Method and equipment for marking operation parameters, electronic device and storage medium

Abstract

The embodiment of the invention discloses a method and equipment for marking operation parameters, an electronic device and a medium. The method comprises the following steps: acquiring a three-dimensional image sequence about the movement process of a main shaft of the machine tool, wherein the three-dimensional image sequence is captured by an imaging assembly; acquiring an operation parameter curve about the movement process of the main shaft; identifying a main shaft motion mode from the three-dimensional image sequence; time information of the main shaft motion mode is determined; and marking the operating parameter curve based on the time information and motion description information associated with the spindle motion pattern. The motion description information can be marked in the operating parameter curve, so that the operating parameters are easy to understand.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a method, device, electronic device and medium for marking operation parameters. Background Art

[0002] With the rapid development of digital technology, a large amount of data is collected for process simulation, optimization and in-depth analysis to improve production efficiency. One of the main challenges is to map production data to the real process and then explain the process details to data analysis experts or production applications to demonstrate the value behind the data.

[0003] A machine tool refers to a machine that manufactures machines. Machine tools include lathes, boring machines, milling machines, planers, grinders and other types. A lathe is a machine tool mainly used for turning a rotating workpiece with a turning tool. On a lathe, drills, reamers, taps, dies and knurling tools can also be used for corresponding processing. Lathes are mainly used for processing shafts, discs, sleeves and other workpieces with rotating surfaces. They are widely used in mechanical manufacturing and repair plants.

[0004] Currently, how to mark the operation parameters of machine tools so that users can understand the meaning of the operation parameters is a technical problem to be solved. Summary of the Invention

[0005] Embodiments of the present invention provide a method, device, electronic device and medium for marking operation parameters.

[0006] In one aspect, a method for marking operation parameters is provided. The method includes:

[0007] Obtaining a three-dimensional image sequence of the main shaft movement process of a machine tool, where the three-dimensional image sequence is captured by an imaging component;

[0008] Obtaining an operation parameter curve of the main shaft movement process;

[0009] Identifying the main shaft movement pattern from the three-dimensional image sequence;

[0010] Determining the time information of the main shaft movement pattern; and

[0011] Marking the operation parameter curve based on the time information and movement description information associated with the main shaft movement pattern.

[0012] Therefore, in the embodiments of the present invention, movement description information is marked in the operation parameter curve to facilitate understanding of the operation parameters.

[0013] Preferably, identifying the main shaft movement pattern from the three-dimensional image sequence includes:

[0014] Input the three-dimensional image sequence into a trained motion pattern recognition model, where the motion pattern recognition model is adapted to recognize the spindle motion pattern in an artificial intelligence manner;

[0015] Receive the spindle motion pattern output from the motion pattern recognition model.

[0016] Therefore, the recognition efficiency can be improved by introducing artificial intelligence into the motion pattern recognition process of the machine tool.

[0017] Preferably, where recognizing the spindle motion pattern from the three-dimensional image sequence includes:

[0018] Recognize the spindle motion pattern from the three-dimensional image sequence through computer vision.

[0019] Therefore, the spindle motion pattern of the machine tool can be easily recognized through computer vision.

[0020] Preferably, where the time information includes the start time point and the end time point of the spindle motion pattern.

[0021] Therefore, the start time point and the end time point of the spindle motion pattern are introduced into the marking process to facilitate the user's understanding of the operation parameters.

[0022] Preferably, where marking the operation parameter curve based on the time information and the motion description information associated with the spindle motion pattern includes:

[0023] Determine the first time point corresponding to the start time point in the operation parameter curve;

[0024] Determine the second time point corresponding to the end time point in the operation parameter curve;

[0025] Determine the motion description information associated with the spindle motion pattern;

[0026] Mark the motion description information in the operation parameter curve within the time interval formed by the first time point and the second time point.

[0027] Therefore, by marking the motion description information within the time interval formed by the first time point and the second time point, the user can understand the operation parameters in both the time dimension and the spindle motion dimension, which improves the comprehensiveness of understanding.

