Intelligent monitoring method and system for CNC machining tools based on industrial Internet of Things

Abstract

The present invention provides an intelligent monitoring method and system for CNC machining tools based on industrial Internet of Things, the method comprising: obtaining the apparent information of the tool based on the tool image; obtaining the operating status information of the tool and the CNC machine tool at multiple time points; collecting the workpiece image of at least one machining stage, and determining the workpiece information based on the workpiece image; processing the workpiece information to generate machining quality information; retrieving the apparent information, operating status information and tool machining information, and generating tool wear information; issuing an alarm based on the tool wear information; determining the tool to be replaced based on the tool wear information; and issuing a speed adjustment instruction and / or a frequency adjustment instruction. Through the above method, the timing of tool replacement can be determined more accurately, reducing the waste caused by premature replacement or tool damage, better avoiding the safety risks caused by the sudden breakage and failure of the tool due to the exhaustion of its service life, and ensuring production safety and product quality.

Description

Technical Field

[0001] This specification relates to the field of CNC machining, and in particular to an intelligent monitoring method and system for CNC machining tools based on industrial Internet of Things. Background Art

[0002] Tool wear is a common phenomenon in mechanical processing. Tool wear will reduce workpiece processing accuracy, deteriorate workpiece surface roughness, reduce equipment life, generate turning heat, increase downtime, and directly reduce production efficiency and revenue. In order to avoid losses caused by tool wear, most factories currently replace tools based on processing experience and average tool life, which often results in tools that have been worn but not replaced or are not seriously worn but are replaced. This method cannot effectively solve the mechanical processing problems caused by tool wear. Therefore, it is very necessary to monitor the tool wear status, especially with the gradual popularization of modern fully automatic manufacturing systems, automatic tool monitoring has become an inevitable trend.

[0003] In view of this, it is necessary to provide an intelligent monitoring method and system for CNC machining tools based on industrial Internet of Things to better monitor the status of tools of CNC machine tools. Summary of the invention

[0004] In order to better monitor the tool status of CNC machine tools and replace tools in time, the present invention provides an intelligent monitoring method for CNC machining tools based on industrial Internet of Things.

[0005] The invention content includes a method for intelligent monitoring of CNC machining tools based on industrial Internet of Things, characterized in that it is executed by an industrial Internet of Things management platform of an intelligent monitoring system for CNC machining tools based on industrial Internet of Things; the industrial Internet of Things management platform is configured in a processor and is connected to a perception control platform through a sensor network platform; the sensor network platform is configured on a communication device; the perception control platform is configured in a host of the CNC machine tool, and the perception control platform is configured to control the operation of a camera and a machine tool monitoring device; the method includes: obtaining tool appearance information based on a tool image, and storing the appearance information in a data center of the industrial Internet of Things management platform; the tool image is obtained through the camera at a preset acquisition time; the preset acquisition time includes the time when the tool is in a stopped state; in response to the tool being in a running state, based on the machine tool monitoring device, obtaining the operating status information of the tool and the CNC machine tool at multiple time points, and sending the operating status information to the data center of the industrial Internet of Things management platform through the communication device. In the data center; an image acquisition instruction is issued to the perception control platform to control the camera to acquire the workpiece image of at least one processing stage at a preset frequency, and determine the workpiece information based on the workpiece image; the at least one processing stage is determined based on the running trajectory of the tool; the workpiece information is processed to generate the processing quality information corresponding to the at least one processing stage, and the processing quality information is stored in the data center of the industrial Internet of Things management platform; the appearance information, the operation status information and the processing quality information are retrieved from the data center, and the tool wear information is generated; according to the tool wear information, an alarm is issued through the machine tool early warning device and / or the interactive screen to prompt the wear condition of the tool; according to the tool wear information, the tool to be replaced is determined; the tool replacement component is controlled to clamp the spare tool from the spare tool box; a speed adjustment instruction and / or a frequency adjustment instruction is issued; the speed adjustment instruction is used to control the speed of the tool fixing component to adjust the processing intensity of the tool to be replaced; the frequency adjustment instruction is used to adjust the acquisition frequency of the camera.

[0006] The invention content also includes an intelligent monitoring system for CNC machining tools based on the Industrial Internet of Things, characterized in that the system includes an Industrial Internet of Things management platform, a sensor network platform and a perception control platform; the Industrial Internet of Things management platform is configured in a processor and is communicated with the perception control platform through the sensor network platform; the sensor network platform is configured on a communication device; the perception control platform is configured in the host of the CNC machine tool, and the perception control platform is configured to control the operation of a camera and a machine tool monitoring device; the Industrial Internet of Things management platform is configured to: obtain tool appearance information based on a tool image, and store the appearance information in a data center of the Industrial Internet of Things management platform; the tool image is obtained through the camera at a preset acquisition time; the preset acquisition time includes the time when the tool is in a stopped state; in response to the tool being in an operating state, based on the machine tool monitoring device, the operating status information of the tool and the CNC machine tool is obtained, and the operating status information of the tool and the CNC machine tool is stored in the data center of the Industrial Internet of Things management platform The status information is sent to the data center through the communication device; an image acquisition instruction is issued to the perception control platform to control the camera to acquire workpiece images at a preset frequency, and determine the workpiece information based on the workpiece images; the workpiece information is processed to generate processing quality information, and the processing quality information is stored in the data center through the communication device; the appearance information, the operation status information and the processing quality information are retrieved from the data center, and tool wear information is generated; according to the tool wear information, an alarm is issued through the machine tool early warning device and / or the interactive screen to prompt the wear condition of the tool; the tool to be replaced is determined according to the tool wear information; the tool replacement component is controlled to clamp the spare tool from the spare tool box; and a speed adjustment instruction and / or a frequency adjustment instruction is issued; the speed adjustment instruction is used to control the speed of the tool fixing component to adjust the processing intensity of the tool to be replaced; the frequency adjustment instruction is used to adjust the acquisition frequency of the camera.

[0007] Through the above method and system, the timing of tool replacement can be determined more accurately, reducing waste caused by premature replacement or tool damage, and better ensuring the production efficiency of CNC machine tools; timely determining the tool to be replaced and adjusting the processing intensity of the tool to be replaced before replacement can better avoid the safety risks caused by sudden breakage and failure of the tool due to exhaustion of its service life, thereby ensuring production safety; timely replacement of worn tools can avoid the impact of severe tool wear on workpiece quality, ensure processing degree, and thus improve product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0009] Figure 1 It is a schematic diagram of the platform structure of the intelligent monitoring system for CNC machining tools based on the industrial Internet of Things according to some embodiments of this specification;

[0010] Figure 2 is an exemplary flow chart of an intelligent monitoring method for CNC machining tools based on the industrial Internet of Things according to some embodiments of this specification;

[0011] Figure 3 is a schematic diagram of generating processing quality information according to some embodiments of this specification;

[0012] Figure 4 is a schematic diagram of determining tool wear information according to some embodiments of this specification;

[0013] Figure 5 It is an exemplary schematic diagram of determining a tool to be replaced according to some embodiments of the present specification.

[0014] Explanation of the accompanying drawings: 100-intelligent monitoring system for CNC machining tools based on industrial Internet of Things; 110-industrial Internet of Things management platform; 120-sensor network platform; 130-perception control platform; 310-workpiece material information; 320-tool movement trajectory; 330-workpiece information; 340-machining quality information; 410-camera; 420-first monitoring component; 430-operating status information; 431-cutting fluid change information; 432-cutting force data sequence; 440-second monitoring component; 450-tool; 460-apparent information; 470-wear degree; 480-tool wear information; 510-historical processing data; 520-remaining life sequence; 530-replacement priority; 540-tool to be replaced. DETAILED DESCRIPTION

[0015] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0016] It should be understood that the "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

[0017] Unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0018] Flowcharts are used in this specification to illustrate the operations performed by the system according to the embodiments of this specification. It should be understood that the preceding or following operations are not necessarily performed precisely in order. Instead, the steps may be processed in reverse order or simultaneously. At the same time, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0019] Figure 1 Schematic diagram of the platform structure of the intelligent monitoring system for CNC machining tools based on the industrial Internet of Things according to some embodiments of this specification. Figure 1 As shown, in some embodiments, an intelligent monitoring system 100 for CNC machining tools based on the industrial Internet of Things may include an industrial Internet of Things management platform 110 , a sensor network platform 120 , and a perception control platform 130 .

