A CNC machining intelligent monitoring method and system based on industrial Internet of Things

Abstract

The present invention provides an intelligent monitoring method and system for numerical control machining based on industrial Internet of Things, and relates to the technical field of numerical control machining. The system includes a user platform, a service platform, an industrial Internet of Things management platform, a sensor network platform, and a perception control platform. The method is executed by the industrial Internet of Things management platform, and includes: obtaining the information to be processed corresponding to the task to be processed and determining the numerical control machining parameters and the simulation machining data corresponding to the numerical control machining parameters; based on the numerical control machining parameters, controlling the numerical control machining equipment to execute the task to be processed; collecting actual machining data according to the monitoring frequency during the execution of the task to be processed; performing deviation judgment on the actual machining data and the simulation machining data; generating a machining alarm instruction when the result of the deviation judgment meets the preset alarm condition and sending it to the alarm device; based on the actual machining data, controlling the numerical control machining equipment to adjust the feed step length. The present invention can comprehensively monitor the numerical control machining process to improve production efficiency.

Description

Technical Field

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

[0002] As an important support point of the manufacturing industry, CNC machining is gradually transforming towards intelligence and networking. However, due to factors such as single monitoring means, incomplete data collection, insufficient data analysis capabilities, and reliance on manual monitoring and management, the CNC machining process may lead to problems such as low production efficiency, improper tool use and maintenance, and unstable product quality.

[0003] In order to solve the above problems, CN107584334B discloses a real-time monitoring method for the state of complex structural parts CNC machining tools based on deep learning. By training a deep learning network with a large number of CNC machining monitoring signals, real-time monitoring of the tool state can be achieved. However, this method cannot fully monitor the machining temperature, materials to be processed, etc. during CNC machining, and cannot meet the needs of industrial intelligence.

[0004] Therefore, it is hoped to provide an intelligent monitoring method and system for CNC machining based on industrial Internet of Things, which will help to achieve comprehensive monitoring, data analysis and intelligent control of the CNC machining process, so as to improve production efficiency, ensure machining quality and reduce the occurrence of faults. Summary of the invention

[0005] In order to solve the problem of how to comprehensively monitor the CNC machining process to improve CNC production efficiency and ensure production quality, this specification provides a CNC machining intelligent monitoring method and system based on industrial Internet of Things.

[0006] The invention content includes an intelligent monitoring method for CNC machining based on industrial Internet of Things, which is executed by an industrial Internet of Things management platform, including: based on the input device of a perception control platform, obtaining the information to be processed corresponding to the task to be processed; based on the information to be processed, performing CNC process simulation, determining CNC machining parameters and simulated machining data corresponding to the CNC machining parameters, and the CNC machining parameters include a feed step length; based on the CNC machining parameters, controlling the CNC machining equipment of the perception control platform to execute the task to be processed; during the execution of the task to be processed, collecting actual machining data according to the monitoring frequency through the monitoring device of the perception control platform; performing deviation judgment on the actual machining data and the simulated machining data; in response to the result of the deviation judgment satisfying a preset alarm condition: generating a machining alarm instruction, and sending the machining alarm instruction to the alarm device of the user platform; based on the actual machining data, controlling the CNC machining equipment to adjust the feed step length.

[0007] The invention content includes an intelligent monitoring system for CNC machining based on industrial Internet of Things, the system includes a user platform, a service platform, an industrial Internet of Things management platform, a sensor network platform and a perception control platform, the industrial Internet of Things management platform includes a production process management sub-platform, a data center and an equipment management sub-platform, and the industrial Internet of Things management platform is configured as follows: based on the input device of the perception control platform, obtaining the processing information corresponding to the processing task to be processed; based on the processing information to be processed, performing CNC process simulation, determining CNC machining parameters and simulated machining data corresponding to the CNC machining parameters, the CNC machining parameters including a feed step length; based on the CNC machining parameters, controlling the CNC machining equipment of the perception control platform to execute the processing task to be processed; during the execution of the processing task to be processed, collecting actual machining data according to the monitoring frequency through the monitoring equipment of the perception control platform; performing deviation judgment on the actual machining data and the simulated machining data; in response to the result of the deviation judgment satisfying the preset alarm condition: generating a machining alarm instruction, and sending the machining alarm instruction to the alarm device of the user platform; based on the actual machining data, controlling the CNC machining equipment to adjust the feed step length.

[0008] The beneficial effects brought by the above invention include but are not limited to:

[0009] (1) Based on the information to be processed, the CNC process simulation is carried out to determine the CNC processing parameters and the simulated processing data corresponding to the CNC processing parameters, and the actual processing data is collected during the actual processing. Based on the results of the deviation judgment, the processing alarm instructions are generated and the feed step length is adjusted. This can not only monitor the CNC processing process comprehensively and intelligently, but also issue an alarm and adjust the feed step length when the position deviation or cutting force deviation does not meet the requirements, which can ensure the processing quality, reduce production costs, and enhance the flexibility and applicability of CNC processing;

[0010] (2) The product processing quality can be determined through the measurement data of the product 3D model and the product size data, which can intuitively and accurately judge the quality of product processing and improve the intelligent level of CNC processing;

[0011] (3) By estimating the difference between the deviation value and the first-level deviation threshold and dynamically adjusting the monitoring frequency, the flexibility of sub-route monitoring can be enhanced, which improves the intelligence of CNC machining monitoring while ensuring comprehensive monitoring of the CNC machining process;

[0012] (4) By using the error analysis model to predict the estimated error value of the sub-route, the self-learning ability of the machine learning model can be used to find patterns from a large amount of data, which helps to quickly and accurately determine the monitoring frequency of the sub-route; and

[0013] (5) Combining temperature data with future deformation data to predict the estimated comprehensive deviation, the comprehensive deviation in the future processing process can be predicted in advance, early warning can be given, and the intelligence and accuracy of CNC processing can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] 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:

[0015] Figure 1 It is a platform structure diagram of a CNC machining intelligent monitoring system based on the industrial Internet of Things according to some embodiments of this specification;

[0016] Figure 2 is an exemplary flow chart of an intelligent monitoring method for CNC machining based on industrial Internet of Things according to some embodiments of this specification;

[0017] Figure 3 is an exemplary schematic diagram of determining the monitoring frequency of a sub-route in a tool path according to some embodiments of this specification;

[0018] Figure 4 is an exemplary schematic diagram of an error analysis model according to some embodiments of this specification; and

[0019] Figure 5 It is an exemplary schematic diagram of generating a processing alarm instruction according to some embodiments of the present specification. DETAILED DESCRIPTION

[0020] The following is a brief introduction to the drawings required for describing the embodiments. The drawings do not represent all implementation methods.

[0021] The "system", "device", "unit" and / or "module" used herein are a method for distinguishing different components, elements, parts, portions or assemblies at different levels. If other words can achieve the same purpose, the words can be replaced by other expressions.

[0022] 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.

[0023] When the operations performed in the embodiments of this specification are described in steps, unless otherwise specified, the order of the steps is interchangeable, steps may be omitted, and other steps may be included in the operation process.

[0024] When using CNC machining equipment to process parts, cameras, sensors and other monitoring devices are usually used to monitor the CNC machining process and issue warnings when abnormal situations occur. However, CNC machining lasts for a long time, and the efficiency of monitoring through monitoring devices is low. CN107584334B can realize real-time monitoring of tool status through deep learning models, which improves the intelligence and efficiency of monitoring the CNC machining process to a certain extent, but cannot comprehensively monitor the machining temperature, materials to be processed, etc. during the CNC machining process. In view of this, in some embodiments of this specification, by simulating the CNC process of the processing information to be processed, the CNC machining parameters and the corresponding simulated machining data are determined; based on the CNC machining parameters, the CNC machining equipment of the perception control platform is controlled to perform the processing tasks to be processed; at the same time, during the execution process, the actual processing data in the processing process is collected according to the monitoring frequency through the monitoring equipment of the perception control platform; deviation judgment is made based on the actual processing data and the simulated processing data, and corresponding alarms and adjustment strategies are implemented, which helps to realize industrial intelligent monitoring, ensure processing quality, and improve production efficiency.

[0025] Figure 1 It is a platform structure diagram of an intelligent monitoring system for CNC machining based on industrial Internet of Things as shown in some embodiments of this specification.

[0026] like Figure 1 As shown, the CNC machining intelligent monitoring system 100 based on the industrial Internet of Things may include a user platform 110 , a service platform 120 , an industrial Internet of Things management platform 130 , a sensor network platform 140 and a perception control platform 150 .

[0027] The user platform 110 refers to a platform for interacting with a user. In some embodiments, the user platform 110 may include a user terminal, etc. A user terminal refers to one or more terminal devices or software used by a user. For example, a user terminal may include a mobile device, a tablet computer, a laptop computer, etc. A user may include a user or operator of a CNC machining intelligent monitoring system.

[0028] The service platform 120 refers to a platform for providing industrial Internet of Things management services to users. The service platform 120 can provide input and output services to users. In some embodiments, the service platform 120 can interact with the industrial Internet of Things management platform 130 and the user platform 110. For example, the service platform 120 can obtain the processing alarm instruction uploaded by the industrial Internet of Things management platform 130, and send the processing alarm instruction to the alarm device of the user platform 110.

[0029] The industrial Internet of Things management platform 130 refers to a comprehensive management platform for equipment operation related data. In some embodiments, the industrial Internet of Things management platform 130 can interact with the service platform 120 and the sensor network platform 140. In some embodiments, the industrial Internet of Things management platform 130 can be configured with a processor. The processor can be used to process information and / or data related to the CNC machining intelligent monitoring system. In some embodiments, the processor can process data, information and / or processing results obtained from other devices or system components, and execute program instructions based on these data, information and / or processing results to perform one or more functions described in this specification.