[0028] Preferably, where the operation parameter curve includes at least one of the following:

[0029] Vibration signal curve of the main shaft; Power signal curve of the main shaft motor; Temperature signal curve of the main shaft motor; Power signal curve of the servo motor; Temperature signal curve of the servo motor.

[0030] Therefore, the operation parameter curve has wide applicability.

[0031] Preferably, the main shaft motion mode includes at least one of the following:

[0032] Up and down movement; Down and up movement; Right and left movement; Left and right movement; Back and front movement; Front and back movement.

[0033] Therefore, the main shaft motion mode has wide applicability.

[0034] In a second aspect, a device for marking operation parameters is provided. The device includes:

[0035] A first acquisition module configured to acquire a three-dimensional image sequence of the main shaft movement process of a machine tool, where the three-dimensional image sequence is captured by an imaging component;

[0036] A second acquisition module configured to acquire an operation parameter curve of the main shaft movement process;

[0037] An identification module configured to identify the main shaft motion mode from the three-dimensional image sequence;

[0038] A determination module configured to determine the time information of the main shaft motion mode; and

[0039] A marking module configured to mark the operation parameter curve based on the time information and motion description information associated with the main shaft motion mode.

[0040] Therefore, in the embodiments of the present invention, the motion description information is marked in the operation parameter curve to facilitate understanding of the operation parameters.

[0041] Preferably, the identification module is configured to input the three-dimensional image sequence into a trained motion mode identification model, where the motion mode identification model is adapted to identify the main shaft motion mode in an artificial intelligence manner; and receive the main shaft motion mode output from the motion mode identification model.

[0042] Therefore, the identification efficiency can be improved by introducing artificial intelligence into the motion mode identification process of the machine tool.

[0043] Preferably, the identification module is configured to identify the main shaft motion mode from the three-dimensional image sequence through computer vision.

[0044] Therefore, the spindle motion mode of the machine tool can be easily identified through computer vision.

[0045] Preferably, the time information includes the start time point and the end time point of the spindle motion mode.

[0046] Therefore, the start time point and the end time point of the spindle motion mode are introduced into the marking process to facilitate the user's understanding of the operation parameters.

[0047] Preferably, the marking module is configured to determine a first time point corresponding to the start time point in the operation parameter curve; determine a second time point corresponding to the end time point in the operation parameter curve; determine motion description information associated with the spindle motion mode; and mark the motion description information in the operation parameter curve within the time interval formed by the first time point and the second time point.

[0048] Therefore, by marking the motion description information in the time interval formed by the first time point and the second time point, the user can understand the operation parameters in both the time dimension and the spindle motion dimension, which improves the comprehensiveness of understanding.

[0049] In a third aspect, an electronic device is provided. The device includes a processor and a memory, where an application program executable by the processor is stored in the memory, so that the processor executes the method for marking operation parameters described in any one of the above.

[0050] In a fourth aspect, a computer-readable medium includes computer-readable instructions stored thereon, where the computer-readable instructions are used to execute the method for marking operation parameters described in any one of the above.

[0051] In a fifth aspect, a computer program product includes a computer program, which is used to execute the method for marking operation parameters described in any one of the above when the computer program is executed by a processor. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] To make the technical solutions of the examples of the present disclosure clearer, the drawings used to describe the examples will be briefly introduced below. Obviously, the drawings described below are only some examples of the present disclosure. Those skilled in the art can obtain other drawings without creative efforts.

[0053] Figure 1 is a flowchart of a method for marking operation parameters according to an embodiment of the present invention.

[0054] Figure 2It is a schematic diagram of the system architecture for marking operation parameters according to an embodiment of the present invention.

[0055] Figure 3 It is a schematic diagram of an exemplary process for marking operation parameters according to an embodiment of the present invention.

[0056] Figure 4 It is a schematic diagram of the spindle motion mode according to an embodiment of the present invention.

[0057] Figure 5 It is a schematic diagram of the marked spindle vibration signal curve according to an embodiment of the present invention.

[0058] Figure 6 It is a block diagram of the device for marking operation parameters according to an embodiment of the present invention.

[0059] Figure 7 It is a structural diagram of an electronic device according to an embodiment of the present invention.