[0020] The industrial Internet of Things management platform 110 is a platform that coordinates and coordinates the connections and collaborations between various functional platforms, gathers all the information of the Internet of Things, and provides perception management and control management functions for the Internet of Things operation system.

[0021] In some embodiments, the industrial Internet of Things management platform 110 can supervise and manage the life cycle of CNC machine tools, for example, managing the processing of CNC machine tools, and the maintenance of CNC machine tools and their components.

[0022] In some embodiments, the CNC machine tool may include a host computer.

[0023] In some embodiments, the industrial Internet of Things management platform 110 may include a data center, a production process management sub-platform, and an equipment management sub-platform.

[0024] The data center can be used to store all operation information of the CNC machining tool intelligent monitoring system 100 based on the industrial Internet of Things. In some embodiments, the data center can be configured in a storage device to store data related to the intelligent monitoring of CNC machining tools, etc. For example, the appearance information of the tool, the operation status information of the tool and the CNC machine tool at multiple time points, the workpiece image of at least one machining stage, the workpiece information, the tool operation trajectory, the machining quality information, the tool wear information, etc.; it can also include other data generated during the intelligent monitoring of CNC machining tools.

[0025] The production process management sub-platform interacts with the data center for production process management. The production process management sub-platform can be used to simulate CNC machining tasks and form CNC machining process parameters, including tool speed, feed speed, tool trajectory, etc. The production process management sub-platform is also used to compare the actual tool trajectory data with the simulated trajectory data to determine whether there is any abnormality in the actual trajectory and issue an alarm.

[0026] The equipment management sub-platform interacts with the data center for information monitoring and management of equipment status; tool life is monitored and warned through the tool status monitoring model.

[0027] In some embodiments, the IIoT management platform 110 may be configured in a processor.

[0028] The sensor network platform 120 is a functional platform for managing sensor communication. In some embodiments, the sensor network platform 120 can realize the functions of sensing information sensor communication and controlling information sensor communication.

[0029] In some embodiments, the sensor network platform 120 can connect the industrial Internet of Things management platform 110 and the perception control platform 130 to achieve information interaction between the two.

[0030] In some embodiments, the sensor network platform 120 may be configured on a communication device.

[0031] The perception control platform 130 is a functional platform for generating perception information and executing control information.

[0032] In some embodiments, the perception control platform 130 can be configured in the host of the CNC machine tool to control the operation of the camera and the machine tool monitoring device.

[0033] In some embodiments, the perception control platform 130 can execute CNC machining instructions and collect operating parameters of CNC machine tools; the equipment operating parameters include but are not limited to spindle speed, tool information (tool model, tool material, tool shape, etc.), coordinates (tool coordinates, workpiece coordinates), equipment load (spindle load, X-axis load, Y-axis load, Z-axis load, etc.), feed speed, etc.

[0034] In some embodiments of the present specification, through the CNC machining tool intelligent monitoring system 100 based on the industrial Internet of Things, an information operation closed loop can be formed between the industrial Internet of Things management platform and the perception control platform, and coordinated and regularly operated under unified management, thereby realizing the informatization and intelligence of CNC machining tool intelligent monitoring.

[0035] It should be understood that Figure 1The system and its platform structure shown can be implemented in various ways. In some embodiments, the aforementioned processor, communication device, storage device and host of the CNC machine tool can be integrated in one place or arranged separately.

[0036] It should be noted that the above description of the intelligent monitoring system 100 for CNC machining tools based on the industrial Internet of Things and its platform structure is only for the convenience of description and does not limit this specification to the scope of the embodiments cited. It can be understood that for those skilled in the art, after understanding the principle of the system, it is possible to arbitrarily combine the various platform structures without deviating from this principle, or to form a subsystem connected to other platform structures. For example, each platform structure can share a storage module, or each can have its own storage module. Such variations are within the scope of protection of this specification.

[0037] Figure 2 It is an exemplary flow chart of an intelligent monitoring method for CNC machining tools based on industrial Internet of Things according to some embodiments of this specification.

[0038] In some embodiments, an intelligent monitoring method for CNC machining tools based on the industrial Internet of Things may include: acquiring tool appearance information based on a tool image, and sending the appearance information to a host through a communication device and storing it in a storage device; in response to the tool being in operation, acquiring operation status information of the tool and the CNC machine tool at multiple time points based on a machine tool monitoring device, and sending the operation status information to the host through a communication device and storing it in a storage device; issuing an image acquisition instruction to a perception control platform to control the camera to acquire a workpiece image of at least one machining stage at a preset frequency, and determining workpiece information based on the workpiece image; processing the workpiece information to generate machining quality information corresponding to at least one machining stage, and sending the machining quality information to the host through a communication device and storing it in a storage device; retrieving appearance information, operation status information and machining quality information from the storage device, and generating tool wear information; issuing an alarm through a machine tool early warning device and / or an interactive screen according to the tool wear information to indicate the wear condition of the tool; determining a tool to be replaced according to the tool wear information; controlling a tool replacement component to clamp a spare tool from a spare tool box; issuing a speed adjustment instruction and / or a frequency adjustment instruction.

[0039] like Figure 2 As shown, the process 200 includes the following steps. In some embodiments, the process 200 can be executed by a processor of the industrial Internet of Things management platform 110.

[0040] Step 210: Acquire tool appearance information based on the tool image.

[0041] A tool image refers to an image that records the appearance, structure, and details of a tool. In some embodiments, the tool image may include at least one image of the tool at different time points. For example, an initial tool image before the tool is used, at least one image after the tool is used, and the like.

[0042] In some embodiments, the tool may be an indexable turning tool used in a CNC machine tool, including but not limited to at least one of an external cylindrical turning tool, a drill, a boring tool, a cutting tool, and a thread processing tool.

[0043] In some embodiments, the processor may send an image acquisition instruction to the perception control platform so that the perception control platform controls the camera to acquire the tool image at a preset acquisition time. The preset acquisition time may include the time when the tool is in a stopped state, for example, the time before the CNC machine tool starts working and / or the time after the CNC machine tool ends working, or the time when other tools are in a stopped state.

[0044] Tool appearance information refers to information that can intuitively reflect the state of the tool. For example, tool appearance information may include the state of the tool edge, such as whether the tool edge is deformed (also known as edge flatness) and at least one of the changes in edge width; for another example, tool appearance information may also include other information such as tool shape, size, color, surface texture, etc. As an example only, edge deformation may include but is not limited to at least one of a notch on the edge and a skewed edge.

[0045] In some embodiments, the tool appearance information can be represented in the form of an appearance information vector. As an example only, the appearance information vector can be represented as .in, Indicates whether the cutting edge of the tool is deformed, 0 indicates no deformation, and 1 indicates deformation; Indicates the change in cutting edge width, which can be expressed as a multiple of the initial cutting edge width. For example, (0, 0) indicates that the cutting edge of the tool is not deformed and the cutting edge width does not change; for another example, (1, 0.3) indicates that the cutting edge of the tool is deformed and the cutting edge width changes to 0.3 times the initial cutting edge width. The initial cutting edge width refers to the cutting edge width when the tool is not in use.

[0046] In some embodiments, the processor may pre-process the tool image, analyze the pre-processed tool image, and determine the tool appearance information. The pre-processing may be grayscale processing.

[0047] As an example only, the processor may grayscale the initial tool image and the tool image at at least one time point after the tool is used to obtain the image to be analyzed; and compare and analyze the image to be analyzed by using an image comparison algorithm to determine whether the cutting edge of the tool is deformed at at least one time point after use, and the change in the cutting edge width. The image comparison algorithm may include at least one of a pixel comparison-based method, a histogram comparison-based method, a feature extraction and matching-based method, and a deep learning-based method, or other algorithms capable of performing image difference comparison.

[0048] In some embodiments, the processor can compare the tool image corresponding to a certain time point with the initial tool image to determine the deformation value of the tool edge. If the deformation value is greater than a preset deformation threshold, it is determined that the edge is deformed. The deformation value of the tool edge refers to the difference between the position of the tool edge and the initial position in the initial tool image, which can be expressed as a numerical value, for example, 0.1mm, etc. The preset deformation threshold refers to the minimum deformation value that will cause quality problems when using the tool to process the product, which can be determined based on historical processing data. For example, the preset deformation threshold can be 0.4mm.