[0030] In some embodiments, the industrial Internet of Things management platform 130 can be configured as follows: based on the input device of the perception control platform 150, obtain the processing information corresponding to the processing task; based on the processing information, perform CNC process simulation, determine the CNC processing parameters and the simulated processing data corresponding to the CNC processing parameters, and the CNC processing parameters include the feed step length; based on the CNC processing parameters, control the CNC processing equipment of the perception control platform 150 to execute the processing task; during the execution of the processing task, collect actual processing data according to the monitoring frequency through the monitoring equipment of the perception control platform 150; perform deviation judgment on the actual processing data and the simulated processing data; in response to the result of the deviation judgment satisfying the preset alarm condition: generate a processing alarm instruction, and send the processing alarm instruction to the alarm device of the user platform 110; based on the actual processing data, control the CNC processing equipment to adjust the feed step length.

[0031] In some embodiments, the industrial Internet of Things management platform 130 can be further configured to: generate simulated processing parameters based on the information to be processed; generate a CNC processing program based on the simulated processing parameters and in accordance with programming rules; simulate the CNC processing program and record the simulated processing data; verify the simulated processing parameters based on the simulated processing data; determine the CNC processing parameters and the simulated processing data corresponding to the CNC processing parameters based on the verification results of the simulated processing parameters.

[0032] In some embodiments, the industrial Internet of Things management platform 130 can be further configured to: in response to the estimated comprehensive deviation exceeding the first-level deviation threshold, determine the candidate processing parameters by adjusting the model based on the estimated comprehensive deviation, the first-level deviation threshold, the current processing parameters and the current processing progress, and adjust the model to a machine learning model; verify the candidate processing parameters; based on the verification results of the candidate processing parameters, determine the CNC processing parameters of the sub-route of the tool path.

[0033] In some embodiments, the industrial Internet of Things management platform 130 can be further configured to: divide the tool path to determine sub-paths; determine the estimated error value corresponding to the sub-path based on the CNC machining parameters of the sub-path; and determine the monitoring frequency of the sub-path based on the estimated error value.

[0034] In some embodiments, the industrial Internet of Things management platform 130 can be further configured to: determine the curvature of different points on the tool path; determine the curvature change value of two adjacent points; cluster the points based on the curvature change value to determine the sub-path.

[0035] In some embodiments, the industrial Internet of Things management platform 130 can be further configured to: perform single-point deviation judgment and multi-point deviation judgment: single-point deviation judgment includes: in response to the position deviation of the tool exceeding the first-level deviation threshold, determining that the position of the tool is abnormal and generating a first-level alarm instruction; multi-point deviation judgment includes: in response to the position deviation being between the first-level deviation threshold and the second-level deviation threshold, based on the deviation point ratio, performing multi-level judgment, the multi-level judgment includes: in response to the deviation point ratio exceeding the first-level ratio threshold, determining that the position of the tool is abnormal and generating a first-level alarm instruction; in response to the deviation point ratio being lower than the first-level ratio threshold and higher than the second-level ratio threshold, determining that the position of the tool is abnormal and generating a second-level alarm instruction.

[0036] In some embodiments, the industrial Internet of Things management platform 130 can be further configured to: generate a three-dimensional model of the product based on actual processing data; extract measurement data of the three-dimensional model of the product; and determine the product processing quality based on the measurement data and product dimension data.

[0037] In some embodiments, the industrial Internet of Things management platform 130 may include a production process management sub-platform 131 , a data center 132 , and an equipment management sub-platform 133 .

[0038] The production process management sub-platform 131 refers to a platform for managing the production process. In some embodiments, the production process management sub-platform 131 can be used to determine the numerical control processing parameters. In some embodiments, the production process management sub-platform 131 can interact with the data center 132. For example, the production process management sub-platform 131 can upload the numerical control processing parameters to the data center 132.

[0039] The data center 132 refers to a platform for storing various databases and various data during the operation of the device. In some embodiments, the data center 132 can be configured as a storage device for storing data related to the operation of the device.

[0040] The equipment management sub-platform 133 is a platform for managing equipment. In some embodiments, the equipment management sub-platform 133 can be used to determine the monitoring frequency based on the data during the equipment operation; and generate processing alarm instructions. In some embodiments, the equipment management sub-platform 133 can interact with the data center 132. For example, the equipment management sub-platform 133 can upload the monitoring frequency to the data center 132.

[0041] The sensor network platform 140 is a platform for comprehensive management of sensor information. In some embodiments, the sensor network platform 140 can be configured as a communication network or a gateway.

[0042] The perception control platform 150 refers to a platform for performing perception control during the CNC machining process. In some embodiments, the perception control platform 150 may include an input device, an alarm device, a CNC machining device, a monitoring device, and the like.

[0043] The input device refers to a device or apparatus for receiving input information from a user. For example, the input device may include a keyboard, a mouse, a touch screen, an interface input, etc. The alarm device refers to a device for providing an early warning during the CNC machining process. For example, the alarm device may include a screen, a speaker, and a terminal device that can be worn by the user and can issue an alarm.

[0044] CNC machining equipment refers to equipment for CNC machining, such as CNC machine tools.

[0045] Monitoring equipment refers to related equipment for monitoring the CNC machining process. Exemplarily, the monitoring equipment may include equipment for monitoring the position of the tool, such as a three-dimensional high-definition camera, a motion sensor, etc. Exemplarily, the monitoring equipment may also include equipment for monitoring the cutting force of the tool, such as a pressure sensor, etc.

[0046] For more information about the above platforms, please refer to Figure 2-Figure 5 and related instructions.

[0047] In some embodiments of the present specification, the CNC machining intelligent monitoring system 100 based on the industrial Internet of Things can form an information operation closed loop between various functional platforms, coordinate and operate regularly, and realize the informatization and intelligence of CNC machining monitoring.

[0048] Figure 2 is an exemplary flow chart of a CNC machining intelligent monitoring method based on the Industrial Internet of Things according to some embodiments of this specification. In some embodiments, process 200 can be executed by an Industrial Internet of Things management platform of the CNC machining intelligent monitoring system 100 based on the Industrial Internet of Things. Figure 2 As shown, process 200 includes the following steps:

[0049] Step S210, based on the input device of the perception control platform, obtaining the to-be-processed information corresponding to the to-be-processed task.

[0050] The tasks to be processed refer to the processing tasks to be executed by the CNC processing equipment.

[0051] The information to be processed refers to information related to the task to be processed. In some embodiments, the information to be processed may include processing drawing information, information on the workpiece to be processed, and equipment information.

[0052] The processing drawing information refers to the drawing information corresponding to the target workpiece. For example, the processing drawing information may include the drawing information related to the size information, tolerance information, surface roughness requirements, processing accuracy, etc. of the target workpiece. Among them, the target workpiece refers to the workpiece to be processed after CNC processing. The workpiece to be processed refers to the raw material that needs to be CNC processed.

[0053] The information of the workpiece to be processed refers to information related to the workpiece to be processed. For example, the information of the workpiece to be processed may include the shape, size, size tolerance, material information, etc. of the workpiece to be processed.

[0054] Equipment information refers to information related to CNC machining equipment. For example, equipment information may include the model, machining accuracy, service life, etc. of the CNC machining equipment.

[0055] In some embodiments, the industrial Internet of Things management platform can obtain the tasks to be processed and the processing information corresponding to the tasks to be processed input by the user based on the input device of the perception control platform. For relevant instructions on the perception control platform and input devices, please refer to Figure 1 and its description.

[0056] Step S220, performing numerical control process simulation based on the information to be processed, and determining numerical control processing parameters and simulation processing data corresponding to the numerical control processing parameters.

[0057] CNC process simulation refers to the simulation of the CNC machining process.

[0058] CNC machining parameters refer to parameters related to CNC machining. For example, CNC machining parameters may include machining sequence, tools, fixtures, gauges, tool paths, and step lengths.

[0059] The processing sequence refers to the processing sequence of the workpiece to be processed, for example, the processing sequence may include counterclockwise processing or clockwise processing, etc. In some embodiments, the processing sequence may include the axial processing sequence, the circumferential processing sequence, etc. of the workpiece to be processed.

[0060] A tool is a tool used to cut the workpiece. A fixture is a tool used to clamp the workpiece. A gauge is a tool used to measure the workpiece.

[0061] The tool path refers to the movement trajectory of the tool relative to the workpiece during CNC machining.

[0062] The feed step length refers to the feed amount of the tool. For example, if the feed step length is 0.5mm, the feed amount of the tool is 0.5mm, and the cutting amount of the tool on the workpiece is 0.5mm. The smaller the feed step length, the higher the corresponding processing accuracy and the slower the processing speed.

[0063] The simulated processing data refers to processing data related to the simulated CNC processing process obtained through CNC process simulation. In some embodiments, the simulated processing data may include the simulated coordinate position of the tool and the simulated cutting force. The simulated coordinate position refers to the simulated coordinate position of the tool obtained through CNC process simulation. The simulated cutting force refers to the cutting force of the tool simulated in the CNC process simulation.

[0064] In some embodiments, the industrial Internet of Things management platform can perform CNC process simulation based on the information to be processed, and determine the CNC processing parameters and the simulated processing data corresponding to the CNC processing parameters.

[0065] In some embodiments, the process of numerical control process simulation may include the following steps S221 - S223 .

[0066] Step S221, based on the information to be processed, determine the simulation processing parameters through the first preset rule.

[0067] Simulation machining parameters refer to the NC machining parameters used in the simulated NC machining process.

[0068] The first preset rule refers to a pre-set rule for determining the simulation processing parameters. In some embodiments, the first preset rule can be constructed based on an expert knowledge base and historical processing data. The historical processing data refers to processing data corresponding to the historical CNC processing process, which can be obtained based on historical data.