[0060] List of reference numerals:

[0061]

[0062] Detailed implementation manners

[0063] To make the objectives, technical solutions and advantages of the present invention clearer, the following examples are given to further elaborate on the present invention in detail.

[0064] For the sake of brevity and intuitiveness in description, the following describes the solutions of the present invention by describing several representative embodiments. A large number of details in the embodiments are only used to help understand the solutions of the present invention. However, it is obvious that the technical solutions of the present invention can be implemented without being limited to these details. To avoid unnecessarily obscuring the solutions of the present invention, some embodiments are not described in detail but only the framework is given. Hereinafter, "including" means "including but not limited to", and "according to..." means "at least according to..., but not limited to only according to...". Due to the language habits of Chinese, when the number of elements is not specifically indicated hereinafter, it means that the elements can be one or more, or can be understood as at least one.

[0065] After research, the applicant found that a major challenge in machine tool data analysis is that in many data analysis scenarios, it is necessary to understand each movement of the machine tool spindle. However, currently, many types of machine tools (such as obsolete machine tools) cannot obtain the motion state of each movement of the spindle from the control logic program. Specifically, for some obsolete machine tools, due to their long operation time, they either lack a data interaction interface for motion control logic or cannot even find the control logic program. In addition, since upgrading and reconstruction do not damage the original control logic, external monitoring devices must be added to some obsolete machine tools to obtain the motion state of each movement of the spindle. After understanding and identifying the motion control logic, the operating parameters can be marked. For example, in the scenario of collecting machine tool operating parameters to predict spindle failures, for many obsolete computer numerical control (CNC) machine tools, currently only the program ID of the machine tool can be collected. The program usually contains multiple subroutines, but the subroutines for controlling each movement of the spindle do not have IDs, so it is impossible to obtain the motion state of each movement of the spindle from the control logic program, and it is difficult to accurately mark each movement of the spindle in the operating parameter curve.

[0066] The applicant also found that the data can be manually marked in the operating parameter curve t to solve the problem. However, the disadvantage of this method is that it is inefficient and largely depends on the experience of the engineer.

[0067] In an embodiment of the present invention, a novel method is proposed to solve this problem. By combining the motion pattern identification algorithm with the operating parameters of the automation system, the operating parameters can be accurately marked, which expands the application field and reduces the complexity.

[0068] Figure 1 is a flowchart of a method for marking operating parameters according to an embodiment of the present invention. As Figure 1 shown, method 100 includes:

[0069] Step 101: Obtain a three-dimensional (3D) image sequence of the spindle movement process of the machine tool, where the 3D image sequence is captured by an imaging component.

[0070] Preferably, the machine tool in step 101 is implemented as a machine tool that cannot obtain the motion state of each movement of the spindle from the control logic program of the machine tool. The machine tool may include:

[0071] (1) Conventional machine tools: including conventional lathes, drill presses, boring machines, milling machines, planers, and slotting machines, etc.

[0072] (2) Precision machine tools: including grinding machines, gear processing machines, thread processing machines, and other precision machine tools.

[0073] (3) High-precision machine tools: including jig boring machines, gear grinding machines, thread grinding machines, high-precision marking machines, and other high-precision machine tools.

[0074] (4) Numerical control machine tools (CNC).

[0075] Preferably, the machine tool can be implemented as a CNC machine tool. Generally speaking, the spindle of a CNC machine tool is a hollow stepped shaft, especially the shaft that drives the chuck fixture (workpiece) or tool to rotate on a CNC lathe. It usually consists of a spindle body, bearings, and a transmission part (gear or pulley). During the machining of a CNC machine tool, the spindle drives the workpiece or tool to directly participate in the surface formation movement.

[0076] The above exemplary description of typical examples of machine tools will enable those skilled in the art to recognize that this description is only exemplary and is not intended to limit the scope of protection of the embodiments of the present invention.

[0077] The spindle movement process may include at least one movement mode. For example, the spindle movement process includes: the spindle first moves from top to bottom, and then from bottom to top. Another example, the spindle movement process may include: the spindle moves from right to left, and then from left to right, and so on.