[0049] In some embodiments, the processor can determine the cutting edge width of the tool at a certain point in time and the initial cutting edge width based on the tool image corresponding to the tool at that time point and the initial tool image, and then determine the change value of the cutting edge width of the tool at that time point compared with the initial cutting edge width, and determine the change in cutting edge width based on the change value of the cutting edge width and the initial cutting edge width.

[0050] In some embodiments, the processor can send the tool appearance information to a data center of the industrial Internet of Things management platform. The data center can be configured in a storage device. Exemplarily, the processor can send and store the tool appearance information to the data center in the configuration storage device through a communication device.

[0051] Step 220 , in response to the tool being in operation, obtaining the operation status information of the tool and the CNC machine tool based on the machine tool monitoring device.

[0052] In some embodiments, the operating status information may include at least one of a tool status and a machine tool status.

[0053] The tool status is information used to reflect the operating status of the tool, and may include at least one parameter value reflecting the operating status of the tool, such as tool vibration data, tool processing sound, tool temperature data, etc., and may also include other information that can reflect the operating status of the tool.

[0054] In some embodiments, the tool status may include operating status information of the tool at at least one time point.

[0055] The machine tool status is information used to reflect the operating status of the CNC machine tool, and may include at least one parameter value reflecting the operating status of the CNC machine tool, such as operating power, current size, etc., and may also include other information that can reflect the operating status of the CNC machine tool.

[0056] In some embodiments, the machine tool operating status may include operating status information of the CNC machine tool at at least one time point.

[0057] In some embodiments, the processor may obtain the tool operation status of the tool and the machine operation status of the CNC machine tool in a variety of ways.

[0058] In some embodiments, in response to the tool being in an operating state, the processor may obtain a tool operating state of the tool and a machine operating state of the CNC machine tool based on a machine tool monitoring device.

[0059] For more information about the machine tool monitoring device, please refer to this manual Figure 1 Related description in .

[0060] In some embodiments, the operating status information may also include cutting fluid change information and / or cutting force data sequence. The processor may collect cutting fluid change information through a camera and a first monitoring component configured in a cutting fluid storage tank, and collect cutting force data sequence of a tool through a second monitoring component. For detailed description, please refer to this manual Figure 4 Related description in .

[0061] In some embodiments, the processor can send the operating status information (such as the operating status of the tool and the operating status of the machine tool) to the data center of the industrial Internet of Things management platform. The data center can be configured in the storage device. Exemplarily, the processor can send the operating status information (such as the operating status of the tool and the operating status of the machine tool) to the host of the CNC machine tool through the communication device and store it in the storage device.

[0062] Step 230, sending an image acquisition instruction to the perception control platform to control the camera to acquire the workpiece image at a preset frequency, and determine the workpiece information based on the workpiece image.

[0063] A workpiece image refers to an image that records the appearance, structure, and details of a workpiece. In some embodiments, the workpiece image may include at least one image of the workpiece at at least one processing stage.

[0064] The processing stage refers to one or more specific processing steps or stages that a workpiece is divided into according to its processing requirements and process characteristics during the production or processing of the workpiece. Each processing stage may correspond to a different processing area of ​​the workpiece. Exemplarily, the processing stage may include at least one of a roughing stage, a semi-finishing stage, and a finishing stage. For workpieces with particularly high precision requirements, it may also include a finishing stage and an ultra-precision machining stage.

[0065] In some embodiments, the processor may send an image acquisition instruction to the perception control platform to control the camera to acquire images of the workpiece at a preset frequency.

[0066] The image acquisition instruction is an operation instruction for instructing a device to capture and record an image. The device may be a camera. For example, the processor may control the camera to acquire an image of the workpiece through the perception control platform based on the image acquisition instruction.

[0067] The preset frequency refers to a pre-set parameter used to instruct the device to acquire images at a specific frequency.

[0068] In some embodiments, the processor may determine the preset frequency based on user input. For example, the processor may obtain the preset frequency input by the user through the user terminal, send the preset frequency to the host of the CNC machine tool through the communication device, and store it in the storage device.

[0069] In some embodiments, different processing stages may correspond to different preset frequencies. The higher the processing accuracy requirement of the processing stage, the higher the corresponding preset frequency.

[0070] In some embodiments, the processor may determine the current processing stage of the workpiece based on the tool operation trajectory, and determine the preset frequency that should be used according to the current processing stage.

[0071] As an example only, the processor can obtain the tool trajectory over a period of time in real time, compare the real-time tool trajectory with the historical trajectory stored in the storage device, determine the target trajectory with the highest similarity, and determine the processing stage corresponding to the target trajectory as the current processing stage.

[0072] Workpiece information is a data set describing workpiece properties, and may include at least one data describing workpiece properties, such as at least one of workpiece appearance, workpiece size, size deviation, and workpiece color, and may also include other data that can reflect workpiece properties. Among them, size deviation refers to the difference between the actual size of the workpiece and the standard size.

[0073] In some embodiments, the processor can process the workpiece image (e.g., grayscale processing), and based on the processed workpiece image, determine at least one of the workpiece appearance, workpiece size, and workpiece color through an image analysis algorithm; compare the workpiece appearance with the standard image through an image comparison algorithm to determine the size deviation of multiple key points of the workpiece; and determine the workpiece information based on at least one of the workpiece appearance, workpiece size, workpiece color, and size deviation.

[0074] The standard image refers to a workpiece image obtained by processing under an ideal state. In some embodiments, the standard image can be determined based on the appearance of a standard workpiece extracted from modeling software.

[0075] The key points of a workpiece refer to the characteristic points or positions on the workpiece that are of special importance and / or require special attention. The key points can be used to describe the key attributes of the workpiece, such as shape, size, positional relationship, etc., and play an important role in ensuring the quality, accuracy and functionality of the workpiece.

[0076] The image analysis algorithm may include at least one of a graphic size measurement algorithm, a color feature extraction algorithm, and an appearance feature extraction algorithm; for more information about the image comparison algorithm, please refer to the relevant description in the above step 210.

[0077] Step 240, processing the workpiece information to generate processing quality information.

[0078] The processing quality information is data that characterizes the quality of the workpiece processed by the tool. In some embodiments, the processing quality information may include the quality of at least one area of ​​the workpiece. The aforementioned quality can be represented by a numerical value between 0 and 1, and the larger the numerical value, the better the processing quality.

[0079] At least one region of the workpiece corresponds to at least one processing stage of the workpiece processing. For example, different processing stages can correspond to different regions on the workpiece. For more information about the processing stages, please refer to the relevant description in step 230.

[0080] In some embodiments, the processor may determine the processing quality information based on the size of the local size deviation of the workpiece. For example, the processor may obtain at least one local point on the workpiece where the size deviation exists, and determine the processing quality of each local point based on the following formula (1):

[0081] (1)

[0082] in, is the processing quality of the local point; It is the size deviation. For the description of size deviation, please refer to the previous description; The local workpiece size refers to the minimum size of the area of ​​the workpiece where the local point is located, which can be determined based on the workpiece design drawing and the processing stage where the local point is located. For more information about the processing stage and its corresponding area, please refer to the relevant description in step 230.

[0083] In some embodiments, the processor may determine the machining quality information based on the machining quality of at least one local point on the workpiece where the size deviation exists.

[0084] In some embodiments, the processor may also retrieve a tool running trajectory corresponding to the workpiece information, and generate processing quality information based on the workpiece material information, the tool running trajectory and the workpiece information.

[0085] In some embodiments, the processor may also determine trajectory difference information based on a standard running trajectory corresponding to the workpiece and a tool running trajectory, and generate processing quality information based on the trajectory difference information, workpiece material information, and workpiece information.

[0086] For more detailed instructions, please refer to this manual Figure 3 Related description in .

[0087] In some embodiments, the processor can send the processing quality information to a data center of the industrial Internet of Things management platform. The data center can be configured in a storage device. Exemplarily, the processor can send and store the processing quality information to the aforementioned data center via a communication device.

[0088] Step 250, retrieve appearance information, operation status information and processing quality information from the data center, and generate tool wear information.

[0089] During the cutting process, the tool will wear due to continuous friction with the workpiece material, impact, high temperature and other factors. Tool wear information is data that characterizes the degree of tool wear. In some embodiments, tool wear information can be represented by a value between 0 and 1, where 0 means that the tool is not worn, the larger the value, the higher the degree of tool wear, and 1 means that the tool is severely worn and needs to be replaced.