[0069] The first preset rules may include processing sequence rules, maximum feed step length rules, rotation speed rules, tool selection rules, and tool path rules.

[0070] The processing sequence rule refers to the rule for determining the processing sequence in the simulation processing parameters. The processing sequence rule can be preset by the technician based on the equipment information in the information to be processed.

[0071] The maximum feed step length rule refers to a rule for determining the maximum feed step length of a tool. The maximum feed step length rule may include a mapping relationship between tolerance information in the information to be processed, equipment information, and the maximum feed step length. The aforementioned mapping relationship may be preset by a technician based on the processing accuracy in the equipment information. An exemplary mapping relationship may be: the smaller the tolerance, the higher the processing accuracy, the smaller the corresponding maximum feed step length.

[0072] The rotation speed rule refers to the rule used to determine the rotation speed of the CNC machining equipment. The higher the rotation speed of the CNC machining equipment, the faster the machining speed, the greater the surface roughness of the target workpiece, and the lower the machining accuracy. The rotation speed rule may include a mapping relationship between the machining accuracy in the information to be processed and the rotation speed of the CNC machining equipment, and the aforementioned mapping relationship may be preset by a technician based on the equipment information.

[0073] Tool selection rules refer to the rules used to determine the tools selected for the CNC machining process. Tools can include tools, fixtures, gauges, etc.

[0074] The tool selection rule may include a mapping relationship between the workpiece information and the fixture, which may be preset by a technician. The technician may select a corresponding fixture based on the shape, size, and material information of the workpiece to be processed to avoid damage to the workpiece during CNC machining.

[0075] The tool selection rules may also include the mapping relationship between the material and machining accuracy of the workpiece to be processed and the tool, which can be preset by the technician. The technician can select the corresponding tool based on the material and machining accuracy of the workpiece to be processed to ensure that the tool can effectively process the workpiece to be processed and avoid problems such as tool loss and insufficient machining accuracy.

[0076] The tool selection rules may also include a mapping relationship between the size information and tolerance information of the target workpiece and the measuring tool, which may be preset by a technician. The technician may select a corresponding measuring tool based on the size information and tolerance information of the target workpiece to accurately measure whether the cutting amount meets the requirements.

[0077] Tool path rules refer to the rules used to determine the tool path. Tool path rules can be preset by technicians based on the information to be processed.

[0078] In some embodiments, the industrial Internet of Things management platform can determine the simulation processing parameters according to the information to be processed based on the above-mentioned first preset rule.

[0079] For example, the industrial Internet of Things management platform can determine the processing sequence in the simulated processing parameters based on the processing sequence rules; determine the fixtures, tools and measuring tools in the simulated processing parameters based on the tool selection rules; and determine the tool path in the simulated processing parameters based on the tool path rules.

[0080] For another example, the IIoT management platform can determine the feed step length in the simulation processing parameters based on the maximum feed step length rule and the information to be processed. The IIoT management platform can determine the size difference between the target workpiece and the workpiece to be processed based on the size information of the target workpiece in the information to be processed and the size of the workpiece to be processed, and then determine the cutting amount of different parts of the workpiece to be processed; determine the feed step length in the simulation processing parameters based on the cutting amount and the maximum feed step length.

[0081] For example, the workpiece to be processed is a cylindrical blank with a diameter of 6 cm, and the diameter of part A of the target workpiece is 5 cm. The size difference between the target workpiece and the workpiece to be processed at part A is 1 cm, that is, the cutting amount of part A is 1 cm, and the maximum feed step length determined based on the maximum feed step length rule is 1 mm. The tolerance information is 0.2 cm, so the feed step length can be: the feed step length for the first 9 circles is 1 mm, and the feed step length for the last 5 circles is 0.2 mm.

[0082] Step S222, based on the simulation processing parameters, simulate processing is performed by using numerical control simulation software, and simulation processing data during the simulation processing is recorded.

[0083] CNC simulation software refers to software that can simulate CNC machining processes. CNC simulation software can simulate CNC machining processes, such as the movement of CNC machining equipment, the tool path, and the machining status of the workpiece to be machined, etc., and intuitively display the details of CNC machining without actual machining. Exemplary CNC simulation software may include VNUC, VERICUT, SolidCAM, etc. The Industrial Internet of Things management platform can simulate the CNC machining process under simulated machining parameters based on CNC simulation software and record simulated machining data.

[0084] Step S223, determine whether the simulated workpiece is consistent with the processing drawing information, adjust the simulated processing parameters corresponding to the simulated workpiece that does not meet the requirements until the adjusted simulated workpiece meets the processing drawing information; determine the simulated processing parameters corresponding to the simulated workpiece that meets the requirements as the CNC processing parameters.

[0085] The simulated workpiece refers to the target workpiece that has been completed by the CNC simulation software.

[0086] In some embodiments, the industrial Internet of Things management platform can compare the simulated workpiece with the processing drawing information based on the size information, processing accuracy, etc. of the simulated workpiece to determine whether the simulated workpiece is consistent with the processing drawing information. When the difference between the size information of the simulated workpiece and the size information in the processing drawing information is less than the tolerance information in the processing drawing information, and the processing accuracy of the simulated workpiece is not less than the processing accuracy in the processing drawing information, the industrial Internet of Things management platform can determine that the simulated workpiece is consistent with the processing drawing information.

[0087] When the simulated workpiece does not match the processing drawing information, the Industrial Internet of Things management platform can optimize and adjust the simulated processing parameters that affect the data based on the non-conforming data. Optimization adjustment refers to the adjustment method that can optimize the data that does not match the processing drawing information.

[0088] For example, when the processing accuracy of the simulated workpiece does not meet the processing drawing information, the Industrial Internet of Things management platform can adjust the simulated processing parameters that affect the processing accuracy. For example, the Industrial Internet of Things management platform can reduce the feed step length, select a tool with higher precision, etc.; when the simulated workpiece corresponding to the adjusted simulated processing parameters meets the processing drawing information, the Industrial Internet of Things management platform can determine the adjusted simulated processing parameters as CNC processing parameters.

[0089] In some embodiments, the industrial Internet of Things management platform can generate simulated processing parameters based on the information to be processed; generate CNC processing programs based on the simulated processing parameters and in accordance with programming rules; simulate the CNC processing programs and record simulated processing data; verify the simulated processing parameters based on the simulated processing data; and determine the CNC processing parameters and the simulated processing data corresponding to the CNC processing parameters based on the verification results of the simulated processing parameters.

[0090] For more information on simulation processing parameters and their generation, please refer to Figure 2 Relevant description of step S221.

[0091] Programming rules refer to the rules of a programming language. For example, programming rules may include assembly language, C language, etc. In some embodiments, programming rules may be determined based on device information. For example, an industrial Internet of Things management platform may determine a programming language that a CNC machining device can run as a programming rule.

[0092] CNC machining program refers to the program that controls CNC machining equipment for machining. The Industrial Internet of Things management platform can generate CNC machining programs corresponding to the simulated machining parameters based on the simulated machining parameters and according to the programming rules.

[0093] Simulation refers to the process of simulating the operation of CNC machining programs.

[0094] In some embodiments, the industrial Internet of Things management platform can record the data during the simulation operation of the CNC machining program as simulated machining data.

[0095] In some embodiments, the industrial Internet of Things management platform can verify the simulation processing parameters through various methods based on the simulation processing data.

[0096] In some embodiments, the industrial Internet of Things management platform can determine whether there is a collision between the tool and the workpiece to be processed based on the simulated processing data, and combine the judgment of whether the processing accuracy of the simulated workpiece exceeds the processing capability of the tool and whether the rotation speed exceeds the processing capability of the CNC processing equipment to determine whether the simulated processing parameters are reasonable.

[0097] Reasonable simulation processing parameters mean that the simulation processing parameters can be run reasonably. When the simulated coordinate position of the tool in the simulation processing data overlaps with the coordinate position of the workpiece to be processed, the Industrial Internet of Things Management Platform can determine that the tool and the workpiece to be processed have collided. When the processing accuracy of the simulated workpiece is greater than the maximum processing accuracy of the tool, the Industrial Internet of Things Management Platform can determine that the processing accuracy of the simulated workpiece exceeds the processing capacity of the tool. When the speed is greater than the maximum speed of the CNC processing equipment, the Industrial Internet of Things Management Platform can determine that the speed exceeds the processing capacity of the CNC processing equipment.

[0098] When there is no collision between the tool and the workpiece to be processed, the processing accuracy of the simulated workpiece does not exceed the processing capability of the tool and the rotation speed does not exceed the processing capability of the CNC processing equipment, the industrial Internet of Things management platform can judge that the simulated processing parameters are reasonable, otherwise they are unreasonable.

[0099] In some embodiments, the industrial Internet of Things management platform can determine the simulated processed parts after processing based on the simulated processing parameters based on the simulated processing data; determine whether the simulated processed parts are consistent with the processing drawing information; and then determine whether the simulated processing parameters are accurate. Accurate simulated processing parameters refer to the consistency of the processed parts after processing based on the simulated processing parameters with the processing drawing information. When the simulated processed parts are consistent with the processing drawing information, the industrial Internet of Things management platform can determine that the simulated processing parameters are accurate, otherwise they are inaccurate. For more information about the simulated processed parts and whether the simulated processed parts are consistent with the processing drawing information, please refer to the relevant description of step S223.

[0100] In some embodiments, the industrial Internet of Things management platform can determine the numerical control machining parameters and the simulation machining data corresponding to the numerical control machining parameters based on the verification results of the simulation machining parameters. The industrial Internet of Things management platform can directly determine the verified simulation machining parameters as the numerical control machining parameters, and determine the simulation machining data recorded during the simulation simulation with the simulation machining parameters as the simulation machining data corresponding to the numerical control machining parameters.

