory connected to the at least one processor. The embodiment of the present invention does not limit the specific connection medium between the processor and the memory. Figure 3 The example in this article is that the processor and memory are connected via a bus. Figure 3 The connections between the other components are shown in bold lines, which are only for illustration and not limiting. The bus can be divided into address bus, data bus, control bus, etc. Figure 3 The processor is represented by a single thick line, but this does not mean that there is only one bus or only one type of bus. Alternatively, the processor can also be called a controller, without any limitation on the name.

[0046] In an embodiment of the present invention, the memory stores instructions that can be executed by at least one processor. By executing the instructions stored in the memory, the at least one processor can execute the working methods of the dynamic threshold method state detection model, wear prediction model, and life prediction model discussed above. The processor can implement Figure 3 The functions of each module in the device shown.

[0047] Among them, the processor is the control center of the device, which can use various interfaces and lines to connect the various parts of the entire control device, and monitor the device as a whole by running or executing instructions stored in the memory and calling data stored in the memory, the various functions of the device and processing data.

[0048] In an optional design, the processor may include one or more processing units, and the processor may integrate an application processor and a modem processor, wherein the application processor primarily processes the operating system, user interface, and application programs, and the modem processor primarily processes wireless communications. It is understood that the modem processor may not be integrated into the processor. In some embodiments, the processor and memory may be implemented on the same chip, or in some embodiments, they may be implemented on separate chips.

[0049] The processor can be a general-purpose processor, such as a CPU, digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention. A general-purpose processor can be a microprocessor or any conventional processor. The steps of the operating methods of the dynamic threshold state detection model, wear prediction model, and life prediction model disclosed in the embodiments of the present invention can be directly implemented and executed by a hardware processor, or by a combination of hardware and software modules within the processor.

[0050] As a non-volatile computer-readable storage medium, memory can be used to store non-volatile software programs, non-volatile computer executable programs and modules. Memory can include at least one type of storage medium, for example, can include flash memory, hard disk, multimedia card, card-type memory, random access memory (Random Access Memory, RAM), static random access memory (Static Random Access Memory, SRAM), programmable read-only memory (Programmable Read Only Memory, PROM), read-only memory (Read Only Memory, ROM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, EEPROM), magnetic memory, disk, optical disk, etc. Memory is any other medium that can be used to carry or store desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory in the embodiment of the present invention can also be a circuit or any other device that can realize a storage function, for storing program instructions and / or data.

[0051] By designing and programming the processor, the code corresponding to the working methods of the dynamic threshold method state detection model, wear prediction model, and life prediction model described in the aforementioned embodiments can be embedded in the chip, enabling the chip to execute the steps of the methods of the aforementioned embodiments during operation. Designing and programming a processor is well known to those skilled in the art and will not be further described here.

[0052] Based on the same inventive concept, an embodiment of the present invention also provides a storage medium, which stores computer instructions. When the computer instructions are run on a computer, the computer executes the working methods of the dynamic threshold method state detection model, wear prediction model, and life prediction model discussed above.

[0053] In some optional embodiments, the present invention also provides various aspects of the working methods of the dynamic threshold method state detection model, wear prediction model, and life prediction model, which can also be implemented in the form of a program product, which includes program code. When the program product is run on the device, the program code is used to enable the control device to execute the steps in the working methods of the dynamic threshold method state detection model, wear prediction model, and life prediction model according to various exemplary embodiments of the present invention described above in this specification.

[0054] It should be noted that although several units or subunits of the device are mentioned in the detailed description above, this division is merely exemplary and not mandatory. In fact, according to an embodiment of the present invention, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of a unit described above can be further divided into multiple units to be embodied. In addition, although the operations of the method of the present invention are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. Additionally or alternatively, certain steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0055] It will be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0056] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as a combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a server, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the process in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0057] Program code for performing the operations of the present invention may be written using any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computing device, partially on the user's device, as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0058] Where a remote computing device is involved, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0059] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0061] The above-described embodiments merely represent specific implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of protection of the present application. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the technical concept of the present application, and all such variations and improvements fall within the scope of protection of the present application.

[0062] This background section is provided to generally present the context of the invention, and the work of the presently named inventors, the work to the extent described in this background section, and aspects of the description in this section that did not constitute prior art at the time of filing are neither explicitly nor implicitly admitted to be prior art to the present invention.