[0090] In some embodiments, the processor may determine tool wear information in a variety of ways.

[0091] As an example only, the processor can retrieve the tool's appearance information, operating status information and processing quality information from the data center, and based on the aforementioned appearance information, operating status information and processing quality information, query the wear degree reference table to determine the tool wear information.

[0092] In some embodiments, the wear degree reference table may include reference appearance information, reference operating status and reference quality information and their corresponding reference wear information.

[0093] In some embodiments, the wear degree reference table can be determined based on historical processing data. For example, the processor can determine the reference appearance information, reference operation state and reference quality information based on the historical appearance information, historical operation state information and historical processing information of the tool in the historical processing data; the processor can obtain manual input to determine, under the processing conditions of the aforementioned reference appearance information, reference operation state information and reference quality information, the reference wear information corresponding to the tool. For example, when the tool is deformed, the reference wear information is marked as 1, when the edge width is greater than the preset width threshold, the reference wear information is marked as 1, and when the edge width is greater than the preset width threshold to determine that the processing quality does not meet the quality threshold, the reference wear information is marked as 1. Among them, the preset width threshold and quality threshold can be set based on prior experience and / or actual needs.

[0094] In some embodiments, the processor may also evaluate the degree of wear of the tool in at least one time period based on the tool's apparent information, tool operating status, and processing quality information; and generate tool wear information based on the degree of wear of the tool in at least one time period.

[0095] For more information, please refer to this manual. Figure 4 Related description in .

[0096] Step 260: Based on the tool wear information, an alarm is issued through the machine tool warning device and / or the interactive screen to indicate the tool wear condition.

[0097] The machine tool early warning device can be a device arranged on the machine tool for indicating the machining state of the machine tool. In some embodiments, the machine tool early warning device can be used to indicate machining failure or tool wear and the like.

[0098] The interactive screen can refer to a screen that can realize human-machine interaction, which can be the screen of a CNC machine tool, the screen of a user terminal, etc. The interactive screen can be managed by the industrial Internet of Things management platform, and the user can control the machine tool and obtain relevant information about the machine tool from the interactive screen, such as the model of the machine tool, the machine tool status, processing information, and warning information.

[0099] The alarm may be information indicating the wear of the tool. In some embodiments, the alarm may include but is not limited to at least one of an audible and visual warning, a text warning, and a warning window.

[0100] In some embodiments, the processor can issue an alarm through the machine tool warning device and / or the interactive screen based on the tool wear information to indicate the wear condition of the tool. For example, when the tool wear information reaches a wear degree threshold, an alarm is issued. The wear degree threshold is a critical value of the wear degree. When the wear degree reaches the critical value, the tool needs to be replaced. In some embodiments, the wear degree threshold can be determined based on prior experience and / or actual needs.

[0101] Step 270: Determine the tool to be replaced based on the tool wear information, and control the tool replacement assembly to clamp the spare tool from the spare tool box.

[0102] In some embodiments, the processor may determine a tool whose tool wear information is greater than or equal to a wear level threshold as a tool to be replaced.

[0103] In some embodiments, the processor can send a tool clamping instruction to the perception control platform to control the tool replacement component to clamp the spare tool from the spare tool box and place the spare tool at a designated location to facilitate the staff to replace the tool.

[0104] The tool replacement assembly is a component used to assist in tool replacement. In some embodiments, the tool replacement assembly may include multiple components that cooperate with each other. For example, a mechanical arm, a clamping component, a driving device, etc. Among them, the clamping component is used to clamp the spare tool in the spare tool box, the mechanical arm is used to control the movement of the clamping component, and the driving device is used to provide power. Among them, the spare tool box is a container for storing spare tools.

[0105] Step 280: issuing a speed adjustment instruction and / or a frequency adjustment instruction.

[0106] In some embodiments, in response to triggering the adjustment condition, the processor may send a speed adjustment instruction and / or a frequency adjustment instruction to the CNC machine tool through the sensing control platform. The adjustment condition may include the processor determining that the tool to be replaced is ready.

[0107] The speed adjustment command is a command used to adjust the speed of the tool fixing component.

[0108] In some cases, when the wear level of the tool reaches the wear threshold, it will not be replaced immediately and other work may continue to be processed. At this time, it is necessary to adjust the rotation speed of the tool fixing assembly to reduce the processing intensity of the tool to be replaced, so as to avoid sudden damage to the tool and affect the processing quality.

[0109] In some embodiments, the speed adjustment instruction may include a speed adjustment value. The speed adjustment value may be determined based on the degree of wear of the tool to be replaced. The higher the degree of wear of the tool to be replaced, the lower the processing intensity it can withstand, and the lower the speed of the corresponding tool fixing assembly.

[0110] The frequency adjustment instruction is an instruction used to adjust the image acquisition frequency of the camera.

[0111] In some embodiments, the frequency adjustment instruction may include an adjusted acquisition frequency. The processor may determine the adjusted acquisition frequency based on a preset adjustment rule. The higher the wear degree of the tool to be replaced, the higher the adjusted acquisition frequency.

[0112] In some embodiments, the processor may determine the adjusted acquisition frequency by the following formula (2):

[0113] (2)

[0114] in, is the adjusted acquisition frequency; is the preset frequency, for detailed description, please refer to the description in step 230; The wear degree of the tool to be replaced can be determined based on tool wear information corresponding to the tool to be replaced.

[0115] In some embodiments of this specification, tool wear information is generated by analyzing tool appearance information, tool and CNC machine tool operating status information, and processing quality information, and then an alarm is issued, the tool to be replaced is determined, and the processing intensity of the tool to be replaced before replacement is adjusted in time. Through the above method, the timing of tool replacement can be determined more accurately, reducing waste caused by premature replacement or tool damage, and better ensuring the production efficiency of CNC machine tools; timely determining the tool to be replaced and adjusting the processing intensity of the tool to be replaced before replacement can better avoid the safety risks caused by sudden breakage and failure of the tool due to exhaustion of service life, and ensure production safety; timely replacement of worn tools can avoid the impact of severe tool wear on the quality of the workpiece, ensure the degree of processing, and thus improve product quality.

[0116] It should be noted that the above description of the process 200 is only for example and illustration, and does not limit the scope of application of this specification. For those skilled in the art, various modifications and changes can be made to the process 200 under the guidance of this specification. However, these modifications and changes are still within the scope of this specification.

[0117] Figure 3 is a schematic diagram of generating processing quality information according to some embodiments of this specification. Figure 3 As shown, the process of generating processing quality information includes the following contents. In some embodiments, the process of generating processing quality information can be executed by a processor of the industrial Internet of Things management platform 110.

[0118] In some embodiments, the processor may retrieve a tool running trajectory corresponding to the workpiece information, and generate processing quality information 340 based on the workpiece material information 310 , the tool running trajectory 320 , and the workpiece information 330 .

[0119] The tool movement trajectory refers to the position movement data of the tool during the operation of the CNC machine tool. In some embodiments, the tool movement trajectory can be represented in the form of sequence data, including the position coordinates of multiple sampling points on the tool at multiple time points. Among them, the multiple sampling points on the tool refer to at least one point on the tool that can come into contact with the workpiece; the position coordinates can be determined based on a pre-set coordinate system.

[0120] In some embodiments, the aforementioned multiple time points may include at least one time point of at least one processing stage. For more information about at least one processing stage, please refer to the specification. Figure 2 The relevant description in step 230.

[0121] In some embodiments, the processor can control the CNC machine tool to automatically collect the running trajectory of the tool.

[0122] The workpiece material information is information that characterizes the material of the workpiece, for example, alloy steel, aluminum alloy or other materials. In some embodiments, the workpiece material information can be determined based on user input.

[0123] For detailed information about workpiece information, please refer to this manual Figure 2 Relevant instructions in step 230.

[0124] For detailed information on processing quality, please refer to this manual Figure 2 Relevant instructions in step 240.

[0125] In some embodiments, the processor may generate machining quality information based on workpiece material information, tool operation trajectory and workpiece information.

