Intelligent data control method and system for numerical control machine tool equipment

Abstract

The application relates to an intelligent data control method and system of a numerical control machine tool device, and an integrated hardware architecture of a high-precision off-machine tool setting gauge, an intelligent tool management cabinet, a CNC data gateway and a cloud data processing center is constructed. Tool size and wear precision measurement is completed off-machine and offline, compensation parameters are automatically generated after virtual interference simulation verification and are sent to the machine tool, and production change zero debugging is realized; RFID / visual is used to assign a unique identity to the tool, automatic registration, dynamic counting, life grading early warning and machine tool forced locking are realized; data gateway is used to collect machine tool operation, tool wear and processing quality inspection data in real time, a tool-machine tool-processing batch-size quality inspection strong correlation database is established, and quality root causes can be traced in reverse; meanwhile, a dynamic life threshold, process parameter sedimentation reuse and size drift prediction function are additionally added, and the industry pain points of time consumption of existing small-batch processing production change debugging, extensive tool management, data island and dependence on manual experience are solved.

Description

Technical Field

[0001] This invention relates to the technical field of CNC machine tool control, and in particular to an intelligent data control method and system for CNC machine tool equipment. Background Technology

[0002] Currently, the precision parts processing industry, which focuses on non-standard customization and small-batch production of various products, generally faces the following technical bottlenecks:

[0003] 1. Extremely low efficiency in changeover and debugging: Current technologies mostly employ in-machine tool setting. Each time a new product is introduced, the operator must enter the machine tool for a lengthy process of tool setting, trial cutting, and measurement, typically taking 30-60 minutes, severely impacting the machine tool's effective production time. For small-batch orders, this excessively high debugging time leads to low equipment utilization.

[0004] 2. Lack of data support for tool management: Currently, tool wear management mainly relies on manual experience, lacking accurate service life data. This often leads to the scrapping of batches of parts due to tool wear, or the waste of tool materials due to premature replacement, resulting in high hidden costs.

[0005] 3. Severe data silos in production: Processing parameters, tool wear, and product quality inspection data are independent of each other, lacking a unified big data platform. Once a customer complaint or dimensional deviation occurs, management finds it difficult to quickly pinpoint whether the problem lies with the equipment, the tool, or the operating parameters, leading to difficulties in traceability.

[0006] 4. Reliance on manual experience and lack of standardization: Core process parameters depend on the "feel" of the operator, the training period for new employees is long, and the stability of parameters is difficult to guarantee, which affects the consistency of product quality.

[0007] To address the aforementioned shortcomings, this invention proposes a novel intelligent solution. Summary of the Invention

[0008] In view of the deficiencies in the prior art, the present invention provides an intelligent data control method for CNC machine tool equipment, the method comprising:

[0009] After receiving the order processing information, it sends a feedback message to the cloud data processing center.

[0010] Send control commands to the intelligent tool management cabinet to obtain available target tools;

[0011] The receiver receives the tool setting parameters fed back by the external tool setting device, and collects the precise measurement data of the target tool;

[0012] After the tool setting parameters are fed back to the CNC machine tool, machining begins.

[0013] It receives uploaded processing status data in real time and builds an associated database.

[0014] Correspondingly, the present invention provides an intelligent data control device for CNC machine tool equipment, including,

[0015] The order management module is used to receive order processing information and then send it back to the cloud data processing center.

[0016] The tool management module is used to send control commands to the intelligent tool management cabinet to obtain available target tools;

[0017] The tool setting management module is used to receive tool setting parameters fed back by an external tool setting device and collect accurate measurement data of the target tool.

[0018] The parameter feedback module is used to feed back the tool setting parameters to the CNC machine tool before machining begins;

[0019] The database construction module is used to receive uploaded processing status data in real time and build associated databases.

[0020] Furthermore, the step of issuing control commands to the intelligent tool management cabinet to obtain available target tools includes:

[0021] The target tool is located using its unique identification code.

[0022] The system retrieves the target tool from the intelligent tool cabinet and automatically records the target tool's ID, corresponding order number, and machining station number, and establishes an initial lifespan count.

[0023] Correspondingly, the tool management module includes:

[0024] The tool locking unit is used to lock the target tool using its unique identification code.