[0078] In one embodiment, an imaging component can be used to photograph the machine tool spindle to obtain a 3D image sequence of the movement process of the machine tool spindle. In another embodiment, the 3D image sequence can be obtained from a storage medium (such as the cloud or a local database), where the 3D image sequence is obtained by photographing the machine tool spindle with an imaging component. For example, the 3D image sequence includes a plurality of 3D images captured based on a time series and throughout the movement process of the machine tool spindle. Preferably, the 3D image sequence is real-time data.

[0079] In one embodiment, the imaging component includes at least one 3D camera. The 3D camera uses 3D imaging technology to photograph the machine tool spindle to generate a 3D image sequence of the movement process of the machine tool spindle.

[0080] In one embodiment, the imaging assembly includes at least two 2D (two-dimensional) cameras, each camera being arranged at a predetermined position around the spindle of the machine tool. In fact, those skilled in the art can select a suitable position as the predetermined position to arrange the 2D cameras as needed. The imaging assembly may further include an image processor. The image processor combines a sequence of 2D images captured by each 2D camera into a sequence of 3D images in a time-synchronized manner. The depth-of-field information used by the image processor in the synthesis can be the depth-of-field information of any 2D image sequence. Optionally, each 2D camera may send the sequence of 2D images captured by itself to an image processor outside the imaging assembly, so that the sequence of 2D images captured by the 2D cameras can be combined into a sequence of 3D images synchronously by the image processor outside the imaging assembly, where the depth-of-field information used by the image processor outside the imaging assembly during the synthesis process can also be the depth-of-field information of any 2D image.

[0081] In one embodiment, the imaging assembly may include at least one 2D camera and at least one depth-of-field sensor. At least one 2D camera and at least one depth-of-field sensor are both mounted at the same position around the spindle of the machine tool. The imaging assembly may further include an image processor. The image processor jointly generates a sequence of 3D images using the depth-of-field information provided by the depth sensor and at least one sequence of 2D images provided by at least one 2D camera. Optionally, at least one 2D camera sends at least one sequence of captured 2D images to an image processor outside the imaging assembly, and the depth-of-field sensor sends the collected depth-of-field information to an image processor outside the imaging assembly, so that the image processor outside the imaging assembly can jointly generate a sequence of 3D images using the depth-of-field information and at least one sequence of 2D images.

[0082] After acquiring the sequence of 3D images, the imaging assembly may send the sequence of 3D images to a controller or a server that performs the Figure 1 process via a wired interface or a wireless interface. Preferably, the wired interface includes at least one of the following: Universal Serial Bus interface, Controller Area Network interface, serial port, etc.; the wireless interface includes at least one of the following: infrared interface, Near Field Communication interface, Bluetooth interface, ZigBee interface, Wireless Broadband interface, etc.

[0083] Step 102: Obtain an operation parameter curve regarding the spindle movement process.

[0084] The operation parameter curve is a curve of the operation parameters of the machine tool during the spindle movement process. In one embodiment, the operation parameter curve includes at least one of the following: a vibration signal curve of the spindle; a power signal curve of the spindle motor; a temperature signal curve of the spindle motor; a power signal curve of the servo motor; a temperature signal curve of the servo motor, etc.

[0085] For example, performFigure 1 The controller or server of the process in can obtain the operating parameter curve from the controller of the machine tool (such as a CNC machine tool controller) or from the SCADA system or sensors of the machine tool. Preferably, the operating parameter curve is a real-time curve regarding real-time operating parameters.

[0086] An exemplary description above of typical examples of the operating parameter curve can be implemented by those skilled in the art. This description is only exemplary and is not used to limit the protection scope of the embodiments of the present invention.

[0087] Step 103: Identify the spindle motion mode from the 3D image sequence.

[0088] The spindle motion mode is preset. In one embodiment, the spindle motion mode includes at least one of the following: up and down motion; down and up motion; right and left motion; left and right motion; back and forth motion; front and back motion.

[0089] Figure 4 is a schematic diagram of the spindle motion mode according to an embodiment of the present invention.