[0101] When the simulation processing parameters fail to pass the verification, that is, the simulation processing parameters are unreasonable and / or inaccurate, the industrial Internet of Things management platform can adjust the simulation processing parameters until the adjusted simulation processing parameters pass the verification, and determine the adjusted simulation processing parameters as the CNC processing parameters.

[0102] When the simulated processing parameters are unreasonable, the Industrial Internet of Things management platform can adjust the unreasonable specific parameters. For example, when the tool collides with the workpiece, the Industrial Internet of Things management platform can adjust the tool path so that the tool avoids the collision with the workpiece; when the processing accuracy of the simulated workpiece exceeds the processing capacity of the tool, the Industrial Internet of Things management platform can replace the tool with a higher accuracy; when the speed exceeds the processing capacity of the CNC processing equipment, the Industrial Internet of Things management platform can reduce the speed of the CNC processing equipment.

[0103] When the simulated processing parameters are inaccurate, the Industrial Internet of Things management platform can find out the part where the difference between the dimension information in the simulated processing part and the dimension information in the processing drawing information is less than the tolerance information, and input the processing progress before processing this part as the current processing progress into the adjustment model to obtain the adjusted simulated processing parameters. For more information about the adjustment model, see Figure 2 Related description in the following text.

[0104] In some embodiments of the present specification, CNC machining parameters are determined by verifying the results of simulation machining parameters. Various factors such as equipment capabilities and relevant information of simulated machining parts can be combined to apply reasonable and accurate CNC machining parameters to the CNC machining process, which can improve production efficiency while ensuring machining quality.

[0105] In some embodiments, in response to the estimated comprehensive deviation exceeding the first-level deviation threshold, the industrial Internet of Things management platform can determine candidate processing parameters by adjusting the model based on the estimated comprehensive deviation, the first-level deviation threshold, the current processing parameters and the current processing progress; verify the candidate processing parameters; and determine the CNC processing parameters of the sub-route of the tool path based on the verification results of the candidate processing parameters.

[0106] The estimated comprehensive deviation refers to the deviation in size of the target workpiece caused by the deformation of the workpiece and the position deviation of the tool in the future processing process. For the determination of the estimated comprehensive deviation, please refer to Figure 5 and its related description.

[0107] The first level deviation threshold is a preset threshold related to the deviation of the target workpiece. For more information about the first level deviation threshold, see Figure 5 and its related description.

[0108] The current processing parameters refer to the numerical control processing parameters currently used for numerical control processing. In some embodiments, the industrial Internet of Things management platform can obtain the current processing parameters from the data center.

[0109] The current processing progress refers to the progress of the current CNC processing process. In some embodiments, the industrial Internet of Things management platform can determine the ratio of the length of the route currently completed by the tool to the length of the tool path as the current processing progress. The industrial Internet of Things management platform can determine the length of the route currently completed by the tool based on the moving distance of the actual coordinate position of the tool in the monitoring device, and determine the length of the tool path based on the aforementioned first preset rule.

[0110] The adjustment model refers to a model used to determine candidate processing parameters. In some embodiments, the adjustment model may be a machine learning model, for example, a deep neural network model, etc. The candidate processing parameters refer to the adjusted CNC processing parameters that may be applied to subsequent processing processes.

[0111] In some embodiments, the input of the adjustment model may include the estimated comprehensive deviation, the first level deviation threshold, the current processing parameters, and the current processing progress. The output of the adjustment model may include the candidate NC processing parameters of the sub-route of the subsequent NC processing process. For more information about the sub-route, see Figure 3 Related description.

[0112] In some embodiments, the adjustment model can be obtained through training based on a first training sample with a first label. For example, a plurality of first training samples with a first label can be input into an initial adjustment model, a loss function can be constructed through the first label and the result of the initial adjustment model, and the parameters of the initial adjustment model can be iteratively updated through gradient descent or other methods based on the loss function. When the preset iteration condition is met, the model training is completed and a trained adjustment model is obtained. Among them, the preset iteration condition can be that the loss function converges or tends to be stable, etc.

[0113] The first label and the first training sample can be obtained based on the historical parameter adjustment record. The first training sample can include the CNC machining parameters before adjustment, the estimated comprehensive deviation, the first-level deviation threshold, and the machining progress during the adjustment in the historical parameter adjustment record. The first label can include the adjusted CNC machining parameters corresponding to the first training sample in the historical parameter adjustment record. The historical parameter adjustment record can be constructed based on historical data.

[0114] The verification of candidate processing parameters is the same as that of simulated processing parameters, which can be seen in Figure 2 Related description in the previous article.

[0115] In some embodiments, the industrial Internet of Things management platform can determine the CNC machining parameters of the sub-route of the tool path based on the verification results of the candidate machining parameters.

[0116] The industrial Internet of Things management platform can directly determine the verified candidate processing parameters as the CNC processing parameters of the sub-route.

[0117] When the candidate processing parameters fail to pass the verification, the IIoT management platform can adjust the candidate processing parameters until the adjusted candidate processing parameters pass the verification, and determine the adjusted candidate processing parameters as the CNC processing parameters. The adjustment method for candidate processing parameters is similar to the adjustment method for simulation processing parameters. For related content, please refer to Figure 2 Related description in the previous article.

[0118] In some embodiments, by adjusting the model, the CNC machining parameters can be adjusted in time when the estimated comprehensive deviation exceeds the first-level deviation threshold, effectively avoiding the impact of deviations that may be caused to the workpiece during future machining processes, and helping to improve machining quality.

[0119] Step S230, based on the CNC machining parameters, controlling the CNC machining equipment of the perception control platform to execute the task to be processed.

[0120] In some embodiments, the industrial Internet of Things management platform can interact with the perception control platform based on the sensor network platform to control the CNC machining equipment to perform the processing tasks with CNC machining parameters. For more information about the sensor network platform and the perception control platform, please refer to Figure 1 and its related description.

[0121] Step S240, during the execution of the task to be processed, actual processing data is collected according to the monitoring frequency through the monitoring equipment of the perception control platform.

[0122] For more information about monitoring equipment, see Figure 1 and its related description.

[0123] Monitoring frequency refers to the frequency at which the monitoring equipment collects actual processing data.

[0124] In some embodiments, the monitoring frequency can be obtained in a variety of ways. For example, the higher the rotation speed of the CNC machining equipment, the greater the corresponding monitoring frequency.

[0125] In some embodiments, the industrial Internet of Things management platform can determine the monitoring frequency corresponding to the sub-route based on the estimated error value of the sub-route. For more information, see Figure 3 and its related description.

[0126] The actual processing data refers to the relevant data of the CNC processing equipment during the actual processing. In some embodiments, the actual processing data may include the actual coordinate position of the tool and the actual cutting force of the tool.

[0127] In some embodiments, the IIoT management platform can collect actual processing data according to the monitoring frequency through the monitoring equipment of the perception control platform. For example, the IIoT management platform can obtain the actual coordinate position of the tool through a three-dimensional high-definition camera, motion sensor, etc.; and obtain the actual cutting force of the tool through a pressure sensor, etc. Among them, the IIoT management platform can determine the difference between the collected pressure data and the pressure data in the initial state as the actual cutting force of the tool.

[0128] Step S250, performing deviation judgment on the actual processing data and the simulated processing data.

[0129] Deviation judgment refers to the process of determining the difference between the actual processing data and the simulated processing data. The result of the deviation judgment may include the position deviation of the tool and the cutting force deviation of the tool. The result of the deviation judgment may be used to determine whether to generate a processing alarm instruction. For more information about the processing alarm instruction, please refer to the relevant description of step S260.

[0130] In some embodiments, the industrial Internet of Things management platform can determine the position deviation of the tool based on the difference between the actual coordinate position and the simulated coordinate position; and determine the cutting force deviation of the tool based on the difference between the actual cutting force and the simulated cutting force.

[0131] Step S260 , in response to the result of the deviation judgment satisfying the preset alarm condition: generating a processing alarm instruction, and sending the processing alarm instruction to the alarm device of the user platform.

[0132] The preset alarm condition refers to a preset condition for determining whether to generate a processing alarm instruction. The preset alarm condition can be set by the system or manually. Exemplarily, the preset alarm condition may include: the position deviation exceeds the preset distance threshold and / or the cutting force deviation exceeds the preset force difference threshold. The preset distance threshold and the preset force difference threshold can be preset based on experience. Among them, the preset distance threshold is less than the tolerance information of the target workpiece, so that timely adjustments can be made before the workpiece is scrapped, thereby reducing losses. For example, the preset distance threshold can be 60% of the tolerance information of the target workpiece, etc.

[0133] The processing alarm instruction refers to an instruction for issuing an alarm for CNC processing. In some embodiments, the processing alarm instruction may include position deviation and / or cutting force deviation, current processing progress, and alarm mode. For more information about the current processing progress, please refer to Figure 2 Related description in the previous article.

[0134] The alarm mode refers to the way in which the alarm device issues an early warning. For example, the alarm mode may include highlight display, voice reminder, etc.

[0135] When the result of the deviation judgment meets the preset alarm condition, the industrial Internet of Things management platform can automatically generate a processing alarm instruction based on the result of the deviation judgment. For example, when the processing progress is 20%, the result of the deviation judgment is that the position deviation is 2mm, which exceeds the preset distance threshold. The industrial Internet of Things management platform can generate a processing alarm instruction: the position deviation value of the tool in the current processing part is 2mm, and the current processing progress is 20%. Please use voice reminder for early warning.

[0136] In some embodiments, the industrial Internet of Things management platform can interact with the user platform based on the service platform to send the processing alarm instruction to the alarm device. For more information about the service platform, user platform and alarm device, please refer to Figure 1 and its related description.

[0137] Step S270, based on the actual processing data, controlling the CNC processing equipment to adjust the feed step length.