[0126] In some embodiments, the processor may determine the current processing stage based on the tool running trajectory, determine the corresponding current processing area based on the current processing stage, and determine the matching degree between the tool running trajectory and the contour of the current processing area in the workpiece information. The matching degree is related to the sub-matching degree of the coordinates of the tool position corresponding to at least one time point in the tool running trajectory and the coordinates of the contour of the current processing area.

[0127] If the coordinates of the tool position at a certain time point are consistent with the coordinates of the current processing area contour, the sub-matching degree corresponding to the time point is 1. If the tool position is inconsistent with the coordinates of the current processing area contour, the distance between the coordinates of the tool position and the coordinate origin and the distance between the coordinates of the current processing area contour and the coordinate origin are determined respectively, and the ratio of the smaller distance to the larger distance is used as the sub-matching degree at the time point. It can be understood that the current processing area contour includes at least one point corresponding to the tool position at at least one time point.

[0128] In some embodiments, the coordinate origin can be set based on experience. For example, the center point of the contact surface between the workpiece and the CNC machine tool is used as the coordinate origin. The coordinates of the current processing area contour refer to the coordinates of at least one key point on the current processing area contour.

[0129] In some embodiments, the processor may select points where the coordinates of the tool position are inconsistent with the coordinates of the current processing area contour as sampling points, and use the average value of the sub-matching degrees corresponding to the sampling points as the matching degree.

[0130] In some embodiments, the processor may determine the deformation value of the workpiece by querying a deformation reference table based on the workpiece material information. The deformation reference table includes reference material information of the workpiece and its corresponding reference deformation value, which may be determined based on prior experience.

[0131] The deformation value reflects the possibility of shape change of the workpiece during processing due to factors such as heat, friction, and force. The larger the deformation value, the more likely the workpiece is to deform during processing, which is more likely to affect the tool trajectory. The deformation value can be expressed as a value between 0 and 1. The larger the value, the greater the deformation.

[0132] In some embodiments, the processor may determine processing quality information based on the aforementioned matching degree and deformation value and the initial processing quality.

[0133] Initial machining quality refers to the initially determined machining quality of the workpiece. In some embodiments, the processor may determine the initial machining quality based on the machining quality of at least one local point on the workpiece where a dimensional deviation exists. For details, see this specification Figure 2 In step 240 , the relevant description of the processing quality information is determined.

[0134] In some embodiments, the processor may determine the processing quality information by using the following formula (3).

[0135] (3)

[0136] in, For processing quality information, is the initial processing quality, For the matching degree, is the deformation value.

[0137] In some embodiments, the processor may also determine trajectory difference information based on a standard running trajectory corresponding to the workpiece and a tool running trajectory; and determine processing quality information based on the trajectory difference information, workpiece material information, and workpiece information.

[0138] The standard running trajectory refers to the running trajectory of the tool under ideal conditions. The ideal state refers to the state of the tool when there is no interference from adverse factors.

[0139] In some embodiments, the processor may determine a standard running trajectory based on the processed workpiece model. For example, the processed workpiece model is determined based on the workpiece information, the workpiece contour is determined based on the processed workpiece model, and the workpiece contour is used as the standard running trajectory. The processed workpiece model may be obtained through modeling software (such as CAD, etc.).

[0140] The track difference information refers to the difference information between the tool running track and the standard running track. In some embodiments, the track difference information may include multiple groups of difference points.

[0141] In some embodiments, the processor may compare the coordinates of at least one point on the tool running trajectory with the coordinates of at least one point on the corresponding standard running trajectory, and determine the points with inconsistent coordinates as a group of difference points; determine the distance between the point on the tool running trajectory and the coordinate origin, as well as the distance between the point on the standard running trajectory and the coordinate origin among the difference points, and use the ratio of the smaller distance to the larger distance as the sub-matching degree of the group of difference points.

[0142] In some embodiments, the processor may determine multiple groups of difference points, and determine the matching degree based on an average of the sub-matching degrees corresponding to the multiple groups of difference points.

[0143] In some embodiments, the processor may determine the deformation value of the workpiece by querying a deformation reference table based on the workpiece material information. Detailed descriptions may refer to the above description.

[0144] In some embodiments, the processor may determine the processing quality information based on the aforementioned matching degree, the deformation value of the workpiece, and the initial processing quality. For more detailed descriptions, please refer to the above description of formula (3).

[0145] In some embodiments of the present specification, by analyzing the trajectory difference information between the tool running trajectory and the standard running trajectory, the deviation of the tool running trajectory can be obtained more accurately, thereby better providing data support for determining the degree of tool wear.

[0146] When a CNC machine tool processes a workpiece, in addition to the wear of the tool that may affect the workpiece processing quality, the deformation of the workpiece itself may also affect the workpiece processing quality.

[0147] In some embodiments of the present specification, by considering the tool trajectory information, the change in machining quality caused by tool wear can be determined more accurately, providing reliable data support for analyzing the degree of tool wear, which is conducive to more accurate determination of tool wear conditions.

[0148] Figure 4 Schematic diagram of determining tool wear information according to some embodiments of this specification. Figure 4As shown, the process of generating tool wear information may include the following: In some embodiments, the process of generating tool wear information may be executed by a processor of the industrial Internet of Things management platform 110.

[0149] In some embodiments, Figure 4 As shown, the processor can collect cutting fluid change information 431 through a camera 410 and a first monitoring component 420 configured in a cutting fluid storage tank; collect a cutting force data sequence 432 of a tool 450 through a second monitoring component 440; evaluate the degree of wear 470 of the tool in at least one time period based on the tool's apparent information 460, operating status information 430 and processing quality information 340; the operating status information 430 includes cutting fluid change information 431 and a cutting force data sequence 432; and generate tool wear information 480 based on the degree of wear 470 of the tool in at least one time period.

[0150] For more information about cameras and tools, see Figure 1 For more information about appearance information, operating status information, processing quality information and tool wear information, see Figure 2 and its corresponding description.

[0151] Cutting fluid storage tank refers to a tank-shaped device used to store cutting fluid. For example, plastic barrels of different specifications. Cutting fluid is an industrial liquid used in the process of metal cutting, grinding and grinding to cool and lubricate tools and workpieces.

[0152] The cutting fluid change information is a data sequence reflecting the change of the cutting fluid state over time. In some embodiments, the cutting fluid change information may include the state information of the cutting fluid at at least one time point, wherein the state information may include but is not limited to the cutting fluid temperature, the cutting fluid quality, etc.

[0153] In some embodiments, the processor can obtain cutting fluid change information through the first monitoring component.

[0154] The first monitoring component is a monitoring device for monitoring relevant information of the cutting fluid. Exemplarily, the first monitoring component may include but is not limited to at least one of a temperature sensor and a gravity sensor.

[0155] In some embodiments, the first monitoring component may be disposed in a cutting fluid storage tank.

[0156] The cutting force data sequence is a sequence reflecting the change of the force data of the tool of the numerical control machine tool over time. In some embodiments, the cutting force data sequence may include the force magnitude of the tool of the numerical control machine tool at at least one time point.

[0157] In some embodiments, the processor may obtain the cutting force data sequence through a second monitoring component.

[0158] The second monitoring component is a monitoring device for monitoring the force data of the tool of the CNC machine tool during processing. Exemplarily, the second monitoring component may include but is not limited to a pressure sensor.

[0159] In some embodiments, the second monitoring component can be disposed on a tool fixing assembly of a CNC machine tool. For more information about the tool fixing assembly, see Figure 1 The corresponding description.

[0160] The wear degree of at least one time period refers to the wear degree of the tool in at least one time period. Since tool processing can include at least one processing stage, at least one processing stage can be divided into one or more time periods, and the wear degree of the tool in each processing stage will vary differently. For more information about processing stages, see Figure 2 and its corresponding description.

[0161] In some embodiments, the processor may evaluate the wear degree of the tool in at least one time period in a variety of ways based on the tool's appearance information, operation status information, and processing quality information.

[0162] In some embodiments, the processor may determine a maximum value of the degree of wear of the tool in at least one time period as the tool wear information.

[0163] As an example only, the processor can determine the initial wear degree of the tool by querying the wear degree reference table based on the apparent information of the tool; determine the abnormal machine tool data based on the cutting fluid change information and the cutting force data sequence in the operating status information; determine the wear value actually corresponding to the abnormal machine tool data based on the abnormal machine tool data; and then determine the wear degree of the tool in at least one time period based on the initial wear degree and the wear value actually corresponding to the abnormal machine tool data.