[0090] In Figure 4 the motion coordinate system of the spindle shown in , it is stipulated that the motion of the Z-axis is determined by the cutting power transmitted by the spindle, and the coordinate axis parallel to the spindle axis is the Z-axis. The X-axis is horizontal, parallel to the workpiece clamping surface and perpendicular to the Z-axis. In addition, it is usually stipulated that the direction in which the tool moves away from the workpiece is the positive direction of the coordinate axis. Therefore, the spindle motion mode includes:

[0091] (1) Motion modes in the Z-axis direction, especially including up and down motion (W-) and down and up motion (W+);

[0092] (2) Motion modes in the X-axis direction, especially including left and right motion (U+) and right and left motion (U-);

[0093] (3) Motion modes in the Y-axis direction, especially including back and forth motion (V+) and front and back motion (V-).

[0094] In one embodiment, identifying the spindle motion mode from the 3D image sequence includes: inputting the three-dimensional image sequence into a trained motion mode identification model, where the motion mode identification model is adapted to identify the spindle motion mode in an artificial intelligence manner; receiving the spindle motion mode output from the motion mode identification model. Here, the 3D image sequence is input into the trained motion mode identification model to output the detection result of the 3D image sequence from the motion mode identification model, where the detection result includes one or more motion modes of the spindle motion process.

[0095] Embodiments of the present invention also include the training process of the motion pattern recognition model. The training process particularly includes: obtaining training data, where the training data includes 3D image sequences (usually historical data) respectively marked with spindle motion patterns; the training data is used to train a preset neural network model. When the accuracy of the output result of the neural network model is greater than a predetermined threshold, the training process of the motion pattern recognition model is completed. Specifically, the neural network model can be implemented as: a feedforward neural network model, a radial basis function neural network model, a long and short-term memory (LSTM) network model, an echo state network (ESN), a gate loop unit (GRU) network model, or a deep residual network model, etc.

[0096] Therefore, the recognition efficiency can be improved by introducing artificial intelligence into the motion pattern recognition process of the machine tool.

[0097] In one embodiment, identifying the spindle motion pattern from the 3D image sequence includes: identifying the spindle motion pattern from the 3D image sequence by means of computer vision. In the computer vision mode: First, a spindle motion pattern set containing multiple predetermined spindle motion patterns is generated. Then, image features are extracted from the 3D image sequence using traditional feature extraction methods of computer vision, the image features extracted from the 3D image sequence are compared with the image features of each spindle motion pattern in the spindle motion pattern set, and the spindle motion pattern with the image features closest to the image features extracted from the 3D image sequence is determined as the identified spindle motion pattern. The motion pattern of the machine tool can be easily recognized by computer vision.

[0098] In one embodiment, the traditional feature extraction methods of computer vision include: scale invariant feature transform (SIFT) feature extraction method; Histogram of Orientated Gradient (HOG) feature extraction method; Accelerated Up Robust Features (SURF) extraction method; Oriented FAST and Rotated BRIEF (ORB) feature extraction method; Local binary patterns (LBP) feature extraction method, etc. Therefore, the image features extracted from the 3D image sequence include at least one of the following: SIFT features; HOG features; SURF features; ORB features; LBP features, etc.

[0099] Step 104: Determine the time information of the spindle motion mode.

[0100] Here, the time information is related to the time attributes of the identified spindle motion mode. In one embodiment, the time information includes the start time point and the end time point of the spindle motion mode. Thus, the start time point and the end time point of the spindle motion mode are introduced into the marking process to facilitate the user's understanding of the operation parameters. Preferably, the time information may further include the duration of the spindle motion mode.

[0101] In one embodiment, the time information of the spindle motion mode is determined based on the shooting time points included in the 3D image sequence. For example, the start image frame and the end image frame of the spindle motion mode are determined according to the 3D image sequence, and the shooting time stored in the start image frame is determined as the start time point of the spindle motion mode, and the shooting time stored in the end image frame is determined as the end time point of the spindle motion mode.

[0102] Step 105: Mark the operation parameter curve based on the time information and the motion description information associated with the spindle motion mode.

[0103] Here, the association between the spindle motion mode and the corresponding motion description information can be established in advance. For example, when the spindle motion mode is up and down motion, the corresponding motion description information can be "from top to bottom" in text form; when the spindle motion mode is down and up motion, the corresponding motion description information can be "from bottom to top" in text form.