[0025] The tool retrieval unit is used to retrieve the target tool from the intelligent tool cabinet, and automatically record the ID, corresponding order number, and processing station number of the target tool, and establish an initial life count.

[0026] Furthermore, the steps for receiving the tool setting parameters from the external tool setting device include:

[0027] The initial tool setting parameters for the target tool are sent to the tool setting device;

[0028] Obtain the precise length compensation value and radius compensation value of the target tool;

[0029] A standardized NC compensation program is generated by the tool generator;

[0030] The system algorithm is invoked to perform virtual simulation verification.

[0031] Correspondingly, the tool setting management module includes:

[0032] The tool setting parameter sending unit is used to send the initial tool setting parameters of the target tool to the tool setting device;

[0033] The compensation acquisition unit is used to acquire the precise length compensation value and radius compensation value of the target tool;

[0034] The compensation program generation unit is used to generate standardized NC compensation programs through the tool setter;

[0035] The simulation verification unit is used to call the system algorithm to perform virtual simulation verification.

[0036] Furthermore, the step of feeding back the tool setting parameters to the CNC machine tool and then starting machining includes:

[0037] The pre-adjusted target tool is loaded into the CNC machine tool, and the compensation parameters corrected by artificial intelligence are obtained;

[0038] The number of processed parts is accumulated in real time during the processing process;

[0039] Determine whether the number of times the target tool has been processed has reached the target tool life threshold; if it reaches 80% of the target tool life threshold, an early warning signal is automatically pushed to prompt preparation to replace the spare tool; if it reaches the target tool life threshold, the machine tool is automatically locked or its use is forcibly prohibited.

[0040] Correspondingly, the parameter feedback module includes:

[0041] The offline compensation acquisition unit is used to load the pre-adjusted target tool into the CNC machine tool and acquire the compensation parameters corrected by artificial intelligence.

[0042] The counting unit is used to accumulate the number of processed parts in real time during the processing.

[0043] The lifespan determination unit is used to determine whether the number of times the target tool has been processed has reached the target tool lifespan threshold. If it reaches 80% of the target tool lifespan threshold, an early warning signal is automatically pushed to prompt the replacement of the spare tool. If the target tool lifespan threshold is reached, the machine tool is automatically locked or its use is forcibly prohibited.

[0044] Furthermore, the step of uploading processing status data in real time includes:

[0045] The spindle load, vibration value, and machining parameters of the CNC machine tool are collected through a data gateway, as well as the real-time wear data fed back by the external tool setter.

[0046] Establish a strongly correlated database of tool number, machining batch, dimensional inspection result, and machine tool number;

[0047] Determine if there are dimensional errors in the product processing; if so, record the corresponding tool information, tool parameters and wear amount, and CNC machine tool spindle status.

[0048] An analysis command is sent to the cloud data processing center to perform further analysis and determine the cause of the processing error, and then an analysis report is generated.

[0049] Correspondingly, the database management module includes:

[0050] The data acquisition unit is used to acquire the spindle load, vibration value, machining parameters of the CNC machine tool, and real-time wear data fed back by the external tool setter through the data gateway.

[0051] The database construction unit is used to establish a strongly correlated database of tool number, machining batch, dimensional inspection result, and machine tool number;

[0052] The quality inspection judgment unit is used to determine whether the product processing has dimensional deviations; if so, it records the corresponding tool information, tool parameters and wear amount, and CNC machine tool spindle status.

[0053] The report generation unit is used to send analysis instructions to the cloud data processing center, so that it can perform further analysis and judgment on the cause of the processing error and generate an analysis report.

[0054] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0055] This invention provides an intelligent data control method for CNC machine tools, the method comprising:

[0056] Receive order processing information and build an associated database of orders, equipment, tools, and products; send control commands to the intelligent tool management cabinet to obtain the storage, requisition, and return tracking of available target tools, record the ID, usage count, and lifespan status of each tool, and identify the target tool; collect accurate measurement data of the length, diameter, and wear of the target tool; after receiving tool setting parameter instructions, start processing and upload processing status data in real time.