[0164] For detailed instructions on the wear degree reference table, please refer to this instruction manual Figure 2 The relevant description in step 250.

[0165] The initial wear degree refers to the wear degree of the tool before the CNC machine tool starts working.

[0166] Abnormal machine tool data refers to a data sequence in which an abnormality occurs in the cutting fluid change information and cutting force data sequence. In some embodiments, the processor can compare the current cutting fluid change information and cutting force data sequence with the standard cutting fluid change information and the standard cutting force data sequence, determine the unreasonable data therein, and then obtain the abnormal machine tool data. The unreasonable data may include unreasonable up and down fluctuations, sudden changes in values, etc. in the data. For example, the processor can obtain an image corresponding to the cutting fluid change information and an image corresponding to the first-level standard cutting fluid change information, compare and analyze the images of the two through a pre-set analysis algorithm, determine the points where there are differences, and determine the data corresponding to the points where the differences are greater than the preset tolerance as abnormal machine tool data. Among them, the preset tolerance refers to the acceptable range of differences between the cutting fluid change information and the standard cutting fluid change information. The judgment of the cutting force data sequence can also be carried out in a similar manner.

[0167] The standard cutting fluid change information and the standard cutting force data sequence refer to the cutting fluid change information and the cutting force data sequence used as the reference standard. In some embodiments, the processor can count the number of times the same historical cutting fluid change information and the historical cutting force data sequence appear in the historical data, and use the historical cutting fluid change information and the historical cutting force data sequence with the largest number of appearances as the standard cutting fluid change information and the standard cutting force data sequence, respectively.

[0168] The wear value actually corresponding to the abnormal machine tool data is used to characterize the influence of a certain abnormal situation on the tool, and can be the average of the wear values ​​corresponding to multiple occurrences of the same abnormal machine tool data.

[0169] In some embodiments, the processor may determine the wear value actually corresponding to the abnormal machine tool data by means of vector matching.

[0170] As an example only, the processor may construct a standard vector library. The standard vector library may include multiple standard vectors and multiple labels corresponding to them. The standard vector may include appearance information, operation status information, processing quality information and abnormal machine tool data, and the label may be a reference wear value corresponding to the standard vector.

[0171] In some embodiments, the processor can construct a clustering vector based on the historical appearance information, historical operation status information, historical processing quality information, and historical abnormal machine tool data in the historical data and the historical wear values ​​of at least one historical time period corresponding to the historical data, cluster multiple clustering vectors, and construct a standard vector based on the historical appearance information, historical operation status information, historical processing quality information, and historical abnormal machine tool data corresponding to the cluster center formed by clustering, and use the historical wear value of at least one historical time period corresponding to the cluster center as the label of the standard vector. The historical wear value of at least one historical time period can be determined based on the difference between the initial wear degree corresponding to the start time point of the time period and the final wear degree corresponding to the end time point of the time period. The initial wear degree and the final wear degree can be determined by user input.

[0172] In some embodiments, the processor can construct a vector to be matched based on the current appearance information, operation status information, processing quality information and abnormal machine tool data, match the vector to be matched with a standard vector in a standard vector library, calculate multiple vector similarities between the vector to be matched and multiple standard vectors, and determine the label corresponding to the standard vector with the highest vector similarity as the wear value actually corresponding to the current abnormal machine tool data. The vector similarity can be represented by cosine similarity, Euclidean distance, etc.

[0173] In some embodiments, the processor may sum the initial wear degree and the wear value actually corresponding to the abnormal machine tool data in at least one time period to determine the wear degree in at least one time period.

[0174] In some embodiments, the processor may determine the degree of wear of the tool in at least one time period based on the appearance information, the operation status information and the processing quality information through a wear assessment model.

[0175] The wear assessment model is a model for assessing the wear degree of a tool. In some embodiments, the wear assessment model may be a machine learning model, such as a recurrent neural network (RNN).

[0176] In some embodiments, the input of the wear assessment model may include appearance information, operation status information and processing quality information, and the output may include the wear degree of the tool in at least one future time period. The operation status information includes the operation status of the tool and the CNC machine tool, cutting fluid change information and cutting force data sequence.

[0177] In some embodiments, the wear assessment model can be trained and acquired in a variety of ways. For example, it can be acquired through training with a plurality of training samples with training labels. The training samples may include sample appearance information, sample operation status information, and sample processing quality information. The training labels corresponding to the training samples are the sample wear degree in at least one time period.

[0178] In some embodiments, the processor may determine multiple training samples used for training based on historical data, and historical wear data corresponding to the training samples; determine the historical wear degree based on the historical wear data, and determine the historical wear degree as a label corresponding to the training sample. For example, the processor may determine the training sample based on historical appearance information, historical operating state information, and historical processing quality information in the historical data, and use the historical wear degree of at least one historical time period corresponding to the training sample as the training label of the training sample.

[0179] The historical wear degree refers to the wear degree of the tool in the historical data. The historical wear degree of at least one time period can be determined based on the inspection result input manually. For example, the staff can inspect the tool to determine the wear degree through laser scanning instruments, ultrasonic flaw detection instruments, etc., and the processor obtains the manual monitoring result of the tool wear degree through the user terminal.

[0180] In some embodiments, the processor may input sample appearance information, sample operation status information, and sample processing quality information into the initial wear assessment model, construct a loss function based on the wear degree of at least one time period output by the initial assessment model and the training label, and update the initial assessment model based on the loss function. When the training end condition is met, the initial assessment model training is completed to obtain a trained wear assessment model. The training end condition may be that the loss function converges, the number of iterations reaches a threshold, etc.

[0181] In some embodiments, the processor divides the training samples into multiple training data sets based on historical wear data; based on at least one of the training data sets, performs at least one round of training on the initial evaluation model to determine the initial training effect; determines an adjusted learning rate based on the initial training effect; based on unused data sets in the multiple training data sets and the adjusted learning rate, continues to train the initial evaluation model until the training end condition is met to obtain a wear assessment model.

[0182] In some embodiments, the processor may divide the training sample into multiple training data sets based on the historical wear data. For example, the processor may divide the historical wear degree corresponding to the training sample into several wear degree intervals, and determine multiple training sample sets based on the wear degree intervals, wherein the multiple training sample sets include several training sample sets with different wear degree intervals and training sample sets with unchanged wear degree, and each training sample set may include multiple groups of training samples.

[0183] For at least one of the training sample sets, the processor may perform at least one round of training on the initial evaluation model based on at least one set of training samples therein to determine an initial training effect. The initial training effect may be determined based on the variance of the difference between the output of the model obtained through the at least one round of training and the training label.

[0184] As an example only, if a training sample set includes two groups of training samples, Group A and Group B, the processor performs at least one round of training on the initial evaluation model based on the training samples of Group A to obtain the initial evaluation model with updated parameters; the processor can use the training samples of Group A as the input of the initial evaluation model with updated parameters to obtain a set of initial outputs, and determine the difference between the initial outputs and the labels of the training samples of Group A; the initial training effect is determined based on the variance of the aforementioned difference, for example, the larger the variance, the more unstable the output result of the representation model and the worse the initial training effect.

[0185] In some embodiments, the processor may determine an adjusted learning rate based on initial training; continue training based on unused data sets in multiple training data sets and the adjusted learning rate until a training end condition is met to obtain a trained wear assessment model.

[0186] The learning rate refers to the step size for adjusting parameters when training the wear assessment model, which determines the degree of parameter adjustment during each gradient update.

[0187] In some embodiments, the larger the variance, the worse the initial training effect, and the learning rate of model training should be appropriately lowered to make the model converge better.

[0188] As an example only, after the processor has trained the initial evaluation model for at least one round based on the training samples of group A, if the variance of the difference between the initial output and the label of the training samples of group A is greater than the preset variance threshold, it means that the effect of the initial training is poor and cannot meet the model training requirements. At this time, the learning rate should be adjusted to a smaller value, and based on the adjusted learning rate, the initial evaluation model should continue to be trained using the training samples of group B until the training end conditions are met to obtain a trained wear assessment model. Among them, the preset variance threshold can be determined based on prior experience and / or actual needs. For an explanation of the training end conditions, please refer to the previous description.

[0189] In some embodiments of the present specification, by performing multiple rounds of iterative training on the wear assessment model and adjusting the learning rate during the iterations, the processing result of the wear assessment model finally obtained can be made more accurate.