[0138] In some embodiments, the industrial Internet of Things management platform can control the CNC machining equipment to adjust the feed step length in a variety of ways based on actual machining data.

[0139] In some embodiments, the IIoT management platform may determine the position deviation based on the actual processing data, and adjust the feed step length based on the position deviation. For example, when the position deviation is 0.5 mm, the IIoT management platform may reduce the feed step length by 0.5 mm.

[0140] In some embodiments of the present specification, CNC process simulation is performed based on the information to be processed, CNC processing parameters and simulated processing data corresponding to the CNC processing parameters are determined, and actual processing data is collected during the actual processing. Processing alarm instructions are generated and the feed step length is adjusted based on the results of deviation judgment. This can not only monitor the CNC processing process comprehensively and intelligently, but also issue an alarm and adjust the feed step length at the same time when the position deviation or cutting force deviation does not meet the requirements, thereby ensuring processing quality, reducing production costs, and enhancing the flexibility and applicability of CNC processing.

[0141] In some embodiments, the industrial Internet of Things management platform can generate a three-dimensional model of the product based on actual processing data; extract measurement data of the three-dimensional model of the product; and determine the product processing quality based on the measurement data and product dimension data.

[0142] The product 3D model refers to the 3D model of the target workpiece. In some embodiments, the industrial Internet of Things management platform can determine the actual size of different parts of the target workpiece based on multiple actual coordinate positions of the tool collected by the monitoring device; and reconstruct the workpiece according to the actual size of different parts to obtain the product 3D model.

[0143] The measurement data refers to the dimensional data of different positions of the target workpiece produced by CNC machining. The measurement data can be directly extracted by the system.

[0144] Product dimension data refers to the target dimension information of the target workpiece in the processing drawing information. The industrial Internet of Things management platform can obtain product dimension data based on the processing drawing information.

[0145] Product processing quality refers to the quality of the target workpiece for CNC processing. Product processing quality can be divided into qualified products and unqualified products, and can also be divided into excellent, good, medium, poor and other types.

[0146] In some embodiments, the industrial Internet of Things management platform can determine the product processing quality in a variety of ways based on the measurement data and the product size data. For example, the industrial Internet of Things management platform can determine the product processing quality based on the difference between the measurement data and the product size data and based on the second preset rule. The second preset rule refers to a pre-set rule for determining the product processing quality. For example, the second preset rule may include a corresponding relationship between the difference between the measurement data and the product size data and the product processing quality. The second preset rule may be determined by an expert.

[0147] An exemplary corresponding relationship may be: the smaller the difference between the measurement data and the product size data, the higher the product processing quality. An exemplary corresponding relationship may also be: when the difference between the measurement data and the product size data exceeds the size difference threshold, the product processing quality is unqualified, otherwise it is qualified; the size difference threshold may be preset by the system or manually.

[0148] In some embodiments of the present specification, the product processing quality is determined through the measurement data of the product three-dimensional model and the product size data, the product processing quality can be judged intuitively and accurately, and the intelligent level of CNC processing can be improved.

[0149] Figure 3 It is an exemplary schematic diagram of determining the monitoring frequency of a sub-route in a tool path according to some embodiments of the present specification.

[0150] In some embodiments, the monitoring frequency may include the monitoring frequency of the sub-routes in the tool path; the industrial Internet of Things management platform may divide the tool path 310 to determine the sub-routes 320; determine the estimated error value 340 corresponding to the sub-routes based on the NC machining parameters 330 of the sub-routes; and determine the monitoring frequency 350 of the sub-routes based on the estimated error value 340. For relevant descriptions of tool paths, NC machining parameters, and monitoring frequencies, please refer to Figure 2 and its related description.

[0151] Sub-routes refer to multiple routes obtained after the tool path is divided.

[0152] In some embodiments, the industrial Internet of Things management platform can divide the tool path in a variety of ways to determine sub-routes.

[0153] In some embodiments, the industrial Internet of Things management platform can divide the tool path based on segmentation points, and determine the route between two adjacent segmentation points in the tool path as a sub-route.

[0154] Segmentation points refer to multiple points that segment the tool path. In some embodiments, the segmentation points between sub-paths may include points on the tool path where tools need to be switched during CNC machining. Tools may include tools, gauges, and fixtures, etc. For more information, see Figure 2 Relevant description of step S220.

[0155] In some embodiments, the industrial Internet of Things management platform can determine the curvature 311 of different points on the tool path; determine the curvature change value 312 of two adjacent points; and cluster the points based on the curvature change value 312 to determine the sub-path 320.

[0156] Points refer to the positions of multiple points that make up the tool path.

[0157] In some embodiments, the industrial Internet of Things management platform can calculate the curvature of different points through a curvature formula.

[0158] The curvature change value refers to the change value of the curvature between two adjacent points. In some embodiments, the industrial Internet of Things management platform can calculate the difference between the curvatures of two adjacent points and determine the difference as the curvature change value of the two adjacent points.

[0159] In some embodiments, the industrial Internet of Things management platform can determine the sub-route by clustering the points based on the curvature change value. Exemplary clustering methods may include K-means clustering, hierarchical clustering, etc. Exemplarily, the clustering process may include the following steps S31-S33:

[0160] S31, based on the total length of the tool path, determine the number of cluster centers, that is, the K value.

[0161] In some embodiments, the K value is positively correlated with the total length of the tool path. The longer the total length of the tool path, the greater the K value.

[0162] S32, clustering multiple points on the tool path using a K-means clustering algorithm based on the curvature change value to obtain K clusters, wherein each cluster may include multiple points that are continuous or discontinuous in position.

[0163] S33, determining the routes corresponding to a plurality of consecutive points in each cluster as a sub-route.

[0164] The larger the curvature change value, the more complex the tool path. In some embodiments of this specification, sub-routes are divided based on the curvature change value to ensure that the curvatures of each point in each sub-route are similar, so that the monitoring equipment can monitor the processing process more accurately.

[0165] The NC machining parameters of the sub-route include the NC machining parameters corresponding to the sub-route. For example, the tools, machining sequence, and feed step length used by the sub-route. In some embodiments, the industrial Internet of Things management platform can obtain the NC machining parameters of the sub-route based on the divided sub-routes and the NC machining parameters corresponding to the NC machining process.

[0166] The estimated error value of a sub-route refers to the estimated maximum processing error value when processing the sub-route. In some embodiments, the industrial Internet of Things management platform can determine the estimated error value corresponding to the sub-route in a variety of ways based on the NC processing parameters of the sub-route. For example, the industrial Internet of Things management platform can determine the maximum error value when processing the same sub-route in history with the same NC processing parameters as the estimated error value based on historical data.

[0167] In some embodiments, the industrial Internet of Things management platform can determine the estimated error value based on the error analysis model. For more information, see Figure 4 and its related description.

[0168] In some embodiments, the Industrial Internet of Things management platform can determine the monitoring frequency of the sub-route in a variety of ways based on the estimated error value. Exemplarily, the closer the estimated error value of the sub-route is to the tolerance information corresponding to the target workpiece, the higher the monitoring frequency of the sub-route. In some embodiments, when the estimated error value of the sub-route is not less than the tolerance information, the Industrial Internet of Things management platform can increase the monitoring frequency of the sub-route to the maximum monitoring frequency value that the monitoring device can achieve.

[0169] In some embodiments, the industrial Internet of Things management platform can dynamically adjust the monitoring frequency of the sub-route based on the difference between the estimated comprehensive deviation and the first-level deviation threshold.

[0170] For more information on estimated composite deviation and first-level deviation thresholds, see Figure 2 , Figure 5 Related description.

[0171] In some embodiments, the industrial Internet of Things management platform can adjust the monitoring frequency of the sub-route in a variety of ways based on the difference between the estimated comprehensive deviation and the first-level deviation threshold.

[0172] In some embodiments, when the estimated comprehensive deviation does not exceed the first-level deviation threshold, the smaller the difference between the estimated comprehensive deviation and the first-level deviation threshold, the higher the monitoring frequency of the sub-route. When the estimated comprehensive deviation reaches or exceeds the first-level deviation threshold, the industrial Internet of Things management platform can adjust the monitoring frequency of the sub-route to the maximum monitoring frequency value that the monitoring device can achieve. In some embodiments, the industrial Internet of Things management platform can dynamically obtain the estimated comprehensive deviation, and dynamically adjust the adjustment frequency of the sub-route based on the difference between the estimated comprehensive deviation and the first-level deviation threshold.

[0173] In some embodiments of the present specification, by dynamically adjusting the monitoring frequency by estimating the difference between the deviation value and the first-level deviation threshold, the flexibility of sub-route monitoring can be enhanced, while ensuring comprehensive monitoring of the CNC machining process, the intelligence of CNC machining monitoring is improved.

[0174] In some embodiments of the present specification, by dividing the sub-routes and determining the monitoring frequency of the sub-routes based on the estimated error values ​​of the sub-routes, intelligent monitoring of the CNC machining process is achieved, and the accuracy and flexibility of monitoring can be improved.

[0175] Figure 4 is an exemplary schematic diagram of an error analysis model according to some embodiments of the present specification.

[0176] In some embodiments, the industrial Internet of Things management platform can determine the estimated error value 340 based on the NC machining parameters 330 of the sub-route through the error analysis model 410. For more information about the NC machining parameters and estimated error values ​​of the sub-route, please refer to Figure 3 Related description in the previous article.

[0177] The error analysis model 410 refers to a model for determining the estimated error value of the sub-route. In some embodiments, the error analysis model may be a machine learning model. For example, the error analysis model may be one or any combination of a convolutional neural network (CNN) model, a deep neural network (DNN) model, etc.

[0178] In some embodiments, the error analysis model 410 may include a route feature layer 411 and an error analysis layer 412 .

