Shaft state prediction method and apparatus for computer numerical control machine tool, device, and storage medium

Abstract

The present application relates to the technical field of machine tool state prediction, and discloses a shaft state prediction method and apparatus for a computer numerical control machine tool, a device, and a storage medium. The method comprises: acquiring a vibration acceleration signal of a shaft to be predicted of a target computer numerical control machine tool in at least one direction; respectively performing data processing on the vibration acceleration signal in each direction to obtain at least two acceleration peak-to-peak values in each direction and at least two speeds in each direction; respectively performing feature extraction on the at least two acceleration peak-to-peak values in each direction and the at least two speeds in each direction to obtain target features in each direction; and on the basis of a target state prediction model, performing state prediction on target features in all directions to obtain a state prediction result of said shaft in the at least one direction. The technical solution provided by one or more implementations of the present application can solve the problem of effectively predicting a future state of a shaft of a computer numerical control machine tool.

Description

Methods, devices, equipment and storage media for predicting the axis state of CNC machine tools

[0001] This application claims priority to Chinese Patent Application No. 202410517103.9, filed on April 26, 2024, entitled “Axis State Prediction Method, Apparatus, Equipment and Storage Medium for CNC Machine Tools”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This application relates to the field of machine tool condition monitoring technology, specifically to methods, devices, equipment, and storage media for predicting the axis condition of CNC machine tools. Background Technology

[0003] In view of the shortcomings of related technologies, there is a need for a method that can effectively predict the future state of CNC machine tool axes. Summary of the Invention

[0004] In view of this, this application provides a method, apparatus, device and storage medium for predicting the axis state of a CNC machine tool, in order to solve the problem of effectively predicting the future state of CNC machine tool axes.

[0005] In a first aspect, this application provides a method for predicting the state of an axis in a CNC machine tool. The method includes: acquiring vibration acceleration signals of the axis to be predicted in at least one direction in the target CNC machine tool; performing data processing on the vibration acceleration signals in each direction to obtain at least two peak-to-peak values ​​of acceleration and at least two velocities in each direction; extracting features from the at least two peak-to-peak values ​​of acceleration and the at least two velocities in each direction to obtain target features in each direction; and performing state prediction on the target features in all directions based on a target state prediction model to obtain the state prediction result of the axis to be predicted in at least one direction.

[0006] Secondly, this application provides an axis state prediction device for a CNC machine tool. The device includes: a signal acquisition module for acquiring vibration acceleration signals of the axis to be predicted in at least one direction in the target CNC machine tool; a signal processing module for processing the vibration acceleration signals in each direction to obtain at least two peak-to-peak values ​​of acceleration and at least two velocities in each direction; a feature extraction module for extracting features from the at least two peak-to-peak values ​​of acceleration and the at least two velocities in each direction to obtain target features in each direction; and a state prediction module for performing state prediction on the target features in all directions based on a target state prediction model to obtain the state prediction result of the axis to be predicted in at least one direction.

[0007] Thirdly, this application provides a computer device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to perform the axis state prediction method for CNC machine tools described in the first aspect or any corresponding embodiment.

[0008] Fourthly, this application provides a computer-readable storage medium storing computer instructions for causing a computer to execute the axis state prediction method for a CNC machine tool according to the first aspect or any corresponding embodiment described above.

[0009] Fifthly, this application provides a computer program product, including computer instructions for causing a computer to execute the axis state prediction method for a CNC machine tool according to the first aspect or any corresponding embodiment described above.

[0010] The technical solution provided by one or more embodiments of this application can predict the future state of the axes of a CNC machine tool based on vibration data during operation. Specifically, it involves collecting vibration acceleration signals of the target CNC machine tool axis to be predicted in at least one direction; performing data processing and feature extraction on the vibration acceleration signals in each direction to obtain target features in each direction; training the state prediction model to obtain a target state prediction model; and performing state prediction on the target features in all directions based on the target state prediction model to obtain the state prediction result of the axis to be predicted in at least one direction.