[0104] In one embodiment, marking the operation parameter curve based on the time information and the motion description information associated with the spindle motion mode includes: determining a first time point corresponding to the start time point in the operation parameter curve; determining a second time point corresponding to the end time point in the operation parameter curve; determining the motion description information associated with the spindle motion mode; and marking the motion description information in the operation parameter curve within the time interval formed by the first time point and the second time point. Specifically, in the coordinate axis of the operation parameter curve, the horizontal axis is usually the acquisition time of the parameter, and the vertical axis is usually the parameter value. The first time point having the same time as the start time point and the second time point having the same time as the end time point are determined in the horizontal axis. Subsequently, in the operation parameter curve, within the time interval formed by the first time point and the second time point, the motion description information associated with the spindle motion mode is marked. Usually, the operation parameter curve may contain multiple spindle motion modes, and each spindle motion mode is marked with its own motion description information in the time dimension, so that the user can easily understand the operation parameters.

[0105] Therefore, by marking the motion description information in the time interval composed of the first time point and the second time point, the user can understand the operation parameters in both the time dimension and the main axis motion dimension, which improves the comprehensiveness of understanding.

[0106] Figure 2 is a schematic diagram of a system architecture for marking operation parameters according to an embodiment of the present invention. In Figure 2 it, the imaging component 21 is arranged at the peripheral position of the machine tool 24. The imaging component 21 continuously collects a 3D image sequence of the main axis motion process of the machine tool 24. In addition, the imaging component 21 transmits the 3D image sequence to the server 22. The server 22 obtains an operation parameter curve associated with the motion process from the sensors of the machine tool 24. The server 22 obtains a predefined main axis motion pattern and the corresponding motion description information associated with the main axis motion pattern from the cloud 23. The server 22 identifies the main axis motion pattern from the 3D image sequence, and determines the time information of the identified main axis motion pattern and the motion description information associated with the main axis motion pattern. The server 22 marks the operation parameter curve based on the time information and the motion description information.

[0107] For example, assume that the predefined main axis motion patterns obtained by the server 22 from the cloud 23 include: up and down motion; down and up motion; right and left motion; left and right motion; back and forth motion; front and back motion. The server 22 obtains a main axis vibration signal curve from the machine tool 24. The server 22 obtains a 3D image sequence from the imaging component 21. The main axis vibration signal curve is synchronized with the 3D image sequence in time.

[0108] For example, the server 22 identifies an up and down motion from the 3D image sequence. The start time point of the up and down motion is the first second, and the end time point of the up and down motion is the third second. Subsequently, the server 22 continues to identify a left and right motion from the 3D image sequence. The start time point of the left and right motion is the third second, and the end time point of the left and right motion is the sixth second. Therefore, the server 22 marks "motion from top to bottom" between the first second and the third second of the main axis vibration signal curve, and marks "motion from left to right" between the third second and the sixth second of the main axis vibration signal curve.

[0109] Figure 5 is a schematic diagram of a marked main axis vibration signal curve according to an embodiment of the present invention. In Figure 5 it, the abscissa is time, and the ordinate is the amplitude of the main axis. The first time interval 61 is marked with "motion from top to bottom", and the second time interval 62 is marked with "motion from left to right".

[0110] Figure 3 is a schematic diagram of an exemplary process for marking operation parameters according to an embodiment of the present invention. In Figure 3In this process, camera data 37 (i.e., a 3D image sequence captured by an imaging component during the spindle movement of a machine tool) is provided to a motion pattern identification process 33, where the camera data 37 is associated with the identification information of the machine tool. The motion pattern identification process 33 obtains predetermined motion patterns from a motion pattern database 34. The motion pattern identification process 33 includes a trained motion pattern identification model. The motion pattern identification model is trained based on the motion patterns provided by the motion pattern database 34. The motion pattern identification model identifies a motion pattern from the camera data 37 and determines the start time point and end time point of the motion pattern. The motion pattern identification process 33 provides the identified motion pattern, its motion description information, start time point, end time point, and identification information associated with the machine tool to a marking process 35.