[0179] The route feature layer refers to a model used to determine sub-route features. In some embodiments, the route feature layer can be a machine learning model. For example, the route feature layer can be a CNN model.

[0180] In some embodiments, the input of the route feature layer may include the sub-route 320 and the NC machining parameters 330 of the sub-route, and the output of the route feature layer may include the sub-route features 420 .

[0181] Sub-route features refer to features related to the sub-route, for example, sub-route features may include the length of the sub-route, the curvature change value corresponding to the sub-route, and the like.

[0182] The error analysis layer refers to a model used to determine the estimated error value. In some embodiments, the error analysis layer can be a machine learning model. For example, the error analysis layer can be a DNN model.

[0183] In some embodiments, the input of the error analysis layer 412 may include sub-route features 420 and an estimated error value 430 of a previous sub-route, and the output of the error analysis layer 412 may include an estimated error value 340 corresponding to the sub-route.

[0184] The previous sub-route refers to the previous sub-route of the current sub-route. It can be understood that the estimated error value of the previous sub-route can affect the estimated error value of the current sub-route, so when determining the estimated error value of the current sub-route, the estimated error value of the previous sub-route needs to be analyzed.

[0185] In some embodiments, the industrial Internet of Things management platform can store the estimated error value of each sub-route determined based on the error analysis model in the data center, and obtain the estimated error value of the previous sub-route of the sub-route through the data center. For the first sub-route, the estimated error value of the previous sub-route input in the error analysis layer can be set to null or an invalid value.

[0186] In some embodiments, the error analysis model can be obtained by jointly training the route feature layer and the error analysis layer.

[0187] In some embodiments, the industrial Internet of Things management platform can obtain an error analysis model 410 based on the training data set training route feature layer 411 and the error analysis layer 412. The training data set may include a second training sample with a second label. The second training sample may include a sample sub-route, a numerical control machining parameter corresponding to the sample sub-route, and an actual error value of a previous sub-route of the sample sub-route. The second label may include an actual error value corresponding to the sample sub-route. The second training sample and the second label may be obtained based on historical data.

[0188] An exemplary joint training process includes: inputting the sample sub-route and the CNC machining parameters corresponding to the sample sub-route into the initial route feature layer to obtain the sub-route features output by the initial route feature layer; inputting the sub-route features output by the initial route feature layer and the actual error value of the previous sub-route of the sample sub-route into the initial error analysis layer to obtain the estimated error value output by the initial error analysis layer. A loss function is constructed based on the second label and the estimated error value output by the initial error analysis layer, and the model parameters of the initial route feature layer and the initial error analysis layer are reversely updated based on the loss function until the trained model meets the preset training conditions, and a trained error analysis model is obtained. Among them, the preset training conditions can be that the loss function is less than a threshold, converges, or the training cycle reaches a threshold. In some embodiments, the method of updating the model parameters may include model training methods such as stochastic gradient descent.

[0189] In some embodiments, the industrial Internet of Things management platform can obtain the comprehensive deviation in the processing process; based on the comprehensive deviation, determine the confidence of the training label (second label) corresponding to the error analysis model in this CNC processing; based on the confidence, update the training data set corresponding to the error analysis model; and based on the updated training data set, update the error analysis model.

[0190] The comprehensive deviation refers to the dimensional deviation of the target workpiece caused by the deformation of the workpiece and the position deviation of the tool during the processing of the sub-route. For the determination of the comprehensive deviation, please refer to Figure 5 and its related description.

[0191] Confidence refers to the credibility of the second label of the error analysis model. In some embodiments, the industrial Internet of Things management platform can determine the confidence through the following steps S41-S44:

[0192] Step S41, obtaining the curvature of different points in the sub-route corresponding to the comprehensive deviation, and constructing the sub-route curvature vector. In some embodiments, each time a sub-route is processed, the industrial Internet of Things management platform can calculate the comprehensive deviation of the workpiece after processing the sub-route. The sub-route curvature vector refers to a vector constructed by the curvature of different points in the sub-route corresponding to the comprehensive deviation.

[0193] Step S42, calculating the curvature of different points of the sample sub-route in each second training sample in the training data set, and constructing a sample sub-route curvature vector.

[0194] Step S43, calculating the similarity between the sub-route curvature vector and the sample sub-route curvature vector, and determining the sample sub-route with a similarity higher than a similarity threshold as a target sample sub-route.

[0195] The industrial Internet of Things management platform can determine the similarity between the sub-route curvature vector and the sample sub-route curvature vector based on various feasible similarity algorithms such as Euclidean distance and cosine similarity. The similarity threshold can be manually preset based on experience or actual conditions. The target sample sub-route refers to the sample sub-route whose corresponding training label needs to be updated.

[0196] Step S44, determining the confidence level.

[0197] In some embodiments, the industrial Internet of Things management platform can determine the confidence level based on the number of target sample sub-routes in the second tag whose actual error value is greater than the comprehensive deviation.

[0198] Exemplarily, the greater the number of target sample subroutes whose actual error values ​​in the second label are greater than the comprehensive deviation, the higher the confidence of the corresponding second label. For example, the confidence of the second label can be determined based on the formula: confidence of the second label = the number of target sample subroutes whose actual error values ​​in the second label are greater than the comprehensive deviation ÷ the total number of target sample subroutes.

[0199] In some embodiments, the industrial Internet of Things management platform can update the training data set corresponding to the error analysis model in a variety of ways based on the confidence level. For example, the industrial Internet of Things management platform can replace the actual error value of the second label corresponding to the target sample sub-route in the training data set with the comprehensive deviation when the confidence level of the second label is less than the confidence threshold. The confidence threshold can be manually preset based on experience or actual conditions.

[0200] In some embodiments, the industrial Internet of Things management platform can update and train the error analysis model based on the updated training data set. It can be understood that when the estimated error value predicted by the error analysis model is inaccurate, the error analysis model needs to be updated and trained, and the estimated error value is predicted again using the updated and trained error analysis model. Among them, when the monitoring frequency determined based on the estimated error value is unreasonable (for example, the difference between the monitoring frequency and the historical average monitoring frequency exceeds the frequency difference threshold, etc.), the industrial Internet of Things management platform can determine that the estimated error value predicted by the error analysis model is inaccurate. The frequency difference threshold can be preset by the system or manually. The historical average monitoring frequency can be obtained based on statistics of historical data.

[0201] When the industrial Internet of Things management platform uses the updated trained error analysis model to predict the estimated error value again, the estimated error value of the previous sub-route input by the error analysis layer can be the actual error value of the previous sub-route of this processing.

[0202] In some embodiments of the present specification, the confidence of the training label is evaluated based on the comprehensive deviation in the processing process, and the training data set of the error analysis model is updated by the confidence, thereby updating the training error analysis model, which helps to increase the prediction accuracy of the error analysis model and thus improve production efficiency and processing quality.

[0203] In some embodiments of the present specification, the estimated error value of the sub-route is predicted by the error analysis model, and the self-learning ability of the machine learning model can be used to find patterns from a large amount of data, which helps to quickly and accurately determine the monitoring frequency of the sub-route.

[0204] Figure 5 It is an exemplary schematic diagram of generating a processing alarm instruction according to some embodiments of the present specification.

[0205] In some embodiments, the deviation judgment may include single-point deviation judgment and multi-point deviation judgment, and the processing alarm instruction includes a first-level alarm instruction 541 and a second-level alarm instruction 542 .

[0206] A level one alarm command is a command that causes an alarm device to sound a level one alarm.

[0207] A level 2 alarm command is a command that causes an alarm device to sound a level 2 alarm.

[0208] Among them, the alarm level of the first alarm is higher than that of the second alarm. When the alarm device issues a first alarm, it means that the target workpiece has a high risk of unqualified quality; when the alarm device issues a second alarm, it means that the target workpiece has a certain risk of unqualified quality.

[0209] Single point deviation judgment refers to judging the position deviation of a single processing point. In some embodiments, single point deviation judgment may include: in response to the position deviation 520 of the tool corresponding to the single processing point exceeding the first level deviation threshold, judging that the position of the tool is abnormal and generating a first level alarm instruction.

[0210] The position deviation is the deviation between the actual coordinate position 511 of the tool and the corresponding simulated coordinate position 512. The industrial Internet of Things management platform can determine the coordinate distance between the actual coordinate position and the corresponding simulated coordinate position as the position deviation. For more information about the actual coordinate position, simulated coordinate position and the first-level deviation threshold, please refer to Figure 2 and its related description.

[0211] In some embodiments, the first level deviation threshold may be preset by a technician. It should be noted that the first level deviation threshold is less than the tolerance information of the target workpiece. For example, the first level deviation threshold may be 80% of the tolerance information of the target workpiece.

[0212] In some embodiments, the industrial Internet of Things management platform can determine the historical processing task retrieved from the historical data and having the highest similarity to the task to be processed as the reference processing task based on the information to be processed; and determine the primary deviation threshold based on the statistical value of the historical deformation data of the workpiece to be processed in the reference processing task during the historical processing process, and the tolerance information of the target workpiece. The historical deformation data refers to the deformation data of the workpiece to be processed in the reference processing task during the historical processing process, and can be obtained based on the historical data.

[0213] For more information about deformation data, see Figure 5 The relevant description is as follows. The statistical value of the historical deformation data may include the mean value, variance, etc. of the historical deformation data. The larger the statistical value of the historical deformation data is, the smaller the corresponding first-level deviation threshold is.

[0214] Exemplarily, the primary deviation threshold may be determined by the following formula: primary deviation threshold=tolerance information-(mean of historical deformation data+variance of historical deformation data).