[0011] As can be seen, the technical solution provided in this application can predict the future state values ​​of CNC machine tool axes based on historical operation data, thereby achieving the purpose of knowing the occurrence of abnormal states in advance, performing maintenance operations as early as possible, and avoiding losses caused by abnormalities. Attached Figure Description

[0012] To more clearly illustrate the technical solutions in the specific embodiments of this application or the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0013] Figure 1 is a flowchart illustrating the axis state prediction method for a CNC machine tool according to an embodiment of this application;

[0014] Figure 2 is a schematic diagram of hardware installation according to an embodiment of this application;

[0015] Figure 3 is a schematic diagram of a target state prediction model according to an embodiment of this application;

[0016] Figure 4 is a schematic diagram of data processing and feature extraction according to an embodiment of this application;

[0017] Figure 5 is a schematic diagram of the model training process according to an embodiment of this application;

[0018] Figure 6 is a schematic diagram of the model training process according to an embodiment of this application;

[0019] Figure 7 is a schematic diagram of the model testing process according to an embodiment of this application;

[0020] Figure 8 is a structural block diagram of an axis state prediction device for a CNC machine tool according to an embodiment of this application;

[0021] Figure 9 is a schematic diagram of the hardware structure of a computer device according to an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] In related technologies, monitoring the status of CNC machine tools mainly involves monitoring data from key components such as lead screws and bearings. The current state of these components is analyzed based on the data, and maintenance is performed if abnormalities are detected. However, this approach only detects abnormalities after they occur, and cannot prevent them from happening, potentially leading to damage and losses. Furthermore, machine tools have numerous key components, making individual monitoring tedious and time-consuming, while monitoring only a subset of components fails to represent the overall operating status of the machine tool. Moreover, the spindle and feed axes of CNC machine tools contain many key components that can effectively reflect the overall state of the machine tool. This application provides a method for predicting the axis status of CNC machine tools, which can predict future possible state values ​​based on historical operating data of the CNC machine tool axes, thereby monitoring the overall status of the CNC machine tool.

[0024] This embodiment provides a method for predicting the axis state of a CNC machine tool. Figure 1 is a flowchart of the method for predicting the axis state of a CNC machine tool according to an embodiment of this application. As shown in Figure 1, the process includes the following steps:

[0025] Step S101 is used to acquire the vibration acceleration signal of the axis to be predicted in at least one direction in the target CNC machine tool.

[0026] As shown in Figure 2, a three-dimensional vibration acceleration sensor is used to collect vibration acceleration signals of the target CNC machine tool axes, including the spindle and feed axes. Vibration acceleration signals in three directions (spindle, feed, and spindle) can be detected simultaneously. A vibration acquisition card collects the vibration acceleration signals acquired by the front-end vibration sensor. An I / O module is used to communicate with the target CNC machine tool's PLC to obtain the machine tool's M-code information, which serves as the trigger signal for starting data acquisition.

[0027] Step S102 is used to process the vibration acceleration signals in each direction to obtain at least two acceleration peak values ​​and at least two velocities in each direction.

[0028] As shown in Figure 2, the industrial control computer processes the data, collects vibration acceleration signals in various directions, and obtains at least two peak-to-peak values ​​of acceleration in each direction and at least two velocities in each direction.

[0029] Step S103 is used to extract features from at least two acceleration peak values ​​and at least two velocities in each direction to obtain target features in each direction.

[0030] The surface quality correlation feature is obtained by taking the maximum value of the peak-to-peak value of the acceleration signal, and the size correlation feature is obtained by taking the average value of the velocity signal.

[0031] Step S104 is used to predict the state of the target features in all directions based on the target state prediction model, and obtain the state prediction result of the axis to be predicted in at least one direction.

[0032] First, the collected target feature data is preprocessed by normalization and stabilization. A Long Short-Term Memory (LSTM) network model is then used to predict target features in all directions; the LSTM model is shown in Figure 3. Multiple sets of measured target features from the target CNC machine tool are collected and used to train the model, resulting in a target state prediction model.

[0033] The CNC machine tool axis state prediction method provided in this embodiment can effectively predict the future state of the target CNC machine tool axis. By applying this technology, the possible state of the axis can be known in advance. If a large fluctuation in the future state is found, maintenance measures can be taken in advance to reduce the loss of abnormal machine tool downtime.

[0034] In some optional implementations, the vibration acceleration signal of the axis to be predicted in the target CNC machine tool in at least one direction is acquired; the vibration acceleration signal in each direction is processed to obtain at least two acceleration peak-to-peak values ​​and at least two velocities in each direction; the acceleration peak-to-peak values ​​and velocities in each direction are extracted to obtain target features in each direction.

[0035] Accordingly, step S103 above includes:

[0036] A first statistical analysis is performed on at least two acceleration peak-to-peak values ​​in each direction to obtain the first statistical analysis results for each direction. The first statistical analysis results are used to characterize the first target features in each direction. The first statistical analysis is performed on the acceleration peak-to-peak values ​​in each direction to obtain the first statistical analysis results for each direction, including: for each direction, determining the maximum value among at least two acceleration peak-to-peak values ​​to obtain the first statistical analysis results.