[0057] Secondly, the present invention also provides an intelligent data control device for CNC machine tool equipment, including a data processing module for receiving order processing information and constructing an associated database of order-equipment-tool-product;

[0058] The intelligent tool management module receives control commands to track the storage, requisition, and return of available target tools, records the ID, usage count, and lifespan status of each tool, and identifies the target tool. The external tool setting module collects precise measurement data of the length, diameter, and wear of the target tool. The data acquisition module receives tool setting parameter instructions, starts machining, and uploads machining status data in real time.

[0059] This invention provides an intelligent CNC data control method and system that integrates offline tool setting, intelligent tool life management, and real-time production data tracking, aiming to significantly improve the efficiency of small-batch customized processing, reduce costs, and ensure quality traceability.

[0060] Compared with the prior art, the present invention has the following significant advantages:

[0061] 1. Maximize production efficiency: By off-machine tool setting, the debugging process that originally occupied machine tool time is transferred to offline, reducing the changeover time of a single batch by more than 60% and significantly improving the delivery capability of small batch orders.

[0062] 2. Intelligent cost reduction and efficiency improvement: Data-driven tool life management avoids the waste of consumables caused by blind tool replacement, and eliminates batch scrapping due to tool aging, reducing tool costs by 15%-20%.

[0063] 3. Full-process quality control and traceability: Breaking down information silos, enabling data-driven and visualized processing. A complete quality archive has been established, solving the industry problem of "not being able to trace problems" in non-standard small-batch processing.

[0064] 4. Build up process assets and reduce reliance on talent: Transform human experience into a standardized parameter library that can be executed by machines. New employees can directly call mature parameters for processing, which will significantly reduce training costs and enhance the company's core competitiveness. Attached Figure Description

[0065] Figure 1 A flowchart illustrating an embodiment of an intelligent data control method for CNC machine tool equipment;

[0066] Figure 2 To Figure 1 Flowchart of the improved method in the middle;

[0067] Figure 3 To Figure 1 Flowchart of the improved method in the middle;

[0068] Figure 4 To Figure 1 Flowchart of the improved method in the middle;

[0069] Figure 5 To Figure 1 Flowchart of the improved method in the Chinese method.

[0070] Figure 6 This is a structural diagram of an intelligent data control device for a CNC machine tool provided in one embodiment;

[0071] Figure 7 To Figure 6 A structural diagram of the tool management module in the system;

[0072] Figure 8 To Figure 6 Structure diagram of the tool setting management module in the system;

[0073] Figure 9 To Figure 6 The structural diagram of the parameter feedback module in the middle;

[0074] Figure 10 To Figure 6 The structure diagram of the database building module in the document. Detailed Implementation

[0075] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0076] The terms "first," "second," "third," "fourth," etc. (if present) in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein.

[0077] It should be understood that in the various embodiments of the present invention, the sequence number of each process does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0078] It should be understood that in this invention, "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to such process, method, product, or device.

[0079] It should be understood that in this invention, "multiple" refers to two or more. "And / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, "and / or B" can represent: A existing alone, A and B existing simultaneously, and B existing alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "Contains A, B, and C", "Contains A, B, and C" means that all three A, B, and C are contained; "Contains A, B, or C" means that one of A, B, and C is contained; "Contains A, B, and / or C" means that any one, two, or three of A, B, and C are contained.

[0080] It should be understood that in this invention, "B corresponding to A", "B corresponding to A", "A and B correspond", or "B and A correspond" means that B is associated with A, and B can be determined based on A. Determining B based on A does not mean determining B solely based on A; B can also be determined based on A and / or other information. Matching A and B is defined as a similarity between A and B that is greater than or equal to a preset threshold.

[0081] Depending on the context, "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection."

[0082] The technical solution of the present invention will be described in detail below with reference to specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0083] Example 1

[0084] like Figure 1 As shown, an intelligent data control method for CNC machine tool equipment includes:

[0085] S1. After receiving the order processing information, send it back to the cloud data processing center;

[0086] S2. Send a control command to the intelligent tool management cabinet to obtain available target tools;

[0087] S3. Receive the tool setting parameters fed back by the external tool setting device and collect the accurate measurement data of the target tool;

[0088] S4. After feeding back the tool setting parameters to the CNC machine tool, machining begins.