[0215] In some embodiments, the IIoT management platform can determine that the position of the tool is abnormal and generate a first-level alarm instruction when the position deviation exceeds the first-level deviation threshold. For example, when the position deviation is 2mm and the first-level deviation threshold is 1mm, the IIoT management platform can generate a first-level alarm instruction: "The position of the tool is abnormal, and the target workpiece has a high risk of unqualified quality. Please issue a first-level alarm. The content of the first-level alarm is: highlight the position deviation of 1mm in red, and give three voice reminders at the maximum volume."

[0216] In some embodiments, the industrial Internet of Things management platform can obtain a pressure data sequence based on the pressure sensor of the perception control platform; determine the deformation data of the workpiece to be processed based on the pressure data sequence; determine the comprehensive deviation based on the deformation data and position deviation; in response to the comprehensive deviation exceeding the first-level deviation threshold, determine that the processing error is abnormal and generate a first-level alarm instruction. For relevant instructions on the perception control platform and pressure sensors, please refer to Figure 1 and its related description.

[0217] A pressure data sequence refers to a sequence composed of multiple pressure data. In some embodiments, the industrial Internet of Things management platform can construct multiple pressure data during a tool cutting a circle into a pressure data sequence.

[0218] The deformation data refers to the data related to the deformation of the workpiece to be processed. For example, the deformation data may include the deformation values ​​of the workpiece to be processed in different directions.

[0219] In some embodiments, the industrial Internet of Things management platform can determine the deformation data of the workpiece to be processed in a variety of ways based on the pressure data sequence.

[0220] In some embodiments, the industrial Internet of Things management platform can calculate the difference between the pressure data in two corresponding directions in the pressure data sequence, and determine the deformation data of the workpiece to be processed in this direction based on the difference in the pressure data. The corresponding directions refer to the directions where the workpiece to be processed is located at both ends of the same diameter. For example, the 90° direction and the 270° direction of the cross section of the workpiece to be processed are corresponding directions. The difference between the degrees corresponding to the two corresponding directions is 180°.

[0221] In some embodiments, the industrial Internet of Things management platform may determine the ratio of the pressure data change value to the initial value of the pressure data and the sum of the diameter of the current cross section as the deformation data in that direction. The deformation direction refers to the direction in which the pressure data is larger in the corresponding direction. The initial value of the pressure data refers to the pressure value of the tool cutting the workpiece to be processed when no deformation occurs. The industrial Internet of Things management platform may determine the mean of all pressures in the pressure data sequence as the initial value of the pressure data. The pressure data change value refers to the change value of the pressure data of the tool cutting the workpiece to be processed relative to the initial value of the pressure data. The industrial Internet of Things management platform may determine half of the difference between the pressure data in two corresponding directions in the pressure data sequence as the corresponding pressure data change value.

[0222] The comprehensive deviation refers to the dimensional deviation of the target workpiece caused by the deformation of the workpiece to be processed and the position deviation of the tool when processing the sub-route. In some embodiments, the industrial Internet of Things management platform can determine the comprehensive deviation based on the deformation data, the position deviation, and the geometric law.

[0223] Exemplarily, if the position deviation direction of the tool is in a straight line with the deformation deviation direction of the workpiece to be processed, and the deviation directions of the two are opposite, the industrial Internet of Things management platform can determine the sum of the position deviation of the tool and the deformation deviation of the workpiece to be processed as the comprehensive deviation; if the position deviation direction of the tool is in a straight line with the deformation deviation direction of the workpiece to be processed, and the deviation directions of the two are the same, the industrial Internet of Things management platform can determine the difference between the position deviation of the tool and the deformation deviation of the workpiece to be processed as the comprehensive deviation. For example, the position deviation of the tool is 0.1mm offset in the 0° direction, and the deformation data of the workpiece to be processed is 0.2mm deformed in the 180° direction, then the comprehensive deviation is 0.3mm, and the direction of the comprehensive deviation is in the 180° direction. For another example, the position deviation of the tool is 0.1mm offset in the 90° direction, and the deformation data of the workpiece to be processed is 0.2mm deformed in the 90° direction, then the comprehensive deviation is 0.1mm, and the direction of the comprehensive deviation is in the 90° direction. When the position deviation direction of the tool is not in a straight line with the deformation direction of the workpiece to be processed, the industrial Internet of Things management platform can determine the comprehensive deviation and the corresponding deviation direction based on other geometric laws such as the Pythagorean theorem.

[0224] In some embodiments, in response to the comprehensive deviation exceeding the first-level deviation threshold, the industrial Internet of Things management platform can determine that the processing error is abnormal and generate a first-level alarm instruction. For example, if the comprehensive deviation is 0.3mm and the first-level deviation threshold is 0.1mm, the industrial Internet of Things management platform can generate a first-level alarm instruction: "The processing error is abnormal, and the target workpiece has a high risk of unqualified quality. Please issue a first-level alarm. The content of the first-level alarm is: highlight the comprehensive deviation of 0.3mm in red, and give three voice reminders at the maximum volume."

[0225] In some embodiments of the present specification, single-point deviation judgment is performed based on comprehensive deviation, and abnormal conditions of CNC machining can be judged in combination with tool position and deformation of the workpiece to be machined. This can increase comprehensive monitoring of CNC machining, improve machining accuracy, and improve production efficiency.

[0226] Multi-point deviation judgment refers to judging the deviation of multiple consecutive processing points. In some embodiments, the multi-point deviation judgment may include: in response to the position deviation being between the primary deviation threshold and the secondary deviation threshold, based on the deviation point ratio 530, performing multi-level judgment, the multi-level judgment includes: in response to the deviation point ratio exceeding the primary ratio threshold, judging that the position of the tool is abnormal and generating a primary alarm instruction; in response to the deviation point ratio being lower than the primary ratio threshold and higher than the secondary ratio threshold, judging that the position of the tool is abnormal and generating a secondary alarm instruction.

[0227] The secondary deviation threshold refers to a preset threshold related to the deviation of the target workpiece, and the secondary deviation threshold is smaller than the primary deviation threshold. The secondary deviation threshold can be preset by a technician.

[0228] In some embodiments, the industrial Internet of Things management platform can count the mean and variance of the processing errors of multiple historical target processed parts with qualified processing quality in the reference processing tasks, and determine the difference between the mean and variance as the secondary deviation threshold. For the determination of the reference processing tasks, please refer to Figure 5 Related description in the previous article.

[0229] The deviation point ratio refers to the ratio of the number of processing points whose position deviation is between the first-level deviation threshold and the second-level deviation threshold to the total number of processing points after the start of processing.

[0230] The primary ratio threshold and the secondary ratio threshold are both threshold conditions for determining whether to generate a processing alarm instruction based on the deviation point ratio, and the secondary ratio threshold is lower than the primary ratio threshold.

[0231] In some embodiments, the industrial Internet of Things management platform can count the average of the ratio of the number of processing points whose position deviations are between the first-level deviation threshold and the second-level deviation threshold among the defective products of the reference processing tasks to the total number of processing points, and determine the average as the first-level ratio threshold.

[0232] In some embodiments, the industrial Internet of Things management platform can count the mean and variance of the ratio of the number of processing points whose position deviation is between the first-level deviation threshold and the second-level deviation threshold to the total number of processing points among the qualified products of the reference processing tasks, and determine the difference between the mean and variance of the ratio as the second-level ratio threshold.

[0233] In some embodiments, in response to the deviation point ratio being lower than the primary ratio threshold and higher than the secondary ratio threshold, the industrial Internet of Things management platform may determine that the position of the tool is abnormal and generate a secondary alarm instruction. For example, the industrial Internet of Things management platform may generate a secondary alarm instruction "The position of the tool is abnormal, and there is a certain risk that the target workpiece will be unqualified. Please issue a secondary alarm. The content of the secondary alarm is: highlight the abnormal position of the tool in blue and give a voice reminder at a medium volume."

[0234] In some embodiments of the present specification, single-point deviation judgment and multi-point deviation judgment can be used to comprehensively judge the position of the tool based on one processing point or multiple processing points, thereby improving the applicability and accuracy of deviation judgment and helping to generate more accurate processing alarm instructions; by grading the processing alarm instructions, the staff can flexibly determine a more suitable adjustment method according to the processing alarm instructions of different levels, thereby improving the flexibility and applicability of CNC processing.

[0235] In some embodiments of the present specification, the processing alarm instruction also includes a warning instruction. The industrial Internet of Things management platform can obtain temperature data of the surface of the workpiece to be processed based on a temperature sensor; predict future deformation data based on a temperature data sequence and a pressure data sequence; determine an estimated position deviation of a sub-route based on an estimated error value; determine an estimated comprehensive deviation based on future deformation data and the estimated position deviation; and generate a warning instruction in response to the estimated position deviation exceeding a first-level deviation threshold.

[0236] Temperature data refers to data related to the temperature of the surface of the workpiece to be processed. The Industrial Internet of Things management platform can collect temperature data of the surface of the workpiece to be processed based on temperature sensors.

[0237] Temperature data sequence refers to the sequence of temperature data during the processing process.

[0238] The future deformation data refers to the deformation data of the workpiece to be processed in the next processing process. The next processing process includes the unfinished processing process in the current sub-route, and may also include the processing process of the next sub-route.

[0239] In some embodiments, the industrial Internet of Things management platform can predict future deformation data in a variety of ways based on temperature data sequences and pressure data sequences.

[0240] The Industrial Internet of Things management platform can construct a deformation prediction vector based on the temperature data sequence, pressure data sequence, workpiece information and CNC machining parameters; based on the deformation prediction vector, the historical deformation vector with the highest similarity to the deformation prediction vector in the deformation vector database is used as the reference deformation vector; the deformation data corresponding to the reference deformation vector and the deformation data corresponding to the next sub-route are determined as future deformation data. For more information about workpiece information and CNC machining parameters, please refer to Figure 2 and its related description.