[0037] A second statistical analysis is performed on at least two velocities in each direction to obtain second statistical analysis results for each direction. These results characterize the second target features in each direction, including both first and second target features. The second statistical analysis of velocities in each direction includes determining the average value of at least two velocities for each direction to obtain the second statistical analysis results.

[0038] For example, as shown in Figure 4, the vibration acceleration signals of the axis to be predicted in the X, Y, and Z directions of the target CNC machine tool are acquired; the vibration acceleration signals in the X, Y, and Z directions are calculated to obtain at least two peak-to-peak values ​​of acceleration in the X, Y, and Z directions and at least two velocities in the X, Y, and Z directions; the maximum value of the peak-to-peak values ​​of acceleration in the X, Y, and Z directions is determined to obtain the surface quality correlation characteristics in the X, Y, and Z directions; the average value of the at least two velocities in the X, Y, and Z directions is determined to obtain the dimensional correlation characteristics in the X, Y, and Z directions.

[0039] The vibration acceleration signal data processing and feature extraction method provided in this embodiment can convert the data into several feature values, which greatly reduces the amount of data for model training and shortens the training time.

[0040] In some alternative implementations, the training method for the target state prediction model is shown in Figure 5, and the process includes the following steps:

[0041] Step S201 is used to acquire multiple sets of measured vibration acceleration signals arranged in chronological order. Each set of measured vibration acceleration signals includes vibration acceleration signals of the axis to be predicted in each direction in the target CNC machine tool.

[0042] Step S202 is used to process and extract features from multiple sets of measured vibration acceleration signals to obtain multiple sets of sample vibration features.

[0043] Step S203 is used to extract the vibration features of the first sample of a first preset number from the vibration features of multiple samples as input data, and to use the vibration features of the next sample of the first preset number of samples adjacent to the last sample of the first preset number as a label.

[0044] Step S204 is used to input the input data into the initial state prediction model to obtain the prediction result.

[0045] Step S205 is used to update the parameters of the initial state prediction model based on the prediction results and labels to obtain the target state prediction model.

[0046] For example, as shown in Figure 6, measured vibration acceleration signals of the target CNC machine tool's axes during operation are acquired in chronological order. Multiple sets of measured vibration acceleration signals are processed and feature extracted to obtain multiple sets of sample vibration features. These sample vibration features include surface quality correlation features and size correlation features in the X, Y, and Z directions, resulting in a total of n sets of sample vibration features. From these n sets of sample vibration features, three sets of sample vibration features are extracted at a step size of 1, denoted as X, and the next set of sample vibration features adjacent to the last set is used as a label, denoted as y. The input data is then fed into the initial state prediction model LSTM to obtain the prediction results. Based on the prediction results and labels, the parameters of the initial state prediction model are updated to obtain the target state prediction model.

[0047] The target state prediction model training method provided in this embodiment trains the model before performing axis state prediction, so that the target state prediction model can make good predictions on the data.

[0048] In some optional implementations, the vibration acceleration signal of the last second preset number of measured vibration acceleration signals from multiple sets is extracted to obtain the vibration acceleration signal of the axis to be predicted in at least one direction. Data processing and feature extraction are then performed on the vibration acceleration signal of the axis to be predicted in at least one direction to obtain target features in all directions.

[0049] Accordingly, step S104 above includes:

[0050] Step a11: Input the target features of all directions of the second preset group into the target state prediction model to obtain the prediction features of at least one direction.

[0051] Step a12: Place the predicted features of at least one direction into the last group of adjacent positions of the target features in all directions of the second preset group number to form a new target feature dataset.

[0052] Step a13: Extract the target features of all directions from the last second preset group number in the new target feature dataset and input them into the target state prediction model to obtain the prediction features of at least one direction.

[0053] Step a14: Repeat the operation a preset number of times to obtain the state prediction result of the axis to be predicted in at least one direction.

[0054] For example, as shown in Figure 7, the last three groups of target features T are selected. n-2 T n-1 and T n The first set of predicted feature values ​​y is obtained by inputting the target state prediction model. n+1 . y n+1 Placed in T n-2 T n-1 and T n The end is denoted as T n+1 Then extract T n-1 T n and T n+1 The second set of predicted feature values ​​y is obtained by inputting the target state prediction model. n+2 By repeating this process, the state prediction result of the axis to be predicted in at least one direction can be obtained.

[0055] The axis state prediction method provided in this embodiment inputs the target features into the target state prediction model to obtain the state prediction result of the axis to be predicted in at least one direction, thus completing the prediction of the future state of the axis of the target CNC machine tool.