[0111] A sensor (such as a spindle vibration sensor) detects real-time data during the spindle movement of the machine tool to obtain real-time sensor data 30. The real-time sensor data 30 is provided to a model configuration process 31. The model configuration process 31 obtains the identification information of the machine tool from a cloud 32. The model configuration process 31 retrieves the operating parameters corresponding to the sensor from machine tool design data 36, and the retrieval result is a spindle vibration signal, so it is determined that the real-time sensor data 30 is a spindle vibration signal. The model configuration process 31 associates and stores the identification information with the real-time sensor data 30 and provides the associated data to a marking process 35.

[0112] The marking process 35 compares the identification information sent by the motion pattern identification process 33 with the identification information sent by the model configuration process 31. After confirming the consistency, the marking process 35 determines a first time point corresponding to the start time point and a second time point corresponding to the end time point in the real-time sensor data 30, and marks the motion description information of the motion pattern identified between the first time point and the second time point in the operating parameter curve.

[0113] Figure 6 is a block diagram of a device for marking operating parameters according to an embodiment of the present invention. As Figure 6 shown, the device 600 includes:

[0114] A first acquisition module 601 configured to acquire a three-dimensional image sequence regarding the spindle movement process of a machine tool, where the three-dimensional image sequence is captured by an imaging component; a second acquisition module 602 configured to acquire an operating parameter curve regarding the spindle movement process; an identification module 603 configured to identify a spindle motion pattern from the three-dimensional image sequence; a determination module 604 configured to determine the time information of the spindle motion pattern; and a marking module 605 configured to mark the operating parameter curve based on the time information and motion description information associated with the spindle motion pattern.

[0115] In one embodiment, the identification module 603 is configured to input a three-dimensional image sequence into a trained motion pattern identification model, where the motion pattern identification model is adapted to identify the spindle motion pattern in an artificial intelligence manner; and receive the spindle motion pattern output from the motion pattern identification model.

[0116] In one embodiment, the identification module 603 is configured to identify the spindle motion pattern from the three-dimensional image sequence through computer vision.

[0117] In one embodiment, the time information includes the start time point and the end time point of the spindle motion pattern.

[0118] In one embodiment, the marking module 605 is configured to determine a first time point corresponding to the start time point in the operation parameter curve; determine a second time point corresponding to the end time point in the operation parameter curve; determine the motion description information associated with the spindle motion pattern; and mark the motion description information in the operation parameter curve within the time interval formed by the first time point and the second time point.

[0119] Embodiments of the present invention also provide an electronic device having a processor-memory architecture. Figure 7 is a structural diagram of an electronic device according to an embodiment of the present invention. As Figure 7 shown, the electronic device 700 includes a processor 701, a memory 702, and a computer program stored on the memory 702 and capable of running on the processor 701. When the computer program is executed by the processor 701, the method for marking operation parameters as described above is implemented. The memory 702 can be specifically implemented as various storage media, such as EEPROM, flash memory, PROM, etc. The processor 701 can be implemented to include one or more central processing units or one or more field programmable gate arrays, where the field programmable gate array integrates one or more central processing unit cores. Specifically, the CPU or CPU core can be implemented as a CPU, MCU, or DSP, etc.

[0120] It should be noted that not all steps and modules in the above processes and structural diagrams are necessary, and some steps or modules can be omitted according to actual needs. The execution order of each step is not fixed and can be adjusted as needed. The division of each module is only for the convenience of describing the adopted function division. In actual implementation scenarios, a module can be divided into multiple modules, and the functions of multiple modules can also be implemented by the same module. These modules can be located in the same device or in different devices.

[0121] The hardware modules in each embodiment can be implemented mechanically or electronically. For example, a hardware module can include a specially designed permanent circuit or logic device (e.g., a dedicated processor such as an FPGA or ASIC) to perform specific operations. A hardware module can also include a programmable logic device or circuit (e.g., including a general-purpose processor or other programmable processor) temporarily configured by software for performing specific operations. As for whether to specifically adopt a mechanical method, a dedicated permanent circuit, or a temporarily configured circuit (e.g., configured by software) to implement the hardware module, it can be determined based on cost and time considerations.