[0089] S5. Receive the uploaded processing status data in real time and build a related database.

[0090] It needs to be further explained that, The aforementioned intelligent data control method also includes a process display of intelligent data control; All operational steps will be displayed on the factory's display terminal. .

[0091] It should also be noted that the intelligent tool management cabinet stores various models of usable tools. (System) Control commands are sent to the intelligent tool management cabinet via wireless or wired connection to retrieve a specific target tool. This can be achieved using a robotic arm, or by manually removing the target tool and placing it on a transport robot for further transport. The feed is transported to the lathe, and finally, the target tool can be installed in a specific position on the CNC machine tool using either a robotic arm or manually. Put it on.

[0092] In addition, for each knife in the intelligent knife management cabinet, its usage count and lifespan status can be identified based on its ID information, as well as precise measurement data on the knife's length, diameter, and wear.

[0093] One embodiment includes an RFID electronic tag attached to the cutting tool. The intelligent tool management cabinet is equipped with An RFID reader is used to accurately identify detailed information about all the knives inside. Furthermore, after the knives are returned, Smart knife The cabinet is equipped with The RFID writing device is used to input and write the latest status of the target tool into the RFID electronic tag built into the target tool.

[0094] It should be noted that the entire system also includes a cloud-based data processing center for data storage, computation, and analysis, and can build a database linking orders, equipment, tools, and products.

[0095] This data control system also incorporates artificial intelligence data analysis based on a large amount of machining data. It collects and integrates the following core data from all dimensions—CNC machine tool systems, RFID tool tags, external tool setters, and machine tool sensors—as the foundational dataset for AI analysis, using these as data inputs:

[0096] (1) Machine tool processing data: spindle speed, cutting feed rate, cutting depth, load current, vibration amplitude, temperature, processing time, coordinate trajectory, idle travel time;

[0097] (2) Core data of the cutting tool: tool model, material, cutting edge condition, geometric compensation value (H9 / D9), wear compensation value (Hw / Dw), total compensation value (H total / D total), actual measured value of external tool setting, compensation adjustment frequency, and adjustment range;

[0098] (3) Tool usage data: cumulative cutting time, cumulative number of processed parts, number of tool changes, number of regrindings, and number of abnormal shutdowns;

[0099] (4) Workpiece quality data: measured dimensions, geometric tolerances, surface roughness, and scrap rate of the workpiece;

[0100] (5) Environmental auxiliary data: workshop temperature, cutting fluid concentration, lubrication status, humidity.

[0101] Furthermore, the step of issuing control commands to the intelligent tool management cabinet to obtain available target tools includes:

[0102] S21. Lock the target tool using its unique identification code;

[0103] S22. Retrieve the target tool from the intelligent tool cabinet, and automatically record the ID, corresponding order number, and processing station number of the target tool, and establish an initial lifespan count.

[0104] Furthermore, the steps for receiving the tool setting parameters from the external tool setting device include:

[0105] S31. Send the initial tool setting parameters of the target tool to the tool setting device;

[0106] S32. Obtain the precise length compensation value and radius compensation value of the target tool;

[0107] S33. Generate a standardized NC compensation program using a tool setter;

[0108] S34. Call the system algorithm to perform virtual simulation verification.

[0109] It should be noted that the initial tool setting parameters are obtained from the cloud and then fed back to the tool setting device.

[0110] Meanwhile, virtual simulation verification is based on verifying whether there are risks of interference, overcutting, or undercutting in tool compensation, machining coordinates, and motion trajectory.

[0111] It should be noted that all data is uniformly normalized through the data acquisition gateway to form an integrated time-series dataset of cutting tools, machine tools, machining, and quality, providing high-quality training and inference samples for artificial intelligence models.

[0112] Simultaneously, the collected raw data undergoes artificial intelligence-based noise reduction, missing value imputation, and outlier removal to extract four core feature vectors: tool compensation features, life decay features, machining load features, and wear evolution features.

[0113] (1) Compensation characteristics: fluctuation range of total compensation value, compensation adjustment cycle, and proportion of geometric / wear compensation;

[0114] (2) Life characteristics: cutting time attenuation coefficient, number of workpieces processed life loss rate, wear growth rate;

[0115] (3) Load characteristics: the correlation between spindle load and tool compensation, and the coupling relationship between cutting parameters and tool life;

[0116] (4) Wear characteristics: tool size deviation, compensation correction amount, and quantification value of edge wear.