[0056] This embodiment also provides an axis state prediction device for a CNC machine tool, which is used to implement the above embodiments and optional implementations; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0057] This embodiment provides an axis state prediction device for a CNC machine tool, as shown in Figure 8, including:

[0058] The signal acquisition module 801 is used to acquire the vibration acceleration signal of the axis to be predicted in at least one direction in the target CNC machine tool.

[0059] The signal processing module 802 is used to process the vibration acceleration signals in each direction to obtain at least two peak-to-peak values ​​of acceleration in each direction and at least two velocities in each direction.

[0060] The feature extraction module 803 is used to extract features from at least two acceleration peak values ​​and at least two velocities in each direction to obtain target features in each direction.

[0061] The state prediction module 804 is used to predict the state of the target features in all directions based on the target state prediction model, and obtain the state prediction result of the axis to be predicted in at least one direction.

[0062] In some optional implementations, the vibration acceleration signal of the axis to be predicted in the target CNC machine tool in at least one direction is acquired; the vibration acceleration signal in each direction is processed to obtain at least two acceleration peak-to-peak values ​​and at least two velocities in each direction; the acceleration peak-to-peak values ​​and velocities in each direction are extracted to obtain target features in each direction.

[0063] Feature extraction module 803 includes:

[0064] The first statistical analysis unit is used to perform a first statistical analysis on at least two acceleration peak-to-peak values ​​in each direction to obtain the first statistical analysis results for each direction. The first statistical analysis results are used to characterize the first target features in each direction. The first statistical analysis on the acceleration peak-to-peak values ​​in each direction to obtain the first statistical analysis results for each direction includes: for each direction, determining the maximum value among at least two acceleration peak-to-peak values ​​to obtain the first statistical analysis results.

[0065] The second statistical analysis unit is used to perform a second statistical analysis on at least two velocities in each direction to obtain second statistical analysis results for each direction. These results characterize the second target features in each direction, including both first and second target features. The process of performing the second statistical analysis on the velocities in each direction to obtain second statistical analysis results includes: for each direction, determining the average value of at least two velocities to obtain the second statistical analysis result.

[0066] In some alternative implementations, the training unit of the target state prediction model includes:

[0067] The acceleration acquisition subunit is used to acquire multiple sets of measured vibration acceleration signals arranged in chronological order. Each set of measured vibration acceleration signals includes the vibration acceleration signals of the axis to be predicted in each direction in the target CNC machine tool.

[0068] The feature extraction subunit is used to process and extract features from multiple sets of measured vibration acceleration signals to obtain multiple sets of sample vibration features.

[0069] The data input subunit is used to extract the first sample vibration features of a first preset number of groups from multiple groups of sample vibration features as input data, and to use the next group of sample vibration features adjacent to the last group of the first preset number of groups as labels.

[0070] The result acquisition sub-unit is used to input the input data into the initial state prediction model to obtain the prediction result.

[0071] The model update subunit is used to update the parameters of the initial state prediction model based on the prediction results and labels to obtain the target state prediction model.

[0072] In some optional implementations, the vibration acceleration signal of the last second preset number of measured vibration acceleration signals from multiple sets is extracted to obtain the vibration acceleration signal of the axis to be predicted in at least one direction. Data processing and feature extraction are then performed on the vibration acceleration signal of the axis to be predicted in at least one direction to obtain target features in all directions.

[0073] The state prediction module 804 includes:

[0074] The first feature acquisition unit is used to input the target features of all directions of the second preset group into the target state prediction model to obtain the prediction features of at least one direction.

[0075] The dataset update unit is used to place the predicted features in at least one direction into the last group of adjacent positions of the target features in all directions of a second preset group, forming a new target feature dataset.

[0076] The second feature acquisition unit extracts the target features in all directions of the last second preset group in the new target feature dataset and inputs them into the target state prediction model to obtain prediction features in at least one direction.

[0077] The result acquisition unit is used to perform a preset number of cyclic operations to obtain the state prediction result of the axis to be predicted in at least one direction.

[0078] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0079] In this embodiment, the axis state prediction device of the CNC machine tool is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0080] This application also provides a computer device having the axis state prediction device for the CNC machine tool shown in FIG8.

[0081] Please refer to Figure 9, which is a schematic diagram of the structure of a computer device provided in an optional embodiment of this application. As shown in Figure 9, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting the various components, including high-speed interfaces and low-speed interfaces. The various components communicate with each other using different buses and can be installed on a common motherboard or otherwise as needed. The processor can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some optional embodiments, multiple processors and / or multiple buses can be used with multiple memories and multiple memory modules, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 9 uses one processor 10 as an example.

[0082] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0083] The memory 20 stores instructions executable by at least one processor 10 to cause at least one processor 10 to perform the method shown in the above embodiments.