[0122] The above description is only the preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for marking operation parameters, characterized in that, comprising: acquiring (101) a three-dimensional image sequence of the main spindle movement process of a machine tool, wherein the three-dimensional image sequence is captured by an imaging component; acquiring (102) an operation parameter curve of the main spindle movement process; identifying (103) the main spindle movement pattern from the three-dimensional image sequence; determining (104) the time information of the main spindle movement pattern; and marking (105) the operation parameter curve based on the time information and movement description information associated with the main spindle movement pattern.

2. The method according to claim 1, characterized in that, identifying (103) the main spindle movement pattern from the three-dimensional image sequence comprises: inputting the three-dimensional image sequence into a trained movement pattern identification model, wherein the movement pattern identification model is adapted to identify the main spindle movement pattern in an artificial intelligence manner; receiving the main spindle movement pattern output from the movement pattern identification model.

3. The method according to claim 1, characterized in that, identifying (103) the main spindle movement pattern from the three-dimensional image sequence comprises: identifying the main spindle movement pattern from the three-dimensional image sequence through computer vision.

4. The method according to any one of claims 1 to 3, characterized in that, the time information includes the start time point and the end time point of the main spindle movement pattern.

5. The method according to any one of claims 1 to 3, characterized in that, marking (105) the operation parameter curve based on the time information and movement description information associated with the main spindle movement pattern comprises: determining a first time point corresponding to the start time point in the operation parameter curve; determining a second time point corresponding to the end time point in the operation parameter curve; determining the movement description information associated with the main spindle movement pattern; marking the movement description information in the operation parameter curve within the time interval formed by the first time point and the second time point.

6. The method according to any one of claims 1 to 3, characterized in that, the operation parameter curve includes at least one of the following: the vibration signal curve of the main spindle; the power signal curve of the main spindle motor; the temperature signal curve of the main spindle motor; the power signal curve of the servo motor; the temperature signal curve of the servo motor.

7. The method according to any one of claims 1 to 3, characterized in that, the main spindle movement pattern includes at least one of the following: up and down movement; down and up movement; right and left movement; left and right movement; back and forth movement; front and back movement.

8. A device for marking operation parameters, characterized in that, comprising: a first acquisition module (601), the first acquisition module being configured to acquire a three-dimensional image sequence of the main spindle movement process of a machine tool, wherein the three-dimensional image sequence is captured by an imaging component; a second acquisition module (602), the second acquisition module being configured to acquire an operation parameter curve of the main spindle movement process; an identification module (603), the identification module being configured to identify the main spindle movement pattern from the three-dimensional image sequence; A determination module (604) configured to determine time information of the spindle motion mode; and A marking module (605) configured to mark the operation parameter curve based on the time information and motion description information associated with the spindle motion mode.

9. The apparatus according to claim 8, wherein the identification module (603) is configured to input the three-dimensional image sequence into a trained motion mode identification model, where the motion mode identification model is adapted to identify the spindle motion mode in an artificial intelligence manner; and receive the spindle motion mode output from the motion mode identification model.

10. The apparatus according to claim 8, wherein the identification module (603) is configured to identify the spindle motion mode from the three-dimensional image sequence through computer vision.

11. The apparatus according to any one of claims 8 to 10, wherein the time information includes a start time point and an end time point of the spindle motion mode.

12. The apparatus according to any one of claims 8 to 10, wherein the marking module (605) is configured to determine a first time point corresponding to the start time point in the operation parameter curve; determine a second time point corresponding to the end time point in the operation parameter curve; determine motion description information associated with the spindle motion mode; and mark the motion description information in the operation parameter curve within a time interval formed by the first time point and the second time point.

13. An electronic device, wherein it includes a processor (701) and a memory (702), and an application program executable by the processor (701) is stored in the memory (702) to enable the processor (701) to execute the method for marking operation parameters according to any one of claims 1 to 7.

14. A computer-readable medium, wherein it includes computer-readable instructions stored thereon, and the computer-readable instructions are used to execute the method for marking operation parameters according to any one of claims 1 to 7.

15. A computer program product, wherein it includes a computer program, and when the computer program is executed by a processor, the computer program is used to execute the method for marking operation parameters according to any one of claims 1 to 7.

Images