[0117] It should be noted that this is based on the fundamental formula for total tool compensation:

[0118]

[0119] in, Total tool length compensation;

[0120] : Geometric length compensation (measured value of external tool setting);

[0121] Wear length compensation (AI dynamic correction value);

[0122] Overall tool radius compensation;

[0123] Geometric radius compensation;

[0124] Wear radius compensation.

[0125] The correction values ​​for the aforementioned tool compensation are dynamically generated by artificial intelligence after analyzing the corresponding machining information in the database.

[0126] Furthermore, the step of feeding back the tool setting parameters to the CNC machine tool and then starting machining includes:

[0127] S41. Load the pre-adjusted target tool into the CNC machine tool and obtain the compensation parameters corrected by artificial intelligence;

[0128] S42. During the processing, the number of processed parts is accumulated in real time;

[0129] S43. Determine whether the number of times the target tool has been processed has reached the target tool life threshold; if it reaches 80% of the target tool life threshold, an early warning signal is automatically pushed to prompt the replacement of the spare tool; if it reaches the target tool life threshold, the machine tool is automatically locked or its use is forcibly prohibited.

[0130] It should be noted that the system can issue warnings based on lifespan grading, outputting warnings at 80% remaining lifespan, alarms at 90% remaining lifespan, and lockout commands at 100% remaining lifespan. This triggers a tool change prompt in conjunction with the tool management system, allowing for tool replacement via a robotic arm or manual intervention. Furthermore, lifespan is comprehensively assessed using multi-dimensional lifespan thresholds, including the number of workpieces processed, cutting time, wear amount, and spindle load.

[0131] Secondly, the AI ​​prediction formula for remaining tool life (RUL) is based on LSTM temporal deep learning, which integrates cutting time, number of workpieces processed, compensation fluctuations, and spindle load to predict the remaining life.

[0132] Core formula for remaining life prediction

[0133]

[0134] Among them, the life loss rate formula

[0135]

[0136] in, : The remaining tool life at time t;

[0137] LSTM neural network prediction function;

[0138] : Multi-source data vector at time t;

[0139] Cumulative cutting time;

[0140] : Cumulative number of processed pieces;

[0141] Spindle average load;

[0142] : Processing vibration amplitude;

[0143] , Artificial intelligence training optimization weight coefficients (0<α,β<1)

[0144] Lifespan attrition rate;

[0145] Rated tool life (duration / number of tools).

[0146] Furthermore, the step of uploading processing status data in real time includes:

[0147] S51. Collect the spindle load, vibration value, machining parameters of the CNC machine tool equipment, and the real-time wear data fed back by the external tool setter through the data gateway;

[0148] S52. Establish a strongly correlated database of tool number, machining batch, dimensional inspection result, and machine tool number;

[0149] S53. Determine if there are any dimensional errors in the product processing; if so, record the corresponding tool information, tool parameters and wear amount, and CNC machine tool spindle status.

[0150] S54. Send an analysis command to the cloud data processing center to perform further analysis and determine the cause of the processing error, and then generate an analysis report.

[0151] It should be noted that the data gateway can collect spindle load, vibration values, machining parameters, and real-time wear data from the external tool setter. The collected tool data is then uploaded to the cloud for storage, further facilitating data analysis and AI simulation learning. After continuous learning, the AI ​​subsequently contributes to actual machining decisions.

[0152] An AI-adaptive correction formula for tool compensation is established, aiming to minimize workpiece dimensional error, and automatically calculates the optimal compensation correction amount to achieve closed-loop compensation.

[0153] 1. Optimal Correction Formula for Length Compensation

[0154]

[0155] 2. Optimal Correction Formula for Radius Compensation

[0156]

[0157] 3. Real-time total compensation update formula

[0158]

[0159] in, / : Optimal compensation correction amount for length / radius

[0160] / Compensation correction coefficient (determined by artificial intelligence self-learning)

[0161] : Workpiece length dimension error;

[0162] : Workpiece contour dimensional error;

[0163] / Wear coupling coefficient;

[0164] Tool wear at time t;

[0165] / Temperature compensation coefficient;

[0166] Machine tool / tool ​​temperature rise.