[0241] The deformation vector database may include historical deformation vectors constructed based on historical temperature data sequences, historical pressure data sequences, historical workpiece information, and historical CNC machining parameters, as well as deformation data corresponding to the historical deformation vectors and deformation data corresponding to the next sub-route. The deformation vector database may be constructed based on historical data and stored in the data center. For more information about the data center, please refer to Figure 1 and its description.

[0242] The estimated position deviation refers to the position deviation of the tool in the subsequent processing process. In some embodiments, the industrial Internet of Things management platform can determine the estimated position deviation in a variety of ways based on the estimated error value. For relevant instructions on the estimated error value, see Figure 3 and its related description.

[0243] For example, the industrial Internet of Things management platform can determine the difference between the estimated error value and the historical average deformation data as the estimated position deviation. The historical average deformation data refers to the average value of the historical deformation data corresponding to the processing of the historical sub-route, which can be obtained based on the statistics of the historical data.

[0244] The estimated comprehensive deviation refers to the deviation in size of the target workpiece caused by the deformation of the workpiece to be processed and the position deviation of the tool during the future processing sub-route. The Industrial Internet of Things Management Platform can determine the estimated comprehensive deviation based on future deformation data and estimated position deviation. The method for determining the estimated comprehensive deviation is similar to that for determining the comprehensive deviation. For related content, please refer to Figure 5 Related description in the previous article.

[0245] Early warning instructions refer to instructions related to early warning of future processing processes. In some embodiments, in response to the estimated position deviation exceeding the first-level deviation threshold, the industrial Internet of Things management platform can generate an early warning instruction. For example, when the estimated position deviation exceeds the first-level deviation threshold, the industrial Internet of Things management platform can generate an early warning instruction: "The position deviation in the next processing process may exceed the first-level deviation threshold, please issue an early warning."

[0246] Temperature can change the strength of the workpiece to be processed, thereby affecting the deformation data. In some embodiments of this specification, future deformation data is predicted in combination with temperature data, and then the estimated comprehensive deviation is determined, which can predict the comprehensive deviation in the future processing process in advance, provide early warning, and improve the intelligence and accuracy of CNC processing.

[0247] Furthermore, certain features, structures or characteristics in one or more embodiments of this specification may be appropriately combined.

[0248] 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.

[0249] If there is any inconsistency or conflict between the descriptions, definitions, and / or usage of terms in the materials cited in this specification and the contents described in this specification, the descriptions, definitions, and / or usage of terms in this specification shall prevail.

Claims

1. An intelligent monitoring method for CNC machining based on industrial Internet of Things, characterized in that: The method is executed by an industrial Internet of Things management platform, and includes: Based on the input device of the perception control platform, the processing information corresponding to the processing task is obtained; Performing numerical control process simulation based on the information to be processed, determining numerical control processing parameters and simulated processing data corresponding to the numerical control processing parameters, wherein the numerical control processing parameters include a feed step length and a tool path; Based on the CNC machining parameters, controlling the CNC machining equipment of the perception control platform to execute the task to be processed; During the execution of the task to be processed, actual processing data is collected according to a monitoring frequency through the monitoring device of the perception control platform, wherein the monitoring frequency includes the monitoring frequency of the sub-paths in the tool path, and determining the monitoring frequency includes: Dividing the tool path to determine sub-paths; Based on the numerical control machining parameters of the sub-route, determining an estimated error value corresponding to the sub-route, wherein the estimated error value is an estimated maximum machining error value when machining the sub-route; Based on the estimated error value, determining the monitoring frequency of the sub-route, wherein the closer the estimated error value is to the tolerance information corresponding to the target workpiece, the higher the monitoring frequency is, and when the estimated error value is not less than the tolerance information, the monitoring frequency is increased to the maximum monitoring frequency value that the monitoring device can achieve; Performing deviation judgment on the actual processing data and the simulated processing data; In response to the result of the deviation judgment meeting the preset alarm condition: Generate a processing alarm instruction, and send the processing alarm instruction to an alarm device of a user platform; Based on the actual processing data, the numerical control processing equipment is controlled to adjust the feed step length.

2. The method according to claim 1, characterized in that The performing of numerical control process simulation based on the information to be processed and determining numerical control processing parameters and corresponding simulation processing data comprises: Based on the information to be processed, generating simulation processing parameters; Based on the simulated machining parameters and in accordance with programming rules, a numerical control machining program is generated; Simulating the numerical control machining program and recording the simulated machining data; Based on the simulated processing data, verifying the simulated processing parameters; Based on the verification result of the simulation processing parameter, the numerical control processing parameter and the simulation processing data corresponding to the numerical control processing parameter are determined.

3. The method according to claim 1, characterized in that The numerical control machining parameters include a tool, the simulated machining data include a simulated coordinate position of the tool, the actual machining data include an actual coordinate position of the tool, the deviation judgment includes a single-point deviation judgment and a multi-point deviation judgment, and the machining alarm instruction includes a first-level alarm instruction and a second-level alarm instruction; The single-point deviation judgment includes: in response to the position deviation of the tool exceeding the first-level deviation threshold, determining that the position of the tool is abnormal and generating the first-level alarm instruction, the position deviation being the deviation between the actual coordinate position of the tool and the corresponding simulated coordinate position; The multi-point deviation judgment includes: in response to the position deviation being between the first-level deviation threshold and the second-level deviation threshold, based on the deviation point ratio, performing a multi-level judgment, the second-level deviation threshold being less than the first-level deviation threshold, the multi-level judgment includes: In response to the deviation point ratio exceeding the first-level ratio threshold, determining that the position of the tool is abnormal and generating the first-level alarm instruction; In response to the deviation point ratio being lower than the primary ratio threshold and higher than the secondary ratio threshold, the tool position is judged to be abnormal and the secondary alarm instruction is generated; the secondary ratio threshold is lower than the primary ratio threshold.

4. The method according to claim 1, characterized in that The method further comprises: Based on the actual processing data, a three-dimensional model of the product is generated; Extracting measurement data of the three-dimensional model of the product; Based on the measurement data and product dimension data, the product processing quality is determined.

5. An intelligent monitoring system for CNC machining based on industrial Internet of Things, characterized in that: The system includes a user platform, a service platform, an industrial Internet of Things management platform, a sensor network platform and a perception control platform. The industrial Internet of Things management platform includes a production process management sub-platform, a data center and an equipment management sub-platform. The industrial Internet of Things management platform is configured as follows: Based on the input device of the perception control platform, obtaining the to-be-processed information corresponding to the to-be-processed task; Performing numerical control process simulation based on the information to be processed, determining numerical control processing parameters and simulated processing data corresponding to the numerical control processing parameters, wherein the numerical control processing parameters include a feed step length and a tool path; Based on the CNC machining parameters, controlling the CNC machining equipment of the perception control platform to execute the task to be processed; During the execution of the task to be processed, actual processing data is collected according to a monitoring frequency through the monitoring device of the perception control platform, wherein the monitoring frequency includes the monitoring frequency of the sub-paths in the tool path, and determining the monitoring frequency includes: Dividing the tool path to determine sub-paths; Based on the numerical control machining parameters of the sub-route, determining an estimated error value corresponding to the sub-route, wherein the estimated error value is an estimated maximum machining error value when machining the sub-route; Based on the estimated error value, determining the monitoring frequency of the sub-route, wherein the closer the estimated error value is to the tolerance information corresponding to the target workpiece, the higher the monitoring frequency is, and when the estimated error value is not less than the tolerance information, the monitoring frequency is increased to the maximum monitoring frequency value that the monitoring device can achieve; Performing deviation judgment on the actual processing data and the simulated processing data; In response to the result of the deviation judgment meeting the preset alarm condition: generating a processing alarm instruction, and sending the processing alarm instruction to an alarm device of the user platform; Based on the actual processing data, the numerical control processing equipment is controlled to adjust the feed step length.

6. The system according to claim 5, characterized in that The industrial Internet of Things management platform is further configured to: Based on the information to be processed, generating simulation processing parameters; Based on the simulated machining parameters and in accordance with programming rules, a numerical control machining program is generated; Simulating the numerical control machining program and recording the simulated machining data; Based on the simulated processing data, verifying the simulated processing parameters; Based on the verification result of the simulation processing parameter, the numerical control processing parameter and the simulation processing data corresponding to the numerical control processing parameter are determined.

7. The system according to claim 5, characterized in that The numerical control machining parameters include a tool, the simulated machining data include a simulated coordinate position of the tool, the actual machining data include an actual coordinate position of the tool, the deviation judgment includes a single-point deviation judgment and a multi-point deviation judgment, and the machining alarm instruction includes a first-level alarm instruction and a second-level alarm instruction; The industrial Internet of Things management platform is further configured to perform the single-point deviation judgment and the multi-point deviation judgment: The single-point deviation judgment includes: in response to the position deviation of the tool exceeding the first-level deviation threshold, determining that the position of the tool is abnormal and generating the first-level alarm instruction, the position deviation being the deviation between the actual coordinate position of the tool and the corresponding simulated coordinate position; The multi-point deviation judgment includes: in response to the position deviation being between the first-level deviation threshold and the second-level deviation threshold, based on the deviation point ratio, performing a multi-level judgment, the second-level deviation threshold being less than the first-level deviation threshold, the multi-level judgment includes: In response to the deviation point ratio exceeding the first-level ratio threshold, determining that the position of the tool is abnormal and generating the first-level alarm instruction; In response to the deviation point ratio being lower than the primary ratio threshold and higher than the secondary ratio threshold, the tool position is judged to be abnormal and the secondary alarm instruction is generated; the secondary ratio threshold is lower than the primary ratio threshold.

8. The system according to claim 5, characterized in that The industrial Internet of Things management platform is further configured to: Based on the actual processing data, a three-dimensional model of the product is generated; Extracting measurement data of the three-dimensional model of the product; Based on the measurement data and product dimension data, the product processing quality is determined.

Images