[0190] In some embodiments of the present specification, by using a trained wear assessment model to determine the degree of wear of a tool in at least one time period, the data processing rate of a data processing intelligent monitoring system can be improved and time waste in the processing process can be reduced.

[0191] In some embodiments of the present specification, by monitoring the cutting fluid change information and cutting force data sequence at different times in a CNC machine tool, a more realistic tool wear degree can be estimated, and then a reasonable tool replacement time can be determined to avoid serious machining quality problems and save consumables costs.

[0192] Figure 5 FIG. 1 is an exemplary schematic diagram of determining a tool to be replaced according to some embodiments of this specification. Figure 5 As shown, the process of determining the tool to be replaced may include the following: In some embodiments, the process of determining the tool to be replaced may be executed by a processor of the industrial Internet of Things management platform 110 .

[0193] In some embodiments, the processor may determine a remaining life sequence 520 of a tool based on the tool's historical processing data 510 and tool wear information 480 ; determine a tool replacement priority 530 based on the remaining life sequence 520 ; and determine a tool to be replaced 540 based on the replacement priority 530 .

[0194] For more information about tools and storage devices, see Figure 1 For more information about tool wear and tools to be replaced, see Figure 2 and its corresponding description.

[0195] Historical processing data refers to the data related to the processing of the workpiece by the tool. For example, the historical processing data may include historical tool wear information, historical processing types, historical processing times, etc. Historical tool wear information refers to the tool wear information in the historical data. Historical processing types refer to the types of materials that the tool has processed. Historical processing times refer to the number of times the tool has processed.

[0196] In some embodiments, different tools in a CNC machine tool have their own corresponding historical processing data.

[0197] In some embodiments, the processor can obtain historical processing data from the storage device. For more information about the storage device, see Figure 1 The corresponding description.

[0198] The remaining service life sequence is a sequence of the remaining service life of at least one tool in a CNC machine tool. The remaining service life refers to the time that the tool can still be used for machining.

[0199] In some embodiments, the processor may determine the remaining life sequence of the tool in a variety of ways based on the historical processing data and tool wear information of the tool. For example, the processor may obtain the remaining life corresponding to at least one tool in the CNC machine tool by querying a reference life table based on the tool type, processing type and tool wear information, and then determine the remaining life sequence.

[0200] The reference life table is a table including the correspondence between historical machining data, tool wear information and remaining service life.

[0201] In some embodiments, the processor can count the historical remaining service life corresponding to the historical processing data and tool wear information of different tools, and add it to the reference life table. When the processor obtains multiple remaining service lives based on the same historical processing data and tool wear information, the processor averages the multiple remaining service lives and uses the average as the final corresponding remaining service life.

[0202] In some embodiments, the remaining life sequence of the tool is further related to the wear degree of the tool in at least one time period.

[0203] For more information on the degree of wear and tear over at least one period of time, see Figure 4 and its corresponding description.

[0204] In some embodiments, the processor can determine the remaining life sequence in a variety of ways based on the degree of wear in at least one time period. For example, the processor can count the number of wear changes of the tool according to the degree of wear of the tool in different time periods; obtain the original remaining life of the tool; and calculate the target remaining life based on the original remaining life.

[0205] As an example only, the processor may use the wear value to represent the change in the degree of wear of the tool before and after use. When the wear value is greater than a preset wear threshold, the processor may record one change in tool wear. The preset wear threshold represents the minimum wear value that can affect the service life of the tool and may be set based on prior experience.

[0206] In some embodiments, the processor may divide the wear value into at least one preset stage, and at least one preset stage may be determined by manual input. , +α], ( , +2α], ..., and so on. Among them, is the preset wear threshold, α is the tolerance preset based on prior experience. The preset stage refers to the range of preset wear values.

[0207] In some embodiments, there may be multiple preset stages, and the processor may count the number of wear changes between different preset stages. , … .

[0208] The original remaining life refers to the initially determined tool life. In some embodiments, the original tool life can be determined based on the tool's historical processing data and tool wear information. For detailed description, please refer to the above related description.

[0209] The method of obtaining the original remaining service life of the tool is the same as the method of obtaining the remaining service life sequence based on the historical processing data and tool wear information of the tool. Please refer to the relevant instructions above.

[0210] The target remaining service life refers to the remaining service life that needs to be determined. In some embodiments, the target remaining service life is related to the number of wear changes and the estimated consumption life. The estimated consumption life refers to the life consumption value of the tool corresponding to the preset stages of different wear values.

[0211] In some embodiments, the estimated consumption life can be obtained by analyzing historical processing data or experiments. , +α], the processor can convert the wear value +α corresponding to the life consumption value as the life consumption value corresponding to the preset stage; the processor can select at least one wear value The machining process of +α is taken as the reference machining process. The corresponding remaining tool life before and after the reference machining process is queried through the reference life table, and the difference between the two is taken to determine the reference life consumption value of the aforementioned reference machining process, and the estimated consumption life corresponding to the preset stage is determined based on the average value of the reference life consumption value.

[0212] In some embodiments, the target remaining useful life may be determined by the following formula (4):

[0213] (4)

[0214] in, represents the target remaining useful life, Indicates the number of wear changes that occur within the nth preset stage, express The exponential function of Indicates the estimated consumed life corresponding to the nth preset stage of wear degree.

[0215] In some embodiments, the processor may obtain the remaining service life sequence by obtaining the aforementioned multiple target remaining service life.

[0216] In some embodiments of the present specification, by considering the degree of wear of the tool in at least one time period, when the degree of wear is the same, the remaining service life is determined according to the number of machining times of the tool, so that the determined remaining life sequence of the tool can be made more accurate.

[0217] The replacement priority refers to the degree to which different tools need to be replaced. In some embodiments, the replacement priority can be represented by a numerical value, and the higher the numerical value, the more necessary it is for the tool to be replaced.

[0218] In some embodiments, the processor may determine the replacement priority based on the remaining life sequence in a variety of ways. For example, the processor may sort the tools to be replaced according to their remaining life, and the tools with smaller remaining life have higher replacement priorities.

[0219] In some embodiments, the processor may collect processing dust information based on an environmental sensor; and adjust the replacement priority based on the processing dust information and workpiece material information.

[0220] For more information on workpiece materials, see Figure 3 and its corresponding description.

[0221] Environmental sensors are sensors used to collect information about the environment surrounding tool processing, such as dust detection sensors.

[0222] Processing dust information refers to information related to the dust around the CNC machine tool. For example, dust concentration, etc. For more information about CNC machine tools, please refer to Figure 1 The corresponding description.

[0223] In some embodiments, the processor may adjust the replacement priority based on the machining dust information and the workpiece material information.

[0224] In some embodiments, for each of at least one tool in a CNC machine tool, the processor may obtain historical processing data of the tool, and record historical dust information, historical workpiece material information, and historical tool usage time in the historical processing data as associated data of the tool; and determine the associated data of the processing historical dust information and / or workpiece material that meets preset conditions as target data. The preset conditions include dust concentration being higher than a concentration threshold or the workpiece material being a preset type.

[0225] The concentration threshold refers to a preset maximum value of dust concentration. In some embodiments, the preset concentration threshold may be pre-entered by a user. In some embodiments, the preset concentration threshold may be an average value of historical dust concentrations in historical processing data.

[0226] The preset type refers to a preset type of processing material. In some embodiments, the preset type may be a material type preset by a user, for example, the preset type may be a material type whose material hardness meets the requirements, which may be determined based on user input.

[0227] In some embodiments, the processor can determine the average service life of the tool based on the average value of the theoretical usage time of the tool corresponding to the target data; update the adjusted service life of the current tool based on the time the current tool has been used and the aforementioned average service life, for example, subtract the average service life from the time the current tool has been used to determine the adjusted service life; re-sort the tools to be replaced based on the adjusted service life to adjust the replacement priority.

[0228] In some embodiments of the present specification, by processing dust information, it is possible to effectively avoid the characteristics of certain workpiece materials that are prone to generate dust, which may affect the tool processing stability and shorten the tool life; by using workpiece material information, it is possible to effectively avoid the situation where certain workpiece materials are relatively hard (such as certain alloy steels), which may cause the tool to be more likely to produce tiny crack defects that cannot be captured by the camera during the processing process, thereby reducing its life; considering the impact of the two on replacement priority, it is possible to effectively avoid possible misjudgment of tool wear and ensure processing quality.