[0167] Furthermore, the AI-based fitting formula for tool wear is based on compensating for fluctuations, machining load, and vibration signals, and calculates tool wear non-contactly.

[0168]

[0169] in,

[0170] : Tool wear at time t (mm);

[0171] Total length compensation fluctuation value;

[0172] Spindle load fluctuation value;

[0173] , , Artificial intelligence feature weights (model training output)

[0174] Of course, for the AI-powered abnormal processing judgment formula, thresholds need to be set to automatically distinguish between normal / abnormal wear / chipping / tool ​​breakage.

[0175]

[0176] The judgment principle is as follows:

[0177] <1: The cutting tool is normal;

[0178] E 1.5: Abnormal Wear Warning;

[0179] 1.5: If the blade chipps or breaks, stop the machine immediately.

[0180] Finally, the AI-optimized objective function for process parameters effectively balances machining efficiency, tool life, and stability compensation, outputting optimal cutting parameters:

[0181]

[0182] in, : Optimize the objective function (the smaller the value, the better);

[0183] , , : weighting coefficients, and

[0184] : Cutting feed rate;

[0185] The constraints are: , .

[0186] Furthermore, this application employs a multi-model fusion architecture to construct several intelligent analysis models to address the needs of tool control and machining optimization:

[0187] 1. Tool Remaining Life (RUL) Prediction Model:

[0188] The system uses a Long Short-Term Memory (LSTM) network to process time-series data. It takes tool usage data, compensation data, and machining load data as input and outputs the remaining cutting time and the number of remaining workable parts, thus achieving life prediction in advance. This replaces the traditional fixed threshold determination method and achieves a prediction accuracy of ≥95%.

[0189] 2. Adaptive Optimization Model for Tool Compensation

[0190] Based on BP neural network and reinforcement learning, with workpiece dimensional error as the optimization objective, the mapping relationship between compensation value and machining dimension is analyzed in real time, and the optimal compensation correction amount is automatically calculated.

[0191]

[0192]

[0193] It achieves tool compensation without manual intervention and real-time adaptive correction, controlling dimensional accuracy fluctuations within ±0.003mm.

[0194] 3. Intelligent Diagnostic Model for Tool Wear and Failure

[0195] Convolutional neural networks (CNNs) are used to identify features of tool vibration, load, and compensation fluctuation data, accurately determining the tool's normal wear, abnormal wear, chipping, and breakage states, and issuing failure warnings 0.5 to 2 hours in advance to prevent batch scrap.

[0196] 4. Intelligent optimization model for machining process parameters

[0197] Based on the random forest algorithm, the correlation between tool life, compensation stability and cutting parameters (spindle speed, feed rate, depth of cut) is analyzed, and the optimal combination of cutting parameters is output to maximize tool life and reduce the frequency of compensation adjustment while ensuring machining efficiency.

[0198] After completing the reasoning and analysis through the artificial intelligence model, the decision results are directly sent to the CNC control system and the RFID tool unit, forming a closed-loop intelligent control:

[0199] Intelligent compensation execution: The optimal compensation value calculated by AI is automatically written to the RFID tag and the CNC tool compensation register is updated synchronously, without the need for manual operation;

[0200] Lifespan grading warning: Outputs warnings at 80% remaining lifespan, alarms at 90% remaining lifespan, and lock commands at 100% remaining lifespan, triggering tool change prompts in conjunction with the tool management system;

[0201] Abnormal machining interruption: When a tool abnormality is diagnosed, immediately reduce the cutting load or suspend machining to avoid tool damage and workpiece scrap.

[0202] Process iteration and optimization: The optimal cutting parameters are stored in the process library and synchronized to the same model of machine tool to achieve unified optimization of the process across the entire production line.