Claims

1. A large machine tool tool wear monitoring and interaction device, characterized in that: include: A cantilever support assembly and a protective main housing, wherein the cantilever support assembly is connected to the protective main housing via a quick-release interface; The protective main housing is internally integrated with an edge data acquisition terminal and a human-computer interaction module; The edge data acquisition terminal includes: The data acquisition module includes a vibration acquisition module for acquiring tool vibration signals, a temperature acquisition module for acquiring temperature information near the cutter head, and a current acquisition module for acquiring spindle current signals; The host module serves as the core computing unit and has built-in dynamic threshold method state detection model, wear prediction model, and life prediction model. It can calculate the tool state, wear, and life based on the data collected by the data acquisition module. The CNC system communication module is responsible for communicating with the CNC system to achieve real-time acquisition of processing parameters and issuance of emergency control instructions; The human-computer interaction module exchanges information with the edge data acquisition terminal, can display real-time processing parameters, data collected by the data acquisition module and calculation results of the host module, and has human-computer interaction functions.

2. A large machine tool tool wear monitoring and interaction device according to claim 1, characterized in that: The human-computer interaction module is a touch screen embedded in the protective main housing; The protective main housing is also provided with an audible and visual alarm device, which will sound an alarm when the calculation result of the main module is abnormal.

3. A large machine tool tool wear monitoring and interaction device according to claim 1, characterized in that: The host module communicates with the temperature acquisition module, vibration acquisition module, current acquisition module and CNC system communication module at high speed via the EtherCAT bus. The human-computer interaction module exchanges information with the edge data acquisition terminal through Ethernet.

4. A large machine tool tool wear monitoring and interaction device according to claim 1, characterized in that: A vibration sensor is installed on the tool to obtain the tool vibration signal; a temperature sensor is installed near the cutter head to obtain temperature information near the cutter head; a three-phase current sensor is installed on the spindle to obtain the spindle current signal.

5. A large machine tool tool wear monitoring and interaction device according to claim 4, characterized in that: A filter module is provided between the vibration acquisition module and the vibration sensor, the temperature acquisition module and the temperature sensor, and the current acquisition module and the three-phase current sensor.

6. A large machine tool tool wear monitoring and interaction device according to claim 1, characterized in that: The dynamic threshold method state detection model includes: The tool status is identified by comparing the characteristic values ​​of the signals collected by the data acquisition module with the set dynamic threshold in real time. Based on the preset judgment rules, it is determined whether the tool is abnormal. If it is determined to be abnormal, an emergency command is sent to the CNC system to control the machine tool to stop processing. At the same time, the characteristics that are sensitive to tool wear are analyzed to obtain the percentage of tool wear. When the set value is reached, the operator is prompted to replace the tool through the human-computer interaction module.

7. A large machine tool tool wear monitoring and interaction device according to claim 6, characterized in that: The judgment rules include: single signal threshold triggering and multi-signal collaborative verification; The single signal threshold triggering includes: triggering a preliminary abnormality mark when any signal characteristic value exceeds a dynamic threshold; The multi-signal collaborative verification includes: performing further abnormality judgment based on the tool vibration signal, temperature information near the cutter head, and spindle current signal according to the multi-signal combination relationship constructed based on experience.

8. A large machine tool tool wear monitoring and interaction device according to claim 6, characterized in that: The calculation formula of the dynamic threshold is as follows: λ(t) represents the dynamic threshold at the current moment, that is, the dynamic threshold corresponding to time t; represents the smoothing coefficient; Indicates the number of sliding window samples; (t) indicates the The sampling value of a sensor at time t; Indicates the dynamic threshold at the previous moment.

9. A large machine tool tool wear monitoring and interaction device according to claim 1, characterized in that: The wear prediction model includes: Based on the data collected by the data acquisition module, a cascaded deep learning architecture is designed. The front stage uses a convolutional neural network (CNN) to extract the frequency domain spatial features of the signal, and the back stage uses a bidirectional long short-term memory (Bi-LSTM) network to model the temporal dependency of the signal. The model outputs the wear prediction value of the tool wear.

10. A large machine tool tool wear monitoring and interaction device according to claim 9, characterized in that: The lifespan prediction model comprises: A combined model based on the convolutional neural network (CNN) and the fully connected layer (Dense) was selected to establish the mapping relationship. Historical data was used to train the model to find the best fit relationship between wear value and usage time. Finally, the predicted results were compared with the actual service life to evaluate the error and reliability of the model.

Images