[0229] In some embodiments of the present specification, the remaining service life of different tools is determined based on a large amount of historical processing data, so that the determined remaining life sequence can be more in line with the actual situation, effectively avoiding the problem of a large difference between the life obtained by theoretical calculation and the actual life, making the final determination of the tool to be replaced more accurate, thereby improving the working efficiency of the CNC machine tool.

[0230] One or more embodiments of the present specification provide a computer-readable storage medium, wherein the storage medium stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the above-mentioned intelligent monitoring method for CNC machining tools based on the industrial Internet of Things.

[0231] The basic concepts have been described above. Obviously, for those skilled in the art, the above detailed disclosure is only for example and does not constitute a limitation of this specification. Although not explicitly stated here, those skilled in the art may make various modifications, improvements and corrections to this specification. Such modifications, improvements and corrections are suggested in this specification, so such modifications, improvements and corrections still belong to the spirit and scope of the exemplary embodiments of this specification.

[0232] At the same time, this specification uses specific words to describe the embodiments of this specification. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of this specification. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or more in different positions in this specification does not necessarily refer to the same embodiment. In addition, certain features, structures or characteristics in one or more embodiments of this specification can be appropriately combined.

[0233] In addition, unless explicitly stated in the claims, the order of the processing elements and sequences described in this specification, the use of alphanumeric characters, or the use of other names are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some invention embodiments that are currently considered useful through various examples, it should be understood that such details are only for illustrative purposes, and the attached claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the essence and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0234] Similarly, it should be noted that in order to simplify the description disclosed in this specification and thus help understand one or more embodiments of the invention, in the above description of the embodiments of this specification, multiple features are sometimes combined into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the subject matter of this specification are more than the features mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0235] In some embodiments, numbers describing the number of components and attributes are used. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise specified, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximate values, which may change according to the required features of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining the digits. Although the numerical domains and parameters used to confirm the breadth of the range in some embodiments of this specification are approximate values, in specific embodiments, the setting of such numerical values ​​is as accurate as possible within the feasible range.

[0236] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, documents, etc., cited in this specification is hereby incorporated by reference in its entirety. Except for application history documents that are inconsistent with or conflicting with the contents of this specification, documents that limit the broadest scope of the claims of this specification (currently or later attached to this specification) are also excluded. It should be noted that if the descriptions, definitions, and / or use of terms in the materials attached to this specification are inconsistent or conflicting with the contents described in this specification, the descriptions, definitions, and / or use of terms in this specification shall prevail.

[0237] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. An intelligent monitoring method for CNC machining tools based on industrial Internet of Things, characterized in that: It is executed by the Industrial Internet of Things management platform of the CNC machining tool intelligent monitoring system based on the Industrial Internet of Things; The industrial Internet of Things management platform is configured in the processor and is connected to the perception control platform through the sensor network platform; The sensor network platform is configured on a communication device; The perception control platform is configured in the host of the CNC machine tool, and the perception control platform is configured to control the operation of the camera and the machine tool monitoring device; The method comprises: The tool appearance information is acquired based on the tool image and stored in the data center of the industrial Internet of Things management platform; the tool image is acquired through the camera at a preset acquisition time; the preset acquisition time includes the time when the tool is in a stopped state; In response to the tool being in operation, based on the machine tool monitoring device, obtaining operation status information of the tool and the CNC machine tool, including: Collect cutting fluid change information through the camera and a first monitoring component configured in the cutting fluid storage tank; collecting a cutting force data sequence of the tool through a second monitoring component; Sending the operating status information to the data center of the industrial Internet of Things management platform through the communication device; Sending an image acquisition instruction to the perception control platform to control the camera to acquire workpiece images at a preset frequency, and determining workpiece information based on the workpiece images; Processing the workpiece information to generate processing quality information, and storing the processing quality information in the data center of the industrial Internet of Things management platform; Retrieving the appearance information, the operation status information and the processing quality information from the data center and generating tool wear information, including: Based on the appearance information, the operation status information and the machining quality information of the tool, evaluating the wear degree of the tool in at least one time period; the operation status information includes the cutting fluid change information and / or the cutting force data sequence; generating the tool wear information based on the wear degree of the at least one time period; According to the tool wear information, an alarm is issued through a machine tool early warning device and / or an interactive screen to indicate the wear condition of the tool; Determine the tool to be replaced according to the tool wear information; control the tool replacement component to clamp the spare tool from the spare tool box; and, A rotation speed adjustment instruction and / or a frequency adjustment instruction is issued; the rotation speed adjustment instruction is used to control the rotation speed of the tool fixing component to adjust the processing intensity of the tool to be replaced; the frequency adjustment instruction is used to adjust the acquisition frequency of the camera.

2. The method according to claim 1, characterized in that The processing of the workpiece information to generate processing quality information includes: Retrieving a tool running trajectory corresponding to the workpiece information; The machining quality information is generated based on the workpiece material information, the tool operation trajectory and the workpiece information.

3. The method according to claim 1, characterized in that Determining the tool to be replaced according to the tool wear information includes: Determining the remaining life sequence of the tool according to the historical processing data of the tool and the tool wear information; Determining the replacement priority of the tool according to the remaining life sequence; The tool to be replaced is determined based on the replacement priority.

4. The method according to claim 3, characterized in that The remaining life sequence of the tool is also related to the degree of wear of the tool in the at least one time period.

5. The intelligent monitoring system for CNC machining tools based on industrial Internet of Things is characterized by: The system includes an industrial Internet of Things management platform, a sensor network platform and a perception control platform; The industrial Internet of Things management platform is configured in a processor and is communicatively connected with the perception control platform through the sensor network platform; The sensor network platform is configured on a communication device; The perception control platform is configured in the host of the CNC machine tool, and the perception control platform is configured to control the operation of the camera and the machine tool monitoring device; The industrial Internet of Things management platform is configured to: The tool appearance information is acquired based on the tool image and stored in the data center of the industrial Internet of Things management platform; the tool image is acquired through the camera at a preset acquisition time; the preset acquisition time includes the time when the tool is in a stopped state; In response to the tool being in operation, based on the machine tool monitoring device, obtaining operation status information of the tool and the CNC machine tool, including: Collect cutting fluid change information through the camera and a first monitoring component configured in the cutting fluid storage tank; collecting a cutting force data sequence of the tool through a second monitoring component; Sending the operating status information to the data center of the industrial Internet of Things management platform through the communication device; Sending an image acquisition instruction to the perception control platform to control the camera to acquire workpiece images at a preset frequency, and determining workpiece information based on the workpiece images; Processing the workpiece information to generate processing quality information, and storing the processing quality information in the data center of the industrial Internet of Things management platform; Retrieving the appearance information, the operation status information and the processing quality information from the data center and generating tool wear information, including: Based on the appearance information, the operation status information and the machining quality information of the tool, evaluating the wear degree of the tool in at least one time period; the operation status information includes the cutting fluid change information and / or the cutting force data sequence; generating the tool wear information based on the wear degree of the at least one time period; According to the tool wear information, an alarm is issued through a machine tool early warning device and / or an interactive screen to indicate the wear condition of the tool; Determine the tool to be replaced according to the tool wear information; control the tool replacement component to clamp the spare tool from the spare tool box; and, A rotation speed adjustment instruction and / or a frequency adjustment instruction is issued; the rotation speed adjustment instruction is used to control the rotation speed of the tool fixing component to adjust the processing intensity of the tool to be replaced; the frequency adjustment instruction is used to adjust the acquisition frequency of the camera.

6. The system according to claim 5, characterized in that The industrial Internet of Things management platform includes a production process management sub-platform, the data center and an equipment management sub-platform.

7. The system according to claim 5, characterized in that The industrial Internet of Things management platform is further configured to: Retrieving a tool running trajectory corresponding to the workpiece information; The machining quality information is generated based on the workpiece material information, the tool operation trajectory and the workpiece information.

8. The system according to claim 5, characterized in that The industrial Internet of Things management platform is further configured to: Determining the remaining life sequence of the tool according to the historical processing data of the tool and the tool wear information; Determining the replacement priority of the tool according to the remaining life sequence; The tool to be replaced is determined based on the replacement priority.

Images