[0084] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0085] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0086] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means; Figure 9 shows an example of a connection via a bus.

[0087] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0088] This application also provides a computer-readable storage medium. The methods described in this application can be implemented in hardware or firmware, or implemented as recordable on a storage medium, or implemented as computer code downloaded over a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and subsequently stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the methods shown in the above embodiments are implemented.

[0089] A portion of this application can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to this application through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0090] Although embodiments of this application have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of this application, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for predicting the axis state of a CNC machine tool, characterized in that, The method includes: Acquire the vibration acceleration signal of the axis to be predicted in at least one direction in the target CNC machine tool; The vibration acceleration signals in each direction are processed to obtain at least two peak-to-peak values ​​of acceleration in each direction and at least two velocities in each direction. Feature extraction is performed on at least two acceleration peak values ​​and at least two velocities in each direction to obtain target features in each direction; Based on the target state prediction model, the target features in all directions are predicted to obtain the state prediction result of the axis to be predicted in at least one direction.

2. The method according to claim 1, characterized in that, The step of extracting features from at least two acceleration peak values ​​and at least two velocities in each direction to obtain target features in each direction includes: A first statistical analysis is performed on at least two acceleration peak-to-peak values ​​in each direction to obtain the first statistical analysis results for each direction. The first statistical analysis results are used to characterize the first target features in each direction. A second statistical analysis is performed on at least two velocities in each direction to obtain a second statistical analysis result for each direction. The second statistical analysis result is used to characterize a second target feature in each direction, and the target feature includes the first target feature and the second target feature.

3. The method according to claim 2, characterized in that, The first statistical analysis of the peak-to-peak values ​​of acceleration in each direction, to obtain the first statistical analysis results for each direction, includes: For each of the aforementioned directions, the maximum value among the at least two acceleration peak-to-peak values ​​is determined to obtain the first statistical analysis result.

4. The method according to claim 2, characterized in that, The second statistical analysis of the velocities in each direction, to obtain the second statistical analysis results for each direction, includes: For each of the directions, the average value of the at least two velocities is determined to obtain the second statistical analysis result.

5. The method according to claim 1, characterized in that, The training method for the target state prediction model includes: Acquire multiple sets of measured vibration acceleration signals arranged in chronological order, each set of measured vibration acceleration signals including vibration acceleration signals of the axis to be predicted in each direction in the target CNC machine tool; Data processing and feature extraction are performed on the multiple sets of measured vibration acceleration signals to obtain multiple sets of sample vibration features; The vibration features of the first sample in the first preset number of groups are extracted from the vibration features of the multiple groups of samples as input data, and the vibration features of the next group of samples adjacent to the last group of the first preset number of groups in the vibration features of the multiple groups of samples are used as labels. The input data is input into the initial state prediction model to obtain the prediction result; Based on the prediction results and the labels, the parameters of the initial state prediction model are updated to obtain the target state prediction model.

6. The method according to claim 5, characterized in that, The acquisition of vibration acceleration signals of the axis to be predicted in at least one direction in the target CNC machine tool includes: Extract the vibration acceleration signal of the last second preset number from the multiple sets of measured vibration acceleration signals to obtain the vibration acceleration signal of the shaft to be predicted in at least one direction.

7. The method according to claim 6, characterized in that, The step of performing state prediction on target features in all directions based on the target state prediction model to obtain the state prediction result of the axis to be predicted in at least one direction includes: Input the target features of all directions of the second preset group into the target state prediction model to obtain the prediction features of the at least one direction; The predicted features of at least one direction are placed in the last group of adjacent positions of all the target features of the second preset group number to form a new target feature dataset; Extract the target features of all directions from the last second preset group number in the new target feature dataset and input them into the target state prediction model to obtain the predicted features of at least one direction; The operation is repeated a preset number of times to obtain the state prediction result of the axis to be predicted in at least one direction.

8. A device for predicting the axis state of a CNC machine tool, characterized in that, The device includes: The signal acquisition module is used to acquire the vibration acceleration signal of the axis to be predicted in at least one direction in the target CNC machine tool; The signal processing module is used to process the vibration acceleration signals in each direction to obtain at least two peak-to-peak values ​​of acceleration in each direction and at least two velocities in each direction. The feature extraction module is used to extract features from at least two acceleration peak values ​​and at least two velocities in each direction to obtain target features in each direction. The state prediction module is used to predict the state of the target features in all directions based on the target state prediction model, and to obtain the state prediction result of the axis to be predicted in at least one direction.

9. A computer device, characterized in that, include: A memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, the processor executing the computer instructions to perform the method of any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a computer to perform the method of any one of claims 1 to 6.

Images