[0203] Based on the spindle load, vibration value, and machining parameters of the CNC machine tool collected through the data gateway, as well as the real-time wear data fed back by the external tool setter, and the strongly correlated database of tool number-machining batch-dimensional inspection result-machine tool number, and the corresponding tool information, tool parameters and wear amount, and CNC machine tool spindle status recorded when determining whether the product machining has dimensional deviations, all machining process data collected by the data gateway will be analyzed. Regarding the above basic data preprocessing scheme, multi-source data such as machine tool, tool, compensation, and machining are normalized to eliminate dimensional differences and ensure the stability of the artificial intelligence model. Based on this, the present invention provides the following AI model normalization scheme.

[0204] min-max normalization formula

[0205]

[0206] in, Normalized data (0~1)

[0207] x: Raw acquired data (load / vibration / compensation value / cutting time)

[0208] : Data extreme values.

[0209] Example 2

[0210] like Figure 6 As shown, correspondingly, the present invention also provides an intelligent data control device for CNC machine tool equipment, characterized in that it includes,

[0211] Order management module 1 is used to receive order processing information and then send it back to the cloud data processing center.

[0212] Tool management module 2 is used to send control commands to the intelligent tool management cabinet to obtain available target tools;

[0213] Tool setting management module 3 is used to receive tool setting parameters fed back by an external tool setting device and collect accurate measurement data of the target tool;

[0214] Parameter feedback module 4 is used to feed back the tool setting parameters to the CNC machine tool equipment before starting processing;

[0215] Database building module 5 is used to receive uploaded processing status data in real time and build associated databases.

[0216] like Figure 7 As shown, the tool management module includes:

[0217] The tool locking unit 21 is used to lock the target tool using its unique identification code;

[0218] The tool retrieval unit 22 is used to retrieve the target tool from the intelligent tool cabinet, and automatically record the ID, corresponding order number, and processing station number of the target tool, and establish an initial life count.

[0219] like Figure 8 As shown, the tool setting management module includes:

[0220] Tool setting parameter sending unit 31 is used to send the initial tool setting parameters of the target tool to the tool setting device;

[0221] The compensation acquisition unit 32 is used to acquire the precise length compensation value and radius compensation value of the target tool;

[0222] The compensation program generation unit 33 is used to generate a standardized NC compensation program through the tool setter;

[0223] The simulation verification unit 34 is used to call the system algorithm to perform virtual simulation verification.

[0224] like Figure 9 As shown, the parameter feedback module also includes:

[0225] The offline compensation acquisition unit 41 is used to load the pre-adjusted target tool into the CNC machine tool equipment and acquire the compensation parameters corrected by artificial intelligence.

[0226] The counting unit 42 is used to accumulate the number of processed parts in real time during the processing.

[0227] The lifespan determination unit 43 is used to determine whether the number of times the target tool has been processed has reached the target tool lifespan threshold. If it reaches 80% of the target tool lifespan threshold, an early warning signal is automatically pushed to prompt the replacement of the spare tool. If the target tool lifespan threshold is reached, the machine tool is automatically locked or its use is forcibly prohibited.

[0228] like Figure 10 As shown, finally, the database management module includes:

[0229] The data acquisition unit 51 is used to acquire the spindle load, vibration value, machining parameters of the CNC machine tool equipment, and real-time wear data fed back by the external tool setter through the data gateway;

[0230] Database construction unit 52 is used to establish a strongly correlated database of tool number, machining batch, dimensional inspection result, and machine tool number;

[0231] The quality inspection judgment unit 53 is used to determine whether the product processing has dimensional deviations; if so, it records the corresponding tool information, tool parameters and wear amount, and CNC machine tool spindle status.

[0232] The report generation unit 54 is used to send an analysis command to the cloud data processing center, so that it can perform further analysis and judgment on the cause of the processing error and generate an analysis report.

[0233] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of intelligent data control of a numerically controlled machine tool apparatus, characterized by, The method includes: After receiving the order processing information, it sends a feedback message to the cloud data processing center. Send control commands to the intelligent tool management cabinet to obtain available target tools; The receiver receives the tool setting parameters fed back by the external tool setting device, and collects the precise measurement data of the target tool; After the tool setting parameters are fed back to the CNC machine tool, machining begins. It receives uploaded processing status data in real time and builds an associated database.

2. The control method according to claim 1, characterized by, The step of issuing a control command to the intelligent tool management cabinet to obtain an available target tool includes: The target tool is located using its unique identification code. The system retrieves the target tool from the intelligent tool cabinet and automatically records the target tool's ID, corresponding order number, and machining station number, and establishes an initial lifespan count.

3. The control method according to claim 1, characterized by, The steps for receiving tool setting parameters from the external tool setting device include: The initial tool setting parameters for the target tool are sent to the tool setting device; Obtain the precise length compensation value and radius compensation value of the target tool; A standardized NC compensation program is generated by the tool generator; The system algorithm is invoked to perform virtual simulation verification.

4. The control method according to claim 1, characterized by, The step of feeding back the tool setting parameters to the CNC machine tool and then starting machining includes: The pre-adjusted target tool is loaded into the CNC machine tool, and the compensation parameters corrected by artificial intelligence are obtained; The number of processed parts is accumulated in real time during the processing process; Determine whether the number of times the target tool has been processed has reached the target tool life threshold; if it reaches 80% of the target tool life threshold, an early warning signal is automatically pushed to prompt preparation to replace the spare tool; if it reaches the target tool life threshold, the machine tool is automatically locked or its use is forcibly prohibited.

5. The control method according to claim 1, characterized in that, The step of uploading processing status data in real time includes: The spindle load, vibration value, and machining parameters of the CNC machine tool are collected through a data gateway, as well as the real-time wear data fed back by the external tool setter. Establish a strongly correlated database of tool number, machining batch, dimensional inspection result, and machine tool number; Determine if there are dimensional errors in the product processing; if so, record the corresponding tool information, tool parameters and wear amount, and CNC machine tool spindle status. An analysis command is sent to the cloud data processing center to perform further analysis and determine the cause of the processing error, and then an analysis report is generated.

6. An intelligent data control device for CNC machine tools, characterized in that, include, The order management module is used to receive order processing information and then send it back to the cloud data processing center. The tool management module is used to send control commands to the intelligent tool management cabinet to obtain available target tools; The tool setting management module is used to receive tool setting parameters fed back by an external tool setting device and collect accurate measurement data of the target tool. The parameter feedback module is used to feed back the tool setting parameters to the CNC machine tool before machining begins; The database construction module is used to receive uploaded processing status data in real time and build associated databases.

7. The control device according to claim 6, characterized in that, The tool management module includes: The tool locking unit is used to lock the target tool using its unique identification code. The tool retrieval unit is used to retrieve the target tool from the intelligent tool cabinet, and automatically record the ID, corresponding order number, and processing station number of the target tool, and establish an initial lifespan count.

8. The control device according to claim 6, characterized in that, The tool setting management module includes: The tool setting parameter sending unit is used to send the initial tool setting parameters of the target tool to the tool setting device; The compensation acquisition unit is used to acquire the precise length compensation value and radius compensation value of the target tool; The compensation program generation unit is used to generate standardized NC compensation programs through the tool setter; The simulation verification unit is used to call the system algorithm to perform virtual simulation verification.

9. The control device according to claim 6, characterized in that, The parameter feedback module includes: The offline compensation acquisition unit is used to load the pre-adjusted target tool into the CNC machine tool and acquire the compensation parameters corrected by artificial intelligence. The counting unit is used to accumulate the number of processed parts in real time during the processing. The lifespan determination unit is used to determine whether the number of times the target tool has been processed has reached the target tool lifespan threshold. If it reaches 80% of the target tool lifespan threshold, an early warning signal is automatically pushed to prompt the replacement of the spare tool. If the target tool lifespan threshold is reached, the machine tool is automatically locked or its use is forcibly prohibited.

10. The control device according to claim 6, characterized in that, The database management module includes: The data acquisition unit is used to acquire the spindle load, vibration value, machining parameters of the CNC machine tool, and real-time wear data fed back by the external tool setter through the data gateway. The database construction unit is used to establish a strongly correlated database of tool number, machining batch, dimensional inspection result, and machine tool number; The quality inspection judgment unit is used to determine whether the product processing has dimensional deviations; if so, it records the corresponding tool information, tool parameters and wear amount, and CNC machine tool spindle status. The report generation unit is used to send analysis instructions to the cloud data processing center, so that it can perform further analysis and judgment on the cause of the processing error and generate an analysis